Publications

2024

1. RCIM

   Augmented reality and indoor positioning based mobile production monitoring system to support workers with human-in-the-loop

   L. Xia, J. Lu, Y. Lu, H. Zhang, Y. Fan, Z. Zhang

   Robotics and Computer-Integrated Manufacturing, 2024

   Abs DOI

   With the increasing demand for product customization, the exponential increase in large-scale and small-batch production orders has yielded new challenges for the capacity of traditional production lines. Due to the information redundancy and complex production process on the production site of the factory, the traditional monitoring system is incapable of meeting the information interaction requirements between the factory management level and the executive level. Meanwhile, the traditional augmented reality (AR) based on image recognition is not suitable in the complex industrial environments. To address the gap, we propose a novel mobile production monitoring system (AIMPMs) with human-in-the-loop control by leveraging the cutting-edge AR and indoor positioning technique. In the proposed system, Ultra-wideband (UWB) and Inertial Measurement Unit (IMU) fusion indoor positioning technology is proposed, which provides accurate indoor positioning information for the production factors in the factory. Subsequently, we build the lightweight indoor map for positioning that can serve as the location reference and path planning, and a nearest-neighbor decision algorithm with double rejection decision (NN-DRD) is proposed to match the positioning features to trigger virtual monitoring information. Finally, the AIMPMs is applied in a hydraulic cylinder factory to verify its enforceability and effectiveness, and the human factors evaluation model and index system are constructed to evaluate two systems, (1) the mobile monitoring system based on positioning information, and (2) the mobile monitoring system based on image recognition, respectively. The experimental results indicate that after the application of AIMPMs, the physiological and mental fatigue of the production personnel is immensely decreased. Therefore, the system realizes a smarter and highly humanized human-machine interaction mode with human-in-the-loop control. © 2023 Elsevier Ltd

2. Int J Prod Res

   A multi-objective joint optimisation method for simultaneous part family formation and configuration design in delayed reconfigurable manufacturing system (D-RMS)

   S. Huang, J. Tan, Y. Lu, S.K. Moghaddam, G. Wang, Y. Yan

   International Journal of Production Research, 2024

   Abs DOI

   In the era of Industry 4.0, the demand fluctuation has become fiercer due to the characteristics of diversification, customisation, and uncertainty. Reconfigurability of manufacturing systems has been proven to be a useful and necessary feature when it comes to handling demand uncertainty. This feature can be achieved through the implementation of reconfigurable manufacturing system (RMS) and delayed reconfigurable manufacturing system (D-RMS). D-RMS is a subclass of RMS that focuses primarily on improving the convertibility of the manufacturing system. The two main phases involved in implementing D-RMS are part family formation and configuration design. Therefore, we proposed a multi-objective joint optimisation method of part family formation and configuration design according to the philosophy of D-RMS. Firstly, we develop a multi-objective joint optimisation model that takes into account investment cost, reconfiguration cost, similarity coefficient, and delayed reconfiguration to optimise the part family and configuration of D-RMS simultaneously. Three types of machine tools namely dedicated machine tools, flexible machine tools, and reconfigurable machine tools are considered in the optimisation model. Secondly, the non-dominated sorting genetic algorithm-III (NSGA-III) is adopted to solve the proposed multi-objective integer programming problem. Finally, numerical experiments are presented to demonstrate the effectiveness of the proposed multi-objective joint optimisation method. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

3. RCIM

   Dynamic decision-making for knowledge-enabled distributed resource configuration in cloud manufacturing considering stochastic order arrival

   Y. Zhang, Z. Zhang, Y. Lu, H. Zhu, D. Tang

   Robotics and Computer-Integrated Manufacturing, 2024

   Abs DOI

   The emergence of COVID-19 caused the stagnation of production activities and promoted the changing market demand. These uncertainties not only brought great challenges to the manufacturing approaches led by a single enterprise, but also threatened the stability of inherent supply chain. To maintain market competitiveness, an efficient distributed manufacturing resource allocation method is urgently needed by manufacturers. Cloud manufacturing (CMfg) is an advanced service-oriented manufacturing paradigm that breaks physical space constraints to integrate distributed resources across enterprises, and provides on-demand configuration of manufacturing services for personalized consumer needs in real-time. The focus of this paper is to achieve dynamic configuration of distributed resources in CMfg considering stochastic order arrival, while reducing overall completion time and improving resource utilization. First, a dynamic knowledge graph for distributed resources is constructed, and its definition and construction methods are introduced. Secondly, semantic matching between massive optional manufacturing resources and multiple types of subtasks is achieved through knowledge extraction, thereby obtaining a candidate set of manufacturing resources that meet basic requirements for each subtask. An artificial intelligence (AI) scheduler based on deep reinforcement learning is developed, and order urgency is incorporated into the design of state observation vectors. AI scheduler can generate optimal decision results based on environmental observations, select high-quality manufacturing service compositions over candidate sets, and ultimately achieve efficient distributed resources configuration. Finally, Dueling DQN-based training method is put forward to optimize AI scheduler, enabling adaptable decision-making performance in dynamic environment. In the experiment, a simulation environment with 18 different settings is designed that considers stochastic processing time, random order compositions and various order arrival patterns. The proposed graph-based matching method, scheduling policy learning method and dynamic decision-making method are tested in the simulation environment. The experiment results demonstrate that the cognitive and AI joint driven distributed manufacturing resource configuration method is superior to traditional methods in terms of policy learning speed and scheduling solution quality. © 2023 Elsevier Ltd

4. RCIM

   Human-Robot Shared Assembly Taxonomy: A step toward seamless human-robot knowledge transfer

   R.K.-J. Lee, H. Zheng, Y. Lu

   Robotics and Computer-Integrated Manufacturing, 2024

   Abs DOI

   Future manufacturing will witness a shift in human-robot relationships toward collaboration, compassion, and coevolution. This will require seamless human-robot knowledge transfer. Differences in language and knowledge representation hinder the transfer of knowledge between humans and robots. Thus, a unified knowledge representation system that can be shared by humans and robots is essential. Driven by this need in a product assembly scenario, we propose the Human-Robot Shared Assembly Taxonomy (HR-SAT). With HR-SAT, any comprehensive assembly task can be represented as a knowledge graph that both humans and robots can understand. To ensure consistency in task decomposition and representation, we define the key elements of HR-SAT. HR-SAT incorporates rich assembly information and provides necessary information for diverse applications, e.g., process planning, quality checking, and human-robot collaboration. The usage and practicality of HR-SAT are demonstrated through two case studies. As a unified assembly process representation schema, HR-SAT constitutes a critical step toward seamless human-robot knowledge transfer. The specifications of HR-SAT and the two case studies are available at: https://iai-hrc.github.io/hr-sat. © 2023 The Author(s)

5. Expert Sys Appl

   A method for constructing a machining knowledge graph using an improved transformer

   L. Guo, X. Li, F. Yan, Y. Lu, W. Shen

   Expert Systems with Applications, 2024

   Abs DOI

   Process knowledge base is a core component in the intelligent process, which determines the intelligent degree of product manufacturing and directly affects the production efficiency of products. However, traditional process knowledge base is often constructed manually, which is difficult and time-consuming. In addition, in the field of machining, there is a large amount of unstructured invisible process knowledge, which is not effectively organized and managed. To make use of this knowledge and provide knowledge support for downstream production and maintenance, a process knowledge base construction framework is proposed by using Knowledge Graph (KG) technology. Firstly, the ontology rules of process knowledge are designed from the perspective of the processing method of process characteristics according to the particularity of knowledge in the machining field. The process KG schema layer is then constructed. Secondly, a neural network BERT–Improved TRANSFORMER–CRF (BITC) model is proposed for the machining knowledge extraction task, and the data layer is constructed. Then, entity linking and knowledge fusion are performed by using the word vector cosine similarity algorithm and stored in Neo4j. The process KG is then constructed. Finally, the effectiveness of the proposed method is verified by using an aero-engine casing of an enterprise as an example. Under the same dataset, the BITC model scored higher than several other classical models. The Precision, Recall, and F1-score were 85.27%, 86.40%, and 85.83 %, respectively. © 2023 Elsevier Ltd

6. J Manuf Syst

   A systematic framework for tackling anomalous pre-welding workpiece postures with regular butt joints based on prototype features

   H. Liu, Y. Tian, Y. Lu, J. Feng, T. Wang, L. Li, and 1 more author

   Journal of Manufacturing Systems, 2024

   Abs DOI

   In intelligent welding systems, pre-welding parameter extraction is a foremost technology in upgrading robotic welding and integrating emerging technologies, e.g., digital twins, big data, and cloud manufacturing. However, current workpiece postures still rely on manual judgments based on workers’ experience, which has become one of major issues hindering the further advancement of intelligent welding systems towards mass production. To cope with this issue, aiming at four typical regular butt joints, a systematic tackling framework is proposed and carried out from posture description, posture feature construction, posture metrics to visualization model reconstruction. At a core, the prototype feature is proposed to characterize pre-welding workpiece postures and a series of text characters based on it is introduced to describe various anomalous workpiece postures including concurrent tilt, misalignment, seam variation, and stacking between them. A comprehensive process for constructing prototype features is performed from data acquisition, image processing to key point search, among which the algorithms for extracting differential features of different seam types are integrated. Based on the constructed prototype features, several posture metric parameters are defined, and workpiece posture models can be easily reconstructed. In addition, the good generalizability of the proposed framework for seam types with regular edge and seam features is also discussed. Ultimately, experimental results show that the prototype feature-based posture description of the pre-welding workpiece can efficiently and accurately characterize multiple anomalous postures. © 2023 The Society of Manufacturing Engineers

7. Comput Ind

   Semantic knowledge-driven A-GASeq: A dynamic graph learning approach for assembly sequence optimization

   L. Xia, J. Lu, Y. Lu, W. Gao, Y. Fan, Y. Xu, and 1 more author

   Computers in Industry, 2024

   Abs DOI

   In the context of an increasingly automated and personalized manufacturing mode, efficient assembly sequence planning (ASP) has emerged as a critical factor for enhancing production efficiency, ensuring product quality, and satisfying diverse market demands. To address this need, our study first transforms the assembly topology and process into a weighted precedence graph, wherein parts represent nodes, and the assembly interconnections between parts constitute weighted edges. Then, we formulate the quantitative models of semantic knowledge, encompassing three facets: assembly direction changes, assembly stability, and part assembly interference, and thus constructs a heuristic function. We propose a novel dynamic graph learning algorithm, i.e., assembly-oriented graph attention sequence (A-GASeq), utilizing the heuristic information as edge weights of the assembly graph structure to incrementally direct the search towards optimal sequences. The performance of A-GASeq is first evaluated utilizing three key metrics: area under the receiver operation characteristic curve (AUC), precision score, and time consumption. The results reveal the superiority of our model over competing state-of-the-art graph learning models using a real-world dataset. Concurrently, we apply the algorithm to actual industrial products of diverse complexity, thereby demonstrating its broad utility across different complex products and its potential for addressing complex assembly sequence planning problems in the field of smart manufacturing. © 2023 Elsevier B.V.

2023

1. Comput Ind Eng

   A blockchain-based interactive approach between digital twin-based manufacturing systems

   S. Liu, Y. Lu, J. Li, X. Shen, X. Sun, J. Bao

   Computers and Industrial Engineering, 2023

   Abs DOI

   Cloud manufacturing provides an interactive environment for collaboration between digital twin-based manufacturing systems. However, access to the enterprise cloud by a significant number of digital twin systems would lead to bandwidth competition and severe delays. Therefore, the data exchange process needs to be improved in a more reliable and effective way. To tackle this issue, a blockchain-based data interactive approach is proposed to form the peer-to-peer data exchange mechanism between digital twin-based manufacturing systems. First, the manufacturing edge pool is developed given specific manufacturing tasks. The blockchain enables the digital twin manufacturing systems to exchange data effectively and safely. Besides, the application of the blockchain reduces the dependencies of the digital twin systems on the enterprise cloud and improves the flexibility of the workshops. Finally, the effectiveness of this method is verified by a case study on the engine. © 2022

2. J Manuf Syst

   A digital thread-driven distributed collaboration mechanism between digital twin manufacturing units

   S. Liu, Y. Lu, X. Shen, J. Bao

   Journal of Manufacturing Systems, 2023

   Abs DOI

   The trialing of new products in production typically suffers from quality and productivity problems because of immature manufacturing processes. As an efficient virtual-real interaction technology, digital twin technology can optimize the manufacturing process adaptively in a single station. However, existing digital twin systems lack an effective collaboration mechanism between manufacturing units, thus failing to optimize the overall manufacturing processes dynamically. This paper proposes a practical collaboration theory and methodology between digital twin manufacturing units. To overcome the above challenges, this digital thread-driven method models the manufacturing tasks by heterogeneous information network to analyze the product quality information during the manufacturing process, and adjusts the subsequent manufacturing tasks according to the analysis results. The collaboration between manufacturing units forms a stable and reliable operation mode for improving production efficiency during the whole manufacturing process. The graph-based manufacturing task model can help analyze the machining and assembly process based on the digital thread, distinguish the error sources of products, and dynamically reconstruct production tasks. Finally, the feasibility of the proposed method is verified by a case of a crank and connecting rod mechanism in a manufacturing workshop. © 2023 The Society of Manufacturing Engineers

3. Int J Prod Res

   Semantic-aware event link reasoning over industrial knowledge graph embedding time series data

   B. Zhou, X. Shen, Y. Lu, X. Li, B. Hua, T. Liu, and 1 more author

   International Journal of Production Research, 2023

   Abs DOI

   The time series data in the manufacturing process reflects the sequential state of the manufacturing system, and the fusion of temporal features into the industrial knowledge graph will undoubtedly significantly improve the knowledge process efficiency of the manufacturing system. This paper proposes a semantic-aware event link reasoning over an industrial knowledge graph embedding time series data. Its knowledge graph skeleton is constructed through a specific manufacturing process. NLTK is used to transform technical documents into a structured industrial knowledge graph. We employ deep learning (DL)-based models to obtain semantic information related to product quality prediction using time series data collected from IoT devices. Then the prediction information is attached to the specified node in the knowledge graph. Thus, the knowledge graph will describe the dynamic semantic information of manufacturing contexts. Meanwhile, a dynamic event link reasoning model that uses graph embedding to aggregate manufacturing processes information is proposed. The implicit information with industrial temporal knowledge can be further mined and inferred. The case study has shown that the proposed knowledge graph link reasoning reflects dynamic temporal characteristics. Compared to the classical knowledge graph prediction models, our model is superior to the baseline methods. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

4. J Manuf Syst

   Dynamic production scheduling towards self-organizing mass personalization: A multi-agent dueling deep reinforcement learning approach

   Z. Qin, D. Johnson, Y. Lu

   Journal of Manufacturing Systems, 2023

   Abs DOI

   Mass personalization is rapidly approaching. In response, manufacturing systems should be capable of autonomously changing production plans, configurations and schedules under dynamic manufacturing environments for producing personalized products. Self-organizing manufacturing network is a promising paradigm for mass personalization. The backbone of a self-organizing manufacturing network is an adaptive production scheduling method to dynamically allocate and sequence manufacturing jobs under dynamic settings, such as stochastic processing time or unplanned machine breakdown. However, existing production scheduling methods (i.e., heuristic rules, meta-heuristic algorithms, and existing reinforcement learning models) fail to automatically optimize production schedules while maintaining stable manufacturing performance, under dynamic settings. In this paper, we designed a reinforcement learning-based static-training-dynamic-execution approach for dynamic job shop scheduling problems. The scheduling policies are learned from static scheduling instances by a multi-agent dueling deep reinforcement learning approach. Under this approach, we proposed new representations of observation, action, reward, and cooperation mechanisms between agents. The learned scheduling policies are then deployed to a dynamic scheduling system where stochastic processing time and unplanned machine breakdown randomly occur. Extensive simulation experiments demonstrated that our approach outperforms heuristic rules on makespan under two dynamic manufacturing settings. © 2023 The Society of Manufacturing Engineers

5. Comput Ind

   Full-cycle data purification strategy for multi-type weld seam classification with few-shot learning

   H. Liu, Y. Tian, L. Li, Y. Lu, J. Feng, F. Xi

   Computers in Industry, 2023

   Abs DOI

   Weld seam type confirmation is a key part of intelligent integrated welding to cope with adjustable schemes varying with the seam morphology. However, existing works are mainly based on qualitative joint description (QJD) and machine learning classification (MLC), which entail high costs in balancing multiple given parameters, acquiring sufficient data and generalizing for new seam types. In this article, taking the advantages of few-shot learning, we propose a full-cycle data purification strategy (DPS) to identify seam types. First, five typical weld seams are mapped under three laser stripe patterns to acquire the raw samples. Then, a series of compliance processing algorithms are performed with reference to the target dataset to build a scenario dataset: purified weld seam stripe mapping (P-WSSM). With a few-shot learning pre-model, a positive weld seam classification result is obtained based on a small-volume dataset and analyze several critical factors. In addition, to compensate the application drawbacks caused by the wide randomness of low-volume datasets, compliance distance based on integrated grayscale co-occurrence matrix (I-GLCM) is introduced to quantitatively measure P-WSSM and the target dataset. Ultimately, experiments show that the dual-line stripe mapping achieves 85.4% recognition accuracy for 5-way 5-shot, which is a competitive multi-type weld seam classification via few-shot learning. © 2023 Elsevier B.V.

6. Manuf. Let.

   A Knowledge Graph-based knowledge representation for adaptive manufacturing control under mass personalization

   Z. Qin, Y. Lu

   Manufacturing Letters, 2023

   Abs DOI

   Mass personalization is an achievable manufacturing paradigm, which requires flexible and responsible manufacturing operations in response to dynamic batch sizes of personalized products. A Self-Organizing Manufacturing Network (SOMN) has been proposed to achieve mass personalization. A crucial aspect of SOMN is adaptive manufacturing control, and the Knowledge Graph, a powerful tool, has been recognized as a promising solution to enhance manufacturing intelligence. However, the current Knowledge Graph research mainly focuses on the modeling and ontology definition of the manufacturing environment, but neglects the interaction between manufacturing resources, the dynamic features of the manufacturing environment, and the application of the Knowledge Graph towards adaptive manufacturing control. Therefore, this paper proposes a Knowledge Graph-based semantic representation for adaptive manufacturing control under dynamic manufacturing environments. The proposed approach develops the Knowledge Graph based on historical and real-time scheduling data. Based on the established Knowledge Graph, Multi-Agent Reinforcement Learning has been introduced as an illustrative example of achieving adaptive scheduling control. © 2023 The Author(s)

7. J Manuf Syst

   Prognostics and health management via long short-term digital twins

   Y. Sun, Y. Lu, J. Bao, F. Tao

   Journal of Manufacturing Systems, 2023

   Abs DOI

   Current digital twin-based Prognostics and Health Management (PHM) research mainly focuses on prediction with a few parameters or a single event. However, when the relationship between moving parts of equipment is complex, both instantaneous failure and long-period degradation should be considered. Existing research is challenging to describe the dynamic evolution of the health status of the target object at varied time scales. In addition, data characteristics at different time scales are difficult to be captured simultaneously by current methods. This paper proposes an innovative dual time scale digital twin modeling and analysis method. According to the PHM business rules, the time series signals are decomposed into fine-grained scales and adaptively constructed into short time scale and long time scale digital twins. The generated events of different scales pay attention to the temporal characteristics and uncertainties, and interactive mapping of events at different scales is realized in cyberspace. Events at a short time scale focus on the real-time occurrence of anomalies, and long-term events track equipment degradation and trends. The interaction and collaboration between different time scale models are also discussed. Finally, the paper uses the state monitoring of large cranes in iron and steel enterprises to verify the proposed method. The results show that this modeling method can reduce the uncertainty and incompleteness of system monitoring in a complex system. Real-time performance and reliability of equipment health diagnosis have been effectively improved. © 2023 The Society of Manufacturing Engineers

8. J. Civ. Struct. Health Monit.

   Vibration-based and computer vision-aided nondestructive health condition evaluation of rail track structures

   S. Wang, H. Zheng, L. Tang, Z. Li, R. Zhao, Y. Lu, and 1 more author

   Journal of Civil Structural Health Monitoring, 2023

   Abs DOI

   In railway engineering, monitoring the health condition of rail track structures is crucial to prevent abnormal vibration issues of the wheel–rail system. To address the problem of low efficiency of traditional nondestructive testing methods, this work investigates the feasibility of the computer vision-aided health condition monitoring approach for track structures based on vibration signals. The proposed method eliminates the tedious and complicated data pre-processing including signal mapping and noise reduction, which can achieve robust signal description using numerous redundant features. First, the method converts the raw wheel–rail vibration signals directly into two-dimensional grayscale images, followed by image feature extraction using the FAST-Unoriented-SIFT algorithm. Subsequently, Visual Bag-of-Words (VBoW) model is established based on the image features, where the optimal parameter selection analysis is implemented based on fourfold cross-validation by considering both recognition accuracy and stability. Finally, the Euclidean distance between word frequency vectors of testing set and the codebook vectors of training set is compared to recognize the health condition of track structures. For the three health conditions of track structures analyzed in this paper, the overall recognition rate could reach 96.7%. The results demonstrate that the proposed method performs higher recognition accuracy and lower bias with strong time-varying and random vibration signals, which has promising application prospect in early-stage structural defect detection. © 2022, The Author(s).

9. RCIM

   One-shot, integrated positioning for welding initial points via co-mapping of cross and parallel stripes

   H. Liu, Y. Tian, L. Li, Y. Lu, F. Xi

   Robotics and Computer-Integrated Manufacturing, 2023

   Abs DOI

   Robotic welding is gradually advancing towards intelligent integrated welding with integration of different seam types. In this process, the initial point positioning of weld seams is a foremost technique for ensuring a smooth subsequent welding process. However, existing studies on welding initial point positioning are not well integrated in terms of different groove shapes and generally require robot movement to search multiple times. This problem entails a high development cost in varying welding scenarios and with efficiency to be improved. Meanwhile, robustness of positioning is an ongoing challenge, represented by workpiece tilt and misalignment. To cope with these issues, we developed an integrated vision sensor based on co-mapping of cross and parallel stripes to achieve one-shot initial point positioning within a defined area for four typical seam types. Among them, the cross stripes are used to extract workpiece edge parameters and the parallel stripes to extract seam parameters, both are sequential. At the core, we proposed an interval-restricted search algorithms to extract the seam points, and combine it with the edge parameters to obtain the initial points. In addition, a series of parametric analyses are performed for detecting workpiece misalignment and determining the initial points. Experimental results show that the co-mapping of cross and parallel stripes achieves one-shot high-competitive accuracy for the initial point positioning of the four seam types even if the workpiece is tilted or misaligned. © 2023 Elsevier Ltd

10. Manuf. Let.

    Dual task scheduling strategy for personalized multi-objective optimization of cycle time and fatigue in human-robot collaboration

    S. Chand, Y. Lu

    Manufacturing Letters, 2023

    Abs DOI

    The increased adoption of collaborative robots into human dominated work cells improves production efficiency of hard-to-automate manufacturing tasks. System-centric task scheduling objectives aim to fully utilize all available agents, often physically burdening workers with schedules designed maximized efficiency. Therefore, the modeling and optimization of human fatigue, as one of the main contributors to efficiency decline and adverse health conditions, is significant to task scheduling in Human-Robot Collaboration (HRC). Furthermore, HRC teams often involve drastically different workers with differing capabilities and muscle strengths – with direct implication toward their personalized fatigue responses. As such, we present a dual scheduling strategy for personalized multi-objective optimization of cycle time and fatigue considering recovery in HRC. The scheduling strategy involves two fatigue minimization objectives which either minimize the team’s fatigue state or an individual worker’s fatigue state. This balances fatigue accumulation between workers, providing targeted rest and recovery to specific workers while maintaining production efficiency. We designed a custom NSGA-III genetic algorithm for simultaneously minimizing cycle time and fatigue. Our model and algorithm are applied to an HRC assembly case and show promising results in redistributing tasks between agents to minimize personalized fatigue. © 2023 The Author(s)

11. J Manuf Syst

    Dynamic muscle fatigue assessment using s-EMG technology towards human-centric human-robot collaboration

    S. Chand, A. McDaid, Y. Lu

    Journal of Manufacturing Systems, 2023

    Abs DOI

    Human-centric human-robot collaboration (HHRC) allows seamless collaboration between humans and robots to fulfill flexible manufacturing operations in a shared workspace while maximizing operator autonomy and well-being toward optimal team performance. Therefore, assessing and monitoring an operator’s physical health, specifically fatigue, is paramount to maintaining a comfortable working environment. However, current fatigue assessment models are not suitable for characterizing the fatigue profile of target muscle groups against repetitive dynamic manufacturing operations non-invasively. To solve this problem, we created a theory for quantifying localized muscular fatigue by just understanding the relative task load and the number of repetitive operations the operator conducted. This was achieved by an experimentally proved multivariable linear relationship between localized muscular fatigue, task load, base muscle strength, and number of repetitive operations for an operation type via s-EMG technologies. We also showed the procedures for developing a personalized muscle fatigue profile for a variety of assembly operations via specialized s-EMG experiment design and measurement. This simple fatigue measurement mechanism allows us to constantly monitor operator fatigue via just monitoring repetitive operations conducted using non-invasive sensors, e.g., cameras. We also provide a framework for integrating our work for online fatigue monitoring in a human-robot collaboration system. © 2023 The Society of Manufacturing Engineers

12. Int J Computer Integr Manuf

    Digital twin and parameter correlation-enabled variant design of production lines

    D. Yan, J. Yang, X. Zhu, J. Leng, D. Zhang, Y. Lu, and 1 more author

    International Journal of Computer Integrated Manufacturing, 2023

    Abs DOI

    The rapid transformation of production lines into a new design scheme is the key to improving the market competitiveness of enterprises. The production line is a complex manufacturing system with a complex structure. There are multidisciplinary correlation networks between different design dimensions, such as causality, mapping, and transfer. Clarifying these correlative relations is the key to the design of production line correlation. In this paper, a descriptive system is built for the production line configuration model, the motion model, the control model, and the optimization model, and the design content of production lines is clarified. A design framework of production line correlation based on the digital twin technology is proposed, and an optimization system of design schemes is built in the form of hierarchical iteration. Polychromatic sets are used to identify the relationship between different dimensions. The high-fidelity simulation ability of the digital twin technology is taken advantage of to verify the proposed four-in-one variant design method in the mobile phone welding assembly line. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

2022

1. J Manuf Syst

   Outlook on human-centric manufacturing towards Industry 5.0

   Y. Lu, H. Zheng, S. Chand, W. Xia, Z. Liu, X. Xu, and 3 more authors

   Journal of Manufacturing Systems, 2022

   Abs DOI

   The recent shift to wellbeing, sustainability, and resilience under Industry 5.0 has prompted formal discussions that manufacturing should be human-centric – placing the wellbeing of industry workers at the center of manufacturing processes, instead of system-centric – only driven by efficiency and quality improvement and cost reduction. However, there is a lack of shared understanding of the essence of human-centric manufacturing, though significant research efforts exist in enhancing the physical and cognitive wellbeing of operators. Therefore, this position paper presents our arguments on the concept, needs, reference model, enabling technologies and system frameworks of human-centric manufacturing, providing a relatable vision and research agenda for future work in human-centric manufacturing systems. We believe human-centric manufacturing should ultimately address human needs defined in an Industrial Human Needs Pyramid – from basic needs of safety and health to the highest level of esteem and self-actualization. In parallel, human-machine relationships will change following a 5C evolution map – from current Coexistence, Cooperation and Collaboration to future Compassion and Coevolution. As such, human-centric manufacturing systems need to have bi-directional empathy, proactive communication and collaborative intelligence for establishing trustworthy human-machine coevolution relationships, thereby leading to high-performance human-machine teams. It is suggested that future research focus should be on developing transparent, trustworthy and quantifiable technologies that provide a rewarding working environment driven by real-world needs. © 2022 The Society of Manufacturing Engineers

2. RCIM

   Service-oriented industrial internet of things gateway for cloud manufacturing

   C. Liu, Z. Su, X. Xu, Y. Lu

   Robotics and Computer-Integrated Manufacturing, 2022

   Abs DOI

   Cloud manufacturing represents a service-oriented manufacturing paradigm that allows ubiquitous and on-demand access to various customisable manufacturing services in the cloud. While a vast amount of research in cloud manufacturing has focused on high-level decision-making tasks, such as service composition and scheduling, the link between field-level manufacturing data and the cloud manufacturing platform has not been well established. Efficient data acquisition, communication, storage, query, and analysis of field-level manufacturing equipment remain a significant challenge that hinders the development of cloud manufacturing systems. Therefore, this paper investigates the implementation of the emerging Industrial Internet of Things (IIoT) technologies in a cloud manufacturing system to address this challenge. We propose a service-oriented plug-and-play (PnP) IIoT gateway solution based on a generic system architecture of IIoT-supported cloud manufacturing system. Service-oriented data schemas for manufacturing equipment are developed to capture just-enough information about field-level manufacturing equipment and allow efficient data storage and query in a cloud time-series database (TSDB). We tested the feasibility and advantages of the proposed approach via the practical implementation of the IIoT gateways on a 3D printer and a machine tool. Our research suggests that purposely developed service-oriented data schemas that capture the essential information for high-level cloud manufacturing decision-making via PnP IIoT technologies are a good solution for connecting field-level manufacturing equipment to a cloud manufacturing platform. © 2021 Elsevier Ltd

3. RCIM

   An automatic method for constructing machining process knowledge base from knowledge graph

   L. Guo, F. Yan, T. Li, T. Yang, Y. Lu

   Robotics and Computer-Integrated Manufacturing, 2022

   Abs DOI

   The process knowledge base is the key module in intelligent process design, it determines the intelligence degree of the design system and affects the quality of product design. However, traditional process knowledge base construction is non-automated, time consuming and requires much manual work, which is not sufficient to meet the demands of the modern manufacturing mode. Moreover, the knowledge base often adopts a single knowledge representation, and this may lead to ambiguity in the meaning of some knowledge, which will affect the quality of the process knowledge base. To overcome the above problems, an automatic construction framework for the process knowledge base in the field of machining based on knowledge graph (KG) is introduced. First, the knowledge is classified and annotated based on the function-behavior-states (FBS) design method. Second, a knowledge extraction framework based on BERT-BiLSTM-CRF is established to perform the automatic knowledge extraction of process text. Third, a knowledge representation method based on fuzzy comprehensive evaluation is established, forming three types of knowledge representation with the KG as the main, production rules and two-dimensional data linked list as a supplement. In addition, to overcome the redundancy in the knowledge fusion stage, a hybrid algorithm based on an improved edit distance and attribute weighting is built. Finally, a prototype system is developed, and quality analysis is carried out. Compared with the F values of BiLSTM-CRF and CNN-BiLSTM-CRF, that of the proposed extraction method in the machining domain is increased by 7.35% and 3.87%, respectively. © 2021 Elsevier Ltd

4. RCIM

   Adaptive reconstruction of digital twins for machining systems: A transfer learning approach

   S. Liu, Y. Lu, P. Zheng, H. Shen, J. Bao

   Robotics and Computer-Integrated Manufacturing, 2022

   Abs DOI

   Digital twin technology has been gradually explored and applied in the machining process. A digital twin machining system creates high-fidelity virtual entities of physical entities to observe, analyze, and control the machining process in real-time. However, the current digital twin machining systems lack sufficient adaptability because they are usually customized for specific scenes. Usually, if a decision model is directly reused in a different working condition, the accuracy of the decision model is often poor and difficult to work effectively. Meanwhile, the decision model remodeled from scratch will cause a waste of resources and low modeling efficiency. This paper proposes an adaptive reconstruction method to adjust the decision model in the digital twin machining system to enhance adaptability. The proposed method can ensure the rapid development of the digital twin decision model under new working conditions. Finally, taking the drilling process as an example, this paper establishes the experimental drilling platform and verifies the feasibility of this method in the burr prediction task. © 2022

5. J Manuf Syst

   Establishing a reliable mechanism model of the digital twin machining system: An adaptive evaluation network approach

   S. Liu, Y. Sun, P. Zheng, Y. Lu, J. Bao

   Journal of Manufacturing Systems, 2022

   Abs DOI

   Digital twin technology can build virtual replicas of physical entities to observe, analyze, and control the machining process. The virtual model always simplifies the physical entity as limited by the current technical level, so that the digital twin model cannot fully reflect the physical entity with high-fidelity, leading to a particular error rate in the prediction and decision-making. Such systematic decision-making lacks enough reliability, which could mislead decision-makers and even lead to irreparable losses. To overcome this challenge, this paper constructs an adaptive evaluation network for the digital twin machining system (DTMS), where the decision-making error on the process route is formed into the network to evaluate its reliability. Finally, the feasibility of the proposed method is verified by the reliability evaluation on the DTMS of an aerospace part’s machining process. © 2021 The Society of Manufacturing Engineers

6. J Manuf Syst

   Dynamic reconfiguration optimization of intelligent manufacturing system with human-robot collaboration based on digital twin

   Q. Zhu, S. Huang, G. Wang, S.K. Moghaddam, Y. Lu, Y. Yan

   Journal of Manufacturing Systems, 2022

   Abs DOI

   In Industry 4.0, the emergence of new information technology and advanced manufacturing technology (e.g., digital twin, and robot) promotes the flexibility and smartness of manufacturing systems to deal with production task fluctuation. Digital twin-driven manufacturing system with human-robot collaboration is a typical paradigm of intelligent manufacturing. When production task changes, manufacturing system reconfiguration with dynamic opeartion task allocation between operator (human) and robot is a key manner to maintain the production efficiency of intelligent manufacturing system with human-robot collaboration. However, the differences between operator and robot are neglected during reconfiguration of manufacturing system with human-robot collaboration. To promote the reconfiguration accuracy and production efficiency, a dynamic reconfiguration optimization method of intelligent manufacturing system with human-robot collaboration based on digital twin is proposed in this paper, which the different characteristics between operator and robot are considered during reconfiguration optimiztion. Firstly, a multi-objectives optimization model is constructed involving minimum production cost, minimum production time, and minimum idle time to assign operation tasks between operator and robot, where human factor is considered to ensure the production efficiency of operator. Second, nondominated sorting genetic algorithm-II (NSGA-II) is adopted to solve the proposed dynamic reconfiguration optimization model. Finally, a case study is provided to demonstrate the effectiveness of the proposed reconfiguration optimization method for intelligent manufacturing system with human-robot collaboration. © 2022

7. IEEE Robot. Autom.

   Multi-Agent Reinforcement Learning for Real-Time Dynamic Production Scheduling in a Robot Assembly Cell

   D. Johnson, G. Chen, Y. Lu

   IEEE Robotics and Automation Letters, 2022

   Abs DOI

   As industry rapidly shifts towards mass personalisation, the need for a decentralised multi-agent system capable of dynamic flexible job shop scheduling (FJSP) is evident. Traditional heuristic and meta-heuristic scheduling methods cannot achieve satisfactory results and have limited application to static environments. Recent Reinforcement Learning (RL) approaches that consider dynamic FJSP, lack flexibility and autonomy as they use a single-agent centralised model, assuming global observability. As such, we propose a Multi-Agent Reinforcement Learning (MARL) system for scheduling dynamically arriving assembly jobs in a robot assembly cell. We applied a Double DQN-based algorithm and proposed a generalised observation, action and reward design for the dynamic FJSP setting. Using a centralised training phase, each agent (i.e., robot) in the assembly cell executes decentralised scheduling decisions based on local observations. Our solution demonstrated improved performance against rule-based heuristic methods, for optimising makespan. We also reported the impact of different observation sizes of each agent on optimisation performance. © 2016 IEEE.

8. J Manuf Syst

   3DSMDA-Net: An improved 3DCNN with separable structure and multi-dimensional attention for welding status recognition

   T. Liu, J. Wang, X. Huang, Y. Lu, J. Bao

   Journal of Manufacturing Systems, 2022

   Abs DOI

   The vision-based welding status recognition (WSR) provides a basis for online welding quality control. Due to the severe arc and fume interference in the welding area and limited computational resources at the welding edge nodes, it becomes a challenge to mine the most discriminative feature contained in welding images by using a lightweight model. In this paper, we propose an improved three-dimensional convolutional neural network (3DCNN) with separable structure and multi-dimensional attention (3DSMDA-Net) for WSR. The proposed 3DSMDA-Net uses 3DCNN to adaptively extract abstract spatiotemporal features in a welding process and then leverages such time sequence information to improve the recognition accuracy of WSR. In addition, we decompose the classical 3D convolution into depthwise convolution and pointwise convolution to produce a lightweight model. A multi-dimensional attention mechanism is further proposed to compensate for the loss of accuracy caused by the separation operation. The results of experiments reveal that the proposed method reduces the model size to 1/7 of the classical 3DCNN without sacrificing accuracy. The comparison experiment results have indicated that the accuracy of the proposed method is more accurate and noise-resistant than that of the conventional model. © 2021 The Society of Manufacturing Engineers

9. Int J Prod Res

   Dynamic inventory replenishment strategy for aerospace manufacturing supply chain: combining reinforcement learning and multi-agent simulation

   H. Wang, J. Tao, T. Peng, A. Brintrup, E.E. Kosasih, Y. Lu, and 2 more authors

   International Journal of Production Research, 2022

   Abs DOI

   The (I, R, S) policy is a well-known inventory replenishment strategy, where inventory is raised to an order-up-to-level S at the end of each review interval I, if it falls below a reorder-point R. Determining the optimal values for these parameters by mathematical analysis methods are difficult, especially in sectors with complex and uncertain purchasing, manufacturing and delivering processes. The (I, R, S) policy has been shown to result in low supply chain performance (SCP) composed of sales revenue, tardiness fine, manufacturing cost, inventory holding cost, raw material cost, etc. in industries that involve highly-customised orders, such as aerospace industry. In this paper, we develop a multi-agent simulation model combined with a reinforcement learning-based dynamic inventory replenishment strategy to maximise the SCP. The approach has been applied in an aerospace manufacturing case study. It empirically demonstrates that the dynamic strategy yields considerable improvements, and has an additional benefit of adaptivity to changes, such as demand and supply uncertainties. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

10. RCIM

    A fusion-based spiking neural network approach for predicting collaboration request in human-robot collaboration

    R. Zhang, J. Li, P. Zheng, Y. Lu, J. Bao, X. Sun

    Robotics and Computer-Integrated Manufacturing, 2022

    Abs DOI

    In human-robot collaborative (HRC) manufacturing systems, how the collaborative robots engage in the collaborative tasks and complete the corresponding work in a timely manner according to the actual state has been a critical factor that hinders the efficiency of HRC. Inappropriate collaborative behaviors will result in a poor perceptual experience for human operators (e.g., robots starting action too early or too late). To address this issue, a fusion-based spiking neural networks (FSNNs) approach for collaboration request prediction is proposed, aiming to find the right collaboration timing for robots in HRC assembly system and to minimize human aversion without affecting human operation behaviors. By encoding human behavior, product state and robot pose into spiking signals that can be processed by FSNNs, the spatio-temporal coupling relationship between those three aspects can be comprehensively analyzed, and to solve the appropriate timing of robot participation in collaboration. Finally, demonstrative experiments are carried out on the HRC assembly of generator end caps in the lab environment. Compared with the baseline methods, the decision accuracy of the proposed one is improved by nearly 30%, which further proves its effectiveness. © 2022 Elsevier Ltd

11. Result. Eng.

    Automated conversion of engineering rules: Towards flexible manufacturing collaboration

    X. Ye, Y. Lu, S. Manoharan

    Results in Engineering, 2022

    Abs DOI

    Rapid on-demand manufacturing resource sharing within and between factories are critical to achieving responsive autonomous manufacturing collaborations towards mass personalization. To this end, cloud manufacturing technologies allow resource owners/service providers to virtualize and encapsulate their resources as services accessible over the Internet. Decision-making in cloud manufacturing needs to utilize real-world engineering knowledge from different parties. Many existing systems have adopted the semantic web-based decision-making framework, in which engineering knowledge is modeled using structured syntax. However, manually converting engineering rules to semantic rules is time-consuming and error prone. This research proposes a machine learning model, based on the Transformer model, that uses neural machine translation techniques to convert engineering knowledge expressed in natural language to structured semantic rules directly. The model is implemented using neural network. The model is first trained using typical sentences that are used for describing engineering knowledge. From these sample sentences, the model learns the patterns and the meaning of the sentences. This allows the model to identify the service providers, resource users, and the resources described in the sentences. As a result, the corresponding semantic rules can be constructed. Compared with previous approaches, the proposed scheme not only improves the conversion accuracy but also reduces the amount of required human interaction, simplifying the system and its use. © 2022 The Authors

12. RCIM

    Semantic artificial intelligence for smart manufacturing automation

    Y. Lu, L. Wang, J. Bao, J.M. Lastra, F. Ameri

    Robotics and Computer-Integrated Manufacturing, 2022

    DOI
13. Meas J Int Meas Confed

    A general fault diagnosis framework for rotating machinery and its flexible application example

    H. Zheng, G. Cheng, Y. Lu, C. Liu, Y. Li

    Measurement: Journal of the International Measurement Confederation, 2022

    Abs DOI

    When dealing with the fault diagnosis of different rotating machines (gear or bearing), different working conditions (such as rotating speed), different signals (acoustic signal or vibration signal), it is usually necessary to establish different models, which is, however, time-consuming and laborious. At the same time, the models have poor generality and portability. In order to solve above problems, a general fault diagnosis framework (GFDF) is proposed in this paper. Firstly, the collected signals, whether vibration signals or acoustic signals, are directly converted into two-dimensional gray images; secondly, the FAST-Enhanced-Unoriented-SIFT (FEUS) feature extraction algorithm proposed in this paper is used to extract feature vectors; then, the feature vectors are encoded by using the bag-of-words (BoW) model to obtain the basic words and codebook vectors; finally, the fault diagnosis is completed by calculating the distance between the description vector of the signal to be diagnosed and the codebook vectors. GFDF’s main feature lies in the evitable frequency domain transformation and noise reduction, which makes GFDF insensitive to signal type and has high diagnostic efficiency. The experimental results show that GFDF has high diagnostic accuracy and stability for acoustic signals and vibration signals of rolling bearing and planetary gear at different rotating speeds, which proves that GFDF has generality and portability and is potential for the application in other scenes. Comparative experiments show that GFDF outperforms the representative traditional classification methods and deep learning models in diagnostic accuracy and stability. In addition, GFDF is applied to the fault diagnosis of the acoustic signals collected in motion to simulate the working state of inspection robots, and the ideal diagnostic result is also achieved. The flexible application example of this framework provides experience for other researchers. © 2022 Elsevier Ltd

14. Neural Comput. Appl.

    Special issue on computational intelligence-based modeling, control and estimation in modern mechatronic systems

    H. Wang, J. Zheng, Y. Lu, S. Ding, H. Chaoui

    Neural Computing and Applications, 2022

    DOI

2021

1. J Manuf Syst

   Industry 4.0 and Industry 5.0—Inception, conception and perception

   X. Xu, Y. Lu, B. Vogel-Heuser, L. Wang

   Journal of Manufacturing Systems, 2021

   Abs DOI

   Industry 4.0, an initiative from Germany, has become a globally adopted term in the past decade. Many countries have introduced similar strategic initiatives, and a considerable research effort has been spent on developing and implementing some of the Industry 4.0 technologies. At the ten-year mark of the introduction of Industry 4.0, the European Commission announced Industry 5.0. Industry 4.0 is considered to be technology-driven, whereas Industry 5.0 is value-driven. The co-existence of two Industrial Revolutions invites questions and hence demands discussions and clarifications. We have elected to use five of these questions to structure our arguments and tried to be unbiased for the selection of the sources of information and for the discussions around the key issues. It is our intention that this article will spark and encourage continued debate and discussion around these topics. © 2021

2. Adv. Eng. Inf.

   Digital Twin as a Service (DTaaS) in Industry 4.0: An Architecture Reference Model

   S. Aheleroff, X. Xu, R.Y. Zhong, Y. Lu

   Advanced Engineering Informatics, 2021

   Abs DOI

   Recent findings have shown that Digital Twin served multiple constituencies. However, the dilemma between the scope and scale needs a sophisticated reference architecture, a right set of technologies, and a suitable business model. Most studies in the Digital Twin field have only focused on manufacturing and proposed explicit frameworks and architecture, which faced challenges to support different integration levels through an agile process. Besides, no known empirical research has focused on exploring relationships between Digital Twin and mass individualization. Therefore, the principal objective of this study was to identify suitable Industry 4.0 technologies and a holistic reference architecture model to accomplish the most challenging Digital Twin enabled applications. In this study, a Digital Twin reference architecture was developed and applied in an industrial case. Also, Digital Twin as a Service (DTaaS) paradigm utilized for the digital transformation of unique wetlands with considerable advantages, including smart scheduled maintenance, real-time monitoring, remote controlling, and predicting functionalities. The findings indicate that there is a significant relationship between Digital Twin capabilities as a service and mass individualization. © 2020 Elsevier Ltd

3. J Manuf Syst

   Digital twin modeling method based on biomimicry for machining aerospace components

   S. Liu, J. Bao, Y. Lu, J. Li, S. Lu, X. Sun

   Journal of Manufacturing Systems, 2021

   Abs DOI

   High-performance aerospace component manufacturing requires stringent in-process geometrical and performance-based quality control. Real-time observation, understanding and control of machining processes are integral to optimizing the machining strategies of aerospace component manufacturing. Digital Twin can be used to model, monitor and control the machining process by fusing multi-dimensional in-context machining process data, such as changes in geometry, material properties and machining parameters. However, there is a lack of systematic and efficient Digital Twin modeling method that can adaptively develop high-fidelity multi-scale and multi-dimensional Digital Twins of machining processes. Aiming at addressing this challenge, we proposed a Digital Twin modeling method based on biomimicry principles that can adaptively construct a multi-physics digital twin of the machining process. With this approach, we developed multiple Digital Twin sub-models, e.g., geometry model, behavior model and process model. These Digital Twin sub-models can interact with each other and compose an integrated true representation of the physical machining process. To demonstrate the effectiveness of the proposed biomimicry-based Digital Twin modeling method, we tested the method in monitoring and controlling the machining process of an air rudder. © 2020 The Society of Manufacturing Engineers

4. J Manuf Syst

   Digital Twin-driven online anomaly detection for an automation system based on edge intelligence

   H. Huang, L. Yang, Y. Wang, X. Xu, Y. Lu

   Journal of Manufacturing Systems, 2021

   Abs DOI

   Accurate anomaly detection is critical to the early detection of potential failures of industrial systems and proactive maintenance schedule management. There are some existing challenges to achieve efficient and reliable anomaly detection of an automation system: (1) transmitting large amounts of data collected from the system to data processing components; (2) applying both historical data and real-time data for anomaly detection. This paper proposes a novel Digital Twin-driven anomaly detection framework that enables real-time health monitoring of industrial systems and anomaly prediction. Our framework, adopting the visionary edge AI or edge intelligence (EI) philosophy, provides a feasible approach to ensuring high-performance anomaly detection via implementing Digital Twin technologies in a dynamic industrial edge/cloud network. Edge-based Digital Twin allows efficient data processing by providing computing and storage capabilities on edge devices. A proof-of-concept prototype is developed on a LiBr absorption chiller to demonstrate the framework and technologies’ feasibility. The case study shows that the proposed method can detect anomalies at an early stage. © 2021 The Society of Manufacturing Engineers

5. J Manuf Syst

   A digital twin-driven human-robot collaborative assembly approach in the wake of COVID-19

   Q. Lv, R. Zhang, X. Sun, Y. Lu, J. Bao

   Journal of Manufacturing Systems, 2021

   Abs DOI

   In the wake of COVID-19, the production demand of medical equipment is increasing rapidly. This type of products is mainly assembled by hand or fixed program with complex and flexible structure. However, the low efficiency and adaptability in current assembly mode are unable to meet the assembly requirements. So in this paper, a new framework of human-robot collaborative (HRC) assembly based on digital twin (DT) is proposed. The data management system of proposed framework integrates all kinds of data from digital twin spaces. In order to obtain the HRC strategy and action sequence in dynamic environment, the double deep deterministic policy gradient (D-DDPG) is applied as optimization model in DT. During assembly, the performance model is adopted to evaluate the quality of resilience assembly. The proposed framework is finally validated by an alternator assembly case, which proves that DT-based HRC assembly has a significant effect on improving assembly efficiency and safety. © 2021 The Society of Manufacturing Engineers

6. RCIM

   Multi-scale evolution mechanism and knowledge construction of a digital twin mimic model

   S. Liu, Y. Lu, J. Li, D. Song, X. Sun, J. Bao

   Robotics and Computer-Integrated Manufacturing, 2021

   Abs DOI

   Metal products are susceptible to factors such as cutting force, clamping force and heat in the machining process, resulting in product quality problems, such as geometric deformation and surface defects. The real-time observation and control of product quality are integral to optimizing machining process. Digital twin technologies can be used to monitor and control the quality of products via multi-scale based quality analysis. However, previous research on digital twin lacks a fine-grained expression and generation method for product multi-scale quality, making it impossible to carry out an in-depth analysis of product quality. Aiming at addressing this challenge, we study the multi-scale evolution mechanism of the digital twin model and explore the knowledge generation method of the digital twin data. The proposed method constructed the digital twin quality knowledge model from the macro, meso, and micro levels by utilizing the data of the digital twin mimic model. These multi-scale quality knowledge models can express product quality in a fine-grained way and provide data support for digital twin-based decision-making. Finally, we tested the method in monitoring and controlling the machining quality of an air rudder to verify the feasibility of the proposed method. © 2021

7. Int J Adv Manuf Technol

   Machining process-oriented monitoring method based on digital twin via augmented reality

   S. Liu, S. Lu, J. Li, X. Sun, Y. Lu, J. Bao

   International Journal of Advanced Manufacturing Technology, 2021

   Abs DOI

   The change of size, surface roughness, residual stress, and so on profoundly influence the final machining quality of complex mechanical products. Digital twin machining technology can ensure machining quality by observing the machining process in real time. However, the current digital twin systems mainly adopt the display method of virtual-real separation. It leads to transmitting the useful processing information to the on-site technicians ineffectively, limiting the digital twin system to help field processing. The monitoring technology on the machining process by augmented reality based on the digital twin machining system is proposed to deal with this problem. Firstly, the augmented reality dynamic multi-view is constructed based on multi-source heterogeneous data. Secondly, the augmented reality is integrated into the real-time monitoring of the intermediate process of complex products to promote cooperation among the operators and the digital twin machining system. It can avoid irreparable errors when the finished product is nearly completed. Finally, the effectiveness and feasibility of the proposed method will be verified by a monitoring application case. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

8. J Manuf Syst

   Self-organizing manufacturing network: A paradigm towards smart manufacturing in mass personalization

   Z. Qin, Y. Lu

   Journal of Manufacturing Systems, 2021

   Abs DOI

   Mass personalization is becoming a reality. It requires responsive and flexible manufacturing operations for producing individualized products in dynamic batch sizes at scale in a cost-effective way. Therefore, manufacturing systems should timely respond to meet changing demands and conditions in the factory, in the supply network, and in customer needs. However, current manufacturing systems fail to adapt to dynamic production environments via changing system configurations and production plans while maintaining stable production performance. Therefore, a manufacturing system is required to be capable of self-optimizing manufacturing operations to achieve flexible, autonomous, and error-tolerant production in the mass personalization context. In this article, we systematically reviewed the literature on Self-Organizing Manufacturing Systems (SOMS) and proposed a complete concept of Self-Organizing Manufacturing Network (SOMN) as the next-generation manufacturing automation technologies for achieving mass personalization. Our review started by tracing the roots, origin, and state-of-the-art research of SOMS and concluded that the existing SOMS work could not achieve the mass personalization goal. As a focus of this review paper, we systematically discussed self-organizing manufacturing’s functional requirements to achieve mass personalization and proposed Self-Organizing Manufacturing Network. The concept, functions and essential technological system components (i.e., system modeling and control architecture, peer communications, and adaptive manufacturing control) are discussed by reviewing existing work and highlighting transferrable knowledge from other disciplines. Future research challenges are also discussed. © 2021 The Society of Manufacturing Engineers

9. Engineering

   Humans Are Not Machines—Anthropocentric Human–Machine Symbiosis for Ultra-Flexible Smart Manufacturing

   Y. Lu, J.S. Adrados, S.S. Chand, L. Wang

   Engineering, 2021

   DOI
10. Adv. Eng. Inf.

    An end-to-end tabular information-oriented causality event evolutionary knowledge graph for manufacturing documents

    B. Zhou, B. Hua, X. Gu, Y. Lu, T. Peng, Y. Zheng, and 2 more authors

    Advanced Engineering Informatics, 2021

    Abs DOI

    Industrial tabular information extraction and its semantic fusion with text (ITIESF) is of great significance in converting and fusing industrial unstructured data into structured knowledge to guide cognitive intelligence analysis in the manufacturing industry. A novel end-to-end ITIESF approach is proposed to integrate tabular information and construct a tabular information-oriented causality event evolutionary knowledge graph (TCEEKG). Specifically, an end-to-end joint learning strategy is presented to mine the semantic information in tables. The definition and modeling method of the intrinsic relationships between tables with their rows and columns in engineering documents are provided to model the tabular information. Due to this, an end-to-end joint entity relationship extraction method for textual and tabular information from engineering documents is proposed to construct text-based knowledge graphs (KG) and tabular information-based causality event evolutionary graphs (CEEG). Then, a novel NSGCN (neighborhoods sample graph convolution network)-based entity alignment is proposed to fuse the cross-knowledge graphs into a unified knowledge base. Furthermore, a translation-based graph structure-driven Q&A (question and answer) approach is designed to respond to cause analysis and problem tracing. Our models can be easily integrated into a prototype system to provide a joint information processing and cognitive analysis. Finally, the approach is evaluated by employing the aerospace machining documents to illustrate that the TCEEKG can considerably help workers strengthen their skills in the cause-and-effect analysis of machining quality issues from a global perspective. © 2021 Elsevier Ltd

11. RCIM

    A machining accuracy informed adaptive positioning method for finish machining of assembly interfaces of large-scale aircraft components

    W. Fan, L. Zheng, W. Ji, X. Xu, Y. Lu, L. Wang

    Robotics and Computer-Integrated Manufacturing, 2021

    Abs DOI

    An assembly interface of a large-scale aircraft component is a joint surface to connect adjacent large components. To guarantee the final assembly accuracy of the large components, the assembly interface is finish machined on site before the final assembly to cut the observed machining allowance. Thus, aiming at realizing the high efficiency and high quality in the finish machining operation, in this paper we propose an adaptive positioning method that integrates comprehensive engineering constrains (including Positioning Accuracy Constraints (PACs) of the large component and Machining Accuracy Constraints (MACs) of the assembly interface). In this method, the key Measurement Points (MPs) of a component are assigned to obtain its initial pose. Then the measurement data and the initial pose are used as input data to obtain the optimal pose parameters of the component based on an improved Particle Swarm Optimization Simulated Annealing (PSO-SA) algorithm. The optimal pose parameters can provide data support for the adaptive positioning of the large component, the function of which is implemented based on IEC 61499 Function Block (FB) technology. Finally, a positioning experiment of a vertical tail of a large passenger aircraft is used to validate the proposed method. The experimental results illustrate that the proposed method can improve the efficiency and positioning accuracy of the large component, compared to the traditional method. © 2020 Elsevier Ltd

12. Int J Computer Integr Manuf

    A hybrid 3D feature recognition method based on rule and graph

    L. Guo, M. Zhou, Y. Lu, T. Yang, F. Yang

    International Journal of Computer Integrated Manufacturing, 2021

    Abs DOI

    The implementation of automatic feature recognition (AFR) techniques is considered an indispensable concept in transferring product data between computer-aided design (CAD) and computer-aided process planning (CAPP). Different AFR techniques and systems have been developed to serve this aim; however, each of them have limitations. The main research gap is that each system is restricted to a specific set of predefined manufacturing features, which makes the universality of these methods difficult to extended. To solve this problem, a new hybrid 3D feature recognition method (graph and rule based) is proposed for recognizing machining features, and shaft parts are taken as an example in this paper. First, the reverse modeling method is used to classify the machining features in the part design process. Second, the 3D model is represented by B-Rep, and the weighted attribute adjacency matrix (WAAM) is proposed to represent the data structure of the B-Rep model. Third, the recognition and suppression rules are defined. Finally, three typical shaft parts are used as the test cases in MATLAB. The test results show hybrid feature recognition method can recognize all features. The comparative test shows that the practicability and efficiency of the method are satisfactory. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

13. Int J Computer Integr Manuf

    An automatic machining process decision-making system based on knowledge graph

    L. Guo, F. Yan, Y. Lu, M. Zhou, T. Yang

    International Journal of Computer Integrated Manufacturing, 2021

    Abs DOI

    Automatic process decision-making is a key module in intelligent process design(IPD), which determines the intelligence degree of IPD and affects the quality of product design. The traditional process decision-making method fails to solve the problem of knowledge expression, especially the integration of enterprise manufacturing resources and process knowledge. What’s more, heterogeneous knowledge also leads to the application of traditional knowledge mainly in keyword retrieval. So the process reasoning is mainly applied to the feature level, but the reasoning ability for the part level is weak. To overcome the above problems, the Knowledge Graph(KG) is introduced into the automatic machining process decision-making system. Firstly, a three-level information model is built to reorganize part information, process knowledge, and equipment resources based on KG. Secondly, the process reasoning framework based on KG is established, which is composed of process knowledge graph(PKG) information and process reasoning algorithm. Thirdly, to integrate process reasoning based on PKG, a hybrid reasoning algorithm based on semantic analysis(SA) and attributes weighting(AW) is built, which solved the problem of heterogeneity among process knowledge when making decisions. Finally, a prototype system was developed, and the aero-engine cone gear axis was tested to verify the effectiveness of the proposed system. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

14. Jixie Gongcheng Xuebao

    A Knowledge-Driven Digital Twin Modeling Method for Machining Products Based on Biomimicry [知识驱动的加工产品数字孪生拟态建模方法]

    S. Liu, X. Sun, Y. Lu, B. Wang, J. Bao, G. Guo

    Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2021

    Abs DOI

    Real-time observation, analysis, and control of the machining process are the critical parts of optimizing the machining strategy of parts. By fusing multi-dimensional and real-time processing data such as geometry, physical state and equipment state, the modeling and monitoring of the machining process can be realized. The digital twin model is the core and foundation of the digital twin system. However, there is still a lack of a systematic and adaptive development modeling method of high-fidelity, multi-scale, multi-dimensional digital twin model. A knowledge-driven digital twin mimic modeling method for machining products is proposed, which can adaptively construct the digital twin model during the machining process. According to the adaptive evolution of the machining process, the model can express the products in the process in real-time and provide data support for the digital twin decision-making system. Finally, the method is tested in a case on an aerospace part to verify the feasibility of applying the digital twin mimic model in machining. © 2021 Journal of Mechanical Engineering.

2020

1. RCIM

   Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues

   Y. Lu, C. Liu, K.I.-K. Wang, H. Huang, X. Xu

   Robotics and Computer-Integrated Manufacturing, 2020

   Abs DOI

   This paper reviews the recent development of Digital Twin technologies in manufacturing systems and processes, to analyze the connotation, application scenarios, and research issues of Digital Twin-driven smart manufacturing in the context of Industry 4.0. To understand Digital Twin and its future potential in manufacturing, we summarized the definition and state-of-the-art development outcomes of Digital Twin. Existing technologies for developing a Digital Twin for smart manufacturing are reviewed under a Digital Twin reference model to systematize the development methodology for Digital Twin. Representative applications are reviewed with a focus on the alignment with the proposed reference model. Outstanding research issues of developing Digital Twins for smart manufacturing are identified at the end of the paper. © 2019 Elsevier Ltd

2. J Manuf Syst

   Smart manufacturing process and system automation – A critical review of the standards and envisioned scenarios

   Y. Lu, X. Xu, L. Wang

   Journal of Manufacturing Systems, 2020

   Abs DOI

   Smart manufacturing is arriving. It promises a future of mass-producing highly personalized products via responsive autonomous manufacturing operations at a competitive cost. Of utmost importance, smart manufacturing requires end-to-end integration of intra-business and inter-business manufacturing processes and systems. Such end-to-end integration relies on standards-compliant and interoperable interfaces between different manufacturing stages and systems. In this paper, we present a comprehensive review of the current landscape of manufacturing automation standards, with a focus on end-to-end integrated manufacturing processes and systems towards mass personalization and responsive factory automation. First, we present an authentic vision of smart manufacturing and the unique needs for next-generation manufacturing automation. A comprehensive review of existing standards for enabling manufacturing process automation and manufacturing system automation is presented. Subsequently, focusing on meeting changing demands of efficient production of highly personalized products, we detail several future-proofing manufacturing automation scenarios via integrating various existing standards. We believe that existing automation standards have provided a solid foundation for developing smart manufacturing solutions. Faster, broader and deeper implementation of smart manufacturing automation can be anticipated via the dissemination, adoption, and improvement of relevant standards in a need-driven approach. © 2020 The Society of Manufacturing Engineers

3. Adv. Eng. Inf.

   IoT-enabled smart appliances under industry 4.0: A case study

   S. Aheleroff, X. Xu, Y. Lu, M. Aristizabal, J. Pablo Velásquez, B. Joa, and 1 more author

   Advanced Engineering Informatics, 2020

   Abs DOI

   Manufacturers expect the extra value of Industry 4.0 as the world is experiencing digital transformation. Studies have proved the potential of the Internet of Things (IoT) for reducing cost, improving efficiency, quality, and achieving data-oriented predictive maintenance services. Collecting a wide range of real-time data from products and the environment requires smart sensors, reliable communications, and seamless integration. IoT, as a critical Industry 4.0 enabler emerges smart home appliances for higher customer satisfaction, energy efficiency, personalisation, and advanced Big data analytics. However, established factories with limited resources are facing challenges to change the longstanding production lines and meet customer’s requirements. This study aims to fulfil the gaps by transforming conventional home appliances to IoT-enabled smart systems with the ability to integrate into a smart home system. An industry-led case study demonstrates how to turn conventional appliances to smart products and systems (SPS) by utilising the state-of-the-art Industry 4.0 technologies. © 2020 Elsevier Ltd

4. J. Manuf. Technol. Manage.

   Human Capital 4.0: a workforce competence typology for Industry 4.0

   E. Flores, X. Xu, Y. Lu

   Journal of Manufacturing Technology Management, 2020

   Abs DOI

   Purpose: The purpose of this paper is twofold: to raise and address an important change for the human capital in the future of Industry 4.0, and to propose a human-focused perspective for companies underneath the new Industrial Revolution. Design/methodology/approach: The research study follows a state-of-the-art literature review process. The nature of the selected approach enables to cover the extensive aim of the paper with sufficient scientific solidity that should support the understanding of every topic. Findings: This work has presented three relevant aspects for Industry 4.0 and its human labour force: a workforce architecture with new interactions, a term to embrace the human capital of the future and a typology for referencing the required competences for Industry 4.0. Research limitations/implications: The paper sheds light on an important aspect for the emerging Industrial Revolution, the human force. The result and conclusion sections suggest future implications for academia and the private sector, due to changes at the conceptual and practical levels of human operation in the industry – for example, new structural interactions among employees, additional qualities to human capital and different ways to identify the competences for the workforce. Originality/value: This is an interdisciplinary study that tries to bring together a modern industrial term, a social focus and a company scenario. From this, it was possible to obtain a new social term, a novel typology of competences and a new company-scenario interaction. © 2020, Emerald Publishing Limited.

5. J. Build. Eng.

   Robotic technologies for on-site building construction: A systematic review

   M. Gharbia, A. Chang-Richards, Y. Lu, R.Y. Zhong, H. Li

   Journal of Building Engineering, 2020

   Abs DOI

   Robotic technologies for building construction represent a significant departure from conventional construction approaches. The use of robots is likely to bring a host of opportunities that transform the way we design and construct buildings. To gain an improved understanding of the trend and trajectory of research on robotics application for on-site building construction, this paper provides a systematic review of 52 articles identified through the PRISMA protocol and meta-analysis. The results show that robotic technologies for on-site construction is a growing application field, where additive manufacturing (AM), automated installation system, automated robotic assembly system, autonomous robotic assembly, and robotic bricklaying seem to be most studied and have a potential to influence the development of robotics research in building construction. While most research discussed single construction activities related to vertical reinforced concrete (RC) elements, masonry walls, steel beams, curtain walls, gypsum boards, and floor tiles, only a few papers proposed an integrated robotized construction site. It is suggested that the building construction industry and research organizations could benefit from the current product and work processes that can be improved by taking some measures through innovative construction materials, improved robotics hardware, and more advanced engineering design to streamline construction workflows to achieve a complete on-site robotic system. © 2020 Elsevier Ltd

6. J Manuf Syst

   Semantic communications between distributed cyber-physical systems towards collaborative automation for smart manufacturing

   Y. Lu, M.R. Asghar

   Journal of Manufacturing Systems, 2020

   Abs DOI

   Machine-to-machine (M2M) communication is a crucial technology for collaborative manufacturing automation in the Industrial Internet of Things (IIoT)-empowered industrial networks. The new decentralized manufacturing automation paradigm features ubiquitous communication and interoperable interactions between machines. However, peer-to-peer (P2P) interoperable communications at the semantic level between industrial machines is a challenge. To address this challenge, we introduce a concept of Semantic-aware Cyber-Physical Systems (SCPSs) based on which manufacturing devices can establish semantic M2M communications. In this work, we propose a generic system architecture of SCPS and its enabling technologies. Our proposed system architecture adds a semantic layer and a communication layer to the conventional cyber-physical system (CPS) in order to maximize compatibility with the diverse CPS implementation architecture. With Semantic Web technologies as the backbone of the semantic layer, SCPSs can exchange semantic messages with maximum interoperability following the same understanding of the manufacturing context. A pilot implementation of the presented work is illustrated with a proof-of-concept case study between two semantic-aware cyber-physical machine tools. The semantic communication provided by the SCPS architecture makes ubiquitous M2M communication in a network of manufacturing devices environment possible, laying the foundation for collaborative manufacturing automation for achieving smart manufacturing. Another case study focusing on decentralized production control between machines in a workshop also proved the merits of semantic-aware M2M communication technologies. © 2020 The Society of Manufacturing Engineers

7. RCIM

   Function block-based closed-loop adaptive machining for assembly interfaces of large-scale aircraft components

   W. Fan, L. Zheng, W. Ji, X. Xu, L. Wang, Y. Lu, and 1 more author

   Robotics and Computer-Integrated Manufacturing, 2020

   Abs DOI

   To guarantee the docking accuracy of large-scale components, their assembly interfaces usually need to be finished before the final assembly. However, there are some crucial problems affecting finishing efficiency and quality, e.g. use of hard-to-machine material at the assembly interface, manual interventions and process diversity in finish machining, difficulties in the alignment of the large component, as well as errors between the as-built and as-designed status of the large component. These problems significantly enhance the uncertainty in finish machining on a shop floor. To solve these problems, this paper proposes an approach of adaptive process planning and execution, i.e., IEC 61499 Function Block (FB) based Closed-Loop Adaptive Machining (CLAM). Thus, the adaptive alignment of the large component is achieved, which can guarantee the correct location between the assembly interface and the cutting tool. As well as the on-line CLAM of the assembly interface is also realized to improve the machining efficiency and quality. As a result, a FB based CLAM system for the assembly interfaces is established, which contains a CAD system, a FB enabled High-Level Controller (HLC), and several Low-Level Controllers (LLCs), as well as a mechanical system. The most notable is that the related FBs are designed to plan and execute the finishing process. Finally, the proposed method and system are validated by a large component from a real aviation industry, i.e., a vertical tail of a passenger aircraft. The experimental results indicate that the proposed method and system are feasible and effective to address the above-mentioned problems. © 2020 Elsevier Ltd

8. J. Comput. Inf. Sci. Eng.

   Automatic extraction of engineering rules from unstructured text: A natural language processing approach

   X. Ye, Y. Lu

   Journal of Computing and Information Science in Engineering, 2020

   Abs DOI

   Manufacturers use cloud manufacturing platforms to offer their services. The literature has suggested a semantic web-based cloud manufacturing framework, in which engineering knowledge is modeled using structured syntax. Translating engineering rules to semantic rules by human is a painstaking task and prone to mistakes. We present a scheme that treats converting engineering knowledge into semantic rules as a machine translation task and uses neural machine translation techniques to carry out the conversion. © 2020 by ASME.

9. Arab. J. Sci. Eng.

   Experimental Investigation of the Surface Roughness of Finish-Machined High-Volume-Fraction SiCp/Al Composites

   J. Wang, L. Pan, Y. Bian, Y. Lu

   Arabian Journal for Science and Engineering, 2020

   Abs DOI

   Finish-machined high-volume-fraction SiCp/Al (SiC-particle-reinforced Al matrix) composites tend to have poor surface roughness. To explore the effects of various parameters on the surface roughness of these materials, an orthogonal experiment array L16 (4)4 was designed based on the tool nose radius, cutting depth, feed rate, and cutting speed. Surface roughness values were obtained using a TR200 portable roughness metre during finishing cutting experiments, which were conducted on a Mazak CNC lathe. The Taguchi approach and analysis of variance were used to analyse the significance of the various parameters. A model was developed based on a polynomial regression equation to predict the optimum surface roughness and its corresponding parameters. The confirmation experiments showed that there was good consistency in the optimum surface roughness between the predicted and experimental results. © 2020, King Fahd University of Petroleum & Minerals.

2019

1. RCIM

   Cloud-based manufacturing equipment and big data analytics to enable on-demand manufacturing services

   Y. Lu, X. Xu

   Robotics and Computer-Integrated Manufacturing, 2019

   Abs DOI

   Making manufacturing as on-demand cloud services is a transformative paradigm to achieve the required business flexibility in the context of Industry 4.0 via enabling rapid configuration of loosely-connected manufacturing devices to develop highly customized products. The research in this paper aimed to fill the gap that there is a lack of a feasible solution for cloud-based manufacturing equipment that can provide on-demand manufacturing services accessible via the Internet. The technical challenges in developing cloud-based manufacturing equipment and the enabling technologies are discussed. A generic system architecture for cloud-based manufacturing equipment based on cyber-physical production systems and big data analytics is proposed, allowing manufacturing equipment to be connected to the cloud and made available for the provision of on-demand manufacturing services. An industry implementation in a world-leading machinery solution provider confirms that the proposed system architecture for cloud-based manufacturing equipment can successfully enable on-demand manufacturing services provisioned via the Internet and can be extended to businesses that endeavor to transform legacy production systems into cloud-based cyber-physical production systems. © 2018 Elsevier Ltd

2. J Manuf Syst

   A Cyber-Physical Machine Tools Platform using OPC UA and MTConnect

   C. Liu, H. Vengayil, Y. Lu, X. Xu

   Journal of Manufacturing Systems, 2019

   Abs DOI

   Cyber-Physical Machine Tools (CPMT) represent a new generation of machine tools that are smarter, well connected, widely accessible, more adaptive and more autonomous. Development of CPMT requires standardized information modelling method and communication protocols for machine tools. This paper proposes a CPMT Platform based on OPC UA and MTConnect that enables standardized, interoperable and efficient data communication among machine tools and various types of software applications. First, a development method for OPC UA-based CPMT is proposed based on a generic OPC UA information model for CNC machine tools. Second, to address the issue of interoperability between OPC UA and MTConnect, an MTConnect to OPC UA interface is developed to transform MTConnect information model and its data to their OPC UA counterparts. An OPC UA-based CPMT prototype is developed and further integrated with a previously developed MTConnect-based CPMT to establish a common CPMT Platform. Third, different applications are developed to demonstrate the advantages of the proposed CPMT Platform, including an OPC UA Client, an advanced AR-assisted wearable Human-Machine Interface and a conceptual framework for CPMT powered cloud manufacturing environment. Experimental results have proven that the proposed CPMT Platform can significantly improve the overall production efficiency and effectiveness in the shop floor. © 2019 The Society of Manufacturing Engineers

3. J Intell Manuf

   ManuService ontology: a product data model for service-oriented business interactions in a cloud manufacturing environment

   Y. Lu, H. Wang, X. Xu

   Journal of Intelligent Manufacturing, 2019

   Abs DOI

   The ever-increasing distributed, networked and crowd-sourced cloud environment imposes the need of a service-oriented product data model for explicit representation of service requests in global manufacturing-service networks. The work in this paper aims to develop such a description framework for products based on semantic web technologies to facilitate the make-to-individual production strategy in a cloud manufacturing environment. A brief discussion on the requirements of a product data model in cloud manufacturing and research on product data modelling is given in the first part. A systematic ontology development methodology is then proposed and elaborated. The ontology called ManuService has been developed, consisting of all necessary concepts for description of products in a service-oriented business environment. These concepts include product specifications, quality constraints, manufacturing processes, organisation information, cost expectations, logistics requirements, and etcetera. ManuService ontology provides a module-based, reconfigurable, privacy-enhanced and standardised approach to modelling customised manufacturing service requests. An industrial case is presented to demonstrate possible applications using ManuService ontology. Comprehensive discussions are given thereafter, including a pilot application of a software package for semantic-based product design and a semantic web-based module for intelligent knowledge-based decision-making based on ManuService. ManuService forms the basis for collaborative service-oriented business interactions, intelligent and secure service provision in cloud manufacturing environment. © 2016, Springer Science+Business Media New York.

4. Comput Ind Eng

   Energy-efficient cyber-physical production network: Architecture and technologies

   Y. Lu, T. Peng, X. Xu

   Computers and Industrial Engineering, 2019

   Abs DOI

   Energy efficiency has become an integral aspect of today’s manufacturing. As manufacturing activities become increasingly distributed while connected in the new era of manufacturing – Industry 4.0, energy-efficient manufacturing strategies and methodologies should be implemented in a global production network. The research work reported in this paper endeavors to develop a feasible solution to implementing energy-efficient manufacturing in such an environment by proposing a technical architecture, integrated with the developed platform, MCloud. The overall technical architecture is discussed in detail, particularly, the proposed Energy-efficient Manufacturing (E2M) module and two-round communication procedure. Feature-based technology was adopted in process planning to assess the technical capability and energy consumption of connected virtual factories. MCloud allows each party in this production network to use local energy consumption models for energy assessment with great flexitity and privacy protection. A case study was presented to demonstrate the way distributed manufacturers collaboratively work on a manufacturing job, proving that the enhanced MCloud can coordinate customized production activities based on energy-saving needs in an Industry 4.0 environment. © 2019 Elsevier Ltd

2018

1. J Manuf Syst

   Resource virtualization: A core technology for developing cyber-physical production systems

   Y. Lu, X. Xu

   Journal of Manufacturing Systems, 2018

   Abs DOI

   Smart factory in the context of Industry 4.0 is the next wave of smart manufacturing solution to empower companies to rapidly configure manufacturing facilities and processes to enable the fast production of individualized products at change scales. A key enabling technology for developing a smart factory is resource virtualization or creation of digital twins. The presented research fills the gap that the industry needs a practical methodology to enable themselves to easily virtualize their manufacturing assets for developing a smart factory solution. A test-driven resource virtualization framework is proposed as the recommendation for the industry to adopt to create digital twins for a smart factory. The proposed framework draws inspiration from past resource virtualization outcomes with special attention paid to the usability of the proposed framework in a business environment. It provides a straightforward process for companies to create digital twins by specifying the digital twin hierarchy, the information to be modeled, and the modeling method. To validate the proposed framework, a case study was undertaken at an international company, to create digital twins for all their manufacturing resources. The testing result showed that the proposed resource virtualization framework and developed tools are easy to use in a practical business environment to virtualize complex factory setups in the cyberspace. © 2018

2. Jixie Gongcheng Xuebao

   Design Method and Characteristics Study on Actuator of Giant Magnetostrictive Harmonic Motor [超磁致伸缩谐波电机致动器设计方法与特性研究]

   L. Zhu, X. Cao, Y. Lu

   Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2018

   Abs DOI

   The common harmonic gear drive must be input motion and power by the motor and wave generator, which being low space efficiency, large inertia and poor response, therefore, an active harmonic motor driven by giant magnetostrictive material is proposed. Actuator, as the power source and energy conversion device of harmonic motor, has strict requirements for magnetic field intensity, uniformity, magnetic leakage and space restriction. Accordingly, a structure layout of bias magnetic field produced by segmentally built-in permanent magnet is put forward, which could make full use of space and improve uniformity. The main parameters of actuator are designed, and then of further optimization is carried out by analyzing the influence factors on intensity and uniformity of bias and driving magnetic field. Based on the optimized results, the actuator is modeled and manufactured, thereafter, its magnetic field characteristics of actuator are simulated and analyzed by finite element method (FEM), and the output characteristics are verified by experiments. It shows that structure composed of segmentally built-in permanent magnet has few magnetic leakage, moreover, the proposed design theory and method not only guaranteed the magnetic field intensity and uniformity, but also make the actuator working in a linear range, the law of output meeting the requirements of gearing, and easier to control accurately, which lays the foundation for the practical application of giant magnetostrictive harmonic motor. © 2018 Journal of Mechanical Engineering.

2017

1. J Manuf Syst

   A semantic web-based framework for service composition in a cloud manufacturing environment

   Y. Lu, X. Xu

   Journal of Manufacturing Systems, 2017

   Abs DOI

   Cloud manufacturing has been recognised as a transformative manufacturing paradigm to enable rapid production of highly customised products in a networked environment, through on-demand consumption of cloud-based manufacturing services. The fundamental issue of on-demand manufacturing service provision is service composition, where distributed manufacturing resources are mapped to personalised service requests. This paper examines knowledge-based service composition and adaptive resource planning in a cloud manufacturing environment. The intention is to develop an integrated networked environment, allowing fast resource allocation for a given service request, subject to governance policies, resource access policies, resource availability information and etcetera. The research challenge in this is to explore a feasible service composition method that facilitates easy mapping between service requests and manufacturing resources based on restrictive rule sets in the cloud and availability information about a resource. The research work in this paper analyses the relevant research challenges, proposes a practical approach and implements the solution in the form of a web-based system. The proposed system utilises distributed knowledge for intelligent service composition and adaptive resource planning. A case study is also presented to validate the performance of the proposed approach. © 2016 The Society of Manufacturing Engineers

2. RCIM

   A system framework for OKP product planning in a cloud-based design environment

   P. Zheng, Y. Lu, X. Xu, S.Q. Xie

   Robotics and Computer-Integrated Manufacturing, 2017

   Abs DOI

   Nowadays, one-of-a-kind (OKP) companies, which generally operate in an ’engineer-to-order’ business mode, strive to deliver individualized products with quality to achieve customer satisfaction. Thus, an accurate and prompt analysis of customer requirements (CRs) in the early design stage is critical to its success. However, most OKP companies are small or medium-sized enterprises (SMEs). Due to the limited resources and low product planning budget, they often cannot obtain abundant CR information nor can they afford the expense of complicated planning process. To address these issues, a system framework is proposed in support of OKP product planning process in a cloud-based design (CBD) environment. The challenges and future market niches of OKP companies are presented. The comparison of typical distributed systems shows that CBD, which utilizes advanced information technologies and business model, has advantages in providing sufficient resources, decreasing product development time span for OKP companies in a cost-efficient way. This article describes the proposed system architecture, the business interaction process and the information communication among customers, designers and marketing analysts at the product planning stage. To validate the proposed framework, a prototype system module MyProduct is under development in the CBD environment with an illustrative example. © 2016 Elsevier Ltd

2015

1. Manuf. Let.

   Computer-Integrated Manufacturing, Cyber-Physical Systems and Cloud Manufacturing - Concepts and relationships

   C. Yu, X. Xu, Y. Lu

   Manufacturing Letters, 2015

   Abs DOI

   Computers are deeply entrenched in modern manufacturing systems, giving rise to technologies such as Computer Integrated Manufacturing, Cyber-Physical Systems and most recently Cloud Manufacturing. These technologies have evolved based on existing or similar technologies or manufacturing paradigms. Some misunderstandings exist among these technologies. In spite of similarities, there are sufficient differences among themselves. To start off, the circumstances under which these technologies were incepted and developed are different. There are different methodologies associated with them. Discussions in this paper are made in relationship to Information Technology, Industry and Services. © 2015 Society of Manufacturing Engineers (SME).

2014

1. J Manuf Syst

   Development of a Hybrid Manufacturing Cloud

   Y. Lu, X. Xu, J. Xu

   Journal of Manufacturing Systems, 2014

   Abs DOI

   Cloud manufacturing is emerging as a novel business paradigm for the manufacturing industry, in which dynamically scalable and virtualised resources are provided as consumable services over the Internet. A handful of cloud manufacturing systems are proposed for different business scenarios, most of which fall into one of three deployment modes, i.e. private cloud, community cloud, and public cloud. One of the challenges in the existing solutions is that few of them are capable of adapting to changes in the business environment. In fact, different companies may have different cloud requirements in different business situations; even a company at different business stages may need different cloud modes. Nevertheless, there is limited support on migrating to different cloud modes in existing solutions. This paper proposes a Hybrid Manufacturing Cloud that allows companies to deploy different cloud modes for their periodic business goals. Three typical cloud modes, i.e. private cloud, community cloud and public cloud are supported in the system. Furthermore, it enables companies to set self-defined access rules for each resource so that unauthorised companies will not have access to the resource. This self-managed mechanism gives companies full control of their businesses and boosts their trust with enhanced privacy protection. A unified ontology is developed to enhance semantic interoperability throughout the whole process of service provision in the clouds. A Cloud Management Engine is developed to manage all the user-defined clouds, in which Semantic Web technologies are used as the main toolkit. The feasibility of this approach is verified through a group of companies, each of which has complex access requirements for their resources. In addition, a use case is carried out between customers and service providers. This way, optimal service is delivered through the proposed system. © 2014 The Society of Manufacturing Engineers.

2. Int. J. Manuf. Res.

   Ontology for manufacturing resources in a cloud environment

   Y. Lu, Q. Shao, C. Singh, X. Xu, X. Ye

   International Journal of Manufacturing Research, 2014

   Abs DOI

   Cloud manufacturing is a model for enabling on-demand network access to a shared pool of reconfigurable manufacturing resources that can be rapidly encapsulated, provisioned and released as manufacturing services. Enterprises involved in cloud manufacturing networks share their heterogeneous business models, manufacturing resources and knowledge to provide high quality consumable manufacturing services. Therefore, there is a need to develop a resource description protocol and service description language to cover all the aspects of cloud-based business collaborations in manufacturing industry. This information model needs to be inclusive of representation of all phases of a product’s lifecycle, service model description, and other essential information contributed to e-businesses. This paper presents an ontology-based approach to enable sematic interoperability throughout the whole process of service provision in the clouds. The detailed requirements for enabling cloud-based data exchange are discussed. A generic ontology development process is then proposed with special focus on reusing existing international and/or industrial standards. Specifically highlighted is a systematic guidance on developing ontologies. The utilisation of the proposed ontology in resource virtualisation and resource retrieval in cloud manufacturing environments is also elaborated. Copyright © 2014 Inderscience Enterprises Ltd.

2023

1. IEEE CASE

   Editorial Proceedings of 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE) - Automation for a Resilient Society

   X. Xu, B. Vogel-Heuser, Y. Lu

   2023

   DOI