Yuqian Lu

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

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

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

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

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.

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.

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

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)

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