Journal of Manufacturing Systems最新文献

{"title":"A novel digital twins-driven mutual trust framework for human–robot collaborations","authors":"Junfei Li ,&nbsp;Enshen Zhu ,&nbsp;Wenjun Lin ,&nbsp;Simon X. Yang ,&nbsp;Sheng Yang","doi":"10.1016/j.jmsy.2025.04.009","DOIUrl":"10.1016/j.jmsy.2025.04.009","url":null,"abstract":"<div><div>Trust plays an important role and significantly influences human–robot collaborations (HRC). However, most previous research on trust only emphasizes the human attitude toward robots. There needs more understanding of human uncertainties that may also cause disruptions of trust in collaborations. This paper presents a novel mutual trust framework to provide a relatable vision for future development in HRC from an integrated perspective via the integration of human and robotic digital twins. More specifically, a comprehensive review of current trust research in HRC is first provided, including trust factors and state-of-the-art trust models. Second, a novel human–robot mutual trust framework based on 5-layer digital twins models is introduced. The mutual trust framework highlights the interactions amongst modules of artificial intelligence, simulation, and operation, which can provide wide services in HRC (e.g., task allocation and motion planning). A case study of solving a path planning problem is exemplified to evaluate the performance of the proposed mutual trust framework. Compared with singular trust models, the proposed framework enables robotic systems with real-time response and adaptation to human behavior. Some limitations and future work of the mutual trust framework are elaborated in the end.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 948-962"},"PeriodicalIF":12.2,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic 3D inspection method for AR-assisted assembly based on virtual-to-real registration","authors":"Zhang Yan ,&nbsp;Fu Hongyong ,&nbsp;Jiang Xinyuan ,&nbsp;Qi Xinlong ,&nbsp;Cui Enze ,&nbsp;Zhang Lu","doi":"10.1016/j.jmsy.2025.04.013","DOIUrl":"10.1016/j.jmsy.2025.04.013","url":null,"abstract":"<div><div>Augmented reality (AR) has been widely employed in intelligent assembly tasks to improve assembly efficiency by layering virtual instructions onto real assemblies, providing operators with step-by-step guidance. However, current AR-assisted assembly systems are limited to being visualization tools, requiring manual control of the guide program by operators and potentially causing distractions and increased operational load. Furthermore, these systems lack the ability to detect incorrect assembly during operation, leading to assembly failures without manual inspection. To address these issues, we propose an automatic 3D inspection method based on virtual-to-real registration that leverages cross-domain texture registration and 6D pose registration to align real assembly images with virtual 3D CAD models. This method conducts a 3D assembly inspection by assessing the similarities between real assembly and its virtual CAD instruction, not only from texture but also from spatial pose relations, improving inspection accuracy while retaining 2D real-time computing. By integrating the inspection results, the AR system can automatically verify assembly correctness and proceed to the next guide program only when a successful assembly is confirmed, eliminating any need for extra instructions from the operator. In case of assembly failure, the computed results are fed back to the operator to assist in correcting errors during assembly, thereby improving assembly efficiency.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 933-947"},"PeriodicalIF":12.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated pallet loading of irregularly shaped objects: A deep reinforcement learning and multi-criteria optimization method","authors":"Nikolaos Theodoropoulos,&nbsp;Dionisis Andronas,&nbsp;Emmanouil Kampourakis,&nbsp;Sotiris Makris","doi":"10.1016/j.jmsy.2025.04.014","DOIUrl":"10.1016/j.jmsy.2025.04.014","url":null,"abstract":"<div><div>Palletizing in manufacturing presents a formidable challenge, particularly when dealing with irregularly shaped objects. This paper introduces a novel approach to optimizing pallet loading scenarios integrating Deep Reinforcement Learning (DRL) and heuristic methods with stability assessment and constraint satisfaction within an automated palletization pipeline. The proposed solution consists of four key components. First, each object undergoes preprocessing, involving shape extraction from data files and the generation of metrics to evaluate stability and palletization suitability. Subsequently, object selection is performed using either a DRL agent—trained to predict optimal loading sequences—or a rule-based prioritization strategy, enabling a comparative analysis of selection methods. Constraint satisfaction techniques are then applied to narrow down the search space for candidate placement positions. Finally, optimal object placement is determined using a Multi-Criteria Decision-Making (MCDM) approach that evaluates candidate positions and orientations based on weighted performance criteria. The proposed framework is validated through a case study in the architectural aluminum industry, demonstrating its pivotal role in automating a production line responsible for sorting and packaging customer orders.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 916-932"},"PeriodicalIF":12.2,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing IC substrate manufacturing through differential geometry and lightweight networks for etching defect detection","authors":"Yongxing Yu ,&nbsp;Dan Huang ,&nbsp;Yueming Hu","doi":"10.1016/j.jmsy.2025.04.006","DOIUrl":"10.1016/j.jmsy.2025.04.006","url":null,"abstract":"<div><div>With the advancement of high-density interconnect technology in semiconductor manufacturing, the precision and complexity of integrated circuit (IC) substrates have significantly increased, placing higher demands on quality control. Efficient and accurate detection of complex etching defects, which often occur during manufacturing, has become critical to preventing potential product defects. A defect detection method is proposed that combines a lightweight network with differential geometry tools to address the issue of etching defects in IC substrates. First, an improved deformable model is used to rapidly extract regular circuit trace contours from complex metallographic images, and morphological processing is applied to enhance the details, achieving precise image segmentation. For under-etching defects between circuit traces, differential processing of the original and segmented images is performed to locate abnormal regions. Subsequently, an optimized lightweight network based on MobileNet, termed OMNet, is designed to achieve the rapid identification of under-etching defects in these regions. For etching defects occurring on circuit traces, the DGEtch method employs a high-precision discrete curvature calculation based on the Frenet frame to evaluate angular discontinuities in contours, enabling accurate detection of etching defects. Experimental results demonstrate that the proposed method achieves an average recall rate of over 95% and maintains a precision above 90%. It exhibits high accuracy and stability in detecting etching defects and consistently outperforms existing models, particularly in handling complex mixed defects. This study provides an effective solution for detecting complicated defects in high-density IC substrate manufacturing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 902-915"},"PeriodicalIF":12.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A survey of large language model-augmented knowledge graphs for advanced complex product design","authors":"Xinxin Liang,&nbsp;Zuoxu Wang,&nbsp;Jihong Liu","doi":"10.1016/j.jmsy.2025.04.016","DOIUrl":"10.1016/j.jmsy.2025.04.016","url":null,"abstract":"<div><div>In the Human-AI collaboration rapid development era, the design and development of knowledge-intensive complex products should enable the design process with the help of advanced AI technology, and enhance the reasoning and application of design domain knowledge. Extracting and reusing domain knowledge would greatly facilitate the success of complex product design. Knowledge graphs (KGs), a powerful knowledge representation and storage technology, have been widely deployed in advanced complex product design because of their advantages in mining and applying large-scale, complex, and specialized domain knowledge. But merely KG and its related reasoning approaches still cannot fully support the ill-defined product design tasks. In the future complex product design, Human-AI collaboration will become a mainstream prevention trend. Large language models (LLMs) have outstanding performance in natural language understanding and generation, showing promising potential to collaborate with KGs in complex product design and development. Till 2024/03/04, only a few studies have systematically reviewed the current status of LLM and KG applications in the engineering field, not to mention a further detailed review in the complex product design field, leaving many issues not covered or fully examined. To fill this gap, 100 articles published in the last 4 years (i.e., 2021–2024) were screened and surveyed. This study provides a statistical analysis of the screened research articles, mainstream techniques of LLM &amp; KG, and LLM &amp; KG applications were analyze. To understand how KG and LLM could support complex product design, a framework of LLMs-augmented KG in advanced complex product design was proposed, which contains data layer, KG &amp; LLM collaboration layer, enhanced design capability layer, and design task layer. Furthermore, we also discussed the challenges and future research directions of the LLM-KG-collaborated complex product design paradigm. As an exploratory review paper, it provides insightful ideas for implementing more specialized domain KGs in product design field.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 883-901"},"PeriodicalIF":12.2,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143882806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic simulation models generation in industrial systems: A systematic literature review and outlook towards simulation technology in the Industry 5.0","authors":"Antonio Cimino ,&nbsp;Mohaiad Elbasheer ,&nbsp;Francesco Longo ,&nbsp;Giovanni Mirabelli ,&nbsp;Vittorio Solina ,&nbsp;Pierpaolo Veltri","doi":"10.1016/j.jmsy.2025.03.027","DOIUrl":"10.1016/j.jmsy.2025.03.027","url":null,"abstract":"<div><div>Simulation models are a crucial enabling technology for decision support in the ongoing industrial digitalization hype. Within Industry 4.0, simulations are extensively utilized, providing insights into industrial behavior and responses. As we progress towards Industry 5.0, simulation models continue to play a pivotal role in achieving sustainable, resilient, and human-oriented industrial systems. However, a persistent challenge within Industry 4.0/5.0 is the substantial dynamism of industrial environments. This dynamic and complex landscape necessitates the development of adaptive solutions capable of swiftly responding to the volatile process requirements of modern industrial systems. To this end, Automatic Simulation Model Generation (ASMG) offers an innovative methodological framework to address this practical challenge in the development of industrial simulation models. Employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, this research systematically reviews the current state-of-the-art in ASMG. Complemented by a bibliometric and content analysis of 61 articles spanning more than two decades (from 2000 to 2023), the paper evaluates ASMG’s progression and application in manufacturing through four research questions focusing on ASMG development strategies, objectives, essential data, and developing environments. Ultimately, this article provides valuable insights into ASMG perspective for industrial simulation specialists and offers guidelines for future developments in the era of Industry 5.0.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 859-882"},"PeriodicalIF":12.2,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A methodology for estimating the cost of a digital twin","authors":"Shuo Su ,&nbsp;Aydin Nassehi ,&nbsp;Adam McClenaghan ,&nbsp;Andrew Langridge ,&nbsp;Ben Hicks","doi":"10.1016/j.jmsy.2025.04.004","DOIUrl":"10.1016/j.jmsy.2025.04.004","url":null,"abstract":"<div><div>This paper proposes a methodology for estimating the cost of developing digital twins (DTs) in manufacturing processes. It formulates a cost model that identifies main cost elements and presents the estimation process for establishing an acceptable cost reference based on a given set of physical information entities as DT inputs. To achieve this, six core data activities are derived from the ISO 23247 DT reference framework and the Digital Twin Data concept to characterize the functioning of DTs from a data perspective. These activities are data gathering, data interaction, data storage, data processing, data servitization, and data maintenance. The activity-based costing (ABC) method is applied to allocate six resources in the development of DTs (personnel, machine, equipment, material, facility, and service) to these data-intensive activities. The resultant cost structure comprises 40 cost activities, along with associated quantitative metrics. This work presents a case study on developing a DT for estimating the dimensional accuracy in the MEX process, where thermal and acceleration measurements are considered. For the information set with extruder and build plate temperatures as well as X- and Y-axis acceleration, developing a DT is estimated to cost between £4780 (for one temperature signal) and £39,285 (for two temperature signals and two acceleration signals) for two years of service and one year of data archiving. In addition, the cost distribution across four categories (IT infrastructure, resource, data activity, and investment) are analysed. The derived insights can support cost-related analysis, physical information entity selection, budget control, and standard open databases for DT costs.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 841-858"},"PeriodicalIF":12.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Out-of-order enabled operating system for uncertain planning, scheduling and execution in aviation maintenance","authors":"Fan Yang ,&nbsp;Cheng Ren ,&nbsp;Wei Liu ,&nbsp;Mingxing Li ,&nbsp;Ming Li","doi":"10.1016/j.jmsy.2025.04.011","DOIUrl":"10.1016/j.jmsy.2025.04.011","url":null,"abstract":"<div><div>Maintenance has long been a concern in manufacturing, both in the production and product-service phases. As a type of large product, aviation maintenance produces a collection of services to ensure that aircrafts or aircraft systems, components, and structures meet airworthiness standards. Planning, scheduling, and execution (PSE) is important for maintenance systems to optimize resource utilization and job sequencing through decision-making at different time cycles. However, stochastic uncertainty always exists, affecting the stability of the entire maintenance process. Therefore, in this study, which was inspired by operating systems (i.e., Windows, Android, etc.) for processing uncertain user actions with high efficiency, an out-of-order enabled operation system in aviation maintenance (OoO-AMOS) is designed to mitigate the influence of uncertainties that exist in the PSE procedure. Two key components, namely, thread manager and resource manager, are proposed at the kernel level of the OoO-AMOS. The concept of out-of-order (OoO) is deployed for the thread manager to dynamically select the optimal order sequence based on task dependencies and feasibility. A finite state machine (FSM) model is integrated as the operation validation mechanism to formulize the resource states and their transitions. Finally, a case study is conducted to evaluate the effectiveness of the proposed OoO-AMOS. The results show that OoO-AMOS presents significant advantages over traditional approaches. In uncertain environments, the total setup time was reduced by more than 55 %, whereas the maintenance makespan, average order tardiness, and hangar turnover rate achieved improvements of more than 22 %, 31 %, and 23 %, respectively.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 824-840"},"PeriodicalIF":12.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Q-learning improved differential evolution algorithm for human-centric dynamic distributed flexible job shop scheduling problem","authors":"Xixing Li ,&nbsp;Ao Guo ,&nbsp;Xiyan Yin ,&nbsp;Hongtao Tang ,&nbsp;Rui Wu ,&nbsp;Qingqing Zhao ,&nbsp;Yibing Li ,&nbsp;XiVincent Wang","doi":"10.1016/j.jmsy.2025.04.001","DOIUrl":"10.1016/j.jmsy.2025.04.001","url":null,"abstract":"<div><div>Traditional scheduling less account of human-related dynamic events: worker skill degradation and worker mandatory rest. However, in actual production, workers experience fatigue accumulation that decreases work efficiency, thereby decreasing the precision of jobs, increasing rework rates, and even elevating processing risks. It conflicts with the idea of industrial resilience and human well-being for Industry 5.0. Therefore, a human-centric dynamic distributed flexible job shop scheduling problem (HDDFJSP) has been researched in this paper. Firstly, a multi-objective mathematical model of HDDFJSP is proposed to minimize makespan, worker fatigue, and scheduling deviation. Secondly, a Q-learning improved differential evolution (QLIDE) is designed to solve the HDDFJSP. In the QLIDE, a new four-layer encoding method and two initialization strategies are proposed to generate a high-quality initial population and a novel mutation strategy and two auxiliary mutation methods are designed to enhance the algorithm's exploitation capabilities. Furthermore, three neighborhood search strategies are introduced and combined with mutation operations as part of the Q-learning action phase to improve population convergence and diversity. Thirdly comparative test with four other well-known algorithms has been conducted and the results demonstrate the significant superiority of the QLIDE. Finally, the QLIDE is applied to solve a real case of a labor intensive hydraulic cylinder manufacturing enterprise. The results indicate that considering rescheduling can effectively help production managers to handle dynamic event of humans during the intelligent manufacturing systems.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 794-823"},"PeriodicalIF":12.2,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-level root cause analysis method for production anomalies in manufacturing workshops","authors":"Shengbo Wang ,&nbsp;Yu Guo ,&nbsp;Shaohua Huang ,&nbsp;Qunfen Qi ,&nbsp;Sai Geng ,&nbsp;Weiwei Qian","doi":"10.1016/j.jmsy.2025.04.008","DOIUrl":"10.1016/j.jmsy.2025.04.008","url":null,"abstract":"<div><div>Production anomalies, being one of the main causes of disrupted production schedules and product quality issues, have driven the manufacturing industry to focus on real-time monitoring and effective management, as these measures undoubtedly ensure production continuity and enhance efficiency. The complexity of discrete manufacturing workshops—characterized by diverse products, complex process routes, and frequent disturbances—leads to a corresponding complexity in the occurrence and evolution of production anomalies. Unlike point-to-point models for root cause analysis of production anomalies, this paper proposes a multi-level root cause analysis model for production anomalies to reveal the key influencing factors in their evolution process. First, to address the challenge of single-dimensional manufacturing data failing to effectively represent complex production states, production state representation models of manufacturing elements are built based on a first-order graph model of manufacturing elements, enabling consistent expression of production states. Second, a production anomaly evolution pattern analysis model based on a nonlinear Granger model is proposed to answer the questions of how production anomalies arise and evolve. Then, considering the imbalance in production anomalies, a meta-learning Transformer model is designed to learn evolution patterns of production anomalies and enable root cause analysis. Finally, using a real discrete manufacturing workshop as an example, the proposed method can accurately analyze the evolution patterns of production anomalies. In the evolution pattern learning task, it achieves better learning performance and is at least 69.5 % higher than the baseline models on the root mean square error. Additionally, the method achieves an accuracy of 81.67 % in identifying the top three root cause states of production anomalies. The research results demonstrate that nonlinear networks can effectively analyze the complex evolution processes of production anomalies and enhance the Granger model's accuracy in identifying the evolution patterns. The meta-learning framework improves the generalization ability of the evolution pattern learning model, enabling more precise root cause identification. Consequently, the proposed method offers a new perspective for evolution analysis and root cause analysis of production anomalies.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 776-793"},"PeriodicalIF":12.2,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}