Journal of Manufacturing Systems最新文献

{"title":"Swin-fusion: An adaptive multi-source information fusion framework for enhanced tool wear monitoring","authors":"Kailin Hou ,&nbsp;Rongyi Li ,&nbsp;Xianli Liu ,&nbsp;Caixu Yue ,&nbsp;Ying Wang ,&nbsp;Xiaohua Liu ,&nbsp;Wei Xia","doi":"10.1016/j.jmsy.2025.02.003","DOIUrl":"10.1016/j.jmsy.2025.02.003","url":null,"abstract":"<div><div>Tool wear directly impacts product quality, manufacturing costs, and machining efficiency, serving as a critical factor in digital manufacturing. Existing prediction methods based on singular signals or limited features face constraints in predictive accuracy and generalizability. To address these limitations, this research proposes Swin-fusion, a multi-source information fusion framework integrating convolutional neural networks (CNNs) and Transformers. The framework innovates through an integrated CNN-Transformer architecture that enables efficient local-global feature extraction using focused attention mechanisms for individual signal processing, complemented by cross-attention based fusion for comprehensive multi-sensor information integration and adaptive feature selection for dynamic wear state monitoring. The effectiveness of the proposed approach was validated using both the public PHM2010 dataset and a self-constructed TiAl milling dataset. In tool wear life prediction, Swin-fusion achieves a mean absolute error (MAE) of 1.78 and root mean square error (RMSE) of 2.71 on PHM2010, and an MAE of 2.07 and RMSE of 3.21 on the TiAl dataset, with a coefficient of determination (R²) reaching 0.995. In tool wear state identification, the F1-score attains 98.8 % on PHM2010 and 98.0 % on TiAl. Results demonstrate that Swin-fusion markedly enhances predictive accuracy, identification precision, and generalization ability for practical tool wear monitoring applications.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 435-454"},"PeriodicalIF":12.2,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378077","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-based improved multi-objective genetic algorithm for solving distributed heterogeneous assembly flexible job shop scheduling problems with transfers","authors":"Zhijie Yang ,&nbsp;Xinkai Hu ,&nbsp;Yibing Li ,&nbsp;Muxi Liang ,&nbsp;Kaipu Wang ,&nbsp;Lei Wang ,&nbsp;Hongtao Tang ,&nbsp;Shunsheng Guo","doi":"10.1016/j.jmsy.2025.02.002","DOIUrl":"10.1016/j.jmsy.2025.02.002","url":null,"abstract":"<div><div>With the advancement of economic globalization, the distributed heterogeneous factory environment has become the mainstream in manufacturing enterprises. Scheduling flexible job shops in such a production environment holds practical value. However, due to the high complexity of certain jobs, the transfer of jobs between different factories are often required in practical production to balance machine load rates. Accordingly, this study addresses the distributed heterogeneous assembly flexible job shop scheduling problem with transfers, aiming to minimize both the makespan and total energy consumption. First, a multi-objective optimization model is formulated to define the problem, wherein knowledge of factory assignment and processing sequence for operations is summarized. Subsequently, given the complexity of this problem, a Q-learning-based improved multi-objective genetic algorithm (QL-IMOGA) is proposed as an effective approach. Within the proposed algorithm, a hybrid population initialization method is designed, considering factory load balancing and the earliest product completion time, to generate a high-quality initial population. Furthermore, two types of crossover operators, four types of mutation operators, and six objective-oriented neighborhood search operators are devised to enhance the algorithm’s exploration and exploitation capabilities. Q-learning is employed for adaptive adjustment of key parameters to improve both convergence speed and solution quality. The effectiveness of the proposed population initialization method and neighborhood search operators is validated through 15 test cases. The results demonstrate that the proposed algorithm significantly outperformed four advanced meta-heuristic algorithms. Furthermore, it is observed that the solution employing the job transfer strategy led to an average reduction of 7.5 % in makespan, a 3.9 % decrease in total energy consumption, and an 8.4 % improvement in factory load rates compared to the solution using the job no-transfer strategy.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 398-418"},"PeriodicalIF":12.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350487","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":"Life cycle assessment of an automated multi-cellular case-picking system","authors":"Ilaria Battarra,&nbsp;Riccardo Accorsi,&nbsp;Giacomo Lupi,&nbsp;Riccardo Manzini","doi":"10.1016/j.jmsy.2025.01.017","DOIUrl":"10.1016/j.jmsy.2025.01.017","url":null,"abstract":"<div><div>This study evaluated the environmental impact of an automated multi-cellular case-picking system using a Life Cycle Assessment methodology with the aim of improving logistics efficiency and sustainability. The system integrates advanced technologies, such as laser-guided vehicles, automated storage and retrieval systems, robotized layer-picking and case-picking units, and wrapping units, to create multi-product palletized unit loads for the food and beverage sector. A key contribution of this study is the data-driven approach developed to analyze this complex system comprising thousands of parts. Primary data were gathered from bills of material and onsite energy monitoring, whereas analytical and simulation models provided accurate estimations of energy use across handling activities. Life-cycle impact assessments focus on climate change, specifically its effects on human health and the ecosystem. This study underscores the critical role of high-quality data in environmental assessments and offers insights for advancing sustainable logistics and material handling practices. The proposed methodology is scalable and offers insights into other industrial applications, with a different number and type of robotized cells, working cycles, and material handling vehicles.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 419-434"},"PeriodicalIF":12.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surrogate modelling for continuous ergonomic assessment and adaptive configuration of industrial human-centered workplaces","authors":"Victor Bittencourt,&nbsp;Daniel Saakes,&nbsp;Sebastian Thiede","doi":"10.1016/j.jmsy.2025.02.001","DOIUrl":"10.1016/j.jmsy.2025.02.001","url":null,"abstract":"<div><div>Industry 5.0 highlights the growing need to ensure the adaptability of manufacturing systems around humans. In the context of industrial assembly, the continuous execution of ergonomic assessment is fundamental to promoting a dynamic and safe reconfiguration of workstations. This allows for the accommodation of individual-specific needs, thus contributing to employee well-being and productivity. In practice, however, there is a lack of integrated resources to support operations at this level. This can lead to reduced efficiency due to a mismatch between worker and workstation, risk of injury, and expensive late design modifications. The goal of this research is to provide input for triggering the customization of workstations based on worker-specific parameters, utilizing simulation-based ergonomic assessment as an objective function. A surrogate model was developed to achieve this by combining Digital Human Modelling (DHM) simulation and data-based modelling using supervised machine learning methods. Finally, the proposed framework was applied to an assembly operation case study for validation purposes. Results show that surrogate models can enable proactive ergonomically-oriented customization of workplaces, thus allowing a human-centered design process within operational cycles.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 383-397"},"PeriodicalIF":12.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel multi-agent reinforcement learning framework for robust exception handling of manufacturing service collaboration based on asymmetric information","authors":"Xin Luo ,&nbsp;Chunrong Pan ,&nbsp;Zhengchao Liu ,&nbsp;Lei Wang ,&nbsp;Shibao Pang ,&nbsp;Lifa He","doi":"10.1016/j.jmsy.2025.01.016","DOIUrl":"10.1016/j.jmsy.2025.01.016","url":null,"abstract":"<div><div>Industrial internet platforms enable users to efficiently fulfill their customized needs through the sequential execution of a manufacturing service collaborative chain (MSCC) consisting of networked enterprises. However, various dynamic uncertainties (e.g., equipment failure, emergency order insertion, product quality deterioration) may interrupt the execution of the MSCC, resulting in processing overruns and reduced user willingness to customize. To enhance the ability of MSCC to respond to exception events (namely robustness), the asymmetric informative multi-agent reinforcement learning (AIMARL) method is proposed. AIMARL will re-select the appropriate manufacturing service for the unexecuted subtasks in the event of an MSCC exception. First, the method gives a definition way of MSCC robustness labels from the perspective of the platform and networked enterprises. Subsequently, the asymmetric cascade state and data-rule-driven asymmetric reward are designed based on the characteristics of unidirectional asymmetric information transmission in the sequential execution of the MSCC. Meanwhile, in order to fully utilize the graph features of the MSCC and extract the complex relationships between services, graph convolutional networks are embedded in both the asymmetric cascade state and data-rule-driven asymmetric reward. Experimental results demonstrate that AIMARL outperforms the other four multi-agent reinforcement learning methods for the problem. In addition, AIMARL is able to cope with dynamic uncertainties with better robustness than the anomaly handling methods used in the platform.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 364-382"},"PeriodicalIF":12.2,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143297908","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":"Modelling and optimization of line efficiency for preventive maintenance of robot disassembly line","authors":"Yanqing Zeng,&nbsp;Zeqiang Zhang,&nbsp;Yu Zhang,&nbsp;Wei Liang,&nbsp;Haoxuan Song","doi":"10.1016/j.jmsy.2025.01.021","DOIUrl":"10.1016/j.jmsy.2025.01.021","url":null,"abstract":"<div><div>Regular preventive maintenance of the robot is the key to ensure accurate and stable operation of the robot. It is also an important step to achieve long-term stability of the disassembly line. At present, there is a lack of joint research on preventive maintenance and conventional disassembly for robot disassembly line balancing problem. This study will integrate the joint optimization of the two for conventional disassembly scenario and preventive maintenance scenarios of robot disassembly line. A mixed integer linear programming model considering preventive maintenance of robot disassembly is established, which aims to optimize the disassembly efficiency of conventional disassembly scenario and preventive maintenance disassembly scenario, and optimize the conversion efficiency of the two scenarios. The fore-and-aft tool replacement of the robot in the proposed model is also considered to be closer to the actual disassembly scenario. This study will design a multi-objective improved genetic simulated annealing that matches the problem characteristics to efficiently solve large-scale problems. The performance of the proposed algorithm is verified by solving 21 benchmarks containing task sizes ranging from 7 to 145. Then the correctness of the proposed model and algorithm is verified bidirectionally by analyzing the exact results and the results of the proposed algorithm from a small-scale case. Finally, the performance of the algorithm is further tested through a laptop disassembly case, and the results are analyzed comprehensively to show the importance of the disassembly characteristics considered in the preventive maintenance of the robot.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 347-363"},"PeriodicalIF":12.2,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169037","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":"Multi-workflow dynamic scheduling in product design: A generalizable approach based on meta-reinforcement learning","authors":"Zhen Chen ,&nbsp;Lin Zhang ,&nbsp;Wentong Cai ,&nbsp;Yuanjun Laili ,&nbsp;Xiaohan Wang ,&nbsp;Fei Wang ,&nbsp;Huijuan Wang","doi":"10.1016/j.jmsy.2025.01.010","DOIUrl":"10.1016/j.jmsy.2025.01.010","url":null,"abstract":"<div><div>Multi-stage simulation workflows are a commonly used and crucial means for evaluating and optimizing design performance throughout the stages of product development. Effective multi-workflow scheduling is crucial for ensuring optimal resource utilization and execution time. Addressing simulation multi-workflow dynamic scheduling (SWDS) is challenging due to the variability of tasks and the uncertainty in execution, necessitating flexible and adaptive scheduling strategies. While traditional methods such as heuristic-based algorithms are popular in workflow scheduling, they show weaknesses in robustness, generalization, and adaptability when dealing with highly dynamic environments such as SWDS. To address above issues in SWDS, this paper innovatively proposes a meta-reinforcement learning-based scheduling method that aims to enhance generalization and adaptability to dynamic conditions. An enhanced Model-Agnostic Meta-Learning based deep reinforcement learning (DRL) algorithm is proposed to acquire dynamic scheduling strategies through multi-scenario training. Multi-step state features are extracted to address the issue of insufficient state observations. Conjugate adaptive search and Armijo conditions are applied to enhance the effectiveness of algorithm training. Experimental tests in 180 multi-type scenarios, compared with nine heuristic methods and three state-of-the-art DRL algorithms, comprehensively demonstrate the superiority of the proposed method.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 334-346"},"PeriodicalIF":12.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169031","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 reliability in advanced manufacturing systems: A methodology for the assessment of detection and monitoring techniques","authors":"Monica Katherine Gonzalez ,&nbsp;Mariano Jose Coll-Araoz ,&nbsp;Andreas Archenti","doi":"10.1016/j.jmsy.2025.01.015","DOIUrl":"10.1016/j.jmsy.2025.01.015","url":null,"abstract":"<div><div>Advanced manufacturing systems demand the utilization of technologies, methods and capabilities to improve production efficiency or productivity, while ensuring environmental and societal sustainability. Digitalization emerges as an alternative solution for improving the monitoring capabilities of manufacturing systems and consequently enhance the decision-making process. However, the widespread adoption of digital solutions introduces complexities in measurement reliability, data management, and environmental concerns in terms of e-waste and data storing. Therefore, enhancing monitoring capabilities while minimizing resource consumption is crucial for ensuring system reliability in a sustainable way. This research introduces a methodology for assessing the monitoring condition of manufacturing systems. By integrating functional and dysfunctional analysis, approaches that focus on identifying critical functions and potential failure modes of a system, the proposed methodology provides a comprehensive system perspective and targeted directives for improvement. The effectiveness and versatility of the methodology are demonstrated and discussed through its application to various manufacturing systems at a component, machine, and line level.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 318-333"},"PeriodicalIF":12.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep graph neural network-based link prediction model for proactive anomaly detection in discrete manufacturing workshop","authors":"Shengbo Wang ,&nbsp;Yu Guo ,&nbsp;Shaohua Huang ,&nbsp;Ruixi Lai ,&nbsp;Litong Zhang ,&nbsp;Weiwei Qian","doi":"10.1016/j.jmsy.2025.01.022","DOIUrl":"10.1016/j.jmsy.2025.01.022","url":null,"abstract":"<div><div>Production anomaly has always been one of the main influencing factors that prevent discrete manufacturing workshops from maintaining stability and agility. Proactive anomaly detection can evaluate the production state and serves as a crucial foundation for preventive maintenance decision. Knowledge graph enables the use of multi-source manufacturing data as a data foundation for proactive anomaly detection. Although rich manufacturing data can comprehensively depict complex manufacturing process, constructing an accurate proactive anomaly detection model remains challenging because of insufficient analysis of the local and temporal features of the manufacturing process. This paper presents a link prediction model based on a deep graph neural network to solve the problem. Specifically, the manufacturing knowledge graph is constructed through OPC UA information model, Bert model and OWL semantic mapping model to organize multi-source heterogeneous data. The deep autoencoder model with local graph learning and the Seq2Seq model with attention mechanism are trained to analyze the neighboring relationship and the temporal correlation of the manufacturing elements, respectively. Finally, the link prediction model is designed by integrating both local and temporal features, with a restructured loss function to improve training effectiveness. Experiments suggest that the designed link prediction model has better prediction performance and is at least 25.6 % higher than the baseline models on the mean reciprocal rank.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 301-317"},"PeriodicalIF":12.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169560","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":"‘Genetic exploration’ of metal forming processes through information absent and fragmental data processing","authors":"Heli Liu ,&nbsp;Saksham Dhawan ,&nbsp;Xiao Yang ,&nbsp;Denis J. Politis ,&nbsp;Maxim Weill ,&nbsp;Yang Zheng ,&nbsp;Xiaochuan Liu ,&nbsp;Huifeng Shi ,&nbsp;Lemeng Zhang ,&nbsp;Xiangnan Yu ,&nbsp;Shamsuddeen Muhammad ,&nbsp;Liliang Wang","doi":"10.1016/j.jmsy.2025.01.014","DOIUrl":"10.1016/j.jmsy.2025.01.014","url":null,"abstract":"<div><div>Over 160,000 engineering materials and nearly 90 % (wt%) of products made from metals are manufactured by metal forming processes. Voluminous metal forming data are proliferated daily at an ever-greater scale, and collected from sensing networks and experimentally verified simulations, facilitating the scientific understanding of digital manufacturing. To date, limited research has approached metal forming from the perspective of data, particularly given that most datasets are ‘information absent’ that lack essential information, including data description, quality or condition, or essential features, for a single or several data points, or a specific dataset or database. Furthermore, data collected by sensing networks are most likely to be categorised as ‘fragmental data’, encompassing only a few (e.g., 1–2) essential pieces of information. This phenomenon is mainly due to limitations of data collection capabilities and data privacy, and hinders the extraction of insightful information. Tackling these long-standing challenges requires an emerging scientific approach combining manufacturing and data science knowledge. Here, following thermo-mechanical principles, an Evolutionary Binary (EB) algorithm was developed to process information absent (meta)data, yielding a highly efficient recognition of missing geometric features for metal formed products with nearly 95 % accuracy using sparsely labelled data points (≤1 %). By leveraging this technology, unique digital characteristics (DC) were identified for over 140 manufacturing processes. The DC are defined as the visualisation of manufacturing (meta)data incorporating essential information spanning design, manufacturing and application stages of manufactured products. This leads to the establishment of digital characteristics space (DCS) that provides access to the up-to-date and information-rich manufacturing DC. Using EB algorithm and taking DCS as an alignment reference, the origins of naturally unattributed fragmental data (minimum length of 25 data points) were successfully identified with overall over 80 % accuracy, and reached approximately 93 % with length of 50 data points.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 286-300"},"PeriodicalIF":12.2,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}