Journal of Manufacturing Systems最新文献

{"title":"A novel XR-based real-time machine interaction system for Industry 4.0: Usability evaluation in a learning factory","authors":"Kaveh Amouzgar ,&nbsp;Justus Willebrand","doi":"10.1016/j.jmsy.2025.05.019","DOIUrl":"10.1016/j.jmsy.2025.05.019","url":null,"abstract":"<div><div>Traditional methods of data visualization and process monitoring are increasingly inadequate in fast-paced, data-intensive manufacturing environments. Extended Reality (XR) technologies, including Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR), have the potential to enhance human–machine interaction and operational efficiency in Industry 4.0 framework. While previous research has demonstrated the effectiveness of XR in areas such as assembly, training, maintenance, and human–robot interaction, limited attention has been given to developing and evaluating XR systems for real-time machine data visualization. Most existing studies focus on demonstrating AR applications without rigorous comparative evaluations against other XR technologies or traditional Human–Machine Interfaces (HMIs), often with limited user testing. This study addresses these gaps by developing and evaluating an XR application using Microsoft HoloLens 2 for real-time process control in a Learning Factory environment. A mixed-methods approach, including experimental design, surveys, and time measurements, compared the XR system with conventional 2D HMIs. Data from 22 participants were analyzed, focusing on alarm response times, usability, and preventive maintenance. The findings show that the XR system significantly improves alarm response times, increases frequency of preventive refills, and enhances usability compared to traditional HMIs. However, challenges related to ergonomics and limited field of view were noted. This study contributes to advancing smart manufacturing by showcasing the potential of XR to improve human–machine interfaces and foster better interaction between machines and operators.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 254-283"},"PeriodicalIF":12.2,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331142","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 mutual cross-attention fusion network for surface roughness prediction in robotic machining process using internal and external signals","authors":"Zhiqi Wang,&nbsp;Dong Gao,&nbsp;Yong Lu,&nbsp;Kenan Deng,&nbsp;Zhaojun Yuan,&nbsp;Minglong Huang,&nbsp;Tianci Jiang","doi":"10.1016/j.jmsy.2025.06.018","DOIUrl":"10.1016/j.jmsy.2025.06.018","url":null,"abstract":"<div><div>Compared with machine tools, industrial robots exhibit low, position-dependent stiffness. This dynamic compliance leads to inconsistent surface roughness under identical machining parameters when the robot configuration changes, thereby significantly complicating roughness prediction. Therefore, to address the challenge of predicting surface roughness in robotic machining processes and provide reference for its effective surface roughness monitoring, this paper proposes a Mutual Cross-attention Fusion Network (MCFN) for surface roughness prediction in robotic machining process using internal and external signals. Firstly, the machined surface roughness data set is obtained through the robotic machining experiments with different workpiece placements and machining parameters. The internal torque signals and external vibration signals of the robot are acquired to better reflect the state information during the machining process. Secondly, Uniform Manifold Approximation and Projection(UMAP) is used to reduce the dimension of time domain, frequency domain and time-frequency domain features extracted by signal channel to reduce the interference of redundant features. The features after dimension reduction are used to form a double-branch structure, and the dynamic interaction between different channels features is realized by Parallel Multi-channel Feature Enhancement Module(PMFEM). Then, the mutual fusion module based on the Dual Multi-head Cross-attention Mechanism(Dual-MCM) is used to realize the collaborative interaction of cross-modal information, to complete the bidirectional deep collaborative representation between the robot internal and external signals features in the fusion process. And the features are segmented and aggregated to predict the robot machined surface roughness. Finally, based on the performance evaluation index, the effectiveness of the MCFN is verified through hyperparameter adjustment, ablation experiment, comparison experiment of different dimension reduction techniques and data-driven methods. The verification results show that MCFN can realize the prediction of robot machined surface roughness at different postures and machining parameters, which provides an effective method for the accurate prediction and monitoring of robot machined surface roughness.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 284-300"},"PeriodicalIF":12.2,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331143","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":"Toward digital twins for intelligence manufacturing: Self-adaptive control in assisted equipment through multi-sensor fusion smart tool real-time machine condition monitoring","authors":"Jin Zhang ,&nbsp;Chengchao Li ,&nbsp;Chenjie Deng ,&nbsp;Taimin Luo ,&nbsp;Ruihua Deng ,&nbsp;Daixin Luo ,&nbsp;Guibao Tao ,&nbsp;Huajun Cao","doi":"10.1016/j.jmsy.2025.06.020","DOIUrl":"10.1016/j.jmsy.2025.06.020","url":null,"abstract":"<div><div>Compared to traditional monitoring methods, multi-sensor fusion smart tool offers several advantages, including full-process monitoring and a broader range of applications (e.g., flat, curved, and complex surfaces). When integrated with artificial intelligence models for tool state monitoring, these tools provide strong generalization capabilities and high prediction accuracy. They can also adjust machine tool process parameters to extend tool life. However, the quasi-in-situ regulation of cutting parameters has a limited scope, making it challenging to achieve full working condition adaptability. The introduction of assisted equipment can enhance process adaptability. Furthermore, adaptive control mechanisms can regulate the machining process to reduce energy consumption by adjusting the opening and closing parameters. Despite these advantages, the linkage control mechanism for the smart tool remains unclear, and existing tool wear models struggle to adapt to variable working conditions across multiple scenarios. To address these challenges, this paper explores the digital twin modeling and application of smart tool machining processes. First, a digital twin-driven tool machining process model is developed, with an exploration of specific application scenarios and methods. Secondly, an adaptive coupling mechanism for assisted equipment based on digital twins is established, which simultaneously improves machining quality and reduces energy consumption. Additionally, the online tool wear identification model is enhanced to increase its generalization and reduce the cost of model reconstruction when working conditions change, thus enabling green intelligent manufacturing under high-quality machining conditions.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 301-318"},"PeriodicalIF":12.2,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331144","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":"Matrix manufacturing system layout and scheduling via graph neural network and multi‐action deep reinforcement learning","authors":"Tong Zhu ,&nbsp;Xuemei Liu ,&nbsp;Yanbin Yu ,&nbsp;Ling Fu","doi":"10.1016/j.jmsy.2025.06.005","DOIUrl":"10.1016/j.jmsy.2025.06.005","url":null,"abstract":"<div><div>Matrix manufacturing system (MMS) is a novel production paradigm in Industry 4.0 that provides a highly flexible production environment based on the principles of decentralization, modularity, and unrestricted connectivity. MMS effectively addresses the challenges of personalized customization, which, in turn, imposes stricter demands on the optimization of its layout and scheduling. However, existing research on MMS primarily focuses on constructing theoretical frameworks, with limited attention to practical layout and scheduling optimization. Moreover, layout and scheduling decisions in MMS are highly coupled, and the system state has complex topological structures and dynamics. Conventional vector representation methods struggle to fully capture these intricate relationships, which limits the ability of MMS to address complex production demands. Therefore, to solve the MMS layout and scheduling (MMSLS) problem, this paper proposes an end-to-end multi-action deep reinforcement learning (MADRL) method based on a three-stage embedded heterogeneous graph neural network (HGNN) to learn the optimal policy for parallel decision-making for MMSLS, which aims to minimize makespan. Firstly, the traditional disjunctive graph of flexible scheduling problems is expanded into a heterogeneous graph by incorporating workstation and location nodes, which more intuitively captures the complex associations in MMS between operations and workstations and between workstations and locations. Secondly, we propose a novel HGNN algorithm to enhance representation learning by first transforming MMSLS heterogeneous graph into node-level embeddings and then using heterogeneous graph-level representation vectors as inputs. Finally, the agent sequentially performs actions based on two parameterized sub-policies, operation-workstation actions and location actions, which are trained to learn the optimal MMSLS policy using the proximal policy optimization (PPO) algorithm. Experimental results from both randomized and benchmark instances reveal that the proposed method not only outperforms manually crafted heuristic scheduling rules in solution quality but also exceeds metaheuristic algorithms in computational velocity. Furthermore, it demonstrates strong generalization when handling larger-scale instances.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 239-253"},"PeriodicalIF":12.2,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313218","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":"Q-learning-based multi-objective spotted hyena algorithm for flexible open shop scheduling problem with consideration of preventive maintenance and travel/setup times","authors":"Jun Guo ,&nbsp;Bin Peng ,&nbsp;Baigang Du ,&nbsp;Kaipu Wang ,&nbsp;Yibing Li","doi":"10.1016/j.jmsy.2025.06.001","DOIUrl":"10.1016/j.jmsy.2025.06.001","url":null,"abstract":"<div><div>This paper presents a flexible open shop scheduling problem considering preventive maintenance, travel time between machines, and sequence-dependent setup time (FOSSP-PM&amp;TT) to address the impact of routine maintenance on shop productivity. According to the characteristics of the problem, a mathematical model is developed to simultaneously minimize the makespan and mean flow time. Then, a Q-learning-based multi-objective spotted hyena optimization algorithm (Q-MSHO) is proposed to solve this problem. Four neighborhood structures are designed in accordance with characteristics of the FOSSP-PM&amp;TT. And a Q-learning-based variable neighborhood search strategy is proposed to update the selection of local search operations in each iteration. Finally, computational experiments are performed on test instances of different sizes to evaluate the performance of the proposed algorithm. The experimental outcomes demonstrate that the Q-MSHO algorithm exhibits superior performance compared to the other algorithms in addressing the FOSSP-PM&amp;TT problem.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 224-238"},"PeriodicalIF":12.2,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290566","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":"An Integrated Mathematical Programming and Reinforcement Learning Algorithm for the Flexible Job Shop Scheduling with Variable Lot-sizing","authors":"Chuanzhao Yu,&nbsp;Chunjiang Zhang,&nbsp;Jiaxin Fan,&nbsp;Weiming Shen","doi":"10.1016/j.jmsy.2025.05.002","DOIUrl":"10.1016/j.jmsy.2025.05.002","url":null,"abstract":"<div><div>The Flexible Job Shop Scheduling Problem with Variable Lot-Sizing (FJSP-VLS) extends the Flexible Job shop Scheduling Problem (FJSP) by permitting variable lot-sizing for jobs of the same type across different operations. This approach provides enhanced flexibility compared to the conventional method of consistent lot-sizing. However, existing algorithms face efficiency bottlenecks when scaling to real-world production scenarios. To address this challenge, the authors propose an Integrated Mathematical Programming and Reinforcement Learning (IMPRL) algorithm that synergistically combines a dual-attention neural network with Proximal Policy Optimization (PPO) for adaptive scheduling, coupled with a Mixed Integer Linear Programming (MILP) model for joint lot-sizing and machine optimization. Extensive experiments on 10 benchmark-derived instance classes demonstrate IMPRL’s superiority: it reduces makespan by 6.86% (up to 11.87% for 30<span><math><mo>×</mo></math></span> 10 instances) compared to TOP PDR, achieves 9.81% improvement in generalization tests, and maintains solution quality while being an order-of-magnitude faster than MILP and GA-MH<span><math><msub><mrow></mrow><mrow><mtext>ER</mtext></mrow></msub></math></span> approaches. The algorithm’s hierarchical architecture effectively resolves inconsistencies in sublot completion times, while the case study fully demonstrates its practicality in large-scale FJSP-VLS implementations. The key managerial insights derived from the research findings are also highlighted, along with an acknowledgment of the algorithm’s limitations.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 210-223"},"PeriodicalIF":12.2,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144279529","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":"Human-in-the-loop in smart manufacturing (H-SM): A review and perspective","authors":"Duck Bong Kim ,&nbsp;Mahdi Sadeqi Bajestani ,&nbsp;Ju Yeon Lee ,&nbsp;Seung-Jun Shin ,&nbsp;Goo-Young Kim ,&nbsp;Seyed Mohammad Mehdi Sajadieh ,&nbsp;Sangdo Noh","doi":"10.1016/j.jmsy.2025.05.020","DOIUrl":"10.1016/j.jmsy.2025.05.020","url":null,"abstract":"<div><div>Smart manufacturing, also known as Industry 4.0, is a manufacturing paradigm that aims to realize autonomous processes, minimizing human involvement. In the advent of manufacturing-unfriendly situations (e.g., pandemics), it has been learned that the paradigm does not work correctly and has limitations in handling those situations. There is a consensus that humans still play a crucial role in manufacturing, and the ultimate goal of manufacturing is to benefit them. To align with this, the European Commission introduced Industry 5.0, targeting human centricity, sustainability, and resilience. Operator 5.0 has also been presented to improve the physical and cognitive capabilities of shop operators. In contrast, the new concept of human-in-the-loop in smart manufacturing (H-SM), aiming for the involvement of diverse stakeholders, has been recently proposed. In this paper, we introduce the research methodology to elaborate on the current application fields of the H-SM concept. For this, we revisit the existing paradigms and their case studies. Also, we categorize them in terms of different components in H-SM and with respect to different levels of physical and cognitive capabilities and experiences. Then, we identify seven technology clusters and twenty-one key-enabling technologies for the H-SM implementation. It can be concluded the H-SM is well-aligned with human-intervened autonomous manufacturing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 178-199"},"PeriodicalIF":12.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271191","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":"Inverse design of ideal pre-stress distribution in assembly interface based on service performance","authors":"Qiyin Lin ,&nbsp;Kaiyi Zhou ,&nbsp;Mingjun Qiu ,&nbsp;Tao Wang ,&nbsp;Hao Guan ,&nbsp;Lifei Chen ,&nbsp;Chen Wang ,&nbsp;Jian Zhuang ,&nbsp;Jun Hong","doi":"10.1016/j.jmsy.2025.06.012","DOIUrl":"10.1016/j.jmsy.2025.06.012","url":null,"abstract":"<div><div>This paper proposes an inverse design method (IPIDM) that integrates deep learning with FEM for assembly interfaces under extreme service conditions. IPIDM provides a universal framework to inversely derive the contact stress distribution at the assembly stage (referred to as the ideal pre-stress distribution) from a uniform stress distribution on the assembly interfaces during the service state. This distribution is designed to ensure uniform contact stress under extreme service conditions. Concurrently, IPIDM predicts morphology layouts to guide manufacturing. In IPIDM, the displacement of mesh nodes is utilized to extract the mapping relationship between interface morphology and stress. A U-Net-based deep learning network is developed and trained on this mapping model to simultaneously output the static contact stress distribution and the corresponding morphology layout. Compared with open-source neural networks, the proposed model demonstrates superior capabilities in global feature extraction and training efficiency. The training stability and predictive accuracy of IPIDM are verified, and the optimization effects of the predicted morphology layouts are verified through FEM. Results indicate that IPIDM significantly outperforms mainstream assembly interfaces optimization methods in optimization efficiency, particularly for 3D interfaces subjected to complex stress states. This makes IPIDM a promising tool for fast FEM simulations and digital twin applications.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 200-209"},"PeriodicalIF":12.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271192","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":"Process failure mode – product failure mechanism- effect analysis ((PFM)²EA): A novel risk assessment methodology for automated battery disassembly - Integrating process and product safety in repurposing","authors":"Stefan Grollitsch ,&nbsp;Gernot Schlögl ,&nbsp;Florian Feist ,&nbsp;Franz Haas ,&nbsp;Sinisa Jovic ,&nbsp;Harald Sehrschön ,&nbsp;Christian Ellersdorfer","doi":"10.1016/j.jmsy.2025.06.006","DOIUrl":"10.1016/j.jmsy.2025.06.006","url":null,"abstract":"<div><div>The increasing adoption of electric vehicles has led to a surge in end-of-life traction batteries, necessitating safe and efficient repurposing strategies. This study introduces a novel risk assessment methodology, the process failure mode - product failure mechanism - effect analysis ((PFM)²EA), designed to evaluate safety risks in automated battery disassembly processes. The (PFM)²EA method combines two established risk analysis approaches: one focused on manufacturing processes (process failure mode and effects analysis - PFMEA) and another on product failure behaviors (failure modes, mechanisms, and effects analysis - FMMEA). By linking these perspectives, the method addresses the critical gap between process and product risks in separation processes for battery repurposing. Our approach employs a tripartite risk categorization framework, distinguishing between immediate safety hazards, long-term safety risks, and potential performance issues of reused components. The method introduces a fourth variable to the traditional scoring system, which considers severity, likelihood of occurrence, and detectability of a product failure, by adding a fourth factor: the likelihood of process failure. The determination of which was simplified by implementing an analytic hierarchy process. This enhancement allows for a more comprehensive assessment of potential hazards originating from product failure mechanisms triggered by process faults. To validate the (PFM)²EA method, a preemptive risk assessment of theoretical automated disassembly processes for three commercially available battery systems has been conducted. The study focused on processes aimed at extracting energy storage components for reuse and repurposing, examining how safety considerations influence process selection. The findings demonstrate the effectiveness of the (PFM)²EA method in identifying and prioritizing safety risks in battery disassembly processes. A Monte Carlo Simulation confirmed the robustness of the risk evaluations under input uncertainty, reinforcing the method’s reliability. This research contributes to the development of safer and more efficient battery repurposing strategies, addressing critical challenges in the circular economy of energy storage systems.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 137-160"},"PeriodicalIF":12.2,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263141","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":"ConfigRec: An efficient recommendatory configuration design method for customized products","authors":"Zhiwei Pan ,&nbsp;Zili Wang ,&nbsp;Lemiao Qiu ,&nbsp;Shuyou Zhang ,&nbsp;Hong Zhu ,&nbsp;Huang Zhang ,&nbsp;Feifan Xiang ,&nbsp;Changlong Cheng","doi":"10.1016/j.jmsy.2025.06.013","DOIUrl":"10.1016/j.jmsy.2025.06.013","url":null,"abstract":"<div><div>Product configuration design is essential in mass customization and enables the rapid selection of configurable components to assemble a desired product. However, existing configuration methods struggle to balance customization flexibility with production efficiency. The configurators process multiple components and orders sequentially, leading to extended computation times. Additionally, component coupling relationships introduce extra costs and complexity. To address these challenges, we propose ConfigRec, an end-to-end recommendatory configuration design method that leverages the parallel computing capabilities of deep learning. Specifically, our approach: (1) constructs specialized parameter embeddings for components by encoding diverse design parameters; (2) decouples complex relationships within the product configuration tree through top-down and bottom-up message passing, while capturing implicit dependencies using a linear attention mechanism; and (3) predicts instance recommendation scores and generates a customized Engineering Bill of Materials based on a formally defined configuration decision law. A real-world case study on elevator products demonstrates that ConfigRec achieves up to 99.51 % accuracy within seconds. The proposed method is interpretable, efficient, and highly accurate, significantly reducing customized product delivery times.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 161-177"},"PeriodicalIF":12.2,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271190","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}