Journal of Manufacturing Systems最新文献

{"title":"An adaptive genetic algorithm based on Q-learning for energy-efficient e-waste disassembly line balancing and rebalancing considering task failures","authors":"Kaipu Wang ,&nbsp;Xiaoyi Ma ,&nbsp;Yibing Li ,&nbsp;Yabo Luo ,&nbsp;Yingli Li ,&nbsp;Liang Gao","doi":"10.1016/j.jmsy.2025.02.009","DOIUrl":"10.1016/j.jmsy.2025.02.009","url":null,"abstract":"<div><div>The efficient disassembly and recycling of e-waste not only provides economic benefits but also contributes to reducing energy consumption. However, the disassembly process is often influenced by uncertainties, such as damage or deformation of components, which may result in potential task failures. These failures can disrupt the balance of the disassembly line, affecting the efficiency of subsequent tasks. Therefore, it is crucial to develop a decision-making model and optimization method to address disassembly failures. This study presents a predictive disassembly line balancing model with objectives focused on the number of workstations, the smoothness index, and energy consumption. The optimization objective of adjusting the disassembly sequence is introduced, and a rebalancing model is developed to reallocate the remaining tasks in response to various failures. The sequence combination that minimizes comprehensive energy consumption is selected as the optimal disassembly strategy. Considering the complexity and dynamic disturbance of the problem, an adaptive multi-objective genetic algorithm based on Q-learning is proposed. To improve the quality of the disassembly solutions, six evolutionary actions and four population performance states are designed. During the algorithm’s iteration, the search strategy is dynamically adjusted through Q-learning. The effectiveness of the proposed algorithm is verified by solving several classic disassembly cases and comparing the results with those from six advanced algorithms. Finally, in an actual refrigerator disassembly case, 11 disassembly schemes are generated, accounting for task failures. The results indicate that, compared to traditional disassembly methods, the rebalancing approach not only optimizes the station loads but also increases revenue by 11.98 %, demonstrating the effectiveness of the proposed model and method in handling task failures on disassembly lines.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 1-19"},"PeriodicalIF":12.2,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487380","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":"Rescheduling human-robot collaboration tasks under dynamic disassembly scenarios: An MLLM-KG collaboratively enabled approach","authors":"Weigang Yu,&nbsp;Jianhao Lv,&nbsp;Weibin Zhuang,&nbsp;Xinyu Pan,&nbsp;Sijie Wen,&nbsp;Jinsong Bao,&nbsp;Xinyu Li","doi":"10.1016/j.jmsy.2025.02.015","DOIUrl":"10.1016/j.jmsy.2025.02.015","url":null,"abstract":"<div><div>During product recycling, the uncertainty of the degradation level of end-of-life products leads to dynamic conditions such as component corrosion and damage during the disassembly process. Therefore, enhancing the robot's perception of disassembly scenarios and matching historical disassembly experiences is crucial for task rescheduling in human-robot collaborative disassembly (HRCD) under dynamic conditions. To address this, this paper proposes a dynamic task rescheduling method for human-robot collaborative disassembly, empowered by the synergy of Knowledge Graph (KG) and Multimodal Large Language Model (MLLM). Leveraging a Mark-Aware image preprocessing module and prompt-based scene understanding, the physical characteristics and occlusion relationships of disassembly targets are extracted. The concept of affordance is introduced, and an Affordance KG is constructed to recommend disassembly actions based on the physical features of objects in the scene. A task allocation standard for human-robot collaboration is designed, which, combined with depth and human factor information from mixed reality scenarios, enables dynamic task rescheduling and reconstruction of the entire human-robot collaborative disassembly process. The proposed method is validated through a case study on human-robot collaborative disassembly of end-of-life automotive lithium-ion batteries. Experimental results demonstrate that the method exhibits strong robustness and generalizability in dynamic disassembly scenarios, accurately identifying the physical features of components and recommending appropriate disassembly actions under conditions such as component corrosion, damage, and tool unavailability, thus achieving effective task rescheduling.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 20-37"},"PeriodicalIF":12.2,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487681","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":"Bayesian neural networks for predicting quality in reclaimed waste sand for foundry applications","authors":"Boyeon Kim ,&nbsp;Wonjong Jung ,&nbsp;Youngsim Choi ,&nbsp;Jeongsu Lee","doi":"10.1016/j.jmsy.2025.02.007","DOIUrl":"10.1016/j.jmsy.2025.02.007","url":null,"abstract":"<div><div>Although advancements in smart manufacturing technologies have profoundly transformed the manufacturing industry, their application in traditional industries remains challenging. In particular, the casting industry faces significant obstacles, such as limited quality data acquisition for quantifying tacit knowledge and insufficient adoption of smart manufacturing technologies. As a potential remedy, this study demonstrates the application of smart manufacturing technologies for predicting the quality of reclaimed sand, specifically tailored for the sand casting industry. The developed strategy integrates: 1) detailed measurements of the environmental conditions in the sand reclamation process, and 2) a deep-learning-based model for predicting the loss on ignition (LOI) of reclaimed sand as a quality measure. The model is constructed using feature extraction from time-series data and Bayesian neural networks to predict LOI with quantified uncertainty. We propose a normality score-based reclaimed sand management strategy, which was evaluated over one and a half years of production conditions and reclaimed sand quality monitoring experiments. The demonstration case exhibits an average accuracy of 96.83 % in detecting problematic sand quality. Notably, the method significantly improved failure detection accuracy, increasing test data results from 38.34 % without uncertainty consideration to 72.5 % when uncertainty was incorporated. The proposed approach has the potential to advance the casting industry by enabling quality-data-driven management of the sand reclamation process, ultimately reducing defect rates and optimizing production costs.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 584-597"},"PeriodicalIF":12.2,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437240","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":"Resilient manufacturing: A review of disruptions, assessment, and pathways","authors":"Jiewu Leng ,&nbsp;Junxing Xie ,&nbsp;Rongjie Li ,&nbsp;Xueliang Zhou ,&nbsp;Xi Gu ,&nbsp;Qiang Liu ,&nbsp;Xin Chen ,&nbsp;Wenjun Zhang ,&nbsp;Andrew Kusiak","doi":"10.1016/j.jmsy.2025.02.006","DOIUrl":"10.1016/j.jmsy.2025.02.006","url":null,"abstract":"<div><div>Manufacturers are increasingly concerned with the resilience of manufacturing systems due to rising disruptions. This paper reviews the research on resilient manufacturing, emphasizing the definitions and drivers of resiliency in manufacturing. Typical disruptions affecting manufacturing are discussed and classified. The assessment of resilience is explored through three key pillars: absorbency, adaptability, and recoverability. Resilience is also benchmarked against other manufacturing performance indicators. Pathways to resilient manufacturing are outlined, focusing on system design, configuration, and operations. Practical implementations are discussed, along with challenges and research directions aligned with Industry 5.0. This study aims to establish a foundational framework for integrating resiliency into modern manufacturing systems.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 563-583"},"PeriodicalIF":12.2,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437239","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":"Review of manufacturing system design in the interplay of Industry 4.0 and Industry 5.0 (Part II): Design processes and enablers","authors":"Jiewu Leng ,&nbsp;Jiwei Guo ,&nbsp;Junxing Xie ,&nbsp;Xueliang Zhou ,&nbsp;Ang Liu ,&nbsp;Xi Gu ,&nbsp;Dimitris Mourtzis ,&nbsp;Qinglin Qi ,&nbsp;Qiang Liu ,&nbsp;Weiming Shen ,&nbsp;Lihui Wang","doi":"10.1016/j.jmsy.2025.02.005","DOIUrl":"10.1016/j.jmsy.2025.02.005","url":null,"abstract":"<div><div>Following up on our previous review paper ‘Review of manufacturing system design in the interplay of Industry 4.0 and Industry 5.0 (Part I): Design thinking and modeling methods’ ^[1], based on the proposed Thinking-Modelling-Process-Enabler (TMPE) framework of Manufacturing System Design (MSD), this paper (Part II of the two-part review) further reviews the Process and Enabler dimensions of MSD in the interplay of Industry 4.0 and Industry 5.0. MSD methods are reviewed from the single-dimensional design process and cross-dimensional design process perspectives, respectively. MSD methods are reorganized and categorized from the key enabler's perspective. Finally, challenges are discussed along with directions for future research in the domain of MSD. This review is anticipated to offer novel insights for advancing MSD research and engineering in the interplay of Industry 4.0 and Industry 5.0.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 528-562"},"PeriodicalIF":12.2,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437238","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":"Why decision support systems are needed for addressing the theory-practice gap in assembly line balancing","authors":"Christoffer Fink,&nbsp;Ulf Bodin,&nbsp;Olov Schelén","doi":"10.1016/j.jmsy.2025.01.019","DOIUrl":"10.1016/j.jmsy.2025.01.019","url":null,"abstract":"<div><div>The efficiency of an assembly line depends on how the work is distributed along the line. This is known as the Assembly Line Balancing Problem, an NP-hard optimization problem. Automatic solvers for this problem have been studied for decades but have not been widely adopted in the industry, resulting in a theory-practice gap. The typical automation approach assumes that all constraints and objectives are known and can be statically defined ahead of time such that solvers with a precisely defined objective function can take a fully specified problem instance as input and produce a (near) optimal solution as output. In some industries, meeting these assumptions is particularly challenging because of properties such as mixed-model production with high model variance, multi-manned stations, large task graphs, etc. This paper explains why, in certain industries, such as automotive end assembly, complete automation is likely infeasible in practice due to challenges in modeling the problem, collecting data, and specifying the objective function. Manual intervention by an engineer as a decision-maker is therefore unavoidable. We argue that maximizing automation, by helping the decision-maker be as effective as possible, requires a decision support system (DSS) that supports an interactive and iterative workflow, thereby enabling assisted planning. Furthermore, we identify solver features that become relevant in the DSS context, thus making the case that focusing on standalone solvers, and treating the integration into a DSS as an implementation detail, is not a viable option. We conclude that decision support systems play a central role in closing the theory-practice gap.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 515-527"},"PeriodicalIF":12.2,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420439","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":"ChatCNC: Conversational machine monitoring via large language model and real-time data retrieval augmented generation","authors":"Jurim Jeon ,&nbsp;Yuseop Sim ,&nbsp;Hojun Lee ,&nbsp;Changheon Han ,&nbsp;Dongjun Yun ,&nbsp;Eunseob Kim ,&nbsp;Shreya Laxmi Nagendra ,&nbsp;Martin B.G. Jun ,&nbsp;Yangjin Kim ,&nbsp;Sang Won Lee ,&nbsp;Jiho Lee","doi":"10.1016/j.jmsy.2025.01.018","DOIUrl":"10.1016/j.jmsy.2025.01.018","url":null,"abstract":"<div><div>Human-Centric Smart Manufacturing (HCSM) has become a central theme of Industry 5.0, promoting collaborative interactions between humans and intelligent systems. Nevertheless, HCSM technologies have been struggling to reach their full potential due to the lack of digital literacy among manufacturing workers, particularly in real-time machine monitoring. Current monitoring systems with rigid interfaces limit the operators to handle Industrial Internet of Things (IIoT) systems to directly query manufacturing data for further analysis without external technical support. To address such bottlenecks, we propose ChatCNC, a conversational machine monitoring framework that integrates Large Language Models (LLMs) to enable natural language-driven interactions with real-time Computer Numerical Control (CNC) machine data. Leveraging LLM-based multi-agent collaboration and Retrieval-Augmented Generation (RAG), ChatCNC interactively retrieves data from real-time IIoT database while also supporting context-aware responses based on the collected data, which reduces reliance on technical support from software engineers. As ChatCNC allows rapid adaptation of LLM Application Programming Interfaces (APIs) via prompting techniques, its performance is evaluated across multiple versions, each combining different LLMs and prompts, using various types of questions. Notably, our framework demonstrates its reliability in human-data interaction for industrial applications, achieving 93.3% accuracy in responding to complex queries that require advanced data inference like production tracking. Furthermore, possible failure modes are thoroughly analyzed based on interaction scenarios among multiple LLM-based agents. Such results highlight the potential of the framework as a cornerstone for HCSM.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 504-514"},"PeriodicalIF":12.2,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420438","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":"Demonstrating a Swarm Production lifecycle: A comprehensive multi-robot simulation approach","authors":"Akshay Avhad ,&nbsp;Casper Schou ,&nbsp;Halldor Arnarson ,&nbsp;Ole Madsen","doi":"10.1016/j.jmsy.2025.01.020","DOIUrl":"10.1016/j.jmsy.2025.01.020","url":null,"abstract":"<div><div>Swarm Production is a structurally self-organising paradigm that aligns with flexible and reconfigurable manufacturing principles to achieve high-variant and changeable volume market demand. The production lifecycle defines an adaptive topology planning phase, a coherent workstation and multi-robot task-allocation &amp; scheduling phase, and a fleet management phase. A Topology Manager system handles the layout optimisation and reconfiguration within the planning phase of Swarm Production. The layout optimisation undergoes recurrence during a production lifecycle and hence, becomes a dynamic layout planning problem. A Swarm Manager system executes production scheduling and multi-robot fleet management tasks based on the optimised layout in the Topology Manager. The exhibition of an entire lifecycle is crucial to demonstrate the capability of this paradigm and study the stochastic nature of production output due to the changing topologies. A software-in-the-loop simulation for Swarm Production demonstrates multiple scenarios executing multiple production orders with different product mixes. This research work also includes integrating all the systems to form a production suite. The work concludes with quantitative data acquired from the scenario-specific simulations and a formal analysis based on the results. The research contributes as a first full factory demonstration and a potential test bed for upcoming research undertakings within Swarm Production.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 484-503"},"PeriodicalIF":12.2,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420659","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":"R-DMDQN: A rule embedding based dynamic multi-objective deep Q-network for mass-individualized production scheduling of printed circuit board","authors":"Chunrong Pan ,&nbsp;Teng Yu ,&nbsp;Zhengchao Liu ,&nbsp;Hongtao Tang ,&nbsp;Xixing Li ,&nbsp;Shibao Pang ,&nbsp;Lifa He","doi":"10.1016/j.jmsy.2025.01.011","DOIUrl":"10.1016/j.jmsy.2025.01.011","url":null,"abstract":"<div><div>The printed circuit board (PCB) industry is currently facing the challenge of mass customization demands, which places an urgent need for efficient scheduling in PCB production. Due to the production process’s complexity and the environment’s variability, traditional scheduling algorithms often fail to achieve optimal performance in practical applications. This paper establishes a dynamic multi-objective flexible PCB shop scheduling model to address the challenges above. The model uses total tardiness, maximum completion time, and average machine utilization as optimization objectives. Moreover, a rule-embedded deep Q-network (R-DMDQN) algorithm is developed to address the complex dynamic characteristics of the PCB production process. The algorithm integrates characteristics of PCB production, extracting seven selected features to describe the system state. Simultaneously, it embeds six composite scheduling rules developed and guided by specialized knowledge to enhance the interpretability of learned strategies, and to augment the adaptability and flexibility of the algorithm. Through extensive experimental verification, the results show that the R-DMDQN model proposed in this study has significant superiority and stability in improving scheduling performance compared to the existing well-known scheduling rules and the NSGA-II algorithm. The research provides an innovative approach to the automation and optimization of scheduling in the PCB industry. It is expected to promote the application of related technologies in other complex production systems.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 466-483"},"PeriodicalIF":12.2,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388181","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 novel dynamic spatio-temporal graph based condition monitoring framework for consistency retention of digital twin","authors":"Xiaofeng Wang ,&nbsp;Jihong Yan ,&nbsp;Xun Xu","doi":"10.1016/j.jmsy.2025.01.006","DOIUrl":"10.1016/j.jmsy.2025.01.006","url":null,"abstract":"<div><div>A responsive consistency retention strategy is crucial for the engineering application of digital twin (DT). The condition monitoring technique based on graph theory can provide an overall reliability assessment and thus guide DT model updating. However, most existing studies constructed graph topology merely based on data information without incorporating prior engineering knowledge, which restricts the performance of such approaches. To tackle this limitation, a novel graph construction paradigm based on the mechanism of performance degradation and fault propagation is developed in this study. On this basis, unsupervised learning is further combined to form a dynamic spatio-temporal graph based condition monitoring framework for DT consistency retention. Specifically, the spatial dependencies of multi-sensors are quantified based on the evolution of the fault-related frequency band, and then multidomain features are assigned to each graph node. After that, the spatio-temporal graph set is fed to a dual-decoder graph autoencoder to extract the essential features of normal conditions, where a domain adaptation module is introduced to eliminate environmental effects. Hypothesis testing is conducted at last to inspect the machine state over time and make the final decision. Validation and comprehensive comparison experiments were carried out on two engineering scenarios with different scales (component and system level). The Numenta Anomaly Benchmark (NAB) was employed to evaluate the effectiveness of the proposed approach and the results revealed the great potential of the proposed framework for DT consistency retention.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 455-465"},"PeriodicalIF":12.2,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388180","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}