Journal of Manufacturing Systems最新文献

{"title":"SFRGNN-DA: An enhanced graph neural network with domain adaptation for feature recognition in structural parts machining","authors":"Xiaohu Zheng ,&nbsp;Hongbo Chen ,&nbsp;Fangzhou He ,&nbsp;Xiaojia Liu","doi":"10.1016/j.jmsy.2025.05.005","DOIUrl":"10.1016/j.jmsy.2025.05.005","url":null,"abstract":"<div><div>Optimizing the recognition of machining features in structural parts is vital for enhancing the efficiency of NC machining planning and ensuring quality control. However, the inherent complexity and stringent precision requirements of these parts often render existing feature recognition methods inadequate for accurately identifying model features. To address this challenge, a novel graph neural network model (SFRGNN) is introduced. The methodology begins with a specialized feature extraction module that captures both geometric and topological properties of the parts, providing a comprehensive basis for further analysis. Following this, SFRGNN integrates a graph neural network with a Spatial Self-Attention (SSA) module, a configuration designed to enhance the extraction of high-level semantic information crucial for accurately distinguishing machining features. This network architecture allows SFRGNN to interpret complex feature relationships with improved precision. Additionally, an enhanced domain adaptation module (DA) is incorporated to improve SFRGNN’s generalization capabilities and performance in machining feature recognition. Numerous experiments on different data sets confirmed that SFRGNN achieved excellent accuracy in identifying real-world structural part features and demonstrated enhanced performance, which will be helpful for subsequent process planning for part features in real-world scenarios.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 16-33"},"PeriodicalIF":12.2,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072253","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":"Puzzle mode graph learning with pattern composition relationships reasoning for defect detection of printed products","authors":"Zixun Zhu ,&nbsp;Jie Zhang ,&nbsp;Junliang Wang ,&nbsp;Peng Zhang ,&nbsp;Jiacheng Li","doi":"10.1016/j.jmsy.2025.05.013","DOIUrl":"10.1016/j.jmsy.2025.05.013","url":null,"abstract":"<div><div>Patterns are designs composed of specific elements and are widely present in various printed products, representing particular design intentions. However, due to printing errors, pattern defects are extremely common in these products, significantly impacting their visual quality and market price, especially in high-value customized products like luxury apparel, premium wallpapers and decorative tiles. Traditional detection methods struggle to provide effective judgments with conventional visual cues purely and frequently fall short due to the intricate nature of the pattern composition. To overcome this challenge, we propose a puzzle mode graph learning method capable of reasoning about pattern composition relationships. This novel detection framework simulates the logical reasoning ability of humans in assembling unordered puzzle pieces into a complete pattern, thus surpassing spatial structure limitations and enabling structural defect detection in patterns. Specifically, a parametric representation function is integrated into convolutional layers to enhance the segmentation accuracy of shape masks. Then, cross-graph semantic matching rules are developed to dynamically re-encode the adjacency matrix, enabling the construction of an attribute relationship graph that explicitly describes pattern attributes, including pattern elements, color sequences and shape positions. Moreover, the defective reasoning mechanism calculates puzzle-mode scores to decouple semantic relationships of defect features, inferring anomalous node and edge weights affecting the graph structure, thereby facilitating more precise judgments of pattern defects. Comparative experiments conducted on a real printed defect dataset validate this method. Results demonstrate its effectiveness and robustness in identifying complex pattern defects, providing essential support for appearance quality control in high-end industrial products.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 34-48"},"PeriodicalIF":12.2,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071820","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":"Data-physics collaborativige fusion prediction method for tool remaining useful life based on Mamba state space and physical description","authors":"Caixu Yue,&nbsp;Yiyuan Qin,&nbsp;Xianli Liu,&nbsp;Hao Gu,&nbsp;Shaocong Sun","doi":"10.1016/j.jmsy.2025.05.012","DOIUrl":"10.1016/j.jmsy.2025.05.012","url":null,"abstract":"<div><div>Tool wear is an inherent phenomenon of the metal cutting process, the traditional replacement strategy relies on experience or a fixed cycle easily leads to waste of resources or workpiece damage, accurate prediction of the tool's remaining useful life (RUL) has become a key issue in the field of intelligent manufacturing urgently need to break through. Aiming at the problems of insufficient nonlinear processing capability of physical models and weak interpretability of data-driven models in the existing RUL prediction, this study proposes a data-physics collaborative fusion prediction method for tool remaining useful life based on Mamba state space and physical description. The method breaks through the traditional single-model paradigm and achieves in-depth characterization of the cutting process through a dual modeling mechanism: firstly, a time-series feature extraction network based on the Mamba state space is constructed, and a selective memory mechanism is adopted to achieve the screening of degradation features and non-linear characterization; secondly, a two-stage piecewise physical degradation model is established. The explicit mathematical expressions are deduced based on the geometrical features of the tool wear curve, and the prior distributions of the model parameters are estimated from historical data. The Particle Filter (PF) algorithm is introduced to establish a collaborative optimization mechanism for the dual models, and the physical parameters are dynamically updated through importance sampling to achieve tool RUL prediction under Data-physics collaborative fusion (DPCF). The experimental results show that the method can achieve accurate monitoring of tool RUL and has a certain reference value for efficient tool change in the metal-cutting process.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 1-15"},"PeriodicalIF":12.2,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070792","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":"Advances and innovations in manufacturing systems research 2025","authors":"Xun Xu,&nbsp;Stefania Bruschi,&nbsp;Robert X. Gao","doi":"10.1016/j.jmsy.2025.04.020","DOIUrl":"10.1016/j.jmsy.2025.04.020","url":null,"abstract":"","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 1072-1073"},"PeriodicalIF":12.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942452","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-view fully connected graph to fuse multi-sensor signals for mechanical equipment remaining useful life prediction","authors":"Jinxin Wu ,&nbsp;Deqiang He ,&nbsp;Zhenzhen Jin ,&nbsp;Ming Zhao ,&nbsp;Xianwang Li ,&nbsp;Yanjun Chen","doi":"10.1016/j.jmsy.2025.05.009","DOIUrl":"10.1016/j.jmsy.2025.05.009","url":null,"abstract":"<div><div>Accurate remaining useful life prediction is essential for enhancing equipment reliability and optimizing maintenance strategies. However, existing methods struggle to effectively integrate multi-sensor data while quantifying uncertainty. To address these challenges, a multi-view fully connected graph neural network is proposed for multi-sensor mechanical equipment remaining useful life prediction. Firstly, local fully connected graphs and global graphs are constructed to comprehensively characterize the multi-view spatial correlations from global and local views. Meanwhile, the graph convolution operations are performed on local and global graphs to extract the intricate spatial dependencies within multi-sensor signals. Then, the learned multi-view spatial representations are fed into the temporal convolutional network to capture the temporal dependencies across sensor timestamps. Finally, a joint optimization network is developed to simultaneously predict the remaining useful life and its associated prediction interval, enabling uncertainty quantification. Extensive experiments on two multi-sensor monitoring degradation datasets demonstrate the superior performance of the proposed model, offering valuable technical support for predictive maintenance.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 1029-1052"},"PeriodicalIF":12.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935156","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 explainable multi-layer graph attention network for product completion time prediction in aircraft final assembly lines","authors":"Bolin Chen ,&nbsp;Jie Zhang ,&nbsp;Jun Xiong ,&nbsp;Wenbin Tang ,&nbsp;Shoushan Jiang","doi":"10.1016/j.jmsy.2025.04.018","DOIUrl":"10.1016/j.jmsy.2025.04.018","url":null,"abstract":"<div><div>Predicting product completion time (PCT) is a critical challenge in aircraft manufacturing systems, especially for make-to-order production. This necessitates manufacturers to comprehensively analyze operational state features, including task completion, resource allocation, and material supply, to estimate delivery dates effectively. With the increasing availability of production site perception, data-driven methods for PCT prediction have gained significant attention. However, the coupled interactions among various manufacturing elements, combined with the demand for real-time scheduling in digital twin scenarios, have limited the accuracy and explainability of traditional black-box predictive models. To address these challenges, this paper proposes an explainable multi-layer heterogeneous graph attention network (M-HGAT) customized for predicting PCT in the aircraft final assembly line (AFAL). First, a heterogeneous graph representation method is introduced to model the aircraft assembly status, focusing on the interactions among assembly tasks, materials, and workers. Then, a two-layer state feature aggregation neural network is designed to learn the mapping relationship between the target PCT and input features, incorporating logical and demand constraints among various elements inherent in the aircraft assembly process. Finally, the accuracy and explainability of the proposed model have been validated through an industrial case study focused on PCT prediction. Compared to four benchmark predictive models, the proposed model achieves superior predicted results, reducing the root mean square error by 48 % compared to the best benchmark. Furthermore, the explainability of the M-HGAT is demonstrated through its ability to identify key manufacturing elements and bottleneck assembly stations by analyzing attention weights within the neural network, which provides valuable insights for production managers to optimize AFAL operations and enhance production efficiency.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 1053-1071"},"PeriodicalIF":12.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935157","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 digital twin calibration for an automated material handling system in a semiconductor fab","authors":"Bonggwon Kang ,&nbsp;Chiwoo Park ,&nbsp;Haejoong Kim ,&nbsp;Soondo Hong","doi":"10.1016/j.jmsy.2025.04.015","DOIUrl":"10.1016/j.jmsy.2025.04.015","url":null,"abstract":"<div><div>To address the complex, dynamic, and stochastic nature of an automated material handling system (AMHS) in a semiconductor fabrication facility (fab), practitioners have used a high-fidelity discrete-event simulation as its digital twin model for decision-making over several decades. Previous studies have focused on fast digital twin-based decision-making in AMHSs under the assumption that their digital twin models are credible enough to prescribe decisions. However, parameter uncertainty and intrinsic bias in an AMHS digital twin model can lead to an inaccurate representation of its field system. To address the challenge, this paper introduces the Bayesian calibration, which modularly estimates a digital twin outcome and its discrepancy using Gaussian process priors. A calibration framework for digital twin-based decision-making is also presented using an AMHS example. Our experimental results with various AMHS operating scenarios demonstrate that: (1) a sophisticated digital twin calibration is necessary, especially when AMHSs operate under heavy-workload scenarios; and (2) exploring model bias considerably decreases the prediction error of an AMHS digital twin within a limited number of field observations. Moreover, we discuss the applicability of the approach to digital twins in various fields.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 1013-1028"},"PeriodicalIF":12.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923341","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 LLM-guided SD-LDM Digital Twin Construction Strategy (LSDT) for multi-industrial scenarios: Enhancing adaptability and efficiency","authors":"Feixiang Wang ,&nbsp;Xiaojun Liu ,&nbsp;Feng Lv ,&nbsp;Chongxin Wang ,&nbsp;Jin Shi ,&nbsp;Xiaotian Zheng ,&nbsp;Chao Li","doi":"10.1016/j.jmsy.2025.04.019","DOIUrl":"10.1016/j.jmsy.2025.04.019","url":null,"abstract":"<div><div>In the rapidly evolving landscape of Industry 5.0, Digital Twin (DT) have emerged as a transformative technology across various industrial sectors. However, as DT theory and practice progress, a critical issue arises: the prolonged building time associated with implementing DTs. To address this challenge, this paper proposes a rapid DT construction method: LLM-Guided SD-LDM Digital Twin Construction Strategy (LSDT) for multi-scenarios. Firstly, we introduce a cross-modal generation framework. This framework leverages Large Language Model (LLM)-Guided Stable Diffusion- Latent Diffusion Model (SD-LDM) technology, which is capable of swiftly constructing high-quality 3D models based on limited multimodal data. Subsequently, the generated models are transferred into the Digital twin construction framework. This framework incorporates both the DT construction method and the assembly and fusion method, enabling the realization of a multi-scale, multi-level DT construction. Finally, we conducted case study in R&amp;D laboratories, prototype warehouses, and packaging units. The multi-dimensional scoring results showed that the model construction efficiency improved significantly, with peak values reaching 39 % (across models) and 73 % (single model), while usability scores peaked at 13.84. Furthermore, the constructed DT successfully met the core Ss requirements of the scenarios. These results indicate that the LSDT method accelerates the efficiency for DT construction and offers good adaptability.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 995-1012"},"PeriodicalIF":12.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916622","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":"Integrated scheduling for ring layout multi-station multi-robot welding system with dual function robots and jump stations operations","authors":"Ye Wang ,&nbsp;Xuewu Wang ,&nbsp;Sanyan Chen ,&nbsp;Yi Hua ,&nbsp;Xingsheng Gu","doi":"10.1016/j.jmsy.2025.04.012","DOIUrl":"10.1016/j.jmsy.2025.04.012","url":null,"abstract":"<div><div>Robotic automated production is the best choice for large-scale manufacturing in the modern automotive industry. Optimizing robotic welding system in an integrated manner is crucial to achieving efficient production. Current research primarily addresses the limited integration of sub-problems for basic production lines. The integrated scheduling of complex coupling challenges in multi-station multi-robot production line is explored in this paper. Tightly coupled sub-problems such as robot allocation, task allocation, dual-function robot scheduling, human–robot cooperative work and welding sequence planning are comprehensively studied and modeled, accounting for numerous constraints in production line composition and parts assembly. Meanwhile, the issue of robot jumping stations operate is also investigated. These complex coupled problems with numerous constraints are incorporated into a unified and novel comprehensive scheduling framework. On this basis, an integrated scheduling model considering robots accessibility, welding accessibility, welding integrity and process feasibility constraints is established, along with an algorithm is proposed to optimize the problems in the model. A five-layer chromosome, featuring two hidden layers, is designed to represent the decision space of the multi-station multi-robot welding system integrated scheduling (MSMRWS-IS) problem. To ensure robot accessibility and welding completeness during evolution, a chromosome correction method is devised. Finally, the proposed STNSGA-DFC is compared with five multi-objective evolutionary algorithms (MOEAs) across four test instance groups. The experimental results demonstrate that STNSGA-DFC outperforms the comparison algorithms in terms of overall performance. The model and optimization method presented in this paper offer significant potential for improving mass production efficiency in industrial environments and hold significant practical value for the complex coupled welding system integrated optimizing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 976-994"},"PeriodicalIF":12.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143905875","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":"Total slack transmission graph-based robust scheduling for flexible job shop scheduling under machine breakdowns","authors":"Lingling Lv ,&nbsp;Wenbing Song ,&nbsp;Weiming Shen","doi":"10.1016/j.jmsy.2025.04.007","DOIUrl":"10.1016/j.jmsy.2025.04.007","url":null,"abstract":"<div><div>In actual manufacturing systems, machine failures happen intermittently due to different types of faults. Therefore, it is important to generate a robust schedule. This paper investigates a flexible job shop scheduling problem under machine breakdowns whereby makespan and the robustness of a schedule have to be considered. The concept of a total slack transmission graph is defined to describe the chain reactions of slack consumption between operations. A total slack transmission algorithm is proposed to update the values of the nodes and edges in the graph. Accordingly, a quality robustness surrogate measure and a solution surrogate measure are derived to introduce the objective of robustness. A two-stage hybrid genetic algorithm is adopted by combining the proposed robustness surrogate measures to generate robust schedules. Six robustness surrogate measures in the existing literature are used for comparisons against the proposed surrogate measures. The experimental results show the superiority of the proposed robustness surrogate measure concerning the deviation of makespan and the completion times of operations between the rescheduled solution and preschedule.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 963-975"},"PeriodicalIF":12.2,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902079","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}