Journal of Manufacturing Systems最新文献

{"title":"Enhancing yield and process efficiency through dual internet of things and augmented reality for AI-driven human-machine interaction in centering mass production","authors":"Yu-Chen Liang,&nbsp;Shiau-Cheng Shiu,&nbsp;Chun-Wei Liu","doi":"10.1016/j.jmsy.2025.06.003","DOIUrl":"10.1016/j.jmsy.2025.06.003","url":null,"abstract":"<div><div>With the emergence of smart manufacturing, artificial intelligence (AI) has become a pivotal technology for enhancing industrial process efficiency and production yield. By integrating data analysis methods, AI can effectively capture process characteristics during manufacturing. However, tasks such as setting machine parameters still rely heavily on human expertise. This study focused on the centering process of optical glass lenses as a case study. To minimize dependence on human expertise, establish real-time diagnostic mechanisms, and shorten calibration times, an intelligent human-machine interactive manufacturing system featuring a Dual Internet of Things (Dual-IoT) architecture and augmented reality (AR) technology was developed. This system employs a feature extraction model that combines root mean square (RMS) with exponentially weighted moving average (EWMA) to analyze time-series signals during processing. Subsequently, an echo state network (ESN) prediction model was established to accurately forecast real-time signals and identify anomalies. In this setup, the control system and AI model are interconnected through a Dual-IoT architecture, enabling real-time data transmission to the intelligent AR-based human-machine interaction system and remote monitoring interface. This setup enables the visualization of process diagnostics and decision-making, providing feedback to the centering machine through remote control mechanisms. According to the verification results, at target specifications of &lt; 0.01 mm roundness and &lt;E0.5 edge cracks, the proposed system enhanced production yield from 64 % to 94 % while reducing production time by 29.2 %. These results confirm the system’s effectiveness in augmenting industrial production processes.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 26-41"},"PeriodicalIF":12.2,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243208","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":"Environmental impact of powder production for additive manufacturing: Carbon footprint and cumulative energy demand of gas atomization","authors":"Svenja Ehmsen ,&nbsp;Janosch Conrads ,&nbsp;Matthias Klar ,&nbsp;Jan C. Aurich","doi":"10.1016/j.jmsy.2025.05.004","DOIUrl":"10.1016/j.jmsy.2025.05.004","url":null,"abstract":"<div><div>The production of metal powder required for certain metal additive manufacturing processes has a significant environmental impact on the process chain. In particular, there is a lack of energy- and resource-related data on the environmental impact of industrial powder production and in-depth analysis of individual process steps. This study aims to provide a reliable life cycle inventory and, based on this, to determine the global warming potential (GWP) and cumulative energy demand (CED) resulting from the industrial production of melt atomized metal powders for additive manufacturing using gas atomization within the framework of a life cycle assessment (LCA). In this LCA, considering an average electricity mix at a production site in Germany, the GWP for closed-coupled atomization ranged from 4.61 kg CO₂-eq./kg to 16.71 kg CO₂-eq./kg. The results are slightly lower than those of free-fall atomization with a GWP between 5.58 kg CO₂-eq./kg and 24.81 kg CO₂-eq./kg. The need for inert gas is a major contributor to the environmental impact. If argon is used as an atomizing gas instead of nitrogen, the environmental impact increases, since argon has a GWP and CED approximately six times higher than nitrogen. Preheating the inert gas reduces the requirement and thus also the resulting environmental impact. This study provides a crucial basis for assessing the environmental impact of powder metal additive manufacturing processes and, enabling environmentally friendly process and product design. In addition, effective strategies to reduce the environmental impact of gas atomization can be identified based.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 13-25"},"PeriodicalIF":12.2,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144221332","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-based condition monitoring system to detect and resolve web slip at traction rollers in a web processing machine","authors":"Arul K. Mathivanan,&nbsp;Jeroen D.M. De Kooning,&nbsp;Kurt Stockman","doi":"10.1016/j.jmsy.2025.05.001","DOIUrl":"10.1016/j.jmsy.2025.05.001","url":null,"abstract":"<div><div>Slippage of web material over rollers is an undesirable phenomenon in web processing applications, causing damage to the web material. This leads to compromised quality and increased waste. While web slippage is commonly observed at high web speeds due to air entrapment on freely rotating rollers, it also occurs at lower web speeds at the traction rollers, which are designed to drive the web through the machine. Installing web speed sensors to detect such web slippage on multiple traction rollers in large-scale web processing machines is expensive. This work presents a novel Digital Twin methodology for online condition monitoring and fault detection to identify web slip at the traction rollers. The Digital Twin uses the contact forces between the web and the traction roller to detect web slippage, greatly reducing the need for web speed sensors and thereby cutting costs and time. Additionally, in response to detected web slip, the newly proposed Digital Twin further acts to resolve the slip. Experimental results demonstrate the effectiveness of the Digital Twin in detecting and resolving web slippage on three different web materials.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"82 ","pages":"Pages 1-12"},"PeriodicalIF":12.2,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195179","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":"Interpretable deep temporal neural networks for in-situ monitoring under varying conditions in micro-electrical discharge machining","authors":"Long Ye ,&nbsp;Cheng Guo ,&nbsp;Ming Wu ,&nbsp;Jun Qian ,&nbsp;Nan Yu ,&nbsp;Dominiek Reynaerts","doi":"10.1016/j.jmsy.2025.05.007","DOIUrl":"10.1016/j.jmsy.2025.05.007","url":null,"abstract":"<div><div>Monitoring is critical enabler of digitalization in modern manufacturing, supporting enhanced process control, quality assurance, and real-time decision-making. By integrating data-driven techniques with the powerful capabilities of deep learning, monitoring systems can efficiently extract valuable insights from complex, high-dimensional time-series data. However, traditional data-driven approaches often lack interpretability, limiting their adoption in industrial applications that demand high reliability and accountability. To address this challenge, this paper proposes an interpretable monitoring framework based on a deep temporal neural network (DTNN). Designed with a modular architecture, the DTNN integrates key components for embedding, temporal feature learning and classification, enabling it to effectively capture complex underlying patterns in temporal process data and overcome the limitations of conventional methods. The DTNN’s capabilities are demonstrated in the context of micro-electrical discharge machining (micro-EDM), a prominent non-traditional machining process known for producing intricate and high-precision components. Through a pulse discrimination task utilizing a large dataset of reliable labels, the DTNN achieves superior classification accuracy under varying processing parameters while providing interpretable insights into discharge phenomena. Furthermore, the DTNN monitoring approach is applied to a deep-hole drilling process in micro-EDM, enabling closed-loop control of discharge status and ensuring long-term process stability. The DTNN’s modular design, interpretability and real-time adaptability underscore its potential for advancing data-driven monitoring systems in digital manufacturing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 222-237"},"PeriodicalIF":12.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144184398","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 method for monitoring machining errors of complex thin-walled parts based on the fusion of physical information and CNN","authors":"Wangfei Li ,&nbsp;Junxue Ren ,&nbsp;Kaining Shi ,&nbsp;Yanru Lu ,&nbsp;Huan Zheng","doi":"10.1016/j.jmsy.2025.05.017","DOIUrl":"10.1016/j.jmsy.2025.05.017","url":null,"abstract":"<div><div>Machining errors of complex thin-walled parts have a direct impact on product quality and performance, making their monitoring essential. The monitoring of machining errors of such parts often depends on relevant physical information. However, time-varying physical information (TVPI) is influenced by the dynamic response of the measurement system, and the spatial dynamic relationship between the physical information and machining errors is highly intricate, posing significant challenges for monitoring. To address these challenges, a method based on the fusion of physical information and Convolutional Neural Network (CNN) is proposed for monitoring machining errors of complex thin-walled parts. Initially, a TVPI identification method based on physical theory is introduced, and the spectrum amplitudes of cutting forces are extracted as the TVPI for monitoring machining errors. The feature extraction and nonlinear regression modeling capabilities of the CNN are then leveraged to filter the physical information intelligently and learn the complex relationship between the physical information and machining errors. Ultimately, a monitoring method for machining errors based on the fusion of physical information and the CNN is proposed and experimentally validated on complex thin-walled parts such as blades. Compared with traditional feature identification methods, the TVPI identification method provides enhanced physical interpretability. Additionally, the fusion of physical information and the CNN notably improves the monitoring performance. Compared with monitoring methods based on Gaussian Process Regression, Deep Neural Network and Long Short-Term Memory, the monitoring method based on the fusion of physical information and the CNN results in at least a 21.74 % reduction in the <em>RMSE</em>. The method not only provides valuable feedback on machining errors of complex thin-walled parts but also offers technical support for the subsequent optimization and adjustment of machining strategies.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 208-221"},"PeriodicalIF":12.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144146700","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":"Machine node-enhanced graph contrastive learning with long-range prompt model for quality propagation in multistage manufacturing systems","authors":"Pei Wang ,&nbsp;Hai Qu ,&nbsp;Jinrui Liu","doi":"10.1016/j.jmsy.2025.05.018","DOIUrl":"10.1016/j.jmsy.2025.05.018","url":null,"abstract":"<div><div>More complex multistage manufacturing systems (MMSs) have become mainstream production processes. Deep learning can accurately predict product quality indicators and help improve product qualification rates. Existing single-stage models can only predict the quality of a single machine or a single stage, ignoring the propagation effects. Although some multistage models consider quality propagation effects, they simply aggregate the machine features within a stage. In addition, existing multistage models do not conform to the actual production process when utilizing machine space relationships. Traditional models with severe label data dependence are difficult to make full use of noise data, resulting in reduced prediction accuracy and lack of interpretability. To address the above problems, this paper proposes a machine node-enhanced graph contrastive learning method with long-range prompt (MNGCLP), extracting propagation effects in both pre-training and fine-tuning. Specifically, the graph data is first used to model the production relationship between machines and form a production process graph. Then, a machine-enhanced graph is designed in contrastive-based pre-training to better add production information to avoid violating the production process and reduce label dependency. Finally, the long-distance relationship between machine nodes captured in the original graph is used as prompts to fine-tune the pre-trained model. Experiments in public production data show that the proposed method outperforms traditional models and provides a reasonable explanation for the prediction results, validating the effectiveness of MNGCLP. Compared with supervised graph neural network, the proposed model improves the overall RMSE, MSE and MAE by 2.4 %, 4.8 % and 9.8 %, respectively. Compared with the contrastive graph neural network, the proposed model improves the overall RMSE, MSE and MAE by 2.5 %, 5.0 %, and 6.3 %, respectively.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 169-188"},"PeriodicalIF":12.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138251","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":"Spatial-temporal dual-stream fusion network with embedded knowledge: A process-generalized framework for tool wear monitoring","authors":"Zhixiang Chen ,&nbsp;Jin Zhang ,&nbsp;Fengze Qin ,&nbsp;Guibao Tao ,&nbsp;Duo Li ,&nbsp;Huajun Cao","doi":"10.1016/j.jmsy.2025.05.014","DOIUrl":"10.1016/j.jmsy.2025.05.014","url":null,"abstract":"<div><div>As a pivotal technology in intelligent computer numerical control (CNC) systems, tool wearing monitoring (TWM) significantly influences machining stability, product quality, and production efficiency. However, the complexity and randomness of the tool wear process pose significant challenges to traditional single-model methods. These methods often struggle to capture diverse data patterns, leading to low accuracy and poor processing generalization. This study proposes a Spatial-Temporal Dual Stream Fusion Network (STDSFnet) with embedded knowledge. The framework establishes strong correlations between multi-modal sensor data and tool wear states. The methodology consists of three key steps: (1) applying Spearman correlation analysis to select sensitive feature vectors, which helps reduce transient signal interference; (2) developing a dual-stream network to extract spatial and temporal wear-related information; and (3) integrating coordinated attention mechanisms and feature fusion modules to enhance the feature representation, thereby improve the TWM accuracy and processing generalization. Besides, to ensure that the trend of TWM results conforms to the actual wear pattern, domain knowledge is introduced to improve the reliability and interpretability of monitoring results. Experiments validate the effectiveness of STDSFnet on block-shaped stainless-steel workpieces and carbon fiber-reinforced polymer (CFRP) machining scenarios. Compared to baseline methods, STDSFnet reduces RMSE by 38.94 %–62.04 %, decreases MAE by 43.64 %–61.70 %, and improves R² by 4.96 %–28.59 %. These results confirm that spatial-temporal fusion with deep ensembles significantly boosts TWM accuracy and reliability.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 189-207"},"PeriodicalIF":12.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144146699","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":"Train small, deploy large: Scaling multi-agent reinforcement learning for multi-stage manufacturing lines","authors":"Kshitij Bhatta,&nbsp;Qing Chang","doi":"10.1016/j.jmsy.2025.04.017","DOIUrl":"10.1016/j.jmsy.2025.04.017","url":null,"abstract":"<div><div>We present a novel control framework using Multi Agent Reinforcement learning (MARL) that is scalable in the number of workstations in a multi-stage manufacturing line. We show that the dynamics of any production line, regardless of size, can be decoupled into three fundamental expressions. These expressions capture the dynamics of (1) the first workstation, (2) all intermediate workstations, and (3) the last workstation. This decoupling, combined with observation engineering enables training a characteristic 3-workstation, 2-buffer model using MARL methods, which can then generalize to production lines with <span><math><mi>w</mi></math></span> workstations with arbitrary cycle times, buffer capacities and reliability models. A numerical study is then conducted to validate the framework.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 155-168"},"PeriodicalIF":12.2,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134807","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":"Coarse-to-fine vision-based welding spot anomaly detection in production lines of body-in-white","authors":"Weijie Liu,&nbsp;Jie Hu,&nbsp;Jin Qi","doi":"10.1016/j.jmsy.2025.05.003","DOIUrl":"10.1016/j.jmsy.2025.05.003","url":null,"abstract":"<div><div>Computer vision-assisted methods for weld quality inspection enable rapid and automated surface defect detection through image data. However, the application of Computer Vision-Assisted Inspection (CVAI) in real-world production lines faces substantial, long-term challenges due to complex environments, imbalanced data samples, real-time processing demands, and safety requirements. Our paper proposes a novel two-stage Coarse-to-Fine Anomaly Detection (CTFAD) framework, which integrates the YOLOv8 network architecture for initial detection with an ensemble of neural networks for fine-grained classification. Additionally, we introduce a voting-based algorithm for improved decision-making accuracy. Experimental results on real-world datasets demonstrate that, compared to standard end-to-end methods, CTFAD enhances detection accuracy and operational efficiency. Our contributions include (1) proposing the CTFAD pipeline for weld anomaly detection, (2) establishing voting-based classification module to increase system robustness and generalization, and (3) developing an integrated weld detection system encompassing data acquisition, processing, analysis, and anomaly alerting. Our code is available at <span><span>https://github.com/wj-liu0730/ctfad-jms</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 144-154"},"PeriodicalIF":12.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115901","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":"Robotic aero-engine pipe grasping posture and motion planning method in multi-stage processing based on multi-objective optimization","authors":"Bo Zhou ,&nbsp;Jibin Zhao ,&nbsp;Tianyu Zhang ,&nbsp;Renbo Xia ,&nbsp;Hongfeng Wang ,&nbsp;Junwei Wang ,&nbsp;Long Gao","doi":"10.1016/j.jmsy.2025.05.011","DOIUrl":"10.1016/j.jmsy.2025.05.011","url":null,"abstract":"<div><div>In the aviation industry, the manufacturing of aero-engine bending pipes consists of multiple processes, e.g., straight pipe bending, allowance removal, precision chamfering, and inspection. Currently, the production of aero-engine bending pipes is carried out mainly manually, and uncontrollable human factors can greatly affect the manufacturing accuracy and efficiency. This paper introduces a grasping posture and motion planning method. It can efficiently and accurately perform multi-stage precision manufacturing tasks on aero-engine bending pipe production lines. First, we provide a gravity deformation model for flexible bending pipes and verify its accuracy through finite element simulations and experiments. It can be used to compensate accurately for the motion of bending pipes entering the processing hole along a straight path. We propose a coordinate transformation method and an accurate calibration method. It can achieve precise transformation of the original posture of the computer-aided design (CAD) model and the postures at the processing stations, e.g., the outlet of the clamping mold of the bending machine, the processing holes of the residual removal and the flat end chamfer. Next, we propose converting the linear paths into NURBS interpolation paths and using the S-shaped acceleration/deceleration (ACC/DEC) feed rate planning method. It can convert the velocity, acceleration, and jerk into the corresponding angular velocity, acceleration, and jerk of each joint in the joint space to ensure that processing and inspection tasks can be performed under appropriate kinematic constraints. Then, an improved NSGA-II algorithm is proposed, which can solve the trade-off minimization problem of processing time, energy consumption, and vibration by incorporating multi-objective optimization functions and motion constraints. The simulation and experimental results demonstrated the superiority of optimization method in terms of processing accuracy, precision, stability, and efficiency. The performance of the improved NSGA-II algorithm is compared with that of other multi-objective optimization algorithms, and the superior performance of the algorithm is verified.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"81 ","pages":"Pages 117-143"},"PeriodicalIF":12.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099869","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}