Journal of Manufacturing Systems最新文献

{"title":"Enhancing manual inspection in semiconductor manufacturing with integrated augmented reality solutions","authors":"Chih-Hsing Chu,&nbsp;Chen-Yu Weng,&nbsp;Yu-Tzu Chen","doi":"10.1016/j.jmsy.2024.10.028","DOIUrl":"10.1016/j.jmsy.2024.10.028","url":null,"abstract":"<div><div>On-site routine inspection often remains a manual operation in the semiconductor manufacturing industry because implementing automated solutions can be costly and technically challenging in such a highly controlled and complex environment. The manual inspection is prone to errors due to the impact of demanding physical and mental workloads. This paper presents an integrated Augmented Reality (AR) solution developed to assist manual inspection tasks in the supporting areas of semiconductor manufacturing, referred to as the sub-fab. The solution is accessible to a human worker wearing an AR headset during the inspection process at the location. We propose a system framework to deploy computational intelligences of varying granularity provided by the solution across cloud, edge, and device levels, accommodating constraints within the sub-fab. A machine maintenance module helps estimate and monitor the health condition of running scrubbers. Incorrect intentions performed by the worker on the scrubber control panel are detected through hand gesture recognition. This instantly prompts warning messages in the AR headset to prevent subsequent wrong actions. The solution can also identify abnormal device states through 6D pose estimation of objects enabled by machine learning models. A test scenario demonstrates how these functional features enhance the inspection efficiency and quality by reducing human workloads. This work demonstrates that semiconductor manufacturing may require AR-assisted functions different from those needed or common in other industrial sectors. It also highlights the potential of AR technology for reducing operational human errors in manual tasks.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 933-945"},"PeriodicalIF":12.2,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663841","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 new cause-mechanism independence estimation based cross-domain learning method for machining deformation prediction","authors":"Yang Ni ,&nbsp;Yingguang Li ,&nbsp;Changqing Liu ,&nbsp;Xu Liu","doi":"10.1016/j.jmsy.2024.11.002","DOIUrl":"10.1016/j.jmsy.2024.11.002","url":null,"abstract":"<div><div>Monitoring data-based machining deformation prediction is fundamental for accurate deformation control and product quality guarantee. For problems where involved unobservable variables like residual stress that can lead to data distribution bias, causal cross-domain learning methods have prominent advantages over other pure data-driven methods by shifting cause distributions and mechanisms. However, existing causal methods are based on the hypothesis that cause and mechanism are independent, which ignores the corresponding changes of mechanism across domains and can limit accuracies. This paper proposes a new causal cross-domain learning method based on cause-mechanism independence estimation, where the hypothesis is broken by taking the dependence of cause and mechanism into consideration. A cause-mechanism independence estimator is established by introducing the structural integral of mechanism derivative multiplies cause distribution, and the estimation value can measure the cross-domain changes of mechanism. As a result, the proposed method based predicting model can make efficient distribution shifts according to the estimation. The machining of aero-engine casings is taken as a case study, and experimental results show that the proposed method could predict the deformation well with limited target domain data. Besides, the proposed method can be readily extended to other cross-domain regression problems involved with unobservable variables.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 919-932"},"PeriodicalIF":12.2,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663840","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":"Simulation-based Digital Twin for enhancing human-robot collaboration in assembly systems","authors":"Antonio Cimino ,&nbsp;Francesco Longo ,&nbsp;Letizia Nicoletti ,&nbsp;Vittorio Solina","doi":"10.1016/j.jmsy.2024.10.024","DOIUrl":"10.1016/j.jmsy.2024.10.024","url":null,"abstract":"<div><div>The advent of new technologies and paradigms such as the Internet of Things (IoTs), Digital Twin (DT), Human-Robot Collaboration (HRC), is offering immense opportunities to improve the performance of manufacturing systems, but also opening new challenges. The current scientific literature highlights the presence of numerous theoretical studies, but limited real-life applications, and the need to address interoperability issues, with the aim of valorizing the data continuously generated by humans, robots, machines. This research presents a novel simulation-based DT, designed for supporting HRC optimization in assembly systems. The proposed approach is tested and validated, through a case study in the automotive sector, specifically focusing on an assembly line for car front doors. The results show that it is possible to achieve HRC improvements through the assessment of different working configurations. Furthermore, it is explained how the simulation-based DT, by leveraging the FIWARE/FIROS paradigm, can effectively and efficiently interact with other systems, to enable real-time data exchange, which is nowadays one of the main open research challenges.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 903-918"},"PeriodicalIF":12.2,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663839","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":"LogicLSTM: Logically-driven long short-term memory model for fault diagnosis in gearboxes","authors":"Eduard Hogea ,&nbsp;Darian M. Onchiş ,&nbsp;Ruqiang Yan ,&nbsp;Zheng Zhou","doi":"10.1016/j.jmsy.2024.10.003","DOIUrl":"10.1016/j.jmsy.2024.10.003","url":null,"abstract":"<div><div>This article introduces LogicLSTM, a hybrid neuro-symbolic model obtained by logically guiding a pretrained Long Short-Term Memory (LSTM) network with the support of a customized Logic Tensor Network (LTN). The model is further optimized by explainable AI techniques, for a refined fault classification of time-series data coming from industrial gearboxes. The framework leverages the intrinsic strengths of LSTMs deep recurrent networks for temporal data processing with logical reasoning capabilities, to improve prediction accuracy and interpretability of the classification. Our approach addresses the challenges of extracting relevant data features and integrating connectionist and symbolic methodologies to form a cohesive predictive model. Results from extensive testing show that our model significantly outperforms traditional LSTM models, particularly in complex fault scenarios where conventional methods may fail. Specifically, the hybrid model demonstrates a 16.03% average improvement in accuracy over standard LSTM models under conditions of sufficient data availability, and a 8.56% improvement in scenarios where data is scarce. This research not only demonstrates the potential of hybrid models in industrial applications but also highlights the importance of explainability in AI systems for critical decision-making processes. The proposed model’s ability to interpret and explain its predictions makes it a valuable tool for advancing predictive maintenance strategies within the Industry 4.0 framework.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 892-902"},"PeriodicalIF":12.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663838","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":"Towards data-driven quality monitoring for advanced metal inert gas welding processes in body-in-white","authors":"Michael Luttmer ,&nbsp;Matthias Weigold ,&nbsp;Heiko Thaler ,&nbsp;Jürgen Dongus ,&nbsp;Anton Hopf","doi":"10.1016/j.jmsy.2024.10.013","DOIUrl":"10.1016/j.jmsy.2024.10.013","url":null,"abstract":"<div><div>In recent years, numerous monitoring approaches have been developed in the field of intelligent welding manufacturing to predict quality-related characteristics using process data and artificial intelligence-based techniques. While most investigations have focused on welding steel with conventional gas metal arc welding processes, the welding of aluminum and its alloys using advanced process variants has been less explored. This work addresses this gap by investigating data-driven methods for fault diagnosis and detection in an advanced metal inert gas welding process commonly used in body-in-white manufacturing. To this end, electrical, acoustic, and spectroscopic signals were recorded from numerous welding tests simulating typical fault causes. Various predictive models, ranging from traditional machine learning algorithms to state-of-the-art deep learning techniques, were trained and evaluated for classifying faulty seams and identifying their root causes. The results demonstrate that combining sensor data enhances the performance of predictive models compared to using individual sensors alone. However, a deep learning approach based solely on electrical signals emerged as the best solution for both use cases, considering both the results and practical aspects. Overall, the experiments highlight the significant potential of data-driven techniques to enhance quality monitoring in advanced MIG welding processes, promoting their more widespread adoption in body-in-white manufacturing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 875-891"},"PeriodicalIF":12.2,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587070","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":"Joint production, maintenance, and quality control in manufacturing systems with imperfect inspection","authors":"Abdessamad Ait El Cadi ,&nbsp;Ali Gharbi ,&nbsp;Karem Dhouib ,&nbsp;Abdelhakim Artiba","doi":"10.1016/j.jmsy.2024.10.020","DOIUrl":"10.1016/j.jmsy.2024.10.020","url":null,"abstract":"<div><div>This paper proposed a joint production control, preventive maintenance, and inspection policy for manufacturing systems prone to failures, quality degradation and quality inspection errors. A stochastic mathematical model is developed taking into account all possible scenarios contingent to imperfect quality inspection errors, while integrating age-based preventive maintenance, dynamic production rates, and sampling inspection plans. The model accounts for both Type I and Type II inspection errors and optimizes the joint policy key parameters, including safety stock levels, preventive maintenance thresholds, and inspection sample size. The model is validated using a 95 % confidence interval obtained from experiments with simulation model that imitates the studied system dynamics when it is controlled by the proposed joint policy. A sensitivity analysis is carried out to give a deeper comprehension of the problem and the complex interactions at play. The study explores the impact of system’s parameters on the new joint policy that accounts for inspection errors, thereby contributing valuable insights to the field of manufacturing systems management. Ultimately, a comprehensive comparative analysis seeks to establish the superiority of the proposed joint policy over existing ones documented in the literature. The proposed policy consistently outperformed alternative approaches, with an overall cost reduction of up to 87 %.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 848-858"},"PeriodicalIF":12.2,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578655","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":"Sustainable management of electric vehicle battery remanufacturing: A systematic literature review and future directions","authors":"Alessandro Neri ,&nbsp;Maria Angela Butturi ,&nbsp;Rita Gamberini","doi":"10.1016/j.jmsy.2024.10.006","DOIUrl":"10.1016/j.jmsy.2024.10.006","url":null,"abstract":"<div><div>The increasing adoption of electric vehicles (EVs) and the corresponding surge in lithium-ion battery (LIB) production have intensified the focus on sustainable end-of-life (EOL) management strategies (i.e., reuse, repurpose, remanufacture, and recycle). This paper presents a systematic literature review of the entire remanufacturing process of LIBs, aiming to offer a cohesive perspective on the approach that reduces the environmental impact of LIB waste by prolonging their lifecycle for reuse in their original EV applications. It reveals major issues from EOL collection to renewed batteries, clustering results into six research streams, and proposes a research agenda to develop integrative, data-driven models that incorporate technical, economic, and environmental considerations. Key findings highlight the need for standardised, non-damaging joining techniques, enhanced safety protocols for disassembly, and scalable cathode re-functionalisation methods. Recommendations include leveraging advanced technologies such as AI, machine learning, IoT, and blockchain to optimise remanufacturing processes and enhance supply chain transparency and efficiency. This comprehensive review aims to foster the development of sustainable remanufacturing practices, contributing to the circular economy and supporting the growth of the EV industry.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 859-874"},"PeriodicalIF":12.2,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578656","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":"Robotic disc grinding path planning method based on multi-objective optimization for nuclear reactor coolant pump casing","authors":"Bo Zhou ,&nbsp;Tongtong Tian","doi":"10.1016/j.jmsy.2024.10.021","DOIUrl":"10.1016/j.jmsy.2024.10.021","url":null,"abstract":"<div><div>In the nuclear industry, the finishing grinding work of the nuclear reactor coolant pump (RCP) casing is mainly performed manually. Uncontrollable grinding tasks cause the grinding disc to be easily worn during the grinding process, which will greatly affect the grinding accuracy and efficiency. This paper introduces a path planning method that can efficiently and accurately perform a disc grinding task on an RCP casing. First, we provide a wear model for rigid grinding discs and verify its accuracy through finite element simulations and experiments. It can be used to predict the wear conditions of grinding discs during grinding. Then, a series of linear geodesic offset paths with the shortest path length characteristic can be generated and converted to NURBS interpolation paths. The velocity, acceleration, and jerk of the of the NURBS interpolated path generated by the <em>S</em>-shaped acceleration/deceleration (ACC/DEC) feedrate planning method in Cartesian space can be converted into the corresponding angular velocity, acceleration, and jerk of each joint in joint space to ensure that the grinding tasks can be performed under appropriate kinematic constraints; Then, an improved NSGA-II algorithm is proposed and its performance is verified based on benchmark test problem suite in three indicators. The verification results showed that the solution set generated by the proposed algorithm has good distribution uniformity, is closer to the true boundary, and has good convergence compared with other advanced optimization algorithms; Furthermore, by substituting the multi-objective optimization functions and kinematic constraints into the improved NSGA-II algorithm, the compromise minimization problem of grinding time, impact, and disc wear can be solved. The simulation and experimental results demonstrate the superiority and effectiveness of the optimized geodesic grinding paths in terms of grinding precision, accuracy, stability, and efficiency. In contrast, multi-directional paths, e.g., optimized cycloid paths, will produce varying grinding contact forces and varying disc sliding velocities, which will lead to more complex material removal situations, thus affecting the accuracy of the optimization solution.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 810-833"},"PeriodicalIF":12.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571450","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":"Research on digital twin monitoring system during milling of large parts","authors":"Yao Lu ,&nbsp;Caixu Yue ,&nbsp;Xianli Liu ,&nbsp;Lihui Wang ,&nbsp;Steven Y. Liang ,&nbsp;Wei Xia ,&nbsp;Xueping Dou","doi":"10.1016/j.jmsy.2024.10.027","DOIUrl":"10.1016/j.jmsy.2024.10.027","url":null,"abstract":"<div><div>In the milling process of large-scale critical parts of energy equipment, the rigidity of the tool can be lower than that of workpieces, which makes it easy to trigger tool chatter. When the vibration is large, the tool cannot act on the workpiece and cannot effectively remove the material. In severe cases, the tool will be embedded inside the workpiece, resulting in the tool and the workpiece being scrapped at the same time. At the same time, in the event of programming errors, the tool or shank could interfere or collide with workpieces or worktable, which may damage the machine parts and reduce the machining accuracy of machine tool, leading to economic losses and even casualties. In response to the problems of tool chatter and tool collision in the milling process, this paper has done four steps as follows to improve the monitoring, modeling, and control of the machining dynamics integrity. First of all, the study constructs a digital twin monitoring system framework for the milling process of large parts, utilizes Unity 3D to build the digital twin virtual system, designs and develops the relevant functions of the virtual machine tool. Secondly, this study establishes a dynamic cutting thickness model for high-feed milling cutter and a milling dynamics model for rigid parts, and builds the stability lobe diagram (SLD) based on the modal parameters and milling force coefficients. In turn, the study obtains the chatter adaptive threshold of the digital twin monitoring system with the guidance of the stabilizing leaf petal diagram. Thirdly, this study also utilizes OPC UA protocol and LabVIEW to acquire the signals of spindle position, speed, acceleration, etc., and process them. Based on the digital twin front-end technology, it will realize user interaction, machine tool collision prevention, and cutting parameters calculation; then based on the digital twin back-end technology, it will obtain the theoretical guidance for chatter monitoring, suppression, and prediction. Finally, it proposes a driver update database based on the MySQL, and utilizes it to update the back-end model of the digital twin monitoring system. According to the experimental test of the digital twin monitoring system under realistic machining process conditions, the results show that the system has a certain improvement in processing safety and processing quality, which has carries practical value and guiding significance.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 834-847"},"PeriodicalIF":12.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571612","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 framework for anomaly detection in industrial robot system based on multiple physics-informed hybrid convolutional autoencoder","authors":"Shijie Wang ,&nbsp;Jianfeng Tao ,&nbsp;Qincheng Jiang ,&nbsp;Wei Chen ,&nbsp;Chengjin Qin ,&nbsp;Chengliang Liu","doi":"10.1016/j.jmsy.2024.10.016","DOIUrl":"10.1016/j.jmsy.2024.10.016","url":null,"abstract":"<div><div>The robot number in industry is growing up rapidly. Building anomaly detection system for them can improve the security of these expensive devices. The article implements an anomaly detection framework based on digital twin, which are built by a hybrid convolutional autoencoder. The framework shares those neural network weight files as digital assets, users can use them to estimate the possible output from real input. It approximates the dynamic relationship between motion, current, temperature and vibration with hybrid convolution. Considering the limited generalization performance of direct data-driven methods in practical physical systems, this article introduces physical information methods to improve the constraint function of neural network. The influence of multiple physical fields on current is established by a unified neural network. Terminals detect anomaly with KL divergence between really current and estimated current. The article collects operational data from real robots and verifies it, and the experiment shows that the RMSE for current estimation is below 1.5 %, the F1-score in anomaly detection is over 98.23 %, false positive is below 1 %, false negative is below 1.7 %. The relevant technologies are gradually being promoted and applied in enterprises.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 798-809"},"PeriodicalIF":12.2,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554251","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}