Journal of Manufacturing Systems最新文献

{"title":"Leveraging the usage of blockchain toward trust-dominated manufacturing systems","authors":"Philip Samaha ,&nbsp;Fadi El Kalach ,&nbsp;Ramy Harik","doi":"10.1016/j.jmsy.2024.10.010","DOIUrl":"10.1016/j.jmsy.2024.10.010","url":null,"abstract":"<div><div>Smart manufacturing has transformed the role of data in manufacturing, with a significant focus on secure data infrastructure. As factories engage with external data sources, cybersecurity becomes crucial. Blockchain technology is introduced to safeguard this infrastructure, ensuring secure and transparent data flow, which is vital for industries like pharmaceutical, aerospace, automotive, and electronics manufacturing. This review provides a comprehensive taxonomy of blockchain architectures, analyzing their working modes, strengths, and weaknesses while identifying appropriate use cases. It also examines consensus algorithms, categorizing them as either crash fault tolerant (CFT) or Byzantine fault tolerant (BFT) and further classifies them based on whether they are proof-based or voting-based. The review explores the intrinsic limitations of blockchain systems and highlights specific manufacturing challenges where blockchain can be instrumental. It also discusses the synergy between blockchain and cybersecurity, emphasizing how they work together to enhance security and accountability. The paper concludes by identifying private blockchain as the most suitable architecture for certain manufacturing applications, particularly in supply chain management and machinery control. A SWOT analysis is conducted on this architecture to provide a detailed understanding of its potential and challenges. The review suggests that while no single consensus algorithm is best universally, each has its own merits depending on the application. Lastly, the SWOT analysis serves as a catalyst for future research, guiding efforts to maximize blockchain’s strengths and mitigate its weaknesses in industrial contexts.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 612-638"},"PeriodicalIF":12.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535596","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":"Anomaly detection in smart manufacturing: An Adaptive Adversarial Transformer-based model","authors":"Moussab Orabi ,&nbsp;Kim Phuc Tran ,&nbsp;Philipp Egger ,&nbsp;Sébastien Thomassey","doi":"10.1016/j.jmsy.2024.09.021","DOIUrl":"10.1016/j.jmsy.2024.09.021","url":null,"abstract":"<div><div>In Industry 5.0, smart manufacturing brings additional intricacies and novel data processing challenges. Given the evolving nature of manufacturing processes and the inherent complexity of data, including noise and missing entries, achieving accurate anomaly detection becomes even more intricate. Conventional methods often miss nuanced anomalies, especially when dealing with high-dimensional, multivariate, non-stationary data. These data types are typical of smart manufacturing environments. Hence, many recent approaches have embraced deep learning to confront these challenges, making use of diverse attention mechanisms to acquire data representations. However, in manufacturing, where the dynamics of time series data change over time, methods relying solely on pointwise or pairwise representations often fall short. Thus, ensuring product quality and operational integrity calls for even more advanced methodologies. The deficiency lies in the capability of state-of-the-art models to effectively capture abnormal patterns while considering both local and global contextual information. This challenge is compounded by the rarity of anomalies, making it exceedingly challenging to establish substantial associations between individual abnormal points and the entire time series. To tackle these challenges, we introduce the “<strong>A</strong>daptive <strong>A</strong>dversarial <strong>T</strong>ransformer” as a novel deep learning technique that combines Transformer architecture with an anomaly attention mechanism and Adversarial Learning. Our Model effectively captures intricate temporal patterns, distinguishes normal and anomalous behaviors, and dynamically adjusts thresholds to align with the evolving dynamics of time-series data. Empirical validation on four benchmark datasets and three real-world manufacturing datasets demonstrates our model’s effectiveness compared to the state-of-the-art, as evidenced by the F1-Score.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 591-611"},"PeriodicalIF":12.2,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535593","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":"BDTM-Net: A tool wear monitoring framework based on semantic segmentation module","authors":"Jiaqi Zhou ,&nbsp;Caixu Yue ,&nbsp;Jiaxu Qu ,&nbsp;Wei Xia ,&nbsp;Xianli Liu ,&nbsp;Steven Y. Liang ,&nbsp;Lihui Wang","doi":"10.1016/j.jmsy.2024.10.012","DOIUrl":"10.1016/j.jmsy.2024.10.012","url":null,"abstract":"<div><div>The integration of advanced manufacturing and the new generation of information technology promotes the development of intelligent manufacturing. In the cutting process, the condition of cutting tools is a critical factor that profoundly affects product surface quality and machining efficiency. Tool Condition Monitoring (TCM) can reduce the cost of processing and improve the quality of processing. It is one of the important technologies to realize intelligent manufacturing. To better identify the amount of tool wear in the cutting process, this research constructs a tool wear detection framework based on a semantic segmentation module. The semantic segmentation task of tool surface wear image collected in a complex environment is carried out by using image pixel information for tool wear monitoring. Because of the uneven illumination of the edge of the wear area and the unclear edge boundary, the self-learning parameters are used to separate the foreground and background of the image and amplify the subtle difference information. While enhancing the feature information of the tool wear image, the detection efficiency is improved. At the same time, to meet the needs of detail segmentation, a dual attention module is introduced to improve the performance of the model. The accuracy of the model is verified by orthogonal experiments and the model is comprehensively compared based on common evaluation indicators. The accuracy rate of 95.34 % in segmenting the tool wear images, demonstrating that the developed detection framework is suitable for accurate and efficient tool wear condition monitoring. This research not only proposes a new semantic segmentation model but also provides valuable insights into key information during the cutting process, validates the patterns of tool wear, and reasonably promotes the development of Tool Condition Monitoring and Remaining Useful Life.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 576-590"},"PeriodicalIF":12.2,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142536177","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 disassembly for end-of-life products focusing on task and motion planning: A comprehensive survey","authors":"Mohammed Eesa Asif ,&nbsp;Alireza Rastegarpanah ,&nbsp;Rustam Stolkin","doi":"10.1016/j.jmsy.2024.09.010","DOIUrl":"10.1016/j.jmsy.2024.09.010","url":null,"abstract":"<div><div>The rise of mass production and the resulting accumulation of end-of-life (EoL) products present a growing challenge in waste management and highlight the need for efficient resource recovery. In response to this challenge, robotic disassembly has emerged as a vital tool for the circular economy. Combining accuracy, adaptability, and the potential for handling hazardous materials offers a sustainable solution for dismantling complex EoL objects. This comprehensive survey delves into the motivations for robotic disassembly and the pivotal role of task and motion planning (TAMP) in optimising disassembly processes. It analyses the evolution of disassembly strategies, from conventional methods to those driven by cutting-edge artificial intelligence (AI) techniques, for the future of waste management. Additionally, the survey explores several case study applications, focusing on the disassembly of EV lithium-ion batteries. It highlights how TAMP and AI integration can bolster adaptability, safety, and informed decision-making within real-world disassembly challenges. Finally, the review examines promising future research directions in robotics that hold the potential to advance further improvement in robotic disassembly to increase sustainability and the responsible management of EoL products.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 483-524"},"PeriodicalIF":12.2,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535591","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":"Data-driven inpainting for full-part temperature monitoring in additive manufacturing","authors":"Jiangce Chen ,&nbsp;Mikhail Khrenov ,&nbsp;Jiayi Jin ,&nbsp;Sneha Prabha Narra ,&nbsp;Christopher McComb","doi":"10.1016/j.jmsy.2024.09.022","DOIUrl":"10.1016/j.jmsy.2024.09.022","url":null,"abstract":"<div><div>Understanding the temperature history over a part during additive manufacturing (AM) is important for optimizing the process and ensuring product quality, as temperature impacts melt pool geometry, defect formation, and microstructure evolution. While in-process temperature monitoring holds promise for evaluating the part quality, existing thermal sensors used in AM provide only partial measurements of the temperature distribution over the part. In this work, we introduce an innovative approach for reconstructing the complete temperature profile using partial data. We formulate this challenge as an inpainting problem, a canonical task in machine learning which entails recovering missing information across a spatial domain. We present a data-driven model based on graph convolutional neural networks. To train the inpainting model, we employ a finite element simulation to generate a diverse dataset of temperature histories for various part geometries. Cross-validation indicates that the inpainting model accurately reconstructs the spatial distribution of part temperature with strong generalizability across various geometries. Further application to experimental data using infrared camera measurements shows that the model accuracy could be improved by augmenting the training data with simulation data that shares process parameters and geometry with the experimental part. By presenting a solution to the temperature inpainting problem, our approach not only improves the assessment of part quality using partial measurements but also paves the way for the creation of a temperature digital twin of the part using thermal sensors.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 558-575"},"PeriodicalIF":12.2,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535597","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":"Study on the application of single-agent and multi-agent reinforcement learning to dynamic scheduling in manufacturing environments with growing complexity: Case study on the synthesis of an industrial IoT Test Bed","authors":"David Heik,&nbsp;Fouad Bahrpeyma,&nbsp;Dirk Reichelt","doi":"10.1016/j.jmsy.2024.09.019","DOIUrl":"10.1016/j.jmsy.2024.09.019","url":null,"abstract":"<div><div>Industry 4.0, smart manufacturing and smart products have recently attracted substantial attention and are becoming increasingly prevalent in manufacturing systems. As a result of the successful implementation of these technologies, highly customized products can be manufactured using responsive, autonomous manufacturing processes at a competitive cost. This study was conducted at HTW Dresden’s Industrial Internet of Things Test Bed, which simulates state-of-the-art manufacturing scenarios for educational and research purposes. Apart from the physical production facility itself, the associated operational information systems have been fully interconnected in order to allow fast and efficient information exchange between the various manufacturing stages and systems. The presence of this characteristic provides a strong foundation for dealing appropriately with unexpected or planned environmental changes, as well as prevailing uncertainty, which greatly increases the overall system’s resilience. The main objective of this study is to increase the efficiency of the manufacturing system in order to optimize resource consumption and minimize the overall completion time (makespan). This manuscript discusses our experiments in the area of flexible job-shop scheduling problems (FJSP). As part of our research, different methods of representing the state space were explored, heuristic, meta-heuristic, reinforcement learning (RL), and multi-agent reinforcement learning (MARL) methods were evaluated, and various methods of interaction with the system (designing the action space and filtering in certain situations) were examined. Furthermore, the design of the reward function, which plays an important role in the formulation of the dynamic scheduling problem into an RL problem, has been discussed in depth. Finally, this paper studies the effectiveness of single-agent and multi-agent RL approaches, with a special focus on the Proximal Policy Optimization (PPO) method, on the fully-fledged digital twin of an industrial IoT system at HTW Dresden. As a result of our experiments, in a multi-agent setting involving individual agents for each manufacturing operation, PPO was able to manage the resources in such a way as to improve the manufacturing system’s performance significantly.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 525-557"},"PeriodicalIF":12.2,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535592","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":"Industrial data space application framework for semiconductor wafer manufacturing system scheduling","authors":"Da Chen ,&nbsp;Jie Zhang ,&nbsp;Lihui Wu ,&nbsp;Peng Zhang ,&nbsp;Ming Wang","doi":"10.1016/j.jmsy.2024.09.013","DOIUrl":"10.1016/j.jmsy.2024.09.013","url":null,"abstract":"<div><div>The complex, large-scale semiconductor wafer manufacturing generates substantial diverse data, creating management hurdles and making efficient use of historical scheduling data difficult. To address these challenges, we propose a four-layer application framework for industrial data space for wafer manufacturing system (IDWFS). Firstly, a multi-level model ontology centred on scheduling tasks is constructed to effectively map the evolution of elemental relationships during wafer processing and adaptively change the data organisation. Then, a system architecture for mining the correlation between dynamic and static element data is proposed to fully explore the spatiotemporal correlation relationship of data elements in the processing process. Finally, a scheduling system architecture of “learning + prediction + scheduling” is proposed to fully utilise the scheduling historical domain knowledge and data correlation relationship in semiconductor wafer manufacturing system during the scheduling process. In addition, through three case studies related to the scheduling of semiconductor wafer manufacturing system, IDWFS is effective in heterogeneous data management, coupling relationship mining of element data, logistics scheduling processing, etc., thereby achieving logistics scheduling control of wafer manufacturing system.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 464-482"},"PeriodicalIF":12.2,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535590","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":"Federated domain generalization for condition monitoring in ultrasonic metal welding","authors":"Ahmadreza Eslaminia ,&nbsp;Yuquan Meng ,&nbsp;Klara Nahrstedt ,&nbsp;Chenhui Shao","doi":"10.1016/j.jmsy.2024.09.023","DOIUrl":"10.1016/j.jmsy.2024.09.023","url":null,"abstract":"<div><div>Ultrasonic metal welding (UMW) is a key joining technology with widespread industrial applications. Condition monitoring (CM) capabilities are critically needed in UMW applications because process anomalies, such as tool degradation and workpiece surface contamination, significantly deteriorate the joining quality. Recently, machine learning models emerged as a promising tool for CM in many manufacturing applications. Yet, many existing models lack the generalizability or adaptability and cannot be directly applied to new manufacturing process configurations (i.e., domains). Although several domain generalization techniques have been proposed, their successful deployment often requires substantial training data, which can be expensive and time-consuming to collect in a single factory. Such issues may be potentially alleviated by pooling data across factories, but data sharing raises critical data privacy concerns that have prohibited data sharing for collaborative model training in the industry. To address these challenges, this paper presents a Federated Domain Generalization for Condition Monitoring (FDG-CM) framework that provides domain generalization capabilities in distributed learning while ensuring data privacy. By effectively learning a unified representation from the feature space, FDG-CM can adapt CM models for new clients (factories) with different process configurations. To demonstrate the effectiveness of FDG-CM, we investigate two distinct UMW CM tasks, including tool condition monitoring and workpiece surface condition classification. Compared with state-of-the-art federated learning algorithms, FDG-CM achieves a 5.35%–8.08% improvement in CM accuracy. FDG-CM is also shown to achieve excellent performance in challenging scenarios involving unbalanced data distributions and limited participating clients. Furthermore, by implementing the FDG-CM method on an edge–cloud architecture, we show that this method is both viable and efficient in practice. The FDG-CM framework is readily extensible to other manufacturing applications.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 1-12"},"PeriodicalIF":12.2,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142444772","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 vision-enabled fatigue-sensitive human digital twin towards human-centric human-robot collaboration","authors":"Saahil Chand,&nbsp;Hao Zheng,&nbsp;Yuqian Lu","doi":"10.1016/j.jmsy.2024.10.002","DOIUrl":"10.1016/j.jmsy.2024.10.002","url":null,"abstract":"<div><div>Within a Human-centric Human-Robot Collaboration (HHRC) system, monitoring, assessing, and optimizing for an operator’s well-being is essential to creating an efficient and comfortable working environment. Currently, monitoring systems are used for independent assessment of human factors. However, the rise of the Human Digital Twin (HDT) has provided the framework for synchronizing multiple operator well-being assessments to create a comprehensive understanding of the operator’s performance and health. Within manufacturing, an operator’s dynamic well-being can be attributed to their physical and cognitive fatigue across the assembly process. As such, we apply non-invasive video understanding techniques to extract relevant assembly process information for automatic physical fatigue assessment. Our novelty involves a video-based fatigue estimation method, in which the boundary-aware dual-stream MS-TCN combined with an LSTM is proposed to detect the operation type, operation repetitions, and the target arm performing each task in an assembly process video. The detected results are then input into our physical fatigue profile to automatically assess the operator’s localized physical fatigue impact. The assembly process of a real-world bookshelf is recorded and tested against, with our algorithm results showing superiority in operation segmentation and target arm detection as opposed to other recent action segmentation models. In addition, we integrate a cognitive fatigue assessment tool that captures operator physiological signals in real-time for body response detection caused by stress. This provides a more robust HDT of the operator for an HHRC system.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 432-445"},"PeriodicalIF":12.2,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440958","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":"A prediction method of tool wear distribution for ball-end milling under various postures based on WVEM-T","authors":"Xudong Wei ,&nbsp;Xianli Liu ,&nbsp;Changxia Liu ,&nbsp;Anshan Zhang ,&nbsp;Zhongran Zhang ,&nbsp;Zhitao Chen ,&nbsp;Zhiming Gou","doi":"10.1016/j.jmsy.2024.09.017","DOIUrl":"10.1016/j.jmsy.2024.09.017","url":null,"abstract":"<div><div>The contact positions corresponding to various tool location point during ball-end milling are complex, and the actual cutting area of flank face presents uneven wear form, which is closely related to its effective cutting distance, linear velocity of edge line microelement, and instantaneous undeformed chip thickness, etc. It is difficult to accurately predict the actual tool wear distribution by theoretical modeling. Therefore, it is necessary to put forward a prediction method of tool wear distribution to ensure the quality of workpiece and the stable state of tool during machining. In this paper, the effective cutting length of tool edge line microelement is calculated, and the instantaneous undeformed chip thickness under various postures considering edge wear is determined. A weighted voting ensemble multi-Transformer transfer learning (WVEM-T) model is established, motion parameters and the actual wear widths <em>VB</em> per edge line are used as training data. The selective freezing strategy is adopted to update the training parameters of the network, so that the trained multi-layer network can accurately predict the wear distribution of flank face in ball-end milling tool under various machining inclination angles. Finally, the accuracy and effectiveness of the prediction method in this paper are verified by the whole life cycle experiment of milling Ti6Al4V alloy.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 446-463"},"PeriodicalIF":12.2,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142441581","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}