Journal of Manufacturing Systems最新文献

{"title":"Enhancing reliability in advanced manufacturing systems: A methodology for the assessment of detection and monitoring techniques","authors":"Monica Katherine Gonzalez ,&nbsp;Mariano Jose Coll-Araoz ,&nbsp;Andreas Archenti","doi":"10.1016/j.jmsy.2025.01.015","DOIUrl":"10.1016/j.jmsy.2025.01.015","url":null,"abstract":"<div><div>Advanced manufacturing systems demand the utilization of technologies, methods and capabilities to improve production efficiency or productivity, while ensuring environmental and societal sustainability. Digitalization emerges as an alternative solution for improving the monitoring capabilities of manufacturing systems and consequently enhance the decision-making process. However, the widespread adoption of digital solutions introduces complexities in measurement reliability, data management, and environmental concerns in terms of e-waste and data storing. Therefore, enhancing monitoring capabilities while minimizing resource consumption is crucial for ensuring system reliability in a sustainable way. This research introduces a methodology for assessing the monitoring condition of manufacturing systems. By integrating functional and dysfunctional analysis, approaches that focus on identifying critical functions and potential failure modes of a system, the proposed methodology provides a comprehensive system perspective and targeted directives for improvement. The effectiveness and versatility of the methodology are demonstrated and discussed through its application to various manufacturing systems at a component, machine, and line level.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 318-333"},"PeriodicalIF":12.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169561","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 deep graph neural network-based link prediction model for proactive anomaly detection in discrete manufacturing workshop","authors":"Shengbo Wang ,&nbsp;Yu Guo ,&nbsp;Shaohua Huang ,&nbsp;Ruixi Lai ,&nbsp;Litong Zhang ,&nbsp;Weiwei Qian","doi":"10.1016/j.jmsy.2025.01.022","DOIUrl":"10.1016/j.jmsy.2025.01.022","url":null,"abstract":"<div><div>Production anomaly has always been one of the main influencing factors that prevent discrete manufacturing workshops from maintaining stability and agility. Proactive anomaly detection can evaluate the production state and serves as a crucial foundation for preventive maintenance decision. Knowledge graph enables the use of multi-source manufacturing data as a data foundation for proactive anomaly detection. Although rich manufacturing data can comprehensively depict complex manufacturing process, constructing an accurate proactive anomaly detection model remains challenging because of insufficient analysis of the local and temporal features of the manufacturing process. This paper presents a link prediction model based on a deep graph neural network to solve the problem. Specifically, the manufacturing knowledge graph is constructed through OPC UA information model, Bert model and OWL semantic mapping model to organize multi-source heterogeneous data. The deep autoencoder model with local graph learning and the Seq2Seq model with attention mechanism are trained to analyze the neighboring relationship and the temporal correlation of the manufacturing elements, respectively. Finally, the link prediction model is designed by integrating both local and temporal features, with a restructured loss function to improve training effectiveness. Experiments suggest that the designed link prediction model has better prediction performance and is at least 25.6 % higher than the baseline models on the mean reciprocal rank.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 301-317"},"PeriodicalIF":12.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169560","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":"‘Genetic exploration’ of metal forming processes through information absent and fragmental data processing","authors":"Heli Liu ,&nbsp;Saksham Dhawan ,&nbsp;Xiao Yang ,&nbsp;Denis J. Politis ,&nbsp;Maxim Weill ,&nbsp;Yang Zheng ,&nbsp;Xiaochuan Liu ,&nbsp;Huifeng Shi ,&nbsp;Lemeng Zhang ,&nbsp;Xiangnan Yu ,&nbsp;Shamsuddeen Muhammad ,&nbsp;Liliang Wang","doi":"10.1016/j.jmsy.2025.01.014","DOIUrl":"10.1016/j.jmsy.2025.01.014","url":null,"abstract":"<div><div>Over 160,000 engineering materials and nearly 90 % (wt%) of products made from metals are manufactured by metal forming processes. Voluminous metal forming data are proliferated daily at an ever-greater scale, and collected from sensing networks and experimentally verified simulations, facilitating the scientific understanding of digital manufacturing. To date, limited research has approached metal forming from the perspective of data, particularly given that most datasets are ‘information absent’ that lack essential information, including data description, quality or condition, or essential features, for a single or several data points, or a specific dataset or database. Furthermore, data collected by sensing networks are most likely to be categorised as ‘fragmental data’, encompassing only a few (e.g., 1–2) essential pieces of information. This phenomenon is mainly due to limitations of data collection capabilities and data privacy, and hinders the extraction of insightful information. Tackling these long-standing challenges requires an emerging scientific approach combining manufacturing and data science knowledge. Here, following thermo-mechanical principles, an Evolutionary Binary (EB) algorithm was developed to process information absent (meta)data, yielding a highly efficient recognition of missing geometric features for metal formed products with nearly 95 % accuracy using sparsely labelled data points (≤1 %). By leveraging this technology, unique digital characteristics (DC) were identified for over 140 manufacturing processes. The DC are defined as the visualisation of manufacturing (meta)data incorporating essential information spanning design, manufacturing and application stages of manufactured products. This leads to the establishment of digital characteristics space (DCS) that provides access to the up-to-date and information-rich manufacturing DC. Using EB algorithm and taking DCS as an alignment reference, the origins of naturally unattributed fragmental data (minimum length of 25 data points) were successfully identified with overall over 80 % accuracy, and reached approximately 93 % with length of 50 data points.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 286-300"},"PeriodicalIF":12.2,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169559","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":"ProjecTwin: A digital twin-based projection framework for flexible spatial augmented reality in adaptive assistance","authors":"Jiazhen Pang ,&nbsp;Pai Zheng","doi":"10.1016/j.jmsy.2024.11.018","DOIUrl":"10.1016/j.jmsy.2024.11.018","url":null,"abstract":"<div><div>Establishing an efficient communication channel between the digital manufacturing system and assembly workers is a key research area in smart assembly. Spatial augmented reality (SAR) technology offers a naked-eye display mode that seamlessly integrates virtual information into real industrial scenes, providing an immersive experience for multiple viewers. However, the challenge arises when facing frequent workstation reconfiguration in customized product assembly tasks, requiring a flexible spatial augmented reality (FSAR) mode. To address the issues of uncertainty in projection layout, distortion in projected display, and lack of mobility in the projector of FSAR, a DT (digital twin)-based projection framework called ProjecTwin is proposed. The ProjecTwin framework can simulate real-time projection scenarios and enables the reconfiguration of projection layouts. Based on ProjecTwin, an FSAR assistance method is proposed. An optimization model is employed to solve the DT projection layout issue by considering human-robot collaboration scenarios as constraints. Additionally, a method for reverse generation of DT images is proposed to address the image distortion problem. Furthermore, a DT entity control method based on mobile robots is introduced to tackle the inflexibility of the projector. Three cases are conducted to illustrate how the proposed method supports optimized, adaptive, and human-centric FSAR assistance.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 213-225"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176132","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 tool wear monitoring: Architecture with large-scale CNN and adaptive EMD","authors":"Yi Sun,&nbsp;Hongliang Song,&nbsp;Hongli Gao,&nbsp;Jie Li,&nbsp;Shuang Yin","doi":"10.1016/j.jmsy.2024.12.001","DOIUrl":"10.1016/j.jmsy.2024.12.001","url":null,"abstract":"<div><div>In manufacturing, tool wear monitoring (TWM) is crucial for ensuring product quality and processing efficiency. Numerous data-driven models based on deep learning have been developed to enhance the accuracy of TWM. However, most models necessitate traditional signal preprocessing and heavily depend on expert knowledge for parameter settings. To address these issues, this study proposes a novel TWM architecture, LCNN-EMD, which combines large-scale convolutional neural networks (LCNN) with adaptive empirical mode decomposition (EMD). By analyzing cutting process mechanisms, it is found that sensor signals can be decoupled into low-frequency noise from the machine's inherent frequencies, mid-frequency features from the tool's chatter, and high-frequency noise from the sensor's quantization. The interpretability of the LCNN-EMD architecture is rooted in its sophisticated capability to analyze and suppress specific frequency features from the input signals. The LCNN adeptly captures low- and mid-frequency features while effectively suppressing high-frequency noise. Concurrently, adaptive EMD dynamically mitigates low-frequency noise, ensuring the preservation of critical mid-frequency features. This dual mechanism not only enhances the accuracy and robustness of LCNN-EMD but also provides it with high interpretability, addressing the limitations of traditional models that depend on extensive expert knowledge and static signal preprocessing. Finally, we conduct tool life experiments and compare the LCNN-EMD with mainstream models for a comprehensive evaluation. Experimental results indicate that LCNN-EMD consistently outperforms the comparative models in terms of accuracy and stability.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 294-307"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176130","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":"Trustworthy AI for human-centric smart manufacturing: A survey","authors":"Dongpeng Li ,&nbsp;Shimin Liu ,&nbsp;Baicun Wang ,&nbsp;Chunyang Yu ,&nbsp;Pai Zheng ,&nbsp;Weihua Li","doi":"10.1016/j.jmsy.2024.11.020","DOIUrl":"10.1016/j.jmsy.2024.11.020","url":null,"abstract":"<div><div>Human-centric smart manufacturing (HCSM) envisions a symbiotic relationship between humans and machines, leveraging human capability and Artificial Intelligence (AI)’s precision and computational power to achieve mutual enhancement. Trustworthy AI (TAI) is a promising enabler in this transition, ensuring that the integration of AI technologies within manufacturing scenarios is safe, transparent, and participatory. This paper systematically reviews TAI within the context of HCSM by adopting a progressive 3-layer framework. This framework aligns with the developmental stages of HCSM and includes basic safety (protection), advancing to explainability, accountability, and uncertainty awareness (perception), and culminating in continuous updating with human involvement (participation). The review explores the role of TAI across key stages of the product lifecycle, demonstrating how TAI can empower humans and highlighting current advancements while identifying ongoing challenges. The paper concludes by discussing future directions and offering insights for developing TAI-integrated HCSM.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 308-327"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176582","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":"Optimizing burn-in and predictive maintenance for enhanced reliability in manufacturing systems: A two-unit series system approach","authors":"Faizanbasha A. ,&nbsp;U. Rizwan","doi":"10.1016/j.jmsy.2024.12.002","DOIUrl":"10.1016/j.jmsy.2024.12.002","url":null,"abstract":"<div><div>In daily life, the reliability of manufacturing systems is critical, influencing everything from consumer goods availability to global supply chain stability. As manufacturing reliability increasingly dictates market leadership, ensuring system dependability and efficiency has become crucial. Despite extensive research, the integration of burn-in processes and Predictive Maintenance (PdM) within operational frameworks remains inadequately explored, especially in the dynamics of a Two-Unit Series Manufacturing System (TUMS). This research addresses this gap by developing an advanced Semi-Markov Decision Process (SMDP) model that synergistically optimizes burn-in and PdM strategies. This model minimizes downtime and operational costs while maximizing system reliability. Employing a combination of theoretical modeling and empirical validation, the study introduces novel algorithms that optimize maintenance schedules and predict system degradation effectively. The robustness of our approach is validated through comprehensive comparison analysis, which highlights the superior performance of our predictive maintenance model over traditional methods. A practical case study involving an EV battery system demonstrates the real-world applicability and significant improvements in battery reliability and operational lifespan. Sensitivity analysis and Monte Carlo simulations further substantiate the model’s effectiveness, showing resilience to parameter variations and consistent performance benefits under varied scenarios. In the specific context of our EV battery case study, implementing the proposed strategies initially resulted in a notable increase in EV battery lifespan and a significant reduction in maintenance costs. Ultimately, this study not only advances the theoretical framework of maintenance optimization but also equips industrial applications with a robust, scalable model, marking a significant step forward in the PdM of complex manufacturing systems.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 244-270"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176579","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 phased robotic assembly policy based on a PL-LSTM-SAC algorithm","authors":"Qianji Wang ,&nbsp;Yongkui Liu ,&nbsp;Zilu Zhu ,&nbsp;Lin Zhang ,&nbsp;Lihui Wang","doi":"10.1016/j.jmsy.2024.12.008","DOIUrl":"10.1016/j.jmsy.2024.12.008","url":null,"abstract":"<div><div>In order to address the problems with current robotic automated assembly such as limitations of model-based methods in unstructured assembly scenarios, low training efficiency of learning-based methods, and limited performance of policy generalization, this paper proposes two modeling methodologies based on deep reinforcement learning under the overall framework of phased assembly for complex robotic assembly tasks, i.e., separated-phased policy modeling (SPM) and integrated policy modeling (IPM). Regarding policy learning with deep reinforcement learning, we present a refined SAC algorithm that merges a policy-lead mechanism and an LSTM network (i.e., PL-LSTM-SAC). A comprehensive testbed based on the assembly of a triple-task planetary gear train is designed to validate the framework and the proposed approach. Experimental results indicate that the trained assembly policies for each task are effective under both policy modeling methodologies, but SPM has higher stability and policy convergence efficiency than IPM. Physical tests indicate the sim-to-real transferability of the trained policies with both SPM and IPM and an average success rate of 92.0 % is achieved. The PL-LSTM-SAC algorithm proposed can significantly accelerate training speed and enhance compliance and overall performance of assembly actions by a 13.9 % reduction in the average contact force during assembly processes.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 351-369"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176129","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-driven industrial context-aware system: A case study of overhead crane operation","authors":"Chao Yang ,&nbsp;Hao Yu ,&nbsp;Yuan Zheng ,&nbsp;Lei Feng ,&nbsp;Riku Ala-Laurinaho ,&nbsp;Kari Tammi","doi":"10.1016/j.jmsy.2024.12.006","DOIUrl":"10.1016/j.jmsy.2024.12.006","url":null,"abstract":"<div><div>With advancements in Information and Communication Technologies (ICT), traditional manufacturing industries are engaged in a digital transformation. This transformation enables the acquisition of vast amounts of data and information, enhancing decision-making capabilities. This, in turn, has raised the expectations of field operators who seek data and information management tailored to the dynamic working environment, thereby improving efficiency in their daily operations. However, there is a lack of a holistic approach to integrating diverse data sources, extracting valuable contextual information, and delivering real-time information to field operators. This paper addresses this gap by proposing an adaptive, interoperable, and user-centered Context-Aware System (CAS). Initially, the paper explores the challenges and requirements associated with CAS’s current practices while proposing potential solutions. Furthermore, it introduces a system framework of CAS that integrates Digital Twin (DT) and semantic technologies. This framework includes three primary technical solutions: (1) Integrating DT to create a comprehensive digital representation of physical entities, enabling real-time data integration and synchronization; (2) Providing an ontology-based approach to model manufacturing context, facilitating knowledge representation and reasoning; (3) Developing a user-centered information delivery system leveraging Augmented Reality (AR) for context-aware visualization. The system architecture has been implemented and tested in a laboratory-scale industrial environment, focusing on crane operations within logistics scenarios. Lastly, three use cases are presented to demonstrate the system’s practical applicability, showcasing its feasibility in furnishing informed contextual information to end-users within the dynamic manufacturing environment.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 394-409"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176134","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":"Unsupervised multimodal fusion of in-process sensor data for advanced manufacturing process monitoring","authors":"Matthew McKinney ,&nbsp;Anthony Garland ,&nbsp;Dale Cillessen ,&nbsp;Jesse Adamczyk ,&nbsp;Dan Bolintineanu ,&nbsp;Michael Heiden ,&nbsp;Elliott Fowler ,&nbsp;Brad L. Boyce","doi":"10.1016/j.jmsy.2024.12.003","DOIUrl":"10.1016/j.jmsy.2024.12.003","url":null,"abstract":"<div><div>Effective monitoring of manufacturing processes is crucial for maintaining product quality and operational efficiency. Modern manufacturing environments often generate vast amounts of complementary multimodal data, including visual imagery from various perspectives and resolutions, hyperspectral data, and machine health monitoring information such as actuator positions, accelerometer readings, and temperature measurements. However, fusing and interpreting this complex, high-dimensional data presents significant challenges, particularly when labeled datasets are unavailable or impractical to obtain. This paper presents a novel approach to multimodal sensor data fusion in manufacturing processes, inspired by the Contrastive Language-Image Pre-training (CLIP) model. We leverage contrastive learning techniques to correlate different data modalities without the need for labeled data, overcoming limitations of traditional supervised machine learning methods in manufacturing contexts. Our proposed method demonstrates the ability to handle and learn encoders for five distinct modalities: visual imagery, audio signals, laser position (x and y coordinates), and laser power measurements. By compressing these high-dimensional datasets into low-dimensional representational spaces, our approach facilitates downstream tasks such as process control, anomaly detection, and quality assurance. The unsupervised nature of our method makes it broadly applicable across various manufacturing domains, where large volumes of unlabeled sensor data are common. We evaluate the effectiveness of our approach through a series of experiments, demonstrating its potential to enhance process monitoring capabilities in advanced manufacturing systems. This research contributes to the field of smart manufacturing by providing a flexible, scalable framework for multimodal data fusion that can adapt to diverse manufacturing environments and sensor configurations. The proposed method paves the way for more robust, data-driven decision-making in complex manufacturing processes.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 271-282"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176578","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}