Journal of Manufacturing Systems最新文献

{"title":"A fidelity evaluation method for digital twin model of aero-engine assembly characteristics","authors":"Yingzhi Zhang,&nbsp;Huibin Sun,&nbsp;Xiaoxia Zhang,&nbsp;Wanxuan Liu","doi":"10.1016/j.jmsy.2024.12.012","DOIUrl":"10.1016/j.jmsy.2024.12.012","url":null,"abstract":"<div><div>Assembly Characteristics Digital Twin Model (ACDTM) enables real-time updates of assembly characteristics in the virtual space, which is crucial for the real-time control of these characteristics. However, the selection of an appropriate model remains a challenge due to the lack of a clear criterion. To address this issue, a fidelity evaluation method is proposed to evaluate accuracy and consistency of ACDTM. This study first analyzes the three dimensions evaluating fidelity and the transmission evolution properties brought by digital twins. Based on this analysis, the fidelity transmission and evolution model are constructed. By combining fidelity network construction methods, Prediction Model (PM) evaluation methods, and input data evaluation methods, a two-level loop evaluation process is proposed. The feasibility of this method is applied in the concentricity of casing assembly. By implementing quantitative fidelity evaluation of ACDTM, this work provides a scientific basis for selecting and optimizing digital twin models in aero-engine assembly.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 444-456"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176528","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":"Platform-based task assignment for social manufacturing (PBTA4SM): State-of-the-art review and future directions","authors":"Yuguang Bao ,&nbsp;Xinguo Ming ,&nbsp;Xianyu Zhang ,&nbsp;Fei Tao ,&nbsp;Jiewu Leng ,&nbsp;Yang Liu","doi":"10.1016/j.jmsy.2024.12.007","DOIUrl":"10.1016/j.jmsy.2024.12.007","url":null,"abstract":"<div><div>Mass individualization is calling for a more sustainable manufacturing paradigm which can address the paradoxes of diversity, complexity, and affordability. Social Manufacturing (SM) represents a democratized servitization trend trying to reshape the traditional production relationship between consumers and manufacturers. To achieve the SM visions, new operational mechanisms for SM should be constructed to overcome the challenges of information sharing, accuracy, efficiency, security, sovereignty, etc. The survey found that task assignment (TA) is one of the foundational mechanisms for the implementation of regular autonomous manufacturing systems, as well as the role of TA is further amplified for distributed collaborative environments. Therefore, inspired by the relevant research of management science, Platform-based Task Assignment (PBTA) is proposed to distinguish and conceptualize this different research topic. In SM platforms, the diverse capacities and resources can be shared, so that knowing \"who can do” and “select whom to do\" is more important than knowing \"how to do\". Furthermore, the studies on TA for SM present a difference from the previous studies on TA in manufacturing. From a perspective of supply-demand mapping, PBTA illustrates the foundational operational mechanism for SM attracting many researchers’ attention from different fields. Meanwhile, research on PBTA is also required for the platform practices in the era of digital, shared, and platform economy. Given the academic importance and practical value, this survey carefully selects 250 valuable research articles relevant to PBTA for SM. A novel workflow model and knowledge framework, namely PBTA4SM, is proposed to identify and organize the critical issues and challenges. This study shows the state-of-the-art research advancement of PBTA including task design considerations, modelling methods, typical engineering problems, algorithms, decision patterns, key activities, and governance mechanisms. Finally, we complete this holistic survey by highlighting eight potential directions for future research in the Generative Artificial Intelligence (GAI) era.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 328-350"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176527","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":"An intelligent monitoring system for robotic milling process based on transfer learning and digital twin","authors":"Zhaoju Zhu,&nbsp;Wenrong Zhu,&nbsp;Jianwei Huang,&nbsp;Bingwei He","doi":"10.1016/j.jmsy.2024.12.009","DOIUrl":"10.1016/j.jmsy.2024.12.009","url":null,"abstract":"<div><div>Robotic milling is becoming widely used in aerospace and auto manufacturing due to its high flexibility and strong adaptability. However, the practical challenges including complex and time-consuming robot trajectory planning, insufficient monitoring, and lacking three-dimensional visualization limits its further application. To address these challenges, an intelligent monitoring system for robotic milling process based on transfer learning and digital twin was proposed and developed in this paper. Firstly, the fundamental framework of this system was conducted based on a five-dimensional digital twin model for motion simulation, visualization, and tool wear prediction during the robotic milling process. Secondly, the parsing algorithm converting NC code to robot’s machining trajectory and material removal algorithm based on bounding box and mesh deformation were proposed for robotic dynamic milling simulation. Thirdly, a novel transfer learning algorithm named CNN-LSTM-TrAdaBoost.R2 was developed by integrating CNN-LSTM with TrAdaBoost.R2 for automated feature extraction and real-time prediction of tool wear. Finally, the effective and accuracy of tool wear prediction algorithm is verified by ablation experiment and the robotic milling simulation is validated by real milling experiment, as well. The results indicate that the proposed monitoring system for robotic milling process demonstrates great virtual-real mapping. It can offer new insights and technical support for constructing sophisticated digital twin frameworks and enhancing operational monitoring in manufacturing systems.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 433-443"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176529","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":"Ten industrial software towards smart manufacturing","authors":"Tianyi Gao ,&nbsp;Lei Wang ,&nbsp;Wenyan Song ,&nbsp;Ying Cheng ,&nbsp;Ying Zuo ,&nbsp;Feng Xiang ,&nbsp;Haijun Zhang ,&nbsp;Fei Tao","doi":"10.1016/j.jmsy.2025.01.012","DOIUrl":"10.1016/j.jmsy.2025.01.012","url":null,"abstract":"<div><div>Smart manufacturing has received increased attention from academia and industry in recent years, as it provides a competitive advantage for manufacturing companies making the industry more efficient and intelligent. As one of the most important roles for smart manufacturing, industrial software has been widely applied on enterprises and their factories to effectively improve design, management, manufacturing, and service level. This article focuses on a comprehensive review of the industrial software systems towards smart manufacturing. First, the close relationship between industrial software and smart manufacturing is analyzed. Second, we investigate views from national governments and well-known companies on the classification and role of industrial software, and put forward ten classifications of software most closely related to smart manufacturing. Then, the development history, function, academic research status and business application status are summarized. Finally, current challenges and future research directions are presented. It can help industry practitioners and researchers to know each other’s fields, while promoting scientific results to be applied in commerce, and application difficulties to be focused in the scientific research.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 255-285"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169035","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":"Employing deep reinforcement learning for machining process planning: An improved framework","authors":"Hang Zhang ,&nbsp;Wenhu Wang ,&nbsp;Yue Wang ,&nbsp;Yajun Zhang ,&nbsp;Jingtao Zhou ,&nbsp;Bo Huang ,&nbsp;Shusheng Zhang","doi":"10.1016/j.jmsy.2024.12.010","DOIUrl":"10.1016/j.jmsy.2024.12.010","url":null,"abstract":"<div><div>Utilizing Deep Reinforcement Learning (DRL) in machining process planning presents a promising avenue to enhance automation, efficiency, and adaptability to diverse scenarios. The definition of the environment plays a crucial role in ensuring the effective application of DRL algorithms, serving as the conduit for formalizing real-world problems into reinforcement learning frameworks. Within the realm of machining process planning, the definition of the environment typically revolves around harnessing components such as processing status, machining operations, and machining resources to reasonably specify the states, actions, reward mechanisms, and other pertinent elements essential for the operation of the DRL algorithm. However, existing DRL-based methods are hampered by various limitations in the definition of the environment. These limitations result in reduced exploration and learning efficiency of the agent, consequently yielding suboptimal machining process planning results. To address these challenges, this paper presents an improved DRL-based framework for machining process planning, specifically targeting aluminum aircraft structural parts. In this context, the framework improves the definition of the state, action, and reward mechanism within the environment, as well as the policy network within the agent. These improvements effectively confine the agent's exploration within a solution space consisting of feasible machining processes for features, thereby mitigating a multitude of invalid explorations and significantly enhancing exploration and learning efficiency. Moreover, these improvements bolster the practical utility of the methodology. In addition, to conduct a more comprehensive exploration for further pursuing optimal solutions, we investigate the incorporation of the Monte Carlo Tree Search algorithm into the proposed framework during the machining process planning phase. Experimental validation conducted on aircraft structural parts demonstrates the efficacy of the proposed method for machining process planning in this domain. Comparative analysis against existing methodologies further underscores the capacity of our framework to generate optimal or near-optimal machining process planning schemes. In conclusion, the proposed framework contributes to advancing machining process planning methods and facilitates wider adoption of DRL within process planning applications.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 370-393"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176133","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":"Realizing on-machine tool wear monitoring through integration of vision-based system with CNC milling machine","authors":"Aitha Sudheer Kumar ,&nbsp;Ankit Agarwal ,&nbsp;Vinita Gangaram Jansari ,&nbsp;K A Desai ,&nbsp;Chiranjoy Chattopadhyay ,&nbsp;Laine Mears","doi":"10.1016/j.jmsy.2024.12.004","DOIUrl":"10.1016/j.jmsy.2024.12.004","url":null,"abstract":"<div><div>The paper systematically realizes a vision-based on-machine Tool Wear Monitoring (TWM) system for integration with a CNC milling machine to identify tool wear states during machining hard materials such as Inconel 718 (IN718). The proposed TWM system consists of a microscope-based image acquisition setup mounted inside the machine and pre-defined programmed motions to capture high-resolution images of worn side cutting edges. The pre-trained Convolutional Neural Network (CNN) model, Efficient-Net-b0, was developed using transfer learning to identify tool wear states utilizing labeled image datasets generated in the machining environment. The labeled datasets were generated systematically by intermittently capturing images during IN718 machining at varying surface speeds. The present study considered four tool wear states, Flank, Flank+BUE, Flank+Face, and Chipping, representing combinations of abrasion, adhesion, diffusion, and fracture wear mechanisms. The effectiveness of the proposed TWM system was evaluated by identifying the wear state for previously unseen test datasets. The results showed that the TWM system can identify tool wear states with an accuracy of 94.11%. Furthermore, the study analyzes reasons for misclassifications using feature maps and classification probability scores to achieve better prediction abilities.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 283-293"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176131","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":"Method for drill-bit arrangement in CNC woodworking drilling machine for mass customization","authors":"Zhouzhou Ouyang ,&nbsp;Yiqiang Wu ,&nbsp;Haidong Shao ,&nbsp;Xun Wang ,&nbsp;Tao Tao ,&nbsp;Xingyan Chen ,&nbsp;Tao Peng","doi":"10.1016/j.jmsy.2024.11.019","DOIUrl":"10.1016/j.jmsy.2024.11.019","url":null,"abstract":"<div><div>In response to the growing demand for personalized products and dynamic changes in the global market, the consumer goods manufacturing industry, particularly the furniture sector, is increasingly adopting the mass customization (MC) production model. In this context, computer numerical control (CNC) woodworking drilling machines play a critical role in enabling flexible MC furniture production, especially during the drilling phase, which often becomes a bottleneck due to lengthy operation times and significant variability. Traditional methods aimed at speeding up equipment operation can no longer improve drilling efficiency. Therefore, optimizing parameter configurations by focusing on the practical usage of the equipment and implementing reconfigurable manufacturing systems (RMS) is essential. This study addresses the bottleneck by proposing an innovative approach to drill-bit arrangement based on the positional relationship between holes, considering real-world scenarios of multi-machine parallel processing and the challenges of quickly and accurately evaluating results. A universal \"grouping-solving-evaluation\" method is introduced, incorporating clustering, intelligent optimization, and neural networks within artificial intelligence. This method organizes datasets, solves problems, and evaluates results through a deep understanding of CNC machine operations, extensive analysis of large-scale production data, and the creation of a precise mathematical model. The effectiveness of this approach is validated using data from a production site. Our method showed the potential to reduce drilling times by up to 22.99 %, increase efficiency by as much as 17.80 %, and achieve typical improvements of 19.16 % in time reduction and 14.67 % in efficiency compared to traditional manual configurations. These findings provide valuable insights for advancing MC furniture manufacturing and promoting the intelligent production of customized furniture. By enabling the shift from traditional to more personalized and automated manufacturing processes, this research makes a significant contribution to overcoming current production limitations.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 200-212"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176526","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":"Development of intelligent system to consider worker's comfortable work duration in assembly line work scheduling","authors":"Venkata Krishna Rao Pabolu ,&nbsp;Divya Shrivastava ,&nbsp;Makarand S. Kulkarni","doi":"10.1016/j.jmsy.2024.11.016","DOIUrl":"10.1016/j.jmsy.2024.11.016","url":null,"abstract":"<div><div>The Fifth Industrial Revolution, or Industry 5.0, is a way to bring collaboration between human expertise and intelligent machines in making customized products, where humans guide the intelligent machines and machines to support the human. The fundamental purpose of Industry 5.0 is for human well-being in intelligent manufacturing. This research aims to prevent the assembly line workforce from physiological work stress using an intelligent work scheduling system and support assembly line managers by avoiding worker work rotations during assembly time. The worker’s comfortable work duration time (WCWDT) is proposed through this work to be considered during the assembly worker’s work scheduling. A knowledge-based intelligent system (KBIS) is proposed to make the worker’s work scheduling by considering the WCWDT. The knowledge of the worker’s WCWDT is learned with a learning mechanism from the historical data of the worker’s WCWDT. The intelligent algorithm selects the workers from the available workforce and assigns assembly work by considering their WCWDT. Industrial Internet of Things (IIoT) and Assembly line worker assignment and balancing problem (ALWABP) frameworks are adapted for workers’ WCWDT data acquisition and worker selection, respectively. Moreover, the proposed KBIS is smart enough to prioritize the aged workers from the available workforce. Finally, a use-case illustrative example is discussed to describe the scope of this research for a multi-model assembly line.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 226-243"},"PeriodicalIF":12.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143176580","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":"ScaloAdaptAlert, a novel framework for supervised anomaly detection in industrial acoustic data, integrating power scalograms, adaptive filter banks, and convolutional neural networks — A case study","authors":"M.A. Zakeri Harandi ,&nbsp;Tzu-Yuan Lin ,&nbsp;Chen Li ,&nbsp;Sigurd L. Villumsen ,&nbsp;Maani Ghaffari ,&nbsp;Ole Madsen","doi":"10.1016/j.jmsy.2025.01.007","DOIUrl":"10.1016/j.jmsy.2025.01.007","url":null,"abstract":"<div><div>Acoustic data, as a modality for building data-driven industrial monitoring systems, is particularly notable for its comprehensive insights into both operational and machinery states of a process. However, the effectiveness of existing time–frequency representation (TFR)-based frameworks remains limited in industrial contexts. Originally designed for analyzing human speech and music signals, these frameworks often struggle with the complex, non-stationary, and non-harmonic nature of manufacturing sound data. Addressing these challenges, this paper introduces ‘ScaloAdaptAlert’ (SAdAlert), a novel, domain-agnostic framework for deriving time–frequency representations from industrial acoustic data. SAdAlert employs wavelet transform to capture both local and global spectral characteristics, uses Gaussian filter banks in an adaptive fashion to identify spectral features at both low and high frequencies, and applies max-pooling to reduce temporal dimensionality. The presented framework effectively preserves dominant information of the acoustic data while isolating its relevant features in noisy settings and addressing class imbalance. Our method, validated on a real-world anomaly detection dataset from a robotic screwing process, demonstrates superior performance compared to state-of-the-art deep learning models and conventional TFR methods. This validation underscores SAdAlert’s potential to advance industrial acoustic monitoring by providing a robust, efficient, and highly adaptable tool for analyzing complex industrial acoustic data.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 234-254"},"PeriodicalIF":12.2,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169039","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":"Human-robot collaborative disassembly in Industry 5.0: A systematic literature review and future research agenda","authors":"Gang Yuan ,&nbsp;Xiaojun Liu ,&nbsp;Xiaoli Qiu ,&nbsp;Pai Zheng ,&nbsp;Duc Truong Pham ,&nbsp;Ming Su","doi":"10.1016/j.jmsy.2025.01.009","DOIUrl":"10.1016/j.jmsy.2025.01.009","url":null,"abstract":"<div><div>Collaborative human-robot units have attracted recognition for their ability to be used for flexible product disassembly to help achieve intelligent, sustainable, and service-oriented remanufacturing. The adoption of human-robot collaborative disassembly (HRCD) in Industry 5.0 contributes to enhancing the flexibility of the eco-friendly sustainable manufacturing supply chain, realising a circular product life cycle, and facilitating the transition to carbon neutrality. To conduct a systematic examination of the development and research trends in HRCD, a quantitative analysis was carried out on 99 studies retrieved from databases. The research topic structure was examined from an array of perspectives, shedding light on the current state, future pathways, and focal areas in conjunction with a visually depicted knowledge graph. This paper enables scholars to comprehend the trajectory and pivotal aspects of HRCD through investigations of intelligent remanufacturing, thereby clarifying the path for further advancements in sustainable manufacturing practices.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"79 ","pages":"Pages 199-216"},"PeriodicalIF":12.2,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169034","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}