Journal of Manufacturing Systems最新文献_第7页

Chat with MES: LLM-driven user interface for manipulating garment manufacturing system through natural language 与MES聊天：llm驱动的用户界面，用于通过自然语言操纵服装制造系统

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-20 DOI: 10.1016/j.jmsy.2025.02.008

Zhaolin Yuan , Ming Li , Chang Liu , Fangyuan Han , Haolun Huang , Hong-Ning Dai

{"title":"Chat with MES: LLM-driven user interface for manipulating garment manufacturing system through natural language","authors":"Zhaolin Yuan , Ming Li , Chang Liu , Fangyuan Han , Haolun Huang , Hong-Ning Dai","doi":"10.1016/j.jmsy.2025.02.008","DOIUrl":"10.1016/j.jmsy.2025.02.008","url":null,"abstract":"<div><div>This paper presents Chat with MES (CWM), an AI agent system, which integrates LLMs into the Manufacturing Execution System (MES), serving as the “ears, mouth, and the brain”. This system promotes a paradigm shift in MES interactions from Graphical User Interface (GUI) to natural language interface”, offering a more natural and efficient way for workers to manipulate the manufacturing system. Compared with the traditional GUI, both the maintenance costs for developers and the learning costs and the complexity of use for workers are significantly reduced. This paper also contributes two technical improvements to address the challenges of using LLM-Agent in serious manufacturing scenarios. The first one is Request Rewriting, designed to rephrase or automatically follow up on non-standardized and ambiguous requests from users. The second innovation is the Multi-Step Dynamic Operations Generation, which is a pre-execution planning technique similar to Chain-of-Thought (COT), used to enhance the success rate of handling complex tasks involving multiple operations. A case study conducted on a simulated garment MES with 55 manually designed requests demonstrates the high execution accuracy of CWM (80%) and the improvement achieved through query rewriting (9.1%) and Multi-Step Dynamic operations generation (18.2%). The source code of CWM, along with the simulated MES and benchmark requests, is publicly accessible.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 1093-1107"},"PeriodicalIF":12.2,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144116884","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}

引用次数: 0

Designing worker assistance systems–Methodology development and industrial validation 设计工人辅助系统-方法开发和工业验证

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-19 DOI: 10.1016/j.jmsy.2025.02.022

Patrick Bründl , Christina Wegener , Micha Stoidner , Johannes Bayer , Benedikt Scheffler , Huong Giang Nguyen , Jörg Franke

{"title":"Designing worker assistance systems–Methodology development and industrial validation","authors":"Patrick Bründl , Christina Wegener , Micha Stoidner , Johannes Bayer , Benedikt Scheffler , Huong Giang Nguyen , Jörg Franke","doi":"10.1016/j.jmsy.2025.02.022","DOIUrl":"10.1016/j.jmsy.2025.02.022","url":null,"abstract":"<div><div>This research paper presents a comprehensive methodology for the design and implementation of worker assistance systems, with a focus on enhancing technology acceptance in industrial settings. A systematic literature review was conducted to analyze existing approaches, identify gaps, and define requirements for the methodology. The proposed methodology TERA-AS (Tasks, Environment, Relevance, Acceptance of Assistance Systems) begins with a detailed analysis of the initial working environment, capturing physical strain, task complexity, and job-specific conditions using a structured questionnaire and guidelines. A catalog of necessary assistance functions is then derived, and a system matrix matches these needs to 16 different assistance systems, facilitating the selection of an optimal solution based on a cost-benefit analysis. TERA-AS emphasizes employee involvement in system design and clear communication throughout the implementation process to foster technology acceptance. Therefore, this approach not only focuses on creating technologically and economically viable assistance functions, but also ensures technology acceptance. It was applied in a real-world industrial use case, specifically in control cabinet manufacturing. The tested system was a laser projection optical assistance system based on AI-generated positional data. Evaluation of the system showed significant time savings for manual assembly processes —approximately 69.05 % in wiring and 26.04 % in electrical assembly—despite involving untrained personnel. Feedback from operators highlighted both the system's effectiveness and areas for improvement, such as material provision and user interface design. Overall, TERA-AS provides a structured methodology to digital worker assistance system implementation, ensuring successful adoption through early employee engagement and continuous system improvement.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 272-293"},"PeriodicalIF":12.2,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654550","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}

引用次数: 0

MaViLa: Unlocking new potentials in smart manufacturing through vision language models MaViLa：通过视觉语言模型释放智能制造的新潜力

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-18 DOI: 10.1016/j.jmsy.2025.02.017

Haolin Fan , Chenshu Liu , Neville Elieh Janvisloo , Shijie Bian , Jerry Ying Hsi Fuh , Wen Feng Lu , Bingbing Li

{"title":"MaViLa: Unlocking new potentials in smart manufacturing through vision language models","authors":"Haolin Fan , Chenshu Liu , Neville Elieh Janvisloo , Shijie Bian , Jerry Ying Hsi Fuh , Wen Feng Lu , Bingbing Li","doi":"10.1016/j.jmsy.2025.02.017","DOIUrl":"10.1016/j.jmsy.2025.02.017","url":null,"abstract":"<div><div>In smart manufacturing, there remains a gap in the system-level understanding of manufacturing processes that hinders the effective integration of artificial intelligence (AI) for autonomous planning and execution in dynamic real-world scenarios. This paper presents MaViLa, an advanced vision language model (VLM) specifically designed for the smart manufacturing domain. MaViLa enhances visual understanding in the manufacturing domain through two key approaches: first, it uses a retrieval augmented generation (RAG) pipeline to incorporate domain knowledge during dataset creation, and second, it implements a robust two-stage training paradigm of pre-training followed by instruction fine-tuning. Comparative evaluations of domain-relevant benchmarks demonstrate MaViLa’s superior performance over general-purpose VLMs, particularly in manufacturing-specific tasks such as process optimization and quality control. Experimental results, including laboratory tests and in-situ monitoring applications, highlight the effectiveness of MaViLa in scene understanding and decision-making support. With its scalability and seamless integration of external tools, MaViLa paves the way for more efficient human–machine interactions and the development of autonomous, holistic manufacturing systems. These advancements establish MaViLa as a key technology that unlocks new potential for smart manufacturing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 258-271"},"PeriodicalIF":12.2,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654738","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}

引用次数: 0

Sensor placement utilizing a digital twin for thermal error compensation of machine tools 利用数字孪生体进行机床热误差补偿的传感器安置

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-17 DOI: 10.1016/j.jmsy.2025.03.003

Sebastian Lang , Mario Zorzini , Stephan Scholze , Josef Mayr , Markus Bambach

{"title":"Sensor placement utilizing a digital twin for thermal error compensation of machine tools","authors":"Sebastian Lang , Mario Zorzini , Stephan Scholze , Josef Mayr , Markus Bambach","doi":"10.1016/j.jmsy.2025.03.003","DOIUrl":"10.1016/j.jmsy.2025.03.003","url":null,"abstract":"<div><div>Thermal errors in machine tools significantly impact precision and, therefore, productivity. Mitigating these errors often results in a trade-off between energy efficiency and accuracy. While data-driven compensation models show promise in addressing this challenge and achieving sustainable precision, their effectiveness hinges on the careful selection and placement of sensors as model inputs. This paper introduces a novel temperature sensor positioning method for thermal error compensation that leverages a digital twin framework to virtually determine ideal sensor positions and their effects on the compensation model. By accurately identifying temperature-sensitive points, our approach improves compensation accuracy and reduces the number of sensors required, thus enhancing both model robustness and operational efficiency. For choosing this set not only one simulation model is used but an ensemble with varying boundary conditions and thus model properties. Validation results show that the proposed method outperforms traditional, manually determined sensor placement strategies, providing a scalable solution for adaptable, energy-efficient thermal management in precision manufacturing. The selected sensor set based on a hybrid singular value decomposition and Least Absolute Shrinkage and Selection Operator approach yields a more robust compensation using only 7 instead of the manually chosen 22 temperature sensors. The thermal error reduction ranges from 77%–94% using simulated data with a corresponding reduction of 75%–85% achieved on the physical machine.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 243-257"},"PeriodicalIF":12.2,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637558","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}

引用次数: 0

Meta-knowledge triple driven multi-modal knowledge graph construction method and application in production line control with Gantt charts 元知识三重驱动多模态知识图构建方法及其在甘特图生产线控制中的应用

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-13 DOI: 10.1016/j.jmsy.2025.03.002

Laiyi Li, Maolin Yang, Inno Lorren Désir Makanda, Pingyu Jiang

{"title":"Meta-knowledge triple driven multi-modal knowledge graph construction method and application in production line control with Gantt charts","authors":"Laiyi Li, Maolin Yang, Inno Lorren Désir Makanda, Pingyu Jiang","doi":"10.1016/j.jmsy.2025.03.002","DOIUrl":"10.1016/j.jmsy.2025.03.002","url":null,"abstract":"<div><div>Digital manufacturing involves complex and multidimensional interactions among production line resources, resulting in massive multi-modal knowledge. The knowledge often lacks correlation and contextual readability, leading to data silos. The rapid development of knowledge graphs (KGs) has rekindled interest in manufacturing knowledge engineering. Investigating the framework of multi-modal manufacturing data assets in enterprises and transforming them into a general-purpose KG database to support manufacturing processes is of significant importance. Guided by the principle of using KG as a manufacturing database, this study developed a multi-modal production line manufacturing knowledge graph (PLMKG) to support dynamic manufacturing on production lines. Firstly, the schema layer of the PLMKG is constructed using the Entity-Relationship model and a manufacturing knowledge pattern framework, with meta-knowledge triples proposed for schema data expression. Secondly, an event-state trigger dynamic instantiation method based on triples binding is proposed to enable self-growth. Third, a method integrating dynamic Gantt charts is introduced to synchronize the control of PLMKG and the manufacturing process. The anomaly detection model is employed to detect production, with the results stored in the PLMKG and Gantt charts for process control. Finally, a PLMKG prototype system for data management and process visualization is developed, with a 3D printing production line case study validating the construction and application of PLMKG. The results indicate that the proposed PLMKG integrates multi-modal manufacturing knowledge structurally and provides AI readiness for manufacturing, finally supporting the production line operation as a database.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 224-242"},"PeriodicalIF":12.2,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621440","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}

引用次数: 0

A dynamic task allocation framework for human-robot collaborative assembly based on digital twin and IGA-TS 基于数字孪生和IGA-TS的人机协同装配动态任务分配框架

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-13 DOI: 10.1016/j.jmsy.2025.02.014

Zenggui Gao , Jingwei Tang , Hongjiang Lu , Yuyan Yao , Xinjie Cao , Chunyang Yu , Lilan Liu

{"title":"A dynamic task allocation framework for human-robot collaborative assembly based on digital twin and IGA-TS","authors":"Zenggui Gao , Jingwei Tang , Hongjiang Lu , Yuyan Yao , Xinjie Cao , Chunyang Yu , Lilan Liu","doi":"10.1016/j.jmsy.2025.02.014","DOIUrl":"10.1016/j.jmsy.2025.02.014","url":null,"abstract":"<div><div>Human-robot collaborative assembly is recognized as an essential component of intelligent manufacturing systems, combining human flexibility with machine efficiency, thereby enhancing the effectiveness and adaptability of assembly tasks. However, challenge in adaptability, decision-making, and responsiveness to changing scenarios persist. To address these, this paper propose a digital twin-driven decision-making approach for task allocation, using an Improved Genetic Algorithm with Tabu Search (IGA-TS). First, an assembly task evaluation model and digital twin framework are developed to support dynamic decision-making. Subsequently, the IGA-TS algorithm integrates a custom encoding scheme, fitness function, tabu list, and neighborhood search to avoid local optima, enhancing global optimization and convergence speed. Lastly, a digital twin-assisted system, combining human body modeling and motion recognition, enables real-time optimization feedback, forming a closed-loop for collaboration. Experimental results show that IGA-TS outperforms traditional genetic algorithms and heuristic methods in multi-objective optimization, reducing assembly time, task complexity, and human workload. In addition, the designed digital twin system demonstrates strong adaptability and robustness in responding to dynamic changes during the assembly process, providing a practical and feasible solution for manufacturing workshop assembly. It significantly enhances production efficiency and product quality, offering substantial industrial application value.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 206-223"},"PeriodicalIF":12.2,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610064","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}

引用次数: 0

A multimodal hierarchical learning approach for virtual metrology in semiconductor manufacturing 半导体制造中虚拟计量的多模态分层学习方法

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-11 DOI: 10.1016/j.jmsy.2025.02.010

Qunlong Chen , Wei Qin , Hongwei Xu

{"title":"A multimodal hierarchical learning approach for virtual metrology in semiconductor manufacturing","authors":"Qunlong Chen , Wei Qin , Hongwei Xu","doi":"10.1016/j.jmsy.2025.02.010","DOIUrl":"10.1016/j.jmsy.2025.02.010","url":null,"abstract":"<div><div>Achieving high-precision wafer yield prediction is a crucial step in improving the quality of semiconductor manufacturing. However, existing methods overlook the multimodal characteristics in wafer fabrication, leading to limitations in prediction accuracy and interpretability. To address the problem, this paper proposes an adaptive modal division and hierarchical learning method for wafer yield prediction. Firstly, Bayesian optimization is employed to adaptively search for the optimal modal division locations in the training samples, categorizing the samples into three distinct yield groups (high, medium, and low) with explicit production relevance. Concurrently, a novel degradation and incremental learning mechanism is designed to address the problem of declining prediction accuracy due to sample imbalance. Subsequently, a classification-regression hierarchical learning architecture is established to separately learn the distribution characteristics of each modality. This involves training classifiers using the labels derived from modal division, followed by distinct regressors for each category to facilitate precise yield predictions. Finally, experimental validations based on simulation and real-world manufacturing data demonstrate that the proposed virtual metrology approach accounting for multimodal characteristics exhibits enhanced performance and robustness.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 194-205"},"PeriodicalIF":12.2,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143593310","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}

引用次数: 0

Selection of manufacturing processes using graph neural networks 用图神经网络选择制造工艺

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-07 DOI: 10.1016/j.jmsy.2025.02.016

Marco Hussong , Patrick Ruediger-Flore , Matthias Klar , Marius Kloft , Jan C. Aurich

{"title":"Selection of manufacturing processes using graph neural networks","authors":"Marco Hussong , Patrick Ruediger-Flore , Matthias Klar , Marius Kloft , Jan C. Aurich","doi":"10.1016/j.jmsy.2025.02.016","DOIUrl":"10.1016/j.jmsy.2025.02.016","url":null,"abstract":"<div><div>The increasing complexity of modern manufacturing, driven by trends such as product customization and shorter product life cycles, presents significant challenges in process planning. Traditional methods for selecting manufacturing processes in industry rely on expert knowledge and manual intervention, which can be time-consuming and error-prone. Systems that can automate the selection of manufacturing processes become increasingly important. Current approaches for the selection of manufacturing processes focus on deep learning that convert the 3D CAD models to intermediate representations such as voxels, point clouds or dexels. However, this transformation can result in the loss of topological, geometrical, or Product and Manufacturing Information (PMI). To address these challenges, this paper proposes a neural network architecture MaProNet. MaProNet is a graph attention neural network (GAT) designed to capture topological and geometrical information through the analysis of Attributed Adjacency Graphs (AAG) and Mesh structures. MaProNet also incorporates a wide range of PMI information.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 176-193"},"PeriodicalIF":12.2,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563069","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}

引用次数: 0

Tool digital twin based on knowledge embedding for precision CNC machine tools: Wear prediction for collaborative multi-tool 基于知识嵌入的精密数控机床工具数字孪生：协同多工具的磨损预测

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-06 DOI: 10.1016/j.jmsy.2025.02.021

Jiacheng Sun , Dong Wang , Zhenyu Liu , Chan Qiu , Hui Liu , Guodong Sa , Jianrong Tan

{"title":"Tool digital twin based on knowledge embedding for precision CNC machine tools: Wear prediction for collaborative multi-tool","authors":"Jiacheng Sun , Dong Wang , Zhenyu Liu , Chan Qiu , Hui Liu , Guodong Sa , Jianrong Tan","doi":"10.1016/j.jmsy.2025.02.021","DOIUrl":"10.1016/j.jmsy.2025.02.021","url":null,"abstract":"<div><div>Tool wear prediction is vital for enhancing machining accuracy and ensuring production safety. However, challenges arise from non-processing data interference and missing tool wear samples, complicating the construction of accurate prediction models. Additionally, the complexity of collaborative multi-tool operations on precision computer numerical control (CNC) machine tools, where varying tool types and complex working conditions exist, further exacerbates the difficulty of achieving precise wear prediction. To address these challenges, this paper introduces a digital twin architecture for tool wear prediction, based on knowledge embedding. The proposed architecture is designed to predict the wear of multiple tools, incorporating modules for processing data screening, missing value completion, wear state classification, and so on. On the basis of obtaining high-quality sensing data and complete tool wear values, the wear state and machining process knowledge are embedded into the prediction process. A tool wear prediction model is then constructed based on a Kolmogorov-Arnold integrated time convolutional network (KA-TCN), so as to achieve accurate prediction of multi-tool wear. The effectiveness of the method is validated using data from two grinding wheel wear test platforms and two milling datasets, PHM2010 and NASA. Experimental results demonstrate that the knowledge embedded KA-TCN model outperforms existing approaches, improving prediction accuracy by over 22.4 % on the milling dataset, and by 76.4 % in grinding wheel wear prediction compared to classical methods.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 157-175"},"PeriodicalIF":12.2,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563068","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}

引用次数: 0

A design framework for high-fidelity human-centric digital twin of collaborative work cell in Industry 5.0 工业5.0中以人为中心的高保真协同工作单元数字孪生设计框架

IF 12.2 1区工程技术

Journal of Manufacturing Systems Pub Date : 2025-03-06 DOI: 10.1016/j.jmsy.2025.02.018

Tianyu Wang , Zhihao Liu , Lihui Wang , Mian Li , Xi Vincent Wang

{"title":"A design framework for high-fidelity human-centric digital twin of collaborative work cell in Industry 5.0","authors":"Tianyu Wang , Zhihao Liu , Lihui Wang , Mian Li , Xi Vincent Wang","doi":"10.1016/j.jmsy.2025.02.018","DOIUrl":"10.1016/j.jmsy.2025.02.018","url":null,"abstract":"<div><div>Digital Twin (DT) of a manufacturing system mainly involving materials and machines has been widely explored in the past decades to facilitate the mass customization of modern products. Recently, the new vision of Industry 5.0 has brought human operators back to the core part of work cells. To this end, designing human-centric DT systems is vital for an ergonomic and symbiotic working environment. However, one major challenge is the construction and utilization of high-fidelity digital human models. In the literature, preset universal human avatar models such as skeletons are mostly employed to represent the human operators, which overlooks the individual differences of physical traits. Besides, the fundamental utilization features such as motion tracking and procedure recognition still do not well address the practical issues such as occlusions and incomplete observations. To deal with the challenge, this paper proposes a systematic design framework to quickly and precisely build and utilize the human-centric DT systems. The mesh-based customized human operator models with rendered appearances are first generated within one minute from a short motion video. Then transformer-based deep learning networks are developed to realize the motion-related operator status synchronization in complex conditions. Extensive experiments on multiple real-world human–robot collaborative work cells show the superior performance of the proposed framework over the state-of-the-art.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"80 ","pages":"Pages 140-156"},"PeriodicalIF":12.2,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563067","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}

引用次数: 0