Robotics and Computer-integrated Manufacturing最新文献_第4页

Reviewing human-robot collaboration in manufacturing: Opportunities and challenges in the context of industry 5.0 回顾制造业中的人机协作：工业5.0背景下的机遇与挑战

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-31 DOI: 10.1016/j.rcim.2024.102937

Mandeep Dhanda, Benedict Alexander Rogers, Stephanie Hall, Elies Dekoninck, Vimal Dhokia

Industry 4.0 (I4.0) has been characterized by the increasing use of automation, artificial intelligence, and big data in manufacturing. It has brought different machines, tools, robots and devices together through integration with cyber-physical systems as well as Internet of Things and computer systems. This has dramatically improved efficiency, productivity, and flexibility of automated systems, but it has also raised concerns about the impact of automation on jobs, the ethical considerations and the future of work in general. Industry 5.0 (I5.0) is the next manufacturing paradigm evolution and builds on I4.0 with the addition of ‘people’, in which robots will be designed to work alongside humans in a safe and efficient manner. Human-robot collaboration (HRC) is its key enabler. In manufacturing, HRC has the potential to improve safety, efficiency, and productivity by allowing humans to focus on tasks that require creativity, judgment, and flexibility, while robots perform more repetitive and dangerous tasks.

This paper explores the concept of HRC and its advancement within 21st century industry. It identifies the opportunities and challenges arising from the interactions between robots and humans in manufacturing applications, assembly, and inspection. It also highlights the significance of HRC in I4.0 and its potential in I5.0. In addition, the role of artificial intelligence, machine learning, large language models, information modelling (ontologies) and new emerging digital technologies (augmented reality, virtual reality, digital twins, cyber-physical system) in the development of HRC and I5.0 is documented and discussed adding new perspectives to the growing literature in this area.

This investigation sheds light on the emerging paradigms that have come about as parts of I5.0 and the transformative role of human-robot interaction in shaping the future of manufacturing. This critical review provides a realistic picture of manufacturing automation and the benefits and weaknesses of current HRC systems. It presents a researched view on the concept, needs, enabling technologies and system frameworks of human-robot interaction in manufacturing, providing a practical vision and research agenda for future work in this area and its associated systems.

工业4.0 （I4.0）的特点是在制造业中越来越多地使用自动化、人工智能和大数据。它通过与网络物理系统、物联网和计算机系统的集成，将不同的机器、工具、机器人和设备结合在一起。这极大地提高了自动化系统的效率、生产力和灵活性，但也引起了人们对自动化对工作、道德考虑和未来工作的普遍影响的担忧。工业5.0 （I5.0）是下一个制造范式的演变，它建立在工业4.0的基础上，增加了“人”，其中机器人将被设计成以安全高效的方式与人类一起工作。人机协作（HRC）是其关键推动者。在制造业中，HRC有潜力提高安全性、效率和生产力，允许人类专注于需要创造力、判断力和灵活性的任务，而机器人则执行更多重复和危险的任务。

{"title":"Reviewing human-robot collaboration in manufacturing: Opportunities and challenges in the context of industry 5.0","authors":"Mandeep Dhanda, Benedict Alexander Rogers, Stephanie Hall, Elies Dekoninck, Vimal Dhokia","doi":"10.1016/j.rcim.2024.102937","DOIUrl":"10.1016/j.rcim.2024.102937","url":null,"abstract":"<div><div>Industry 4.0 (I4.0) has been characterized by the increasing use of automation, artificial intelligence, and big data in manufacturing. It has brought different machines, tools, robots and devices together through integration with cyber-physical systems as well as Internet of Things and computer systems. This has dramatically improved efficiency, productivity, and flexibility of automated systems, but it has also raised concerns about the impact of automation on jobs, the ethical considerations and the future of work in general. Industry 5.0 (I5.0) is the next manufacturing paradigm evolution and builds on I4.0 with the addition of ‘people’, in which robots will be designed to work alongside humans in a safe and efficient manner. Human-robot collaboration (HRC) is its key enabler. In manufacturing, HRC has the potential to improve safety, efficiency, and productivity by allowing humans to focus on tasks that require creativity, judgment, and flexibility, while robots perform more repetitive and dangerous tasks.</div><div>This paper explores the concept of HRC and its advancement within 21st century industry. It identifies the opportunities and challenges arising from the interactions between robots and humans in manufacturing applications, assembly, and inspection. It also highlights the significance of HRC in I4.0 and its potential in I5.0. In addition, the role of artificial intelligence, machine learning, large language models, information modelling (ontologies) and new emerging digital technologies (augmented reality, virtual reality, digital twins, cyber-physical system) in the development of HRC and I5.0 is documented and discussed adding new perspectives to the growing literature in this area.</div><div>This investigation sheds light on the emerging paradigms that have come about as parts of I5.0 and the transformative role of human-robot interaction in shaping the future of manufacturing. This critical review provides a realistic picture of manufacturing automation and the benefits and weaknesses of current HRC systems. It presents a researched view on the concept, needs, enabling technologies and system frameworks of human-robot interaction in manufacturing, providing a practical vision and research agenda for future work in this area and its associated systems.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102937"},"PeriodicalIF":9.1,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Personalized federated unsupervised learning for nozzle condition monitoring using vibration sensors in additive manufacturing 基于增材制造中振动传感器的喷嘴状态监测的个性化联合无监督学习

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-27 DOI: 10.1016/j.rcim.2024.102940

Inno Lorren Désir Makanda, Pingyu Jiang, Maolin Yang

Additive manufacturing (AM), particularly the fused filament fabrication (FFF) process, enables the production of personalized products with unique features. However, the FFF process is prone to issues such as nozzle clogging, which can degrade print quality or cause print failure. Data-driven approaches present viable solutions for real-time monitoring and defect identification in AM, enhancing both the precision and reliability of the FFF process. Despite these advantages, practical deployment faces obstacles including limited availability of high-quality data, significant labeling costs, and the rarity of anomalous data. While similar data may exist across other AM manufacturers or machines, data centralization and sharing are often constrained by privacy and competition concerns. This paper introduces FULAM, a personalized federated unsupervised learning method designed to detect anomalies in FFF machine vibration data. The framework addresses critical challenges such as data privacy, heterogeneity, and labeling costs by enabling collaborative training of unsupervised anomaly detection models across multiple clients while keeping data decentralized. A systematic analysis and comparison of recent unsupervised deep anomaly detection methods of varying complexity, traditionally evaluated in centralized settings, is conducted under federated learning (FL) environments to identify the most effective model for FFF machine vibration data. Experimental results highlight the personalized adaptation and regularization benefits of FULAM, showing cases where it outperforms both centralized approaches and state-of-the-art FL algorithms. FULAM demonstrates potential for developing robust anomaly detection models, advancing real-time condition monitoring in AM.

增材制造（AM），特别是熔丝制造（FFF）工艺，可以生产具有独特功能的个性化产品。然而，FFF过程容易出现喷嘴堵塞等问题，这可能会降低打印质量或导致打印失败。数据驱动的方法为AM中的实时监控和缺陷识别提供了可行的解决方案，提高了FFF过程的精度和可靠性。尽管有这些优势，但实际部署面临着障碍，包括高质量数据的有限可用性、显著的标记成本以及异常数据的稀有性。虽然类似的数据可能存在于其他AM制造商或机器中，但数据集中和共享通常受到隐私和竞争问题的限制。本文介绍了一种用于FFF机器振动数据异常检测的个性化联合无监督学习方法FULAM。该框架通过支持跨多个客户端协作训练无监督异常检测模型，同时保持数据分散，解决了数据隐私、异质性和标签成本等关键挑战。在联邦学习（FL）环境下，系统分析和比较了最近不同复杂性的无监督深度异常检测方法，以确定FFF机器振动数据的最有效模型。实验结果突出了FULAM的个性化适应和正则化优势，显示了它优于集中式方法和最先进的FL算法的情况。FULAM展示了开发鲁棒异常检测模型的潜力，推进了AM的实时状态监测。

{"title":"Personalized federated unsupervised learning for nozzle condition monitoring using vibration sensors in additive manufacturing","authors":"Inno Lorren Désir Makanda, Pingyu Jiang, Maolin Yang","doi":"10.1016/j.rcim.2024.102940","DOIUrl":"10.1016/j.rcim.2024.102940","url":null,"abstract":"<div><div>Additive manufacturing (AM), particularly the fused filament fabrication (FFF) process, enables the production of personalized products with unique features. However, the FFF process is prone to issues such as nozzle clogging, which can degrade print quality or cause print failure. Data-driven approaches present viable solutions for real-time monitoring and defect identification in AM, enhancing both the precision and reliability of the FFF process. Despite these advantages, practical deployment faces obstacles including limited availability of high-quality data, significant labeling costs, and the rarity of anomalous data. While similar data may exist across other AM manufacturers or machines, data centralization and sharing are often constrained by privacy and competition concerns. This paper introduces FULAM, a personalized federated unsupervised learning method designed to detect anomalies in FFF machine vibration data. The framework addresses critical challenges such as data privacy, heterogeneity, and labeling costs by enabling collaborative training of unsupervised anomaly detection models across multiple clients while keeping data decentralized. A systematic analysis and comparison of recent unsupervised deep anomaly detection methods of varying complexity, traditionally evaluated in centralized settings, is conducted under federated learning (FL) environments to identify the most effective model for FFF machine vibration data. Experimental results highlight the personalized adaptation and regularization benefits of FULAM, showing cases where it outperforms both centralized approaches and state-of-the-art FL algorithms. FULAM demonstrates potential for developing robust anomaly detection models, advancing real-time condition monitoring in AM.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102940"},"PeriodicalIF":9.1,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142889404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel pose estimation method for robot threaded assembly pre-alignment based on binocular vision 一种基于双目视觉的机器人螺纹装配预对准姿态估计方法

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-25 DOI: 10.1016/j.rcim.2024.102939

Yi Zhang , Zhonghai Song , Jiuwei Yu , Bingzhang Cao , Lei Wang

Threaded assembly plays a critical role in industrial manufacturing; however, achieving a fully automated threaded assembly remains challenging. In this study, an automatic robot thread assembly system based on binocular vision was developed, along with a novel approach for spatial circle pose estimation. Notably, this method utilises the chamfering circle of the threaded hole as the recognition target and achieves precise pose estimation without requiring any prior knowledge, from a geometric perspective. Utilising only a chord of the ellipse projected from the circular feature of the threaded hole, the method effectively addresses the traditional reliance on complete target features. Additionally, it avoids the need for point cloud fitting, which is commonly used in conventional 3D pose estimation, thereby significantly reducing computational complexity and improving both efficiency and accuracy. An innovative method for verifying the spatial circle positioning accuracy is proposed based on the calibration plate coordinate system. The proposed method achieved position error ranges of [0.0419, 0.0837], [-0.0864, 0.0148], and [-0.0434, 0.0286] in mm along the x, y, and z axes, respectively. Furthermore, the orientation error ranged from 0.649° - 1.752° To comprehensively consider the origin of the various errors, a workpiece was designed to conduct robot alignment experiments. The average errors along the x, y, and z axes were -0.23, -0.57, and -0.45 mm, respectively. Overall, the proposed vision measurement method demonstrated excellent pose estimation accuracy and significantly enhanced the automation of robotic threaded assembly processes. This advancement holds great potential for widespread applications in industrial manufacturing environments.

螺纹装配在工业制造中起着至关重要的作用；然而，实现全自动螺纹装配仍然具有挑战性。本研究开发了一种基于双目视觉的机器人螺纹自动装配系统，并提出了一种新的空间圆位姿估计方法。值得注意的是，该方法从几何角度利用螺纹孔的倒角圆作为识别目标，无需任何先验知识即可实现精确的姿态估计。该方法仅利用螺纹孔圆形特征投射的椭圆弦，有效地解决了传统上对完整目标特征的依赖。此外，它避免了传统3D姿态估计中常用的点云拟合的需要，从而大大降低了计算复杂度，提高了效率和精度。提出了一种基于标定板坐标系的空间圆定位精度验证方法。该方法在x、y和z轴上的位置误差范围分别为[0.0419、0.0837]、[-0.0864、0.0148]和[-0.0434、0.0286]mm。为了综合考虑各种误差的来源，设计了一个工件进行机器人对中实验。沿x、y、z轴的平均误差分别为-0.23、-0.57、-0.45 mm。总体而言，所提出的视觉测量方法具有良好的姿态估计精度，显著提高了机器人螺纹装配过程的自动化程度。这一进步在工业制造环境中具有广泛应用的巨大潜力。

{"title":"A novel pose estimation method for robot threaded assembly pre-alignment based on binocular vision","authors":"Yi Zhang , Zhonghai Song , Jiuwei Yu , Bingzhang Cao , Lei Wang","doi":"10.1016/j.rcim.2024.102939","DOIUrl":"10.1016/j.rcim.2024.102939","url":null,"abstract":"<div><div>Threaded assembly plays a critical role in industrial manufacturing; however, achieving a fully automated threaded assembly remains challenging. In this study, an automatic robot thread assembly system based on binocular vision was developed, along with a novel approach for spatial circle pose estimation. Notably, this method utilises the chamfering circle of the threaded hole as the recognition target and achieves precise pose estimation without requiring any prior knowledge, from a geometric perspective. Utilising only a chord of the ellipse projected from the circular feature of the threaded hole, the method effectively addresses the traditional reliance on complete target features. Additionally, it avoids the need for point cloud fitting, which is commonly used in conventional 3D pose estimation, thereby significantly reducing computational complexity and improving both efficiency and accuracy. An innovative method for verifying the spatial circle positioning accuracy is proposed based on the calibration plate coordinate system. The proposed method achieved position error ranges of [0.0419, 0.0837], [-0.0864, 0.0148], and [-0.0434, 0.0286] in mm along the x, y, and z axes, respectively. Furthermore, the orientation error ranged from 0.649° - 1.752° To comprehensively consider the origin of the various errors, a workpiece was designed to conduct robot alignment experiments. The average errors along the x, y, and z axes were -0.23, -0.57, and -0.45 mm, respectively. Overall, the proposed vision measurement method demonstrated excellent pose estimation accuracy and significantly enhanced the automation of robotic threaded assembly processes. This advancement holds great potential for widespread applications in industrial manufacturing environments.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102939"},"PeriodicalIF":9.1,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reality-guided virtual assembly for contact-prohibited stepped shaft-in-hole task 面向无接触阶梯式井内轴任务的现实引导虚拟装配

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-24 DOI: 10.1016/j.rcim.2024.102933

Hongtai Cheng , Zelong Wang, Xiaohan Guan, Feng Gao

Contact-prohibited stepped Shaft in Hole (SSiH) task widely exists in structural docking mechanisms of aerospace equipment such as rockets or airplanes. However, the tight clearance, irregular deformation, large scale/volume/weight, and sensitivity to contacts, make it difficult to automate the assembly process. The answers to the questions of whether it can be assembled or not and what is the optimal installation posture are vital to the task. To address these problems, a reality-guided virtual assembly method is proposed to assess the clearance of the mating surfaces and ascertain their assembly feasibility before real installation. Firstly, the method takes 3D point clouds scanned from real parts as input and registers the shaft and hole point clouds to their corresponding CAD models, then a geometric-consistent registration algorithm is proposed to precisely align the shaft/hole point clouds. Secondly, by analyzing the geometric constraints, the original 6 DOF posture optimization problem is reduced to a 2 DOF one. To increase the calculation efficiency, a point cloud polarization and repair algorithm is proposed to convert the 3D stepped shaft model into a series of 2D polar models. The clearance/interference can be calculated by subtracting the polar radius. Finally, a two-staged grid search method is used to find the optimal installation posture by maximizing the minimum gap across all the shaft segments. Simulation and experimentation are performed to verify the effectiveness and reliability of this algorithm.

禁止接触阶梯式孔内轴任务广泛存在于火箭、飞机等航天设备的结构对接机构中。然而，紧凑的间隙，不规则的变形，大的规模/体积/重量，以及对接触的敏感性，使装配过程的自动化变得困难。是否可以组装，最佳安装姿势是什么，这些问题的答案对任务至关重要。为了解决这些问题，提出了一种现实引导的虚拟装配方法，在实际安装前评估配合面间隙并确定其装配可行性。该方法首先以实际零件扫描的三维点云为输入，将轴和孔点云注册到相应的CAD模型中，然后提出一种几何一致配准算法，实现轴/孔点云的精确对齐。其次，通过几何约束分析，将原来的6自由度姿态优化问题简化为2自由度姿态优化问题；为了提高计算效率，提出了一种点云极化修复算法，将三维阶梯轴模型转换为一系列二维极化模型。通过减去极半径可以计算出间隙/干涉。最后，采用两阶段网格搜索方法，通过最大化所有轴段之间的最小间隙来寻找最佳安装姿态。通过仿真和实验验证了该算法的有效性和可靠性。

{"title":"Reality-guided virtual assembly for contact-prohibited stepped shaft-in-hole task","authors":"Hongtai Cheng , Zelong Wang, Xiaohan Guan, Feng Gao","doi":"10.1016/j.rcim.2024.102933","DOIUrl":"10.1016/j.rcim.2024.102933","url":null,"abstract":"<div><div>Contact-prohibited stepped Shaft in Hole (SSiH) task widely exists in structural docking mechanisms of aerospace equipment such as rockets or airplanes. However, the tight clearance, irregular deformation, large scale/volume/weight, and sensitivity to contacts, make it difficult to automate the assembly process. The answers to the questions of whether it can be assembled or not and what is the optimal installation posture are vital to the task. To address these problems, a reality-guided virtual assembly method is proposed to assess the clearance of the mating surfaces and ascertain their assembly feasibility before real installation. Firstly, the method takes 3D point clouds scanned from real parts as input and registers the shaft and hole point clouds to their corresponding CAD models, then a geometric-consistent registration algorithm is proposed to precisely align the shaft/hole point clouds. Secondly, by analyzing the geometric constraints, the original 6 DOF posture optimization problem is reduced to a 2 DOF one. To increase the calculation efficiency, a point cloud polarization and repair algorithm is proposed to convert the 3D stepped shaft model into a series of 2D polar models. The clearance/interference can be calculated by subtracting the polar radius. Finally, a two-staged grid search method is used to find the optimal installation posture by maximizing the minimum gap across all the shaft segments. Simulation and experimentation are performed to verify the effectiveness and reliability of this algorithm.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102933"},"PeriodicalIF":9.1,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Strategic algorithm for cable wiring using dual arm with compliance control 带柔度控制的双臂电缆布线策略算法

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-24 DOI: 10.1016/j.rcim.2024.102924

Youngsu Cho , Minsu Cho , Jongwoo Park, Byung-Kil Han, Young Hun Lee, Sung-Hyuk Song, Chanhun Park, Dong Il Park

A variety of electronic products are in daily use to serve a variety of needs. Electronic products require different types of cable harnesses for production. Nowadays, user preferences vary and change quickly. Therefore, a variety of small-volume products are made, and producing various kinds of complex harnesses to satisfy people’s needs is difficult. In robotic automation, the wiring harness assembly process in the manufacturing of deformable objects is challenging. Because of the characteristics of a deformable object, the manufacturing task cannot be standardized. However, relying solely on image sensors is not advisable, due to the challenges involved in recognizing complex cables with image sensors. Additionally, even when cable recognition is possible, it requires too much time. To address these issues, this paper introduces a strategic algorithm for the wiring harness assembly process. The algorithm minimizes the dependence on image sensors by enabling the use of a robotic dual-arm system. The proposed method includes techniques such as cable estimation, frictional models, and trajectory planning in the algorithms. On the basis of these methods, for a provided assembly board, the algorithm outputs a systematic process for wiring harness assembly. Experimental results validate the algorithm, demonstrating its good performance.

各种各样的电子产品在日常使用中服务于各种需求。电子产品需要不同类型的电缆线束进行生产。如今，用户偏好变化很大，变化很快。因此，制作各种小批量产品，生产各种复杂的线束来满足人们的需求是很困难的。在机器人自动化中，可变形物体制造中的线束装配过程具有挑战性。由于可变形物体的特性，制造任务无法标准化。然而，仅仅依靠图像传感器是不可取的，因为使用图像传感器识别复杂电缆所涉及的挑战。此外，即使有线识别是可能的，也需要太多的时间。针对这些问题，本文提出了一种线束装配过程的策略算法。该算法通过启用机器人双臂系统，最大限度地减少了对图像传感器的依赖。该方法在算法中包含了电缆估计、摩擦模型和轨迹规划等技术。在这些方法的基础上，对于所提供的装配板，该算法输出线束装配的系统化过程。实验结果验证了该算法的有效性。

{"title":"Strategic algorithm for cable wiring using dual arm with compliance control","authors":"Youngsu Cho , Minsu Cho , Jongwoo Park, Byung-Kil Han, Young Hun Lee, Sung-Hyuk Song, Chanhun Park, Dong Il Park","doi":"10.1016/j.rcim.2024.102924","DOIUrl":"10.1016/j.rcim.2024.102924","url":null,"abstract":"<div><div>A variety of electronic products are in daily use to serve a variety of needs. Electronic products require different types of cable harnesses for production. Nowadays, user preferences vary and change quickly. Therefore, a variety of small-volume products are made, and producing various kinds of complex harnesses to satisfy people’s needs is difficult. In robotic automation, the wiring harness assembly process in the manufacturing of deformable objects is challenging. Because of the characteristics of a deformable object, the manufacturing task cannot be standardized. However, relying solely on image sensors is not advisable, due to the challenges involved in recognizing complex cables with image sensors. Additionally, even when cable recognition is possible, it requires too much time. To address these issues, this paper introduces a strategic algorithm for the wiring harness assembly process. The algorithm minimizes the dependence on image sensors by enabling the use of a robotic dual-arm system. The proposed method includes techniques such as cable estimation, frictional models, and trajectory planning in the algorithms. On the basis of these methods, for a provided assembly board, the algorithm outputs a systematic process for wiring harness assembly. Experimental results validate the algorithm, demonstrating its good performance.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102924"},"PeriodicalIF":9.1,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robotic grinding of curved parts with two degrees of freedom active compliant force-controlled end-effector using decoupling control algorithm 基于解耦控制算法的二自由度主动柔性末端执行器曲面零件机器人磨削研究

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-23 DOI: 10.1016/j.rcim.2024.102935

Haiqing Chen, Jixiang Yang, Han Ding

This paper proposes a novel two degrees of freedom (2-DOF) active compliant force-controlled end-effector (EE) using decoupling control algorithm to improve grinding efficiency, material removal accuracy, and surface quality of the curved parts for robotic grinding. First, a robotic grinding system is described, which consists of an industrial robot for tool-path control and a novel 2-DOF compliant EE to improve grinding efficiency and compliance. Second, the dynamic relationship between the friction coefficient and the normal force is established to develop an online prediction model for the normal force. The tangential tool tip displacement model is also established. A force-position decoupling control algorithm, which comprises force–position decoupling and fuzzy force–position switching controllers, is then proposed to improve the normal force and the tangential tool tip displacement control accuracy of the 2-DOF compliant EE. Finally, the developed methodology is validated through grinding experiments to confirm its effectiveness. The grinding results show that under the premise of ensuring the neglectable tangential tool tip displacement error to the original grinding process, the developed 2-DOF compliant EE with decoupling control demonstrates similar high force control accuracy and grinding depth accuracy to the 1-DOF compliant EE, and the machining efficiency is improved by approximately 30 % compared to that of the 1-DOF compliant EE. Compared with the traditional 2-DOF rigid EE using hybrid control, the normal force and tangential tool tip displacement control errors of the developed 2-DOF compliant EE with decoupling control are reduced by approximately 60 % and 33 %, respectively, and the overshoot is reduced from 30 % to almost 0. The developed 2-DOF compliant EE with decoupling control improves the grinding depth accuracy and surface quality compared to the traditional 2-DOF rigid EE with hybrid control.

为了提高机器人磨削加工曲面零件的磨削效率、材料去除精度和表面质量，提出了一种采用解耦控制算法的二自由度主动柔性末端执行器。首先，介绍了一种机器人磨削系统，该系统由一个用于刀具轨迹控制的工业机器人和一个新型的2自由度柔性EE组成，以提高磨削效率和顺应性。其次，建立摩擦系数与法向力之间的动态关系，建立法向力在线预测模型；建立了切向刀尖位移模型。提出了一种由力-位置解耦和模糊力-位置切换控制器组成的力-位置解耦控制算法，以提高二自由度柔性机械臂的法向力和切向刀尖位移控制精度。最后，通过磨削实验验证了该方法的有效性。磨削结果表明，在保证刀尖切向位移误差对原磨削过程可忽略不计的前提下，采用解耦控制的二自由度柔性EE具有与一自由度柔性EE相似的高力控制精度和磨削深度精度，加工效率比一自由度柔性EE提高了约30%。与采用混合控制的传统2-DOF刚性EE相比，采用解耦控制的2-DOF柔性EE法向力和切向刀尖位移控制误差分别降低了约60%和33%，超调量从30%降至接近0。采用解耦控制的二自由度柔性EE与传统的混合控制的二自由度刚性EE相比，提高了磨削深度精度和表面质量。

{"title":"Robotic grinding of curved parts with two degrees of freedom active compliant force-controlled end-effector using decoupling control algorithm","authors":"Haiqing Chen, Jixiang Yang, Han Ding","doi":"10.1016/j.rcim.2024.102935","DOIUrl":"10.1016/j.rcim.2024.102935","url":null,"abstract":"<div><div>This paper proposes a novel two degrees of freedom (2-DOF) active compliant force-controlled end-effector (EE) using decoupling control algorithm to improve grinding efficiency, material removal accuracy, and surface quality of the curved parts for robotic grinding. First, a robotic grinding system is described, which consists of an industrial robot for tool-path control and a novel 2-DOF compliant EE to improve grinding efficiency and compliance. Second, the dynamic relationship between the friction coefficient and the normal force is established to develop an online prediction model for the normal force. The tangential tool tip displacement model is also established. A force-position decoupling control algorithm, which comprises force–position decoupling and fuzzy force–position switching controllers, is then proposed to improve the normal force and the tangential tool tip displacement control accuracy of the 2-DOF compliant EE. Finally, the developed methodology is validated through grinding experiments to confirm its effectiveness. The grinding results show that under the premise of ensuring the neglectable tangential tool tip displacement error to the original grinding process, the developed 2-DOF compliant EE with decoupling control demonstrates similar high force control accuracy and grinding depth accuracy to the 1-DOF compliant EE, and the machining efficiency is improved by approximately 30 % compared to that of the 1-DOF compliant EE. Compared with the traditional 2-DOF rigid EE using hybrid control, the normal force and tangential tool tip displacement control errors of the developed 2-DOF compliant EE with decoupling control are reduced by approximately 60 % and 33 %, respectively, and the overshoot is reduced from 30 % to almost 0. The developed 2-DOF compliant EE with decoupling control improves the grinding depth accuracy and surface quality compared to the traditional 2-DOF rigid EE with hybrid control.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102935"},"PeriodicalIF":9.1,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DFGAT for recognizing design features from a B-rep model for mechanical parts 从机械零件的B-rep模型中识别设计特征的DFGAT

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-21 DOI: 10.1016/j.rcim.2024.102938

Jun Hwan Park , Seungeun Lim , Changmo Yeo , Youn-Kyoung Joung , Duhwan Mun

Design feature recognition plays a crucial role in digital manufacturing and is a key technology in automatic design verification. Traditional methods and deep learning approaches provide various strategies for feature recognition. However, these methods primarily address part classification or machining feature recognition, with limited research focusing on design feature recognition. To address this gap, a novel deep learning network called the design feature graph attention network (DFGAT) was proposed specifically for design feature recognition. In this study, the original boundary representation (B-rep) model is first converted into graph representation. Design feature recognition is then achieved using the DFGAT, which is based on the GAT. Additionally, the dataset generation process was generalized to efficiently train the deep learning model. To validate the performance of the DFGAT, experiments were conducted to recognize the representative faces of design features, such as snap-fit hooks, cups, and plates, in the EIF_Panel, Real_Panel, and Anemometer models. The experiments demonstrated F1-scores of 0.9924, 0.9982, and 1.0000.

设计特征识别在数字化制造中起着至关重要的作用，也是自动设计验证的一项关键技术。传统方法和深度学习方法为特征识别提供了各种策略。然而，这些方法主要针对零件分类或加工特征识别，而针对设计特征识别的研究却非常有限。针对这一空白，我们提出了一种专门用于设计特征识别的新型深度学习网络--设计特征图注意力网络（DFGAT）。在这项研究中，首先将原始的边界表示（B-rep）模型转换为图表示。然后使用基于 GAT 的 DFGAT 实现设计特征识别。此外，还对数据集生成过程进行了通用化，以高效地训练深度学习模型。为了验证 DFGAT 的性能，我们在 EIF_Panel、Real_Panel 和 Anemometer 模型中对设计特征的代表面进行了识别实验，如卡扣式挂钩、杯子和盘子。实验结果表明，F1 分数分别为 0.9924、0.9982 和 1.0000。

{"title":"DFGAT for recognizing design features from a B-rep model for mechanical parts","authors":"Jun Hwan Park , Seungeun Lim , Changmo Yeo , Youn-Kyoung Joung , Duhwan Mun","doi":"10.1016/j.rcim.2024.102938","DOIUrl":"10.1016/j.rcim.2024.102938","url":null,"abstract":"<div><div>Design feature recognition plays a crucial role in digital manufacturing and is a key technology in automatic design verification. Traditional methods and deep learning approaches provide various strategies for feature recognition. However, these methods primarily address part classification or machining feature recognition, with limited research focusing on design feature recognition. To address this gap, a novel deep learning network called the design feature graph attention network (DFGAT) was proposed specifically for design feature recognition. In this study, the original boundary representation (B-rep) model is first converted into graph representation. Design feature recognition is then achieved using the DFGAT, which is based on the GAT. Additionally, the dataset generation process was generalized to efficiently train the deep learning model. To validate the performance of the DFGAT, experiments were conducted to recognize the representative faces of design features, such as snap-fit hooks, cups, and plates, in the EIF_Panel, Real_Panel, and Anemometer models. The experiments demonstrated F1-scores of 0.9924, 0.9982, and 1.0000.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102938"},"PeriodicalIF":9.1,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A contour error prediction method for tool path correction using a multi-feature hybrid model in robotic milling systems 机器人铣削系统中使用多特征混合模型进行刀具路径修正的轮廓误差预测方法

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-21 DOI: 10.1016/j.rcim.2024.102936

Shizhong Tan , Congcong Ye , Chengxing Wu , Jixiang Yang , Han Ding

Achieving high precision in robotic milling presents significant challenges due to inherent errors caused by various factors such as robot stiffness deformation and uneven machining allowances in large workpieces. Traditional error corrected methods often fall short in effectively addressing the complexity and dynamic nature of such errors. To address these challenges, a contour error prediction model has been proposed by using a combination of Gaussian Processes and a CNN-BiLSTM architecture. Firstly, extract the potential error features, including the robot's posture and stiffness information, as well as the workpiece's machining allowance during the milling process. Then, process these features to create a uniformly structured training set. Subsequently, develop a CNN-BiLSTM neural network model to realize an accurate contour error prediction, where the CNN layers are responsible for extracting hidden local features from the structured data, while the BiLSTM layers capture temporal correlations and hidden features related to tool path. Finally, validate on a saddle-shaped workpiece with surface features similar to those found in aero-engine casing cavities. The results demonstrate that the fusion-based error prediction model effectively reduces the maximum contour error from 0.9629 mm to 0.4881 mm, and decreases the mean absolute contour error from 0.7171 mm to 0.3048mm, representing reductions of 49.30 % and 57.40 %, respectively. These reductions well validate the effectiveness of the proposed method.

由于机器人刚度变形和大型工件加工余量不均等各种因素造成的固有误差，在机器人铣削加工中实现高精度是一项重大挑战。传统的误差修正方法往往无法有效解决此类误差的复杂性和动态性。为了应对这些挑战，我们结合高斯过程和 CNN-BiLSTM 架构，提出了一种轮廓误差预测模型。首先，提取潜在误差特征，包括机器人的姿势和刚度信息，以及铣削过程中工件的加工余量。然后，处理这些特征，创建结构统一的训练集。然后，开发一个 CNN-BiLSTM 神经网络模型来实现精确的轮廓误差预测，其中 CNN 层负责从结构化数据中提取隐藏的局部特征，而 BiLSTM 层则捕捉与刀具路径相关的时间相关性和隐藏特征。最后，在一个鞍形工件上进行验证，该工件的表面特征与航空发动机机壳型腔中的表面特征相似。结果表明，基于融合的误差预测模型有效地将最大轮廓误差从 0.9629 毫米减少到 0.4881 毫米，将平均绝对轮廓误差从 0.7171 毫米减少到 0.3048 毫米，分别减少了 49.30 % 和 57.40 %。这些误差的减少充分验证了建议方法的有效性。

{"title":"A contour error prediction method for tool path correction using a multi-feature hybrid model in robotic milling systems","authors":"Shizhong Tan , Congcong Ye , Chengxing Wu , Jixiang Yang , Han Ding","doi":"10.1016/j.rcim.2024.102936","DOIUrl":"10.1016/j.rcim.2024.102936","url":null,"abstract":"<div><div>Achieving high precision in robotic milling presents significant challenges due to inherent errors caused by various factors such as robot stiffness deformation and uneven machining allowances in large workpieces. Traditional error corrected methods often fall short in effectively addressing the complexity and dynamic nature of such errors. To address these challenges, a contour error prediction model has been proposed by using a combination of Gaussian Processes and a CNN-BiLSTM architecture. Firstly, extract the potential error features, including the robot's posture and stiffness information, as well as the workpiece's machining allowance during the milling process. Then, process these features to create a uniformly structured training set. Subsequently, develop a CNN-BiLSTM neural network model to realize an accurate contour error prediction, where the CNN layers are responsible for extracting hidden local features from the structured data, while the BiLSTM layers capture temporal correlations and hidden features related to tool path. Finally, validate on a saddle-shaped workpiece with surface features similar to those found in aero-engine casing cavities. The results demonstrate that the fusion-based error prediction model effectively reduces the maximum contour error from 0.9629 mm to 0.4881 mm, and decreases the mean absolute contour error from 0.7171 mm to 0.3048mm, representing reductions of 49.30 % and 57.40 %, respectively. These reductions well validate the effectiveness of the proposed method.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102936"},"PeriodicalIF":9.1,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synthesis and prototyping of a backdrivable parallel robot for metal finishing tasks

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-20 DOI: 10.1016/j.rcim.2024.102934

Pierre-Luc Beaulieu, Thierry Laliberté, Simon Foucault, Clément Gosselin

This article presents the synthesis, control and experimental validation of a backdrivable three-degree-of-freedom translational mini robot used to control the interaction between a robot and a machined part during finishing tasks, such as polishing, sanding and deburring without requiring the use of a force/torque sensor. The mini robot acts as an active contact flange, allowing an industrial robot (the macro robot) to adapt to a part using an impedance control algorithm. Firstly, different three-degree-of-freedom parallel robot architectures are compared and the most suitable architecture is selected. Geometrical properties are chosen for the robot and the physical capabilities of the architecture are predicted to ensure that the design criteria are satisfied. An impedance control algorithm is then developed for the mini robot. The macro-mini system is formed by installing the mini robot on a gantry robot. Sanding tests are carried out in order to validate the performance of the system and the mini robot is compared to other contact flanges already available on the market. Finally, a method allowing the determination of the magnitude of the friction forces in the mini robot is presented and a preliminary friction compensation algorithm is developed. As opposed to existing tools, the novel mini robot proposed in this work is based on a compact parallel architecture, which makes it possible to ensure the backdrivability of the system in three directions. An impedance control algorithm can therefore be implemented thereby providing stability even with stiff environments and eliminating the need for a force/torque sensor.

{"title":"Synthesis and prototyping of a backdrivable parallel robot for metal finishing tasks","authors":"Pierre-Luc Beaulieu, Thierry Laliberté, Simon Foucault, Clément Gosselin","doi":"10.1016/j.rcim.2024.102934","DOIUrl":"10.1016/j.rcim.2024.102934","url":null,"abstract":"<div><div>This article presents the synthesis, control and experimental validation of a backdrivable three-degree-of-freedom translational mini robot used to control the interaction between a robot and a machined part during finishing tasks, such as polishing, sanding and deburring without requiring the use of a force/torque sensor. The mini robot acts as an active contact flange, allowing an industrial robot (the macro robot) to adapt to a part using an impedance control algorithm. Firstly, different three-degree-of-freedom parallel robot architectures are compared and the most suitable architecture is selected. Geometrical properties are chosen for the robot and the physical capabilities of the architecture are predicted to ensure that the design criteria are satisfied. An impedance control algorithm is then developed for the mini robot. The macro-mini system is formed by installing the mini robot on a gantry robot. Sanding tests are carried out in order to validate the performance of the system and the mini robot is compared to other contact flanges already available on the market. Finally, a method allowing the determination of the magnitude of the friction forces in the mini robot is presented and a preliminary friction compensation algorithm is developed. As opposed to existing tools, the novel mini robot proposed in this work is based on a compact parallel architecture, which makes it possible to ensure the backdrivability of the system in three directions. An impedance control algorithm can therefore be implemented thereby providing stability even with stiff environments and eliminating the need for a force/torque sensor.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102934"},"PeriodicalIF":9.1,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143150860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A unified sampling method for optimal feature coverage and robot placement 优化特征覆盖和机器人位置的统一采样方法

IF 9.1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2024-12-19 DOI: 10.1016/j.rcim.2024.102932

Domenico Spensieri, Edvin Å blad, Raad Salman, Johan S. Carlson

Designing a robot line includes the critical decision about the number of robots needed to carry out all the tasks in the stations and their placement. Similarly, having a robot manipulator mounted on a mobile base, such as an Automated Guided Vehicle (AGV), needs a careful choice of the base positions to minimize cycle time for the operations. In this paper, we solve both the robot placement and the AGV positioning problems by relating them to feature coverage applications, where the challenge is to place cameras (or other sensors) to inspect all points on a workpiece for metrology tasks. These similarities allow us to design an efficient divide&conquer-based algorithm which can be adapted to solve all three problems above, where finding the minimum number of positions for sensors, AGVs and robots is crucial to reduce cycle time and costs.

The algorithm is divided in two parts: the first one is responsible for identifying candidate positions, whereas the second solves a set covering problem. We show that these two parts can even be interlaced to obtain high-quality solutions in short time.

A successful computational study has been carried out with both artificial instances and three industrial scenarios, ranging from laser sensor inspection cells in the aerospace industry, to an automated cleaning room, and ending with a stud welding station for automotive applications.

The results show that geometric and industrial tests, even accounting for kinematics and distance queries, can be handled with high accuracy in reasonable computing time.

机器人生产线的设计包括对在各工位执行所有任务所需的机器人数量及其位置进行关键决策。同样，将机器人机械手安装在移动底座（如自动导引车（AGV））上，也需要谨慎选择底座位置，以尽量缩短操作周期。在本文中，我们通过将机器人放置和 AGV 定位问题与特征覆盖应用联系起来来解决这两个问题，在特征覆盖应用中，我们面临的挑战是放置摄像头（或其他传感器）来检测工件上的所有点，以完成计量任务。这些相似之处使我们能够设计出一种基于分而治之的高效算法，该算法可用于解决上述所有三个问题，在这些问题中，找到传感器、AGV 和机器人的最小位置数对于减少周期时间和成本至关重要。

{"title":"A unified sampling method for optimal feature coverage and robot placement","authors":"Domenico Spensieri, Edvin Å blad, Raad Salman, Johan S. Carlson","doi":"10.1016/j.rcim.2024.102932","DOIUrl":"10.1016/j.rcim.2024.102932","url":null,"abstract":"<div><div>Designing a robot line includes the critical decision about the number of robots needed to carry out all the tasks in the stations and their placement. Similarly, having a robot manipulator mounted on a mobile base, such as an Automated Guided Vehicle (AGV), needs a careful choice of the base positions to minimize cycle time for the operations. In this paper, we solve both the robot placement and the AGV positioning problems by relating them to feature coverage applications, where the challenge is to place cameras (or other sensors) to inspect all points on a workpiece for metrology tasks. These similarities allow us to design an efficient divide&conquer-based algorithm which can be adapted to solve all three problems above, where finding the minimum number of positions for sensors, AGVs and robots is crucial to reduce cycle time and costs.</div><div>The algorithm is divided in two parts: the first one is responsible for identifying candidate positions, whereas the second solves a set covering problem. We show that these two parts can even be interlaced to obtain high-quality solutions in short time.</div><div>A successful computational study has been carried out with both artificial instances and three industrial scenarios, ranging from laser sensor inspection cells in the aerospace industry, to an automated cleaning room, and ending with a stud welding station for automotive applications.</div><div>The results show that geometric and industrial tests, even accounting for kinematics and distance queries, can be handled with high accuracy in reasonable computing time.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102932"},"PeriodicalIF":9.1,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0