Robotics and Computer-integrated Manufacturing最新文献

{"title":"Digital twin-based architecture for wire arc additive manufacturing using OPC UA","authors":"Mohammad Mahruf Mahdi ,&nbsp;Mahdi Sadeqi Bajestani ,&nbsp;Sang Do Noh ,&nbsp;Duck Bong Kim","doi":"10.1016/j.rcim.2024.102944","DOIUrl":"10.1016/j.rcim.2024.102944","url":null,"abstract":"<div><div>This paper presents a digital twin (DT)-based architecture for wire arc additive manufacturing (WAAM) utilizing Open Platform Communications Unified Architecture (OPC UA) for enhanced communication, security, and real-time control. DT is explored at both enterprise management and individual asset scales, providing a comprehensive framework for process optimization. The proposed architecture integrates advanced 3D visualization, real-time defect prediction using convolutional neural networks (CNNs), and structured data management. A practical case study involving a 6-degree-of-freedom (DOF) industrial robotic arm demonstrates the application of the architecture in a WAAM deposition scenario. The architecture's effectiveness is evaluated, focusing on anomaly detection, joint angle accuracy, and communication reliability, highlighting the integration of computer vision and cloud-based data storage. The results indicate significant improvements in defect detection, process monitoring, and real-time interaction between the physical entity and the DT, underscoring the potential of the proposed DT architecture.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"94 ","pages":"Article 102944"},"PeriodicalIF":9.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918029","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}

{"title":"Data-driven modeling and integrated optimization of machining quality and energy consumption for internal gear power honing process","authors":"You Zhang ,&nbsp;Congbo Li ,&nbsp;Ying Tang ,&nbsp;Huajun Cao ,&nbsp;Guibao Tao","doi":"10.1016/j.rcim.2024.102943","DOIUrl":"10.1016/j.rcim.2024.102943","url":null,"abstract":"<div><div>The internal gear power honing process is increasingly used in the gear machining of electric vehicles due to superior tooth surface quality. Most of the existing work only investigates the quality improvement of gear machining processes, and focuses little attention on energy saving. However, the total rated power of multi-axis motion for gear honing process reaches 60 kW, which has great energy-saving potential. To this end, this article proposes a data-driven modeling and integrated optimization method of machining quality and energy consumption for internal gear power honing process. The machining quality formation mechanism and energy consumption characteristics of gear honing process are first analyzed. A gradient-enhanced Kriging (GEK) method is then used to establish data-driven tooth profile form deviation model and energy consumption model. Furthermore, an integrated honing process optimization model considering tooth profile form deviation and energy consumption is constructed. An improved multi-objective coati optimization algorithm (IMOCOA) is used to solve the optimization problem. The experimental results show that the R-square of the GEK model reaches 0.99, which has superior modeling accuracy compared with other methods. The optimization results demonstrate that compared with the empirical scheme, the proposed integrated optimization model reduces the tooth profile form deviation and energy consumption by 38.46 % and 10.26 %, respectively. Moreover, the developed IMOCOA also presents competitive algorithm performance. The proposed integrated optimization scheme significantly balances honing machining quality and energy consumption.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"93 ","pages":"Article 102943"},"PeriodicalIF":9.1,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918030","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}

{"title":"Reviewing human-robot collaboration in manufacturing: Opportunities and challenges in the context of industry 5.0","authors":"Mandeep Dhanda,&nbsp;Benedict Alexander Rogers,&nbsp;Stephanie Hall,&nbsp;Elies Dekoninck,&nbsp;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}

{"title":"Personalized federated unsupervised learning for nozzle condition monitoring using vibration sensors in additive manufacturing","authors":"Inno Lorren Désir Makanda,&nbsp;Pingyu Jiang,&nbsp;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}

{"title":"A novel pose estimation method for robot threaded assembly pre-alignment based on binocular vision","authors":"Yi Zhang ,&nbsp;Zhonghai Song ,&nbsp;Jiuwei Yu ,&nbsp;Bingzhang Cao ,&nbsp;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}

{"title":"Reality-guided virtual assembly for contact-prohibited stepped shaft-in-hole task","authors":"Hongtai Cheng ,&nbsp;Zelong Wang,&nbsp;Xiaohan Guan,&nbsp;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}

{"title":"Strategic algorithm for cable wiring using dual arm with compliance control","authors":"Youngsu Cho ,&nbsp;Minsu Cho ,&nbsp;Jongwoo Park,&nbsp;Byung-Kil Han,&nbsp;Young Hun Lee,&nbsp;Sung-Hyuk Song,&nbsp;Chanhun Park,&nbsp;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}

{"title":"Robotic grinding of curved parts with two degrees of freedom active compliant force-controlled end-effector using decoupling control algorithm","authors":"Haiqing Chen,&nbsp;Jixiang Yang,&nbsp;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}

{"title":"DFGAT for recognizing design features from a B-rep model for mechanical parts","authors":"Jun Hwan Park ,&nbsp;Seungeun Lim ,&nbsp;Changmo Yeo ,&nbsp;Youn-Kyoung Joung ,&nbsp;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}

{"title":"A contour error prediction method for tool path correction using a multi-feature hybrid model in robotic milling systems","authors":"Shizhong Tan ,&nbsp;Congcong Ye ,&nbsp;Chengxing Wu ,&nbsp;Jixiang Yang ,&nbsp;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}