Robotics and Computer-integrated Manufacturing最新文献

{"title":"Real-time defect detection and classification in robotic assembly lines: A machine learning framework","authors":"Fadi El Kalach ,&nbsp;Mojtaba Farahani ,&nbsp;Thorsten Wuest ,&nbsp;Ramy Harik","doi":"10.1016/j.rcim.2025.103011","DOIUrl":"10.1016/j.rcim.2025.103011","url":null,"abstract":"<div><div>Manufacturing systems have witnessed a significant transformation with the introduction of Industry 4.0, introducing new capabilities with the emergence of new technologies. One such instance is the proliferation of sensors enabling the generation and acquisition of vast amounts of data, leading to advancements in Artificial Intelligence (AI) for manufacturing. One field profiting from this is that of Time Series Analytics (TSC) which includes forecasting and classification. TSC can be crucial for fault detection and diagnosis in manufacturing systems. However, there are still challenges in utilizing manufacturing datasets to train and deploy classification algorithms for real time classification. As such this paper aims to tackle these challenges by presenting a closed-loop framework for the testing and deployment process of TSC algorithms. This paper also details the feature selection and extraction process outlining specific criteria to be considered throughout. This is done by presenting a new manufacturing dataset acquired from a robotic assembly line and detailing the full process undergone in this study to train and deploy TSC algorithms on that manufacturing system.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103011"},"PeriodicalIF":9.1,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610073","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":"A five-dimensional digital twin framework driven by large language models-enhanced RL for CNC systems","authors":"Xusheng Lin ,&nbsp;Weiqiang Chen ,&nbsp;Zheng Zhou ,&nbsp;Jinhua Li ,&nbsp;Yiman Zhao ,&nbsp;Xiyang Zhang","doi":"10.1016/j.rcim.2025.103009","DOIUrl":"10.1016/j.rcim.2025.103009","url":null,"abstract":"<div><div>In response to the growing demand for intelligence and digitalization in computer numerical control (CNC) systems, particularly in virtual debugging, performance evaluation, and machining quality optimization within the manufacturing sector, this study explores the mapping process from physical entities in the physical space to twin entities in the digital twin space. It further delves into the data transmission layer that represents the physical mechanisms of these entities. By constructing multi-layered models, digital twin technology facilitates the virtual simulation and personalized services of multi-layer coupled units in CNC systems. However, given the complexity and diversity of internal units in CNC systems, traditional CNC machining systems remain overly reliant on human expertise, while existing digital twin frameworks lack effective representation and efficient optimization methods tailored to the CNC field. This paper proposes a novel five-dimensional framework for digital twins in CNC systems to address these challenges, driven by large language models-assisted enhanced reinforcement learning. The framework leverages the advantages of digital twin technology in dynamic process management and reinforcement learning in intelligent analysis and decision-making. It comprises five key layers: the physical entity layer, the virtual entity layer, the intelligent decision-making layer, the data transmission layer, and the real-time computation layer. It also encompasses multi-domain modeling, including information models, mechanism models, and digital threads, and explores how large language models (LLM) can assist and enhance reinforcement learning in CNC applications. Finally, the study applies the framework to the tool-axis vector planning problem in CNC systems, positioning the LLM as an indirect decision-maker within reinforcement learning. Experimental results demonstrate that integrating LLM-enhanced reinforcement learning algorithms within the CNC system’s digital twin framework effectively reduces tool-axis vector variation rates, thereby decreasing collision interference incidents during machining. To some extent, the proposed digital twin framework’s effectiveness has been validated, providing a valuable approach for the advancement of the CNC system field.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103009"},"PeriodicalIF":9.1,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600618","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":"Learning and planning for optimal synergistic human–robot coordination in manufacturing contexts","authors":"Samuele Sandrini ,&nbsp;Marco Faroni ,&nbsp;Nicola Pedrocchi","doi":"10.1016/j.rcim.2025.103006","DOIUrl":"10.1016/j.rcim.2025.103006","url":null,"abstract":"<div><div>Collaborative robotics cells leverage heterogeneous agents to provide agile production solutions. Effective coordination is essential to prevent inefficiencies and risks for human operators working alongside robots. This paper proposes a human-aware task allocation and scheduling model based on Mixed Integer Nonlinear Programming to optimize efficiency and safety starting from the task planning stages. The approach exploits synergies that encode the coupling effects between pairs of tasks executed in parallel by the agents, arising from the safety constraints imposed on robot agents. These terms are learned from previous executions using a Bayesian estimation; the inference of the posterior probability distribution of the synergy coefficients is performed using the Markov Chain Monte Carlo method. The synergy enhances task planning by adapting the nominal duration of the plan according to the effect of the operator’s presence. Simulations and experimental results demonstrate that the proposed method produces improved human-aware task plans, reducing useless interference between agents, increasing human–robot distance, and achieving up to an 18% reduction in process execution time.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103006"},"PeriodicalIF":9.1,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592522","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":"A two-phase approach for benefit-driven and correlation-aware service composition allocation in cloud manufacturing","authors":"Chunhua Tang ,&nbsp;Qiang Zhang ,&nbsp;Jiaming Ding ,&nbsp;Shuangyao Zhao ,&nbsp;Mark Goh","doi":"10.1016/j.rcim.2025.103007","DOIUrl":"10.1016/j.rcim.2025.103007","url":null,"abstract":"<div><div>Manufacturing service composition (MSC) is a fundamental component of cloud manufacturing that involves multiple stakeholders and associated services. Stakeholders, viewed as autonomous entities, prioritize both temporary gains and long-term benefits, while service interactions significantly influence the feasibility and quality of MSCs. Effective MSC allocation demands a strategic approach that harmonizes stakeholders’ interests and accounts for service correlations to achieve optimal outcomes. Although previous studies have explored stakeholders’ long- and short-term benefits and service correlations independently, a comprehensive framework that integrates these aspects, aligns diverse interests, and thoroughly examines service correlation impacts remains a significant challenge. To bridge this gap, this study proposes a two-phase approach for benefit-driven and correlation-aware MSC allocation. This approach integrates the long- and short-term benefits of platform operators, service requesters, and resource suppliers, as well as the effects of two types of service correlations, composability-focused and quality-focused, on MSCs. The initial phase constructs a bi-objective optimization model with maximizing operational benefits to filter and recommend MSCs. Composability-focused service correlations are incorporated in the model to ensure MSC feasibility. The second phase refines the optimal MSC selection by matching supply and demand, leveraging quality-focused service correlations to modify MSC quality. A hybrid algorithm, combining an improved fast nondominated sorting genetic algorithm (PANSGA-II) with an enhanced technique for order preference by similarity to the ideal solution (TOPSIS-PR), is developed to solve the two-phase problem. The case study and numerical experiments are conducted to validate the applicability and effectiveness of the proposed approach and algorithm.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103007"},"PeriodicalIF":9.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592521","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":"Time-series forecasting in smart manufacturing systems: An experimental evaluation of the state-of-the-art algorithms","authors":"Mojtaba A. Farahani ,&nbsp;Fadi El Kalach ,&nbsp;Austin Harper ,&nbsp;M.R. McCormick ,&nbsp;Ramy Harik ,&nbsp;Thorsten Wuest","doi":"10.1016/j.rcim.2025.103010","DOIUrl":"10.1016/j.rcim.2025.103010","url":null,"abstract":"<div><div>Time-Series Forecasting (TSF) is a growing research area across various domains including manufacturing. Manufacturing can benefit from Artificial Intelligence (AI) and Machine Learning (ML) innovations for TSF tasks. Although numerous TSF algorithms have been developed and proposed over the past decades, the critical validation and experimental evaluation of the algorithms hold substantial value for researchers and practitioners and are missing to date. This study aims to fill this research gap by providing a rigorous experimental evaluation of the state-of-the-art TSF algorithms on thirteen manufacturing-related datasets with a focus on their applicability in smart manufacturing environments. Each algorithm was selected based on the defined TSF categories to ensure a representative set of state-of-the-art algorithms. The evaluation includes different scenarios to evaluate the models using combinations of two problem categories (univariate and multivariate) and two forecasting horizons (short- and long-term). To evaluate the performance of the algorithms, the weighted average percent error was calculated for each application, and additional post hoc statistical analyses were conducted to assess the significance of observed differences. Only algorithms with accessible codes from open-source libraries were utilized, and no hyperparameter tuning was conducted. This approach allowed us to evaluate the algorithms as \"out-of-the-box\" solutions that can be easily implemented, ensuring their usability within the manufacturing sector by practitioners with limited technical knowledge of ML algorithms. This aligns with the objective of facilitating the adoption of these techniques in Industry 4.0 and smart manufacturing systems. Based on the results, transformer- and MLP-based architectures demonstrated the best performance across different scenarios with MLP-based architecture winning the most scenarios. For univariate TSF, PatchTST emerged as the most robust algorithm, particularly for long-term horizons, while for multivariate problems, MLP-based architectures like N-HITS and TiDE showed superior results. The study revealed that simpler algorithms like XGBoost could outperform more complex transformer-based in certain tasks. These findings challenge the assumption that more sophisticated models inherently produce better results. Additionally, the research highlighted the importance of computational resource considerations, showing significant variations in runtime and memory usage across different algorithms.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103010"},"PeriodicalIF":9.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577848","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":"A knowledge graph construction and causal structure mining approach for non-stationary manufacturing systems","authors":"Mingyuan Xia ,&nbsp;Xuandong Mo ,&nbsp;Yahui Zhang ,&nbsp;Xiaofeng Hu","doi":"10.1016/j.rcim.2025.103013","DOIUrl":"10.1016/j.rcim.2025.103013","url":null,"abstract":"<div><div>Knowledge graph (KG) is a method for managing multi-source heterogeneous data and forming knowledge for reasoning using graph structure. It has been extensively utilized in manufacturing systems to promote the advancement of intelligent manufacturing. In non-stationary manufacturing systems, the machining performance of individual elements demonstrates variability and dynamic fluctuations. The significant dynamics and uncertainties of a manufacturing system bring great challenges to KG's modeling, construction, and reasoning. To overcome these challenges, this paper proposes a Digital-Physical Manufacturing Knowledge Graph (DPMKG) construction and reasoning method. Firstly, an ontology-based knowledge representation model is developed to facilitate the integration of digital domain knowledge with the description of physical domain performance fluctuations, thereby establishing the schema layer of DPMKG. Secondly, a SysML model-driven construction pipeline is proposed to facilitate the correlation and integration of multi-source data from both digital and physical domains, thereby establishing the instance layer of DPMKG. Thirdly, a causal structure mining method for DPMKG is developed to enhance the analytical and reasoning capabilities in non-stationary manufacturing systems. Finally, an aero-engine casing machining system is employed as a case study to establish the DPMKG, and reasoning is performed on the process quality prediction task. The case study reveals that the proposed DPMKG modeling, construction, and reasoning approach can effectively describe and analyze performance fluctuations in the physical domain of a non-stationary manufacturing system. By integrating digital and physical domain knowledge, the extensive data can be effectively leveraged to generate knowledge for reasoning, thereby facilitating intelligent and refined control of non-stationary manufacturing systems.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103013"},"PeriodicalIF":9.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577847","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":"Towards safe motion planning for industrial human-robot interaction: A co-evolution approach based on human digital twin and mixed reality","authors":"Bohan Feng,&nbsp;Zeqing Wang,&nbsp;Lianjie Yuan,&nbsp;Qi Zhou,&nbsp;Yulin Chen,&nbsp;Youyi Bi","doi":"10.1016/j.rcim.2025.103012","DOIUrl":"10.1016/j.rcim.2025.103012","url":null,"abstract":"<div><div>Advanced human-robot interaction (HRI) is essential for the next-generation human-centric manufacturing mode such as “Industry 5.0”. Despite recent mutual cognitive approaches can enhance the understanding and collaboration between humans and robots, these methods often rely on predefined rules and are limited in adapting to new tasks or changes of the working environment. These limitations can hinder the popularization of collaborative robots in dynamic manufacturing environments, where tasks can be highly variable, and unforeseen operational changes frequently occur. To address these challenges, we propose a co-evolution approach for the safe motion planning of industrial human-robot interaction. The core idea is to promote the evolution of human worker’s safe operation cognition as well as the evolution of robot’s safe motion planning strategy in a unified and continuous framework by leveraging human digital twin (HDT) and mixed reality (MR) technologies. Specifically, HDT captures real-time human behaviors and postures, which enables robots to adapt dynamically to the changes of human behavior and environment. HDT also refines deep reinforcement learning (DRL)-based motion planning, allowing robots to continuously learn from human actions and update their motion strategies. On the other hand, MR superimposes rich information regarding the tasks and robot in the physical world, helping human workers better understand and adapt to robot’s actions. MR also provides intuitive gesture-based user interface, further improving the smoothness of human-robot interaction. We validate the proposed approach’s effectiveness with evaluations in realistic manufacturing scenarios, demonstrating its potential to advance HRI practice in the context of smart manufacturing.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 103012"},"PeriodicalIF":9.1,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143547999","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":"Transfer learning and augmented data-driven parameter prediction for robotic welding","authors":"Cheng Zhang ,&nbsp;Yingfeng Zhang ,&nbsp;Sichao Liu ,&nbsp;Lihui Wang","doi":"10.1016/j.rcim.2025.102992","DOIUrl":"10.1016/j.rcim.2025.102992","url":null,"abstract":"<div><div>Robotic welding envisioned for the future of factories will promote high-demanding and customised tasks with overall higher productivity and quality. Within the context, robotic welding parameter prediction is essential for maintaining high standards of quality, efficiency, safety, and cost-effectiveness in smart manufacturing. However, data acquisition of welding process parameters is limited by process libraries and small sample sizes, given complex welding working environments, and it also requires extensive and costly experimentation. To address these issues, this study proposes a transfer learning and augmented data-driven approach for high-accuracy prediction of robotic welding parameters. Firstly, a data space transfer method is developed to construct a domain adaptation mapping matrix, focusing on small sample welding process parameters, and a data augmentation method is adopted to transfer welding process parameters with augmented sample data. Then, a DST-Multi-XGBoost model is developed to establish a mapping relationship between welding task features and welding process parameters. The constructed model can consider the relationship between the output, which reduces the complexity of the model and the number of parameters. Even with a small initial sample size, the model can use augmented data to understand complex coupling relationships and accurately predict welding process parameters. Finally, the effectiveness of the developed approach has been experimentally validated by a case study of robotic welding.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 102992"},"PeriodicalIF":9.1,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563172","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 dual-arm robotic cooperative framework for multiple peg-in-hole assembly of large objects","authors":"Dongsheng Ge,&nbsp;Huan Zhao,&nbsp;Dianxi Li,&nbsp;Dongchen Han,&nbsp;Xiangfei Li,&nbsp;Jiexin Zhang,&nbsp;Han Ding","doi":"10.1016/j.rcim.2025.102991","DOIUrl":"10.1016/j.rcim.2025.102991","url":null,"abstract":"<div><div>Single peg-in-hole assembly of small objects has been researched extensively. However, these studies limit applicability to multiple peg-in-hole assembly of large objects, due to the complex contact state, and the large size and weight of the objects. To address these challenges, this paper proposes a dual-arm cooperative multiple peg-in-hole assembly framework (DAC-MPiH) for large objects, leveraging the capabilities of dual robots to manage larger, heavier objects. The DAC-MPiH framework comprises three key components: dual-arm force/position coordination, external force/torque estimation, and an eight-stage assembly strategy. The proposed framework integrates a compliant dynamical system (CDS) into both inner and outer control loops, ensuring robust force/position coordination and stable manipulation at the object level. The framework introduces an object parameter estimation method based on a virtual center of mass and least squares to enhance the accuracy of external force/torque estimation. The assembly strategy includes four preparation stages and four assembly stages, utilizing a CDS-based variable impedance and variable reference force controller for stable adjusting, and a hybrid force/position controller for efficient rotating. Experiments were conducted on a dual-arm robotic platform, and the results demonstrate the effectiveness of the proposed method in achieving stable and efficient multiple peg-in-hole assembly of large objects.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 102991"},"PeriodicalIF":9.1,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143508188","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":"Digital twin-enabled robotics for smart tag deployment and sensing in confined space","authors":"Alan Putranto ,&nbsp;Tzu-Hsuan Lin ,&nbsp;Ping-Ting Tsai","doi":"10.1016/j.rcim.2025.102993","DOIUrl":"10.1016/j.rcim.2025.102993","url":null,"abstract":"<div><div>The deployment of smart sensors in confined spaces presents significant challenges due to limited visibility, environmental constraints, and communication interference. This study introduces a novel integration of digital twin technology with robotics to address these challenges, enabling precise and reliable sensor deployment in complex environments such as steel box girders. The proposed system leverages a digital twin framework for real-time simulation, calibration, and monitoring, ensuring spatial consistency between virtual and physical operations. Advanced calibration methods align the robotic arm with its 3D camera coordinates, enhancing deployment accuracy. Communication robustness is achieved by strategically prioritizing critical control and sensor signals, mitigating the impact of wireless interference in confined spaces. Additionally, the system automates the deployment of RFID-based smart sensors, incorporating 3D-printed protective casings for durability in harsh conditions. Experimental results demonstrate the system's effectiveness in overcoming spatial, visibility, and communication challenges, providing a scalable solution for structural health monitoring and other industrial applications. This study contributes a holistic and innovative robotics and digital twin integration framework in confined and complex environments.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"95 ","pages":"Article 102993"},"PeriodicalIF":9.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474751","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}