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

Novel screw fastening manipulator for small-batch production: Multi-phase operations and Bayesian torque estimation 用于小批量生产的新型螺钉紧固机械手：多相操作和贝叶斯扭矩估计

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2026-01-08 DOI: 10.1016/j.rcim.2026.103230

Gaokun Shi , Zhijian Wang , Guodong Lu , Hassen Nigatu

Screw fastening is a ubiquitous yet automation-resistant task in machinery assembly, particularly in small-batch production where flexibility, cost, and space constraints limit the adoption of conventional robotic systems. Existing solutions often rely on multi-motor designs with complex mechanisms and controls, resulting in high costs, bulky structures, and limited adaptability to varying screw types or confined workspaces. This paper presents a novel screw fastening manipulator that addresses these challenges through mechanical simplification and functional integration. The proposed two-actuator design automates four essential operations – grasping, pressing, tightening, and releasing – within a compact and efficient form factor. A cable-driven reorientation mechanism enables precise screw alignment in restricted environments, while the screw fastening manipulator autonomously regulates the screw feed rate, enabling the robot arm to remain stationary during the tightening process. This decoupling reduces system complexity and ensures consistent screw insertion. Furthermore, a physics-based Bayesian inference model is employed for real-time torque estimation and autonomous phase detection without the need for additional sensors. This sensorless control approach enhances system robustness, reduces hardware dependencies, and ensures optimal torque application through probabilistic decision-making. Experimental validations using M2.5–M6 ISO metric screws – common in home appliance assembly – demonstrate the adaptability, precision, and suitability of the screw fastening manipulator for constrained, small-batch manufacturing environment.

螺钉紧固是机械装配中普遍存在的自动化任务，特别是在小批量生产中，灵活性、成本和空间限制限制了传统机器人系统的采用。现有的解决方案通常依赖于具有复杂机构和控制的多电机设计，导致成本高，结构笨重，对不同螺杆类型或受限工作空间的适应性有限。本文提出了一种新型的螺钉紧固机械手，通过机械简化和功能集成来解决这些问题。提出的两个致动器设计自动化四个基本操作-抓取，按压，收紧和释放-在一个紧凑和高效的形式因素。钢丝绳驱动的重定向机构可以在受限环境下实现螺钉精确对准，螺钉紧固机械手可以自主调节螺钉进给速率，使机械臂在紧固过程中保持静止。这种分离降低了系统的复杂性，并确保了螺杆插入的一致性。此外，在不需要额外传感器的情况下，采用基于物理的贝叶斯推理模型进行实时扭矩估计和自主相位检测。这种无传感器控制方法增强了系统的鲁棒性，减少了硬件依赖性，并通过概率决策确保了最佳扭矩应用。使用家用电器装配中常见的M2.5-M6 ISO公制螺钉进行实验验证，证明了螺钉紧固机械手在受限的小批量制造环境中的适应性、精度和适用性。

{"title":"Novel screw fastening manipulator for small-batch production: Multi-phase operations and Bayesian torque estimation","authors":"Gaokun Shi , Zhijian Wang , Guodong Lu , Hassen Nigatu","doi":"10.1016/j.rcim.2026.103230","DOIUrl":"10.1016/j.rcim.2026.103230","url":null,"abstract":"<div><div>Screw fastening is a ubiquitous yet automation-resistant task in machinery assembly, particularly in small-batch production where flexibility, cost, and space constraints limit the adoption of conventional robotic systems. Existing solutions often rely on multi-motor designs with complex mechanisms and controls, resulting in high costs, bulky structures, and limited adaptability to varying screw types or confined workspaces. This paper presents a novel screw fastening manipulator that addresses these challenges through mechanical simplification and functional integration. The proposed two-actuator design automates four essential operations – grasping, pressing, tightening, and releasing – within a compact and efficient form factor. A cable-driven reorientation mechanism enables precise screw alignment in restricted environments, while the screw fastening manipulator autonomously regulates the screw feed rate, enabling the robot arm to remain stationary during the tightening process. This decoupling reduces system complexity and ensures consistent screw insertion. Furthermore, a physics-based Bayesian inference model is employed for real-time torque estimation and autonomous phase detection without the need for additional sensors. This sensorless control approach enhances system robustness, reduces hardware dependencies, and ensures optimal torque application through probabilistic decision-making. Experimental validations using M2.5–M6 ISO metric screws – common in home appliance assembly – demonstrate the adaptability, precision, and suitability of the screw fastening manipulator for constrained, small-batch manufacturing environment.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103230"},"PeriodicalIF":11.4,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940158","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

Non-prehensile tool-object manipulation by integrating LLM-based planning and manoeuvrability-driven controls 整合基于llm的规划和机动性驱动控制的不可抓握工具-对象操纵

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2026-01-07 DOI: 10.1016/j.rcim.2026.103231

Hoi-Yin Lee , Peng Zhou , Anqing Duan , Wanyu Ma , Chenguang Yang , David Navarro-Alarcon

The ability to wield tools was once considered exclusive to human intelligence, but it is now known that many other animals, like crows, possess this capability. Yet, robotic systems still fall short of matching biological dexterity. In this paper, we investigate the use of Large Language Models (LLMs), tool affordances, and object manoeuvrability for non-prehensile tool-based manipulation tasks. Our novel method leverages LLMs based on scene information and natural language instructions to enable symbolic task planning for tool-object manipulation. This approach allows the system to convert a human language sentence into a sequence of feasible motion functions. We have developed a novel manoeuvrability-driven controller using a new tool affordance model derived from visual feedback. This controller helps guide the robot’s tool utilization and manipulation actions, even within confined areas, using a stepping incremental approach. The proposed methodology is evaluated with experiments to prove its effectiveness under various manipulation scenarios.

使用工具的能力曾经被认为是人类智慧的专利，但现在人们知道，许多其他动物，如乌鸦，也拥有这种能力。然而，机器人系统仍然无法与生物的灵巧性相匹配。在本文中，我们研究了大型语言模型（llm）、工具可视性和对象可操作性在非可掌握的基于工具的操作任务中的使用。我们的新方法利用基于场景信息和自然语言指令的llm来实现工具对象操作的符号任务规划。这种方法允许系统将人类语言句子转换成一系列可行的运动函数。我们开发了一种新的机动驱动的控制器，使用了一种来自视觉反馈的新的工具功能模型。该控制器有助于指导机器人的工具利用和操作动作，即使在有限的区域内，使用步进增量方法。通过实验验证了该方法在不同操作场景下的有效性。

{"title":"Non-prehensile tool-object manipulation by integrating LLM-based planning and manoeuvrability-driven controls","authors":"Hoi-Yin Lee , Peng Zhou , Anqing Duan , Wanyu Ma , Chenguang Yang , David Navarro-Alarcon","doi":"10.1016/j.rcim.2026.103231","DOIUrl":"10.1016/j.rcim.2026.103231","url":null,"abstract":"<div><div>The ability to wield tools was once considered exclusive to human intelligence, but it is now known that many other animals, like crows, possess this capability. Yet, robotic systems still fall short of matching biological dexterity. In this paper, we investigate the use of Large Language Models (LLMs), tool affordances, and object manoeuvrability for non-prehensile tool-based manipulation tasks. Our novel method leverages LLMs based on scene information and natural language instructions to enable symbolic task planning for tool-object manipulation. This approach allows the system to convert a human language sentence into a sequence of feasible motion functions. We have developed a novel manoeuvrability-driven controller using a new tool affordance model derived from visual feedback. This controller helps guide the robot’s tool utilization and manipulation actions, even within confined areas, using a stepping incremental approach. The proposed methodology is evaluated with experiments to prove its effectiveness under various manipulation scenarios.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103231"},"PeriodicalIF":11.4,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940156","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 review on cutting chatter detection and suppression in robotic milling 机器人铣削中切削颤振检测与抑制研究进展

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2026-01-06 DOI: 10.1016/j.rcim.2025.103219

Ning Li, Jiaqi Zhao, Ruiduan Sun, Li Cui, Xin Wang

Robotic milling offers high manufacturing flexibility and reduced tooling costs for machining large, complex workpieces, but its inherently low structural stiffness makes it highly prone to cutting chatter. Chatter deteriorates surface quality and dimensional accuracy, accelerates tool wear, and may compromise robotic system safety. This review comprehensively examines cutting chatter in robotic milling, focusing on mechanisms, monitoring, and suppression strategies. First, it analyses robot-specific chatter mechanisms, including regenerative and modal coupling effects, posture-dependent compliant multi-body dynamics, and nonlinear chatter phenomena within unified rigid–flexible and multi-body dynamic frameworks. Second, chatter monitoring and diagnosis methods are summarised, spanning classical time–frequency and cyclostationary analysis to advanced data-driven and deep learning techniques, with emphasis on multi-sensor fusion and real-time edge deployment in robotic settings. Third, chatter suppression and control strategies are reviewed, covering machining parameter and robot pose optimisation, passive and active damping (e.g., tuned mass dampers, smart materials), and emerging reinforcement learning techniques and digital twin-based approaches. Unlike prior surveys focusing on conventional CNC machines or treating dynamics, detection, and control in isolation, this review uniquely addresses the interplay of posture-dependent robot dynamics with chatter across all stages. By highlighting distinctive challenges such as nonlinear chatter in compliant robotic systems and discussing state-of-the-art solutions, it clarifies research gaps and provides guidance for achieving stable, high-precision robotic milling.

机器人铣削为加工大型复杂工件提供了高制造灵活性和降低刀具成本，但其固有的低结构刚度使其极易产生切削颤振。颤振会使表面质量和尺寸精度恶化，加速刀具磨损，并可能危及机器人系统的安全。这篇综述全面研究了机器人铣削中的切削颤振，重点是机制、监测和抑制策略。首先，分析了机器人特有的颤振机制，包括再生和模态耦合效应、姿态相关的柔性多体动力学以及统一刚柔和多体动力学框架下的非线性颤振现象。其次，总结了颤振监测和诊断方法，从经典的时频和周期平稳分析到先进的数据驱动和深度学习技术，重点是多传感器融合和机器人设置中的实时边缘部署。第三，回顾了颤振抑制和控制策略，包括加工参数和机器人姿态优化，被动和主动阻尼（例如，调谐质量阻尼器，智能材料），以及新兴的强化学习技术和基于数字孪生的方法。与以往的研究不同，以往的研究主要集中在传统的数控机床上，或者孤立地处理动力学、检测和控制问题，本综述独特地解决了姿态依赖的机器人动力学与所有阶段的颤振的相互作用。通过强调柔性机器人系统中的非线性颤振等独特挑战，并讨论最先进的解决方案，它澄清了研究差距，并为实现稳定、高精度的机器人铣削提供了指导。

{"title":"A review on cutting chatter detection and suppression in robotic milling","authors":"Ning Li, Jiaqi Zhao, Ruiduan Sun, Li Cui, Xin Wang","doi":"10.1016/j.rcim.2025.103219","DOIUrl":"10.1016/j.rcim.2025.103219","url":null,"abstract":"<div><div>Robotic milling offers high manufacturing flexibility and reduced tooling costs for machining large, complex workpieces, but its inherently low structural stiffness makes it highly prone to cutting chatter. Chatter deteriorates surface quality and dimensional accuracy, accelerates tool wear, and may compromise robotic system safety. This review comprehensively examines cutting chatter in robotic milling, focusing on mechanisms, monitoring, and suppression strategies. First, it analyses robot-specific chatter mechanisms, including regenerative and modal coupling effects, posture-dependent compliant multi-body dynamics, and nonlinear chatter phenomena within unified rigid–flexible and multi-body dynamic frameworks. Second, chatter monitoring and diagnosis methods are summarised, spanning classical time–frequency and cyclostationary analysis to advanced data-driven and deep learning techniques, with emphasis on multi-sensor fusion and real-time edge deployment in robotic settings. Third, chatter suppression and control strategies are reviewed, covering machining parameter and robot pose optimisation, passive and active damping (e.g., tuned mass dampers, smart materials), and emerging reinforcement learning techniques and digital twin-based approaches. Unlike prior surveys focusing on conventional CNC machines or treating dynamics, detection, and control in isolation, this review uniquely addresses the interplay of posture-dependent robot dynamics with chatter across all stages. By highlighting distinctive challenges such as nonlinear chatter in compliant robotic systems and discussing state-of-the-art solutions, it clarifies research gaps and provides guidance for achieving stable, high-precision robotic milling.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103219"},"PeriodicalIF":11.4,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145902455","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

An enhanced sample generation method for improving flexibility in human-robot cooperative disassembly of end-of-life products 一种改进的样本生成方法，以提高人机协作拆卸报废产品的灵活性

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2026-01-03 DOI: 10.1016/j.rcim.2025.103218

Yicong Gao , Chen Xu , Shanhe Lou , Jianrong Tan

Industrial manufacturing is evolving towards adaptable and intelligent frameworks. Remanufacturing plays a critical role in promoting resource efficiency and resilience, particularly within the paradigm of Industry 5.0. As a foundational step in remanufacturing, disassembly benefits significantly from human-robot cooperative disassembly (HRCD), which synergistically integrates manual dexterity with robotic repeatability. However, uncertainties such as rusty screws might disable the pre-defined disassembly schedules. Computer vision systems (CVS) are integrated into HRCD to assess rusty screws and assist task allocation. Due to the combinatorial complexity of defects, the efficacy of CVS is constrained by the lack of varied defect datasets. This paper proposes the Physics-Constrained Defect Style Transfer Network (PhysDef-STN) to generate samples of screws with diverse types and severities of rusty screws. Realistic scenarios of screw rust were investigated and modeled for deriving related formulas under physicochemical limitations, which was employed as the unique physics-inspired loss function and incorporated into PhysDef-STN to generate high-quality and diversified images of rusty screws. These generated samples resolve the critical challenge of insufficient defect datasets and enable robust and precise detection of varied uncertain screw conditions that hindered adaptive task allocation. Experimental validation confirms that the dataset generated by PhysDef-STN substantially increases the diversity of rusted screws and significantly improves the efficacy of a vision model for rust detection and classification, which achieves up to 95% identification accuracy and 88% classification accuracy. An illustrative case study demonstrates the proposed method's feasibility and practical efficacy, which involves the human-robot cooperative disassembly of a control box. The results reveal that specific uncertainties such as various types and severities of rusty screws are precisely identified and used in task assignments between human operators and robots. It significantly improves the robustness and efficiency of the disassembly process by preventing potential failures.

工业制造正朝着适应性强、智能化的框架发展。再制造在提高资源效率和弹性方面发挥着关键作用，特别是在工业5.0的范例中。作为再制造的基础步骤，人机协同拆卸（HRCD）将人工灵巧性与机器人可重复性协同结合在一起，使拆卸受益匪浅。然而，诸如生锈的螺丝等不确定因素可能会使预定义的拆卸计划失效。将计算机视觉系统（CVS）集成到HRCD中，以评估生锈的螺钉并协助任务分配。由于缺陷组合的复杂性，CVS的有效性受到缺乏不同缺陷数据集的限制。本文提出了物理约束缺陷类型转移网络（PhysDef-STN）来生成不同类型和不同程度生锈螺钉的样品。研究螺钉锈蚀的真实场景并建立模型，推导出物理化学限制下的相关公式，并将其作为独特的物理启发损失函数，整合到PhysDef-STN中，生成高质量、多样化的螺钉锈蚀图像。这些生成的样本解决了缺陷数据集不足的关键挑战，并能够鲁棒和精确地检测阻碍自适应任务分配的各种不确定螺钉条件。实验验证证实，PhysDef-STN生成的数据集大大增加了锈蚀螺钉的多样性，显著提高了视觉模型对锈蚀检测和分类的有效性，识别准确率高达95%，分类准确率高达88%。以控制箱人机协同拆卸为例，验证了该方法的可行性和实用效果。结果表明，特定的不确定性，如不同类型和严重程度的生锈螺丝被精确识别并用于人类操作员和机器人之间的任务分配。它通过防止潜在故障显著提高了拆卸过程的鲁棒性和效率。

{"title":"An enhanced sample generation method for improving flexibility in human-robot cooperative disassembly of end-of-life products","authors":"Yicong Gao , Chen Xu , Shanhe Lou , Jianrong Tan","doi":"10.1016/j.rcim.2025.103218","DOIUrl":"10.1016/j.rcim.2025.103218","url":null,"abstract":"<div><div>Industrial manufacturing is evolving towards adaptable and intelligent frameworks. Remanufacturing plays a critical role in promoting resource efficiency and resilience, particularly within the paradigm of Industry 5.0. As a foundational step in remanufacturing, disassembly benefits significantly from human-robot cooperative disassembly (HRCD), which synergistically integrates manual dexterity with robotic repeatability. However, uncertainties such as rusty screws might disable the pre-defined disassembly schedules. Computer vision systems (CVS) are integrated into HRCD to assess rusty screws and assist task allocation. Due to the combinatorial complexity of defects, the efficacy of CVS is constrained by the lack of varied defect datasets. This paper proposes the Physics-Constrained Defect Style Transfer Network (PhysDef-STN) to generate samples of screws with diverse types and severities of rusty screws. Realistic scenarios of screw rust were investigated and modeled for deriving related formulas under physicochemical limitations, which was employed as the unique physics-inspired loss function and incorporated into PhysDef-STN to generate high-quality and diversified images of rusty screws. These generated samples resolve the critical challenge of insufficient defect datasets and enable robust and precise detection of varied uncertain screw conditions that hindered adaptive task allocation. Experimental validation confirms that the dataset generated by PhysDef-STN substantially increases the diversity of rusted screws and significantly improves the efficacy of a vision model for rust detection and classification, which achieves up to 95% identification accuracy and 88% classification accuracy. An illustrative case study demonstrates the proposed method's feasibility and practical efficacy, which involves the human-robot cooperative disassembly of a control box. The results reveal that specific uncertainties such as various types and severities of rusty screws are precisely identified and used in task assignments between human operators and robots. It significantly improves the robustness and efficiency of the disassembly process by preventing potential failures.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103218"},"PeriodicalIF":11.4,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145894581","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

Modal-aware vibration evaluation and suppression method for robotic milling 铣削机器人模态感知振动评估与抑制方法

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2026-01-03 DOI: 10.1016/j.rcim.2025.103220

Zhao-Yang Liao , Hai-Long Xie , Bing Li , Yu Peng , Xue-Feng Zhou

Robotic milling is prone to chatter instability due to the inherent low stiffness of industrial manipulators, which significantly compromises machining accuracy. Accurate prediction of milling stability requires knowledge of the tool tip Frequency Response Function (FRF), which is closely related to the tool tip dynamics and highly sensitive to the robot’s posture. Traditional methods for obtaining the FRF rely on extensive experimental measurements and struggle to capture large variations in dynamic parameters across complex toolpaths. To address this challenge, this work proposes a modal-aware strategy for robotic vibration evaluation and suppression. A novel prediction method is developed by integrating Generative Adversarial Networks (GAN) with Gaussian Process Regression (GPR), enabling efficient estimation of robot modal parameters across the entire workspace. The proposed framework demonstrates strong robustness to joint angle noise and posture variations, ensuring reliable dynamic prediction under real-world machining uncertainties. Based on the predicted modal data, a stability indicator is constructed, and a posture optimization strategy is introduced by leveraging the robot’s kinematic redundancy to enhance dynamic stability during milling. Both simulation and experimental results demonstrate the effectiveness of the proposed strategy in improving machining stability, reducing energy entropy, and enhancing surface quality. Compared with traditional GPR, the proposed model achieves an

R^{2}

improvement of approximately 10% in modal parameter prediction.

由于工业机械臂固有的低刚度，机器人铣削容易产生颤振不稳定，这严重影响了加工精度。铣削稳定性的准确预测需要了解刀尖频响函数（FRF），它与刀尖动力学密切相关，对机器人的姿态高度敏感。获取FRF的传统方法依赖于大量的实验测量，难以捕获复杂刀具路径上动态参数的大变化。为了解决这一挑战，本工作提出了一种用于机器人振动评估和抑制的模态感知策略。将生成对抗网络（GAN）与高斯过程回归（GPR）相结合，提出了一种新的预测方法，能够在整个工作空间内有效地估计机器人模态参数。该框架对关节角度噪声和姿态变化具有较强的鲁棒性，确保了在实际加工不确定性下的可靠动态预测。基于预测的模态数据，构造了稳定性指标，并利用机器人的运动冗余引入姿态优化策略，提高铣削过程的动态稳定性。仿真和实验结果均证明了该策略在提高加工稳定性、降低能量熵和提高表面质量方面的有效性。与传统探地雷达模型相比，该模型的模态参数预测R2提高了约10%。

{"title":"Modal-aware vibration evaluation and suppression method for robotic milling","authors":"Zhao-Yang Liao , Hai-Long Xie , Bing Li , Yu Peng , Xue-Feng Zhou","doi":"10.1016/j.rcim.2025.103220","DOIUrl":"10.1016/j.rcim.2025.103220","url":null,"abstract":"<div><div>Robotic milling is prone to chatter instability due to the inherent low stiffness of industrial manipulators, which significantly compromises machining accuracy. Accurate prediction of milling stability requires knowledge of the tool tip Frequency Response Function (FRF), which is closely related to the tool tip dynamics and highly sensitive to the robot’s posture. Traditional methods for obtaining the FRF rely on extensive experimental measurements and struggle to capture large variations in dynamic parameters across complex toolpaths. To address this challenge, this work proposes a modal-aware strategy for robotic vibration evaluation and suppression. A novel prediction method is developed by integrating Generative Adversarial Networks (GAN) with Gaussian Process Regression (GPR), enabling efficient estimation of robot modal parameters across the entire workspace. The proposed framework demonstrates strong robustness to joint angle noise and posture variations, ensuring reliable dynamic prediction under real-world machining uncertainties. Based on the predicted modal data, a stability indicator is constructed, and a posture optimization strategy is introduced by leveraging the robot’s kinematic redundancy to enhance dynamic stability during milling. Both simulation and experimental results demonstrate the effectiveness of the proposed strategy in improving machining stability, reducing energy entropy, and enhancing surface quality. Compared with traditional GPR, the proposed model achieves an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> improvement of approximately 10% in modal parameter prediction.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103220"},"PeriodicalIF":11.4,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145894582","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

Learning-based robotic machining error prediction for high precision manufacturing 基于学习的高精度机器人加工误差预测

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2026-01-02 DOI: 10.1016/j.rcim.2025.103217

Chaoyue Niu , Bin Chen , Simon Fletcher , Peace Onawumi , Erdem Ozturk , Mahdi Mahfouf , Visakan Kadirkamanathan

High precision machining with robots is an open challenge. Achieving precision of dimensional and geometrical features with robotic machining would require compensation via feedback control which relies on accurate error prediction. Machining error prediction is a complex problem in high-precision manufacturing, where effective solutions must accurately estimate geometrical errors in different workpieces while minimizing quality inspection costs. It is also compounded by the need for real-time estimation for feedback control. This paper introduces a novel approach for predicting the quality of milled workpieces using low-cost, in-process signals and machine learning. The proposed method fuses internal machine controller commands—comprising end-effector trajectory coordinates and angular changes of six revolute joints in the robotic arm—with external laser tracker sensing signals that capture the real trajectory of the milling tool and predicts dimensional errors as would be obtained by a Coordinate Measuring Machine (CMM). To overcome the lack of knowledge of the dependence of the part dimensional error on the available signals, models with varying combinations of the sensors and the length of the time window of historical data for inclusion in the model were evaluated. In addition, five machine learning algorithms were selected, trained, evaluated and validated on data from two distinct workpieces and various spatial configurations. The best machine learning model achieved a sevenfold improvement in dimensional error prediction compared to solely using laser tracker data, with mean absolute error reduced from 0.0756 mm to 0.0097 mm. This study demonstrates the feasibility of using low-cost, in-process sensing signals to predict high-precision quality dimensional data that is normally measured by costly CMMs, enabling rapid part quality inspection and significant potential cost reduction.

用机器人进行高精度加工是一个公开的挑战。机器人加工要实现尺寸和几何特征的精度，需要通过反馈控制进行补偿，而反馈控制依赖于精确的误差预测。加工误差预测是高精度制造中的一个复杂问题，有效的解决方案必须准确估计不同工件的几何误差，同时最大限度地降低质量检测成本。它还与反馈控制的实时估计需求相结合。本文介绍了一种利用低成本、过程中信号和机器学习预测铣削工件质量的新方法。该方法将机器内部控制器指令（包括末端执行器轨迹坐标和机械臂中六个旋转关节的角度变化）与外部激光跟踪器传感信号融合在一起，这些信号捕获铣刀的真实轨迹并预测由坐标测量机（CMM）获得的尺寸误差。为了克服零件尺寸误差对可用信号依赖性的缺乏，对具有不同传感器组合的模型和历史数据的时间窗口长度进行了评估。此外，在两种不同工件和不同空间配置的数据上选择、训练、评估和验证了五种机器学习算法。与仅使用激光跟踪器数据相比，最好的机器学习模型在尺寸误差预测方面实现了7倍的改进，平均绝对误差从0.0756 mm减少到0.0097 mm。本研究证明了使用低成本的过程传感信号来预测通常由昂贵的三坐标测量机测量的高精度质量尺寸数据的可行性，从而实现快速零件质量检测并显着降低潜在成本。

{"title":"Learning-based robotic machining error prediction for high precision manufacturing","authors":"Chaoyue Niu , Bin Chen , Simon Fletcher , Peace Onawumi , Erdem Ozturk , Mahdi Mahfouf , Visakan Kadirkamanathan","doi":"10.1016/j.rcim.2025.103217","DOIUrl":"10.1016/j.rcim.2025.103217","url":null,"abstract":"<div><div>High precision machining with robots is an open challenge. Achieving precision of dimensional and geometrical features with robotic machining would require compensation via feedback control which relies on accurate error prediction. Machining error prediction is a complex problem in high-precision manufacturing, where effective solutions must accurately estimate geometrical errors in different workpieces while minimizing quality inspection costs. It is also compounded by the need for real-time estimation for feedback control. This paper introduces a novel approach for predicting the quality of milled workpieces using low-cost, in-process signals and machine learning. The proposed method fuses internal machine controller commands—comprising end-effector trajectory coordinates and angular changes of six revolute joints in the robotic arm—with external laser tracker sensing signals that capture the real trajectory of the milling tool and predicts dimensional errors as would be obtained by a Coordinate Measuring Machine (CMM). To overcome the lack of knowledge of the dependence of the part dimensional error on the available signals, models with varying combinations of the sensors and the length of the time window of historical data for inclusion in the model were evaluated. In addition, five machine learning algorithms were selected, trained, evaluated and validated on data from two distinct workpieces and various spatial configurations. The best machine learning model achieved a sevenfold improvement in dimensional error prediction compared to solely using laser tracker data, with mean absolute error reduced from 0.0756 mm to 0.0097 mm. This study demonstrates the feasibility of using low-cost, in-process sensing signals to predict high-precision quality dimensional data that is normally measured by costly CMMs, enabling rapid part quality inspection and significant potential cost reduction.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"100 ","pages":"Article 103217"},"PeriodicalIF":11.4,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886408","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 unified framework for large language model-guided reinforcement learning in digital twin industrial environments 数字孪生工业环境中大型语言模型引导强化学习的统一框架

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2025-12-31 DOI: 10.1016/j.rcim.2025.103215

Haolin Fan , Edward Chow , Thomas Lu , Jerry Ying Hsi Fuh , Wen Feng Lu , Bingbing Li

Digital twin (DT) optimization in industrial environments faces persistent challenges, including sample inefficiency, extensive training requirements, and limited cross-domain adaptability. This paper presents a unified three-phase framework that integrates large language models (LLMs) with reinforcement learning (RL) via imitation learning (IL). The proposed approach comprises three key components: (1) offline expert demonstration collection using LLM-generated multi-agent coordination strategies, (2) offline and supervised IL to clone these strategies using a centralized training and decentralized execution (CTDE) architecture, and (3) lightweight RL fine-tuning to optimize the pre-trained policy. The system resolves equipment assignment conflicts and leverages coordination history for adaptive decision-making. Experiments in multi-agent industrial scenarios, including human–machine collaboration and fatigue-aware maintenance, demonstrate that our IL+RL hybrid reduces online training time by up to 96% while maintaining over 66% of optimal task performance, using only 4% of the training episodes required by standard RL. The approach also achieves 30%–40% task completion in zero-shot cross-domain settings (e.g., warehouse, manufacturing), and up to 99.7% with minimal fine-tuning. Conceptually, the framework establishes a new paradigm of ”language-conditioned IL,” where reasoning from general-purpose LLMs serves as an adaptive prior for efficient multi-agent coordination in DT. The results highlight how LLM-guided demonstrations can bridge symbolic reasoning and adaptive learning, offering both conceptual and practical advances for scalable, sample-efficient decision-making in Industry 5.0 systems.

工业环境中的数字孪生（DT）优化面临着持续的挑战，包括样本效率低下、广泛的培训要求和有限的跨领域适应性。本文提出了一个统一的三阶段框架，该框架通过模仿学习（IL）将大型语言模型（llm）与强化学习（RL）集成在一起。该方法包括三个关键部分：(1)使用llm生成的多智能体协调策略的离线专家演示集合，(2)使用集中训练和分散执行（CTDE）架构的离线和监督IL克隆这些策略，以及(3)轻量级RL微调以优化预训练策略。该系统解决了设备分配冲突，并利用协调历史进行自适应决策。在多智能体工业场景中的实验，包括人机协作和疲劳感知维护，表明我们的IL+RL混合方法将在线训练时间减少了96%，同时保持了超过66%的最佳任务性能，仅使用标准RL所需的4%的训练集。该方法还可以在零射击跨域设置（例如，仓库，制造）中实现30%-40%的任务完成率，并且在最小的微调下达到99.7%。从概念上讲，该框架建立了一个“语言条件IL”的新范式，其中来自通用llm的推理作为DT中有效的多代理协调的自适应先验。研究结果强调了法学硕士指导下的演示如何在符号推理和自适应学习之间架起桥梁，为工业5.0系统中可扩展的、样本高效的决策提供概念和实践上的进步。

{"title":"A unified framework for large language model-guided reinforcement learning in digital twin industrial environments","authors":"Haolin Fan , Edward Chow , Thomas Lu , Jerry Ying Hsi Fuh , Wen Feng Lu , Bingbing Li","doi":"10.1016/j.rcim.2025.103215","DOIUrl":"10.1016/j.rcim.2025.103215","url":null,"abstract":"<div><div>Digital twin (DT) optimization in industrial environments faces persistent challenges, including sample inefficiency, extensive training requirements, and limited cross-domain adaptability. This paper presents a unified three-phase framework that integrates large language models (LLMs) with reinforcement learning (RL) via imitation learning (IL). The proposed approach comprises three key components: (1) offline expert demonstration collection using LLM-generated multi-agent coordination strategies, (2) offline and supervised IL to clone these strategies using a centralized training and decentralized execution (CTDE) architecture, and (3) lightweight RL fine-tuning to optimize the pre-trained policy. The system resolves equipment assignment conflicts and leverages coordination history for adaptive decision-making. Experiments in multi-agent industrial scenarios, including human–machine collaboration and fatigue-aware maintenance, demonstrate that our IL+RL hybrid reduces online training time by up to 96% while maintaining over 66% of optimal task performance, using only 4% of the training episodes required by standard RL. The approach also achieves 30%–40% task completion in zero-shot cross-domain settings (e.g., warehouse, manufacturing), and up to 99.7% with minimal fine-tuning. Conceptually, the framework establishes a new paradigm of ”language-conditioned IL,” where reasoning from general-purpose LLMs serves as an adaptive prior for efficient multi-agent coordination in DT. The results highlight how LLM-guided demonstrations can bridge symbolic reasoning and adaptive learning, offering both conceptual and practical advances for scalable, sample-efficient decision-making in Industry 5.0 systems.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103215"},"PeriodicalIF":11.4,"publicationDate":"2025-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883839","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

Constructing production equipment portraits and their realtime summarization for enabling automatic problem formulation in smart job scheduling 构建生产设备画像及其实时汇总，实现智能作业调度中问题的自动制定

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2025-12-30 DOI: 10.1016/j.rcim.2025.103212

Jiaxiang Xie , Mingyuan Liu , Guofu Ding , Jian Zhang , Jianlin Fu , Haojie Chen

Disruptions in manufacturing workshops, such as new tasks or equipment breakdowns, frequently invalidate the current schedule, necessitating not only schedule adjustments but also the rapid redefinition of the scheduling problem itself. Although advanced scheduling frameworks have been developed for specific scheduling problems, a critical gap remains in a mechanism that can perform automatic problem formulation to respond to disruptions. Specifically, there is a lack of methods for automatically and effectively integrating complex and diverse equipment capability information into problem constraints. To address this, we propose a novel portrait-driven smart job scheduling paradigm. This paradigm introduces the perspective of a dynamic equipment capability portrait, which automatically abstracts raw equipment data into scheduling constraints. Therefore, this paradigm closes the loop from situation perception to problem definition, formulation, solving, and result interpretation. To support this novel paradigm, we propose a Hierarchical Production Equipment Capability Portrait (HPECP) method, which extends traditional self-portrait-based equipment portrait methods into task-driven portraits for decision-makers, thereby providing consistent and interpretable capability representations as well as constraints for the scheduling problem formulation. Additionally, to ensure its generalization and effectiveness in dynamic workshops, a technical implementation framework is proposed with four core components: standardized capability profile construction, task-capability relevance modeling, dynamic portrait reorganization, as well as a parameter-optimized strategy for the portrait reorganization process. At last, a simulation case derived from an actual workshop was performed to validate and analyze the effectiveness of the proposed paradigm. Analysis results demonstrated that the proposed HPECP method/technical framework provides an effective foundation for automatic problem formulation, thereby supporting future implementation and promotion of portrait-driven smart job scheduling in real workshops.

制造车间的中断，例如新的任务或设备故障，经常使当前的计划无效，不仅需要调整计划，而且需要快速重新定义计划问题本身。尽管针对特定的调度问题已经开发了先进的调度框架，但在能够执行自动问题制定以响应中断的机制方面仍然存在重大差距。具体而言，缺乏将复杂多样的设备能力信息自动有效地集成到问题约束中的方法。为了解决这个问题，我们提出了一种新的肖像驱动的智能作业调度范式。该范式引入了动态设备能力画像的视角，自动将原始设备数据抽象为调度约束。因此，这种范式封闭了从情境感知到问题定义、制定、解决和结果解释的循环。为了支持这种新范式，我们提出了一种分层生产设备能力画像（HPECP）方法，该方法将传统的基于自画像的设备画像方法扩展为决策者的任务驱动画像，从而为调度问题的制定提供一致和可解释的能力表示以及约束。此外，为了确保其在动态车间中的通用性和有效性，提出了一个技术实现框架，该框架包含四个核心组件：标准化能力轮廓构建、任务-能力关联建模、动态肖像重组以及肖像重组过程的参数优化策略。最后，通过一个实际车间的仿真案例，验证和分析了所提范式的有效性。分析结果表明，所提出的HPECP方法/技术框架为问题的自动制定提供了有效的基础，从而支持肖像驱动的智能作业调度未来在实际车间的实施和推广。

{"title":"Constructing production equipment portraits and their realtime summarization for enabling automatic problem formulation in smart job scheduling","authors":"Jiaxiang Xie , Mingyuan Liu , Guofu Ding , Jian Zhang , Jianlin Fu , Haojie Chen","doi":"10.1016/j.rcim.2025.103212","DOIUrl":"10.1016/j.rcim.2025.103212","url":null,"abstract":"<div><div>Disruptions in manufacturing workshops, such as new tasks or equipment breakdowns, frequently invalidate the current schedule, necessitating not only schedule adjustments but also the rapid redefinition of the scheduling problem itself. Although advanced scheduling frameworks have been developed for specific scheduling problems, a critical gap remains in a mechanism that can perform automatic problem formulation to respond to disruptions. Specifically, there is a lack of methods for automatically and effectively integrating complex and diverse equipment capability information into problem constraints. To address this, we propose a novel portrait-driven smart job scheduling paradigm. This paradigm introduces the perspective of a dynamic equipment capability portrait, which automatically abstracts raw equipment data into scheduling constraints. Therefore, this paradigm closes the loop from situation perception to problem definition, formulation, solving, and result interpretation. To support this novel paradigm, we propose a Hierarchical Production Equipment Capability Portrait (HPECP) method, which extends traditional self-portrait-based equipment portrait methods into task-driven portraits for decision-makers, thereby providing consistent and interpretable capability representations as well as constraints for the scheduling problem formulation. Additionally, to ensure its generalization and effectiveness in dynamic workshops, a technical implementation framework is proposed with four core components: standardized capability profile construction, task-capability relevance modeling, dynamic portrait reorganization, as well as a parameter-optimized strategy for the portrait reorganization process. At last, a simulation case derived from an actual workshop was performed to validate and analyze the effectiveness of the proposed paradigm. Analysis results demonstrated that the proposed HPECP method/technical framework provides an effective foundation for automatic problem formulation, thereby supporting future implementation and promotion of portrait-driven smart job scheduling in real workshops.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103212"},"PeriodicalIF":11.4,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883837","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

3DprintMIND: An AI-Agent system using large language models and dynamic manufacturing knowledge graphs for smart manufacturing 3DprintMIND：使用大型语言模型和动态制造知识图的AI-Agent系统，用于智能制造

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2025-12-30 DOI: 10.1016/j.rcim.2025.103214

Laiyi Li, Yongwen Zhang, Inno Lorren Désir Makanda, Pingyu Jiang

As an advanced manufacturing paradigm, 3D printing offers significant opportunities for smart manufacturing (SM). However, the prevalence of data silos in its production lines frequently hinders effective process analysis and decision-making. While large language models (LLMs) possess powerful analytical capabilities, their reliability in industrial scenarios is constrained by hallucinations and a disconnection from real-time operational data. Dynamic manufacturing knowledge graphs (MKGs), functioning as structured databases, can integrate structured and unstructured manufacturing data while providing LLMs with real-time data support. Meanwhile, the development of retrieval-augmented generation (RAG) and AI-Agent technologies provides a feasible pathway for the industrial application of LLMs. This study proposes an end-to-end framework ranging from knowledge integration to 3D printing production line applications to enable reliable LLM-driven SM. Firstly, leveraging the semantic analysis capabilities of LLMs, production data and manufacturing knowledge are integrated into a dynamic MKG. Subsequently, an advanced temporal graph network (TGN) model is developed for representation learning on the dynamic MKG, forming the retrieval foundation of an RAG system. A closed-loop manufacturing logic tailored to 3D printing production lines and a “semantic-to-structured” workflow for anomaly analysis were proposed. Finally, an AI-Agent system and a prototype software platform have been developed, and a case study on a laboratory 3D printing production line has been conducted to evaluate the TGN model’s performance and the AI-Agent system’s effectiveness. The results indicate that the dynamic MKG enables continuous learning for SM and provides industries with robust AI-driven data support. The TGN model significantly outperforms baseline models, yielding higher-quality dynamic embeddings for downstream knowledge retrieval tasks. Moreover, the AI-Agent system offers SM reliable intelligent analysis and decision support in 3D printing production lines.

作为一种先进的制造模式，3D打印为智能制造（SM）提供了重要的机会。然而，在其生产线中普遍存在的数据孤岛经常阻碍有效的过程分析和决策。虽然大型语言模型（llm）具有强大的分析能力，但它们在工业场景中的可靠性受到幻觉和与实时操作数据脱节的限制。动态制造知识图（MKGs）作为结构化数据库，可以集成结构化和非结构化制造数据，同时为llm提供实时数据支持。同时，检索增强生成（retrieval-augmented generation， RAG）和AI-Agent技术的发展为llm的产业化应用提供了可行的途径。本研究提出了一个从知识集成到3D打印生产线应用的端到端框架，以实现可靠的llm驱动的SM。首先，利用llm的语义分析能力，将生产数据和制造知识集成到动态MKG中。在此基础上，提出了一种用于动态MKG表示学习的高级时态图网络（TGN）模型，为RAG系统的检索奠定了基础。提出了适合3D打印生产线的闭环制造逻辑和异常分析的“从语义到结构”工作流。最后，开发了AI-Agent系统和原型软件平台，并在实验室3D打印生产线上进行了案例研究，以评估TGN模型的性能和AI-Agent系统的有效性。结果表明，动态MKG使SM能够持续学习，并为行业提供强大的人工智能驱动数据支持。TGN模型显著优于基线模型，为下游知识检索任务提供更高质量的动态嵌入。此外，AI-Agent系统为SM提供了可靠的3D打印生产线智能分析和决策支持。

{"title":"3DprintMIND: An AI-Agent system using large language models and dynamic manufacturing knowledge graphs for smart manufacturing","authors":"Laiyi Li, Yongwen Zhang, Inno Lorren Désir Makanda, Pingyu Jiang","doi":"10.1016/j.rcim.2025.103214","DOIUrl":"10.1016/j.rcim.2025.103214","url":null,"abstract":"<div><div>As an advanced manufacturing paradigm, 3D printing offers significant opportunities for smart manufacturing (SM). However, the prevalence of data silos in its production lines frequently hinders effective process analysis and decision-making. While large language models (LLMs) possess powerful analytical capabilities, their reliability in industrial scenarios is constrained by hallucinations and a disconnection from real-time operational data. Dynamic manufacturing knowledge graphs (MKGs), functioning as structured databases, can integrate structured and unstructured manufacturing data while providing LLMs with real-time data support. Meanwhile, the development of retrieval-augmented generation (RAG) and AI-Agent technologies provides a feasible pathway for the industrial application of LLMs. This study proposes an end-to-end framework ranging from knowledge integration to 3D printing production line applications to enable reliable LLM-driven SM. Firstly, leveraging the semantic analysis capabilities of LLMs, production data and manufacturing knowledge are integrated into a dynamic MKG. Subsequently, an advanced temporal graph network (TGN) model is developed for representation learning on the dynamic MKG, forming the retrieval foundation of an RAG system. A closed-loop manufacturing logic tailored to 3D printing production lines and a “semantic-to-structured” workflow for anomaly analysis were proposed. Finally, an AI-Agent system and a prototype software platform have been developed, and a case study on a laboratory 3D printing production line has been conducted to evaluate the TGN model’s performance and the AI-Agent system’s effectiveness. The results indicate that the dynamic MKG enables continuous learning for SM and provides industries with robust AI-driven data support. The TGN model significantly outperforms baseline models, yielding higher-quality dynamic embeddings for downstream knowledge retrieval tasks. Moreover, the AI-Agent system offers SM reliable intelligent analysis and decision support in 3D printing production lines.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103214"},"PeriodicalIF":11.4,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883838","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

Collaborative industrial product customization in real use environments through augmented reality: A case study of machine tool coolers 通过增强现实在真实使用环境中的协作工业产品定制：机床冷却器的案例研究

IF 11.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Robotics and Computer-integrated Manufacturing

Pub Date : 2025-12-26 DOI: 10.1016/j.rcim.2025.103216

Chih-Hsing Chu, Shau-Min Chen

Mass customization has become a business strategy for enabling companies to address individual customer needs at scale. Its technological realization requires design tools that enable effective engineering communication in the early design stages without the need for physical presence. This study introduces an integrated approach for collaborative industrial product customization conducted directly in real-use environments, using augmented reality (AR) technology as the interface. This study introduces an innovative augmented reality (AR)-based framework that enables customers to perform industrial product customization directly within their real-use environments, thereby transforming the conventional, time-consuming, and in-person customization process. Intelligent functions remotely accessible to on-site users through AR, such as streaming content control, ambient intelligence creation, parametric modeling, and in-situ functional simulation, facilitate the customization process via wireless networks. A real case of industrial cooler design demonstrates the feasibility of a prototyping tool implementing the proposed approach. A comparative study shows that the tool shortens customization steps that previously required hours or days to just minutes and eliminates repetitive iterations, achieving an overall efficiency improvement of over 80%. This work realizes the concept of conducting engineering design and simulation within in-situ environments through AR interfaces.

大规模定制已经成为一种商业策略，使公司能够大规模地满足个人客户的需求。它的技术实现需要设计工具，使有效的工程沟通在早期设计阶段，而不需要物理存在。本研究介绍了一种以增强现实（AR）技术为界面，直接在实际使用环境中进行协同工业产品定制的集成方法。本研究介绍了一种创新的基于增强现实（AR）的框架，该框架使客户能够直接在其实际使用环境中执行工业产品定制，从而改变了传统的、耗时的和面对面的定制过程。现场用户可以通过AR远程访问流媒体内容控制、环境智能创建、参数化建模、现场功能仿真等智能功能，通过无线网络方便定制过程。一个工业冷却器设计的实际案例证明了实现该方法的原型工具的可行性。一项比较研究表明，该工具将以前需要数小时或数天的定制步骤缩短到几分钟，并消除了重复的迭代，实现了80%以上的总体效率提高。本工作通过AR接口实现了在现场环境中进行工程设计和仿真的概念。

{"title":"Collaborative industrial product customization in real use environments through augmented reality: A case study of machine tool coolers","authors":"Chih-Hsing Chu, Shau-Min Chen","doi":"10.1016/j.rcim.2025.103216","DOIUrl":"10.1016/j.rcim.2025.103216","url":null,"abstract":"<div><div>Mass customization has become a business strategy for enabling companies to address individual customer needs at scale. Its technological realization requires design tools that enable effective engineering communication in the early design stages without the need for physical presence. This study introduces an integrated approach for collaborative industrial product customization conducted directly in real-use environments, using augmented reality (AR) technology as the interface. This study introduces an innovative augmented reality (AR)-based framework that enables customers to perform industrial product customization directly within their real-use environments, thereby transforming the conventional, time-consuming, and in-person customization process. Intelligent functions remotely accessible to on-site users through AR, such as streaming content control, ambient intelligence creation, parametric modeling, and in-situ functional simulation, facilitate the customization process via wireless networks. A real case of industrial cooler design demonstrates the feasibility of a prototyping tool implementing the proposed approach. A comparative study shows that the tool shortens customization steps that previously required hours or days to just minutes and eliminates repetitive iterations, achieving an overall efficiency improvement of over 80%. This work realizes the concept of conducting engineering design and simulation within in-situ environments through AR interfaces.</div></div>","PeriodicalId":21452,"journal":{"name":"Robotics and Computer-integrated Manufacturing","volume":"99 ","pages":"Article 103216"},"PeriodicalIF":11.4,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839890","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