Journal of Manufacturing Systems最新文献_第4页

Intelligent disassembly scenario understanding for human behavior and intention recognition towards self-perception human-robot collaboration system 面向人类行为的智能拆卸场景理解和面向自我感知人机协作系统的意图识别

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-18 DOI: 10.1016/j.jmsy.2025.11.012

Jinhua Xiao , Bo Wang , Kaile Huang , Sergio Terzi , Wei Wang , Marco Macchi

The recycling of end-of-life (EOL) products poses significant challenges due to inefficient and unsafe disassembly processes. To address this, we propose a novel self-perception human-robot collaboration (HRC) system that enhances disassembly efficiency and safety through multi-modal human intention recognition. Our core methodological innovation lies in the real-time fusion of three key perception modules: action recognition using a Spatial-Temporal Graph Convolutional Network (ST-GCN), disassembly tool detection based on an enhanced YOLO algorithm, and facial angle recognition for operator awareness inference. A dedicated dataset for retired power battery disassembly was constructed to support this research, encompassing human skeletal data for action recognition, labeled images for tool detection, and facial expression detection. The proposed system was validated on a physical HRC disassembly platform. Experimental results demonstrate a marked improvement, with our integrated intention recognition method achieving an accuracy of approximately 85 %, significantly outperforming traditional single-modality approaches. Furthermore, the HRC disassembly operation was completed in 238 s, which is 60 s (or 20 %) faster than purely manual disassembly. This work provides a robust and efficient HRC disassembly framework for intelligent disassembly scenario understanding, contributing to advancing circular manufacturing.

由于低效率和不安全的拆卸过程，报废产品的回收提出了重大挑战。为了解决这个问题，我们提出了一种新的自我感知人机协作（HRC）系统，该系统通过多模态人类意图识别来提高拆卸效率和安全性。我们的核心方法创新在于三个关键感知模块的实时融合：使用时空图卷积网络（ST-GCN）的动作识别，基于增强YOLO算法的拆卸工具检测，以及用于操作员意识推理的面部角度识别。为支持本研究，构建了退役动力电池拆卸专用数据集，包括用于动作识别的人体骨骼数据、用于工具检测的标记图像和用于面部表情检测的图像。在物理HRC拆卸平台上对该系统进行了验证。实验结果显示了显著的改进，我们的集成意图识别方法达到了大约85 %的准确率，显著优于传统的单模态方法。此外，HRC拆卸操作在238 秒内完成，比纯手动拆卸快60 秒（或20 %）。这项工作为智能拆卸场景理解提供了一个强大而高效的HRC拆卸框架，有助于推进循环制造。

{"title":"Intelligent disassembly scenario understanding for human behavior and intention recognition towards self-perception human-robot collaboration system","authors":"Jinhua Xiao , Bo Wang , Kaile Huang , Sergio Terzi , Wei Wang , Marco Macchi","doi":"10.1016/j.jmsy.2025.11.012","DOIUrl":"10.1016/j.jmsy.2025.11.012","url":null,"abstract":"<div><div>The recycling of end-of-life (EOL) products poses significant challenges due to inefficient and unsafe disassembly processes. To address this, we propose a novel self-perception human-robot collaboration (HRC) system that enhances disassembly efficiency and safety through multi-modal human intention recognition. Our core methodological innovation lies in the real-time fusion of three key perception modules: action recognition using a Spatial-Temporal Graph Convolutional Network (ST-GCN), disassembly tool detection based on an enhanced YOLO algorithm, and facial angle recognition for operator awareness inference. A dedicated dataset for retired power battery disassembly was constructed to support this research, encompassing human skeletal data for action recognition, labeled images for tool detection, and facial expression detection. The proposed system was validated on a physical HRC disassembly platform. Experimental results demonstrate a marked improvement, with our integrated intention recognition method achieving an accuracy of approximately 85 %, significantly outperforming traditional single-modality approaches. Furthermore, the HRC disassembly operation was completed in 238 s, which is 60 s (or 20 %) faster than purely manual disassembly. This work provides a robust and efficient HRC disassembly framework for intelligent disassembly scenario understanding, contributing to advancing circular manufacturing.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 937-962"},"PeriodicalIF":14.2,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145568611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Variational diffusion representation learning framework for semi-supervised industrial soft sensing application 半监督工业软测量应用的变分扩散表示学习框架

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-18 DOI: 10.1016/j.jmsy.2025.11.013

Hengqian Wang, Lei Chen, Kuangrong Hao, Bing Wei

In process manufacturing industries, existing semi-supervised soft sensor methods often exhibit compromised performance under low label rates due to poor generalization, underscoring the urgent need for extracting generalized and transferable features from unlabeled data. Recently, diffusion model-based self-supervised learning (SSL) has shown great potential in addressing this challenge by leveraging powerful generative mechanisms to capture complex data distributions and distill informative representations without extensive supervision. Motivated by this, this paper proposes a variational diffusion representation learning (VDRL) framework for semi-supervised soft sensing modeling under low label rates. First, we propose a self-supervised parametric terminal variational diffusion (PTVD) model for generalized feature extraction. By defining the forward process terminal of the diffusion model as parameterized learnable latent distributions and attempting to recover the original input samples in the reverse process, we successfully achieve a transformation in the role of the diffusion model from the original sample generator to the desired feature extractor. The designed pretext task of patch-level mask reconstruction further improves its capability on temporal data and allows the PTVD model to be trained in a self-supervised manner without the involvement of real labels. Subsequently, we propose a temporal-diffusion joint representation (TDJR) model for the prediction of quality variables based on the extracted generalized multi-granular features. In order to fully exploit the joint dynamic information of multi-granular features in different sequence dimensions, we innovatively extract joint representation information from both time and diffusion dimensions simultaneously and complementarily, and perform supervised training under limited label guidance. A series of experimental evaluations on two real industrial processes validate the framework’s effectiveness and stability in soft sensing applications.

在过程制造业中，现有的半监督软传感器方法由于泛化能力差，在低标记率下往往表现出较差的性能，这强调了从未标记数据中提取泛化和可转移特征的迫切需要。最近，基于扩散模型的自监督学习（SSL）在解决这一挑战方面显示出巨大的潜力，它利用强大的生成机制来捕获复杂的数据分布，并在没有广泛监督的情况下提取信息表示。基于此，本文提出了一种用于低标记率下半监督软感知建模的变分扩散表示学习（VDRL）框架。首先，我们提出了一种自监督参数终端变分扩散（PTVD）模型用于广义特征提取。通过将扩散模型的正向过程终端定义为参数化的可学习潜分布，并尝试在反向过程中恢复原始输入样本，我们成功地实现了扩散模型角色从原始样本生成器到所需特征提取器的转换。所设计的补片级掩码重构的托词任务进一步提高了其对时间数据的处理能力，使PTVD模型能够在不需要真实标签的情况下进行自监督训练。随后，基于提取的广义多颗粒特征，提出了一种用于质量变量预测的时间-扩散联合表示（TDJR）模型。为了充分挖掘多颗粒特征在不同序列维度上的联合动态信息，我们创新地从时间维度和扩散维度同时互补地提取联合表示信息，并在有限标签指导下进行监督训练。在两个实际工业过程中的一系列实验评估验证了该框架在软测量应用中的有效性和稳定性。

{"title":"Variational diffusion representation learning framework for semi-supervised industrial soft sensing application","authors":"Hengqian Wang, Lei Chen, Kuangrong Hao, Bing Wei","doi":"10.1016/j.jmsy.2025.11.013","DOIUrl":"10.1016/j.jmsy.2025.11.013","url":null,"abstract":"<div><div>In process manufacturing industries, existing semi-supervised soft sensor methods often exhibit compromised performance under low label rates due to poor generalization, underscoring the urgent need for extracting generalized and transferable features from unlabeled data. Recently, diffusion model-based self-supervised learning (SSL) has shown great potential in addressing this challenge by leveraging powerful generative mechanisms to capture complex data distributions and distill informative representations without extensive supervision. Motivated by this, this paper proposes a variational diffusion representation learning (VDRL) framework for semi-supervised soft sensing modeling under low label rates. First, we propose a self-supervised parametric terminal variational diffusion (PTVD) model for generalized feature extraction. By defining the forward process terminal of the diffusion model as parameterized learnable latent distributions and attempting to recover the original input samples in the reverse process, we successfully achieve a transformation in the role of the diffusion model from the original sample generator to the desired feature extractor. The designed pretext task of patch-level mask reconstruction further improves its capability on temporal data and allows the PTVD model to be trained in a self-supervised manner without the involvement of real labels. Subsequently, we propose a temporal-diffusion joint representation (TDJR) model for the prediction of quality variables based on the extracted generalized multi-granular features. In order to fully exploit the joint dynamic information of multi-granular features in different sequence dimensions, we innovatively extract joint representation information from both time and diffusion dimensions simultaneously and complementarily, and perform supervised training under limited label guidance. A series of experimental evaluations on two real industrial processes validate the framework’s effectiveness and stability in soft sensing applications.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 923-936"},"PeriodicalIF":14.2,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145568612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

STEP-compliant CNC system featuring real-time material removal simulation for online tool wear monitoring 符合step的数控系统，具有实时材料去除模拟，用于在线工具磨损监测

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-16 DOI: 10.1016/j.jmsy.2025.11.006

Tianze Qiu , Yan Liu , Wenlei Xiao , Gang Zhao , Qiang Liu

With the advancement of intelligent manufacturing, CNC systems are increasingly expected to achieve higher levels of autonomous perception and decision-making. However, conventional CNC systems relying only on sensors have limited online analysis capability in complex machining. STEP-CNC, equipped with a simulation kernel, provides rich semantic information and enables multi-domain data fusion of “simulation + sensing”, offering a novel framework for online process analysis. Taking tool wear as a case study, this paper proposes a comprehensive online monitoring solution integrated into STEP-CNC. First, the geometric simulation is executed to calculate the Cutter Workpiece Engagement (CWE) and quantify instantaneous material removal, effectively characterizing interactions with workpiece. Second, a sparse stacked autoencoder extracts and compresses informative features from multi-sensor signals, yielding compact representations correlated with wear value. Third, an incremental prediction model tailored for online applications is developed, fusing geometric, physical, and process-domain inputs to provide precise wear increment estimates over fixed time windows. Finally, the prediction model is encapsulated as a service and integrated within the STEP-CNC framework, enabling tool wear monitoring with online feedback to the CNC controller. Experimental results demonstrate that the proposed method can accurately track tool wear progression, achieving an online monitoring accuracy exceeding 89%. The monitored wear values can further assist machining decision-making, preventing tool failures and ensuring workpiece quality. The proposed method may also serve as an actionable reference for using STEP-CNC with multi-domain data in intelligent manufacturing applications.

随着智能制造的发展，人们越来越期望数控系统能够实现更高水平的自主感知和决策。然而，传统的仅依靠传感器的数控系统在复杂加工中的在线分析能力有限。STEP-CNC配备仿真内核，提供丰富的语义信息，实现“仿真+传感”的多领域数据融合，为在线过程分析提供了新的框架。以刀具磨损为例，提出了一种集成STEP-CNC的综合在线监测解决方案。首先，执行几何模拟来计算刀具工件啮合（CWE）并量化瞬时材料去除，有效表征与工件的相互作用。其次，稀疏堆叠自编码器从多传感器信号中提取和压缩信息特征，生成与磨损值相关的紧凑表示。第三，针对在线应用开发了一个增量预测模型，融合了几何、物理和过程域的输入，在固定的时间窗口内提供精确的磨损增量估计。最后，将预测模型封装为服务并集成到STEP-CNC框架中，从而实现刀具磨损监测，并在线反馈给CNC控制器。实验结果表明，该方法能准确地跟踪刀具磨损过程，在线监测精度超过89%。监测的磨损值可以进一步辅助加工决策，防止刀具失效，确保工件质量。该方法也为STEP-CNC在智能制造中多领域数据的应用提供了可操作的参考。

{"title":"STEP-compliant CNC system featuring real-time material removal simulation for online tool wear monitoring","authors":"Tianze Qiu , Yan Liu , Wenlei Xiao , Gang Zhao , Qiang Liu","doi":"10.1016/j.jmsy.2025.11.006","DOIUrl":"10.1016/j.jmsy.2025.11.006","url":null,"abstract":"<div><div>With the advancement of intelligent manufacturing, CNC systems are increasingly expected to achieve higher levels of autonomous perception and decision-making. However, conventional CNC systems relying only on sensors have limited online analysis capability in complex machining. STEP-CNC, equipped with a simulation kernel, provides rich semantic information and enables multi-domain data fusion of “simulation + sensing”, offering a novel framework for online process analysis. Taking tool wear as a case study, this paper proposes a comprehensive online monitoring solution integrated into STEP-CNC. First, the geometric simulation is executed to calculate the Cutter Workpiece Engagement (CWE) and quantify instantaneous material removal, effectively characterizing interactions with workpiece. Second, a sparse stacked autoencoder extracts and compresses informative features from multi-sensor signals, yielding compact representations correlated with wear value. Third, an incremental prediction model tailored for online applications is developed, fusing geometric, physical, and process-domain inputs to provide precise wear increment estimates over fixed time windows. Finally, the prediction model is encapsulated as a service and integrated within the STEP-CNC framework, enabling tool wear monitoring with online feedback to the CNC controller. Experimental results demonstrate that the proposed method can accurately track tool wear progression, achieving an online monitoring accuracy exceeding 89%. The monitored wear values can further assist machining decision-making, preventing tool failures and ensuring workpiece quality. The proposed method may also serve as an actionable reference for using STEP-CNC with multi-domain data in intelligent manufacturing applications.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 904-922"},"PeriodicalIF":14.2,"publicationDate":"2025-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145568613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An interpretable industrial digital platform based on Dempster-Shafer theory for pre-diagnosis the quality of hot-rolled strip 基于Dempster-Shafer理论的热轧带钢质量预诊断可解释工业数字平台

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-15 DOI: 10.1016/j.jmsy.2025.11.008

Yu Liu , Wen Peng , Xuemeng Li , Wenteng Wu , Bingquan Zhu , Xudong Li , Yafeng Ji , Dianhua Zhang , Jie Sun

Strip crown is a critical quality indicator in hot-rolled strip, as inaccurate prediction often leads to downstream flatness defects and reduced production efficiency. Traditional physical models and individual machine learning (ML) algorithms struggle to achieve stable and reliable performance under the noisy and imbalanced conditions of industrial production. To address this challenge, this study proposes an adaptive hybrid prediction framework (A-HPF) based on Dempster-Shafer evidence theory. The framework integrates multiple ML, incorporates the support vector machine synthetic minority over-sampling technique to mitigate class imbalance, and introduces an adaptive conflict resolution mechanism with fuzzy affiliation functions to dynamically optimize evidence fusion. To ensure transparency and trustworthiness, SHapley Additive exPlanations combined with a causal network is employed to interpret the A-HPF’s decision logic and trace potential root causes. Validated on a 2160 mm hot rolling line, the proposed method improves classification accuracy by 5.9–15.6 %, reduces misclassification in edge categories by 63.6 %, and achieves an overall accuracy exceeding 0.93 across eight major steel grades. These improvements are further embedded into an industrial digital platform, enabling real-time quality prediction, interpretable analysis, and decision support, providing a practical solution for intelligent quality management in hot strip rolling.

带钢凸度是热轧带钢质量的重要指标，预测不准确往往会导致下游板形缺陷，降低生产效率。传统的物理模型和个体机器学习（ML）算法难以在工业生产的嘈杂和不平衡条件下实现稳定可靠的性能。为了解决这一挑战，本研究提出了一种基于Dempster-Shafer证据理论的自适应混合预测框架（A-HPF）。该框架集成了多个机器学习，引入了支持向量机合成少数派过采样技术来缓解类不平衡，并引入了带有模糊关联函数的自适应冲突解决机制来动态优化证据融合。为了确保透明度和可信度，本文采用SHapley加性解释结合因果网络来解释a - hpf的决策逻辑，并追踪潜在的根本原因。在2160 mm热轧生产线上进行验证，该方法的分类准确率提高了5.9 ~ 15.6 %，减少了63.6 %的边缘分类错误，在8个主要钢种上的总体准确率超过了0.93。这些改进进一步嵌入工业数字平台，实现实时质量预测、可解释分析和决策支持，为热轧带钢的智能质量管理提供实用的解决方案。

{"title":"An interpretable industrial digital platform based on Dempster-Shafer theory for pre-diagnosis the quality of hot-rolled strip","authors":"Yu Liu , Wen Peng , Xuemeng Li , Wenteng Wu , Bingquan Zhu , Xudong Li , Yafeng Ji , Dianhua Zhang , Jie Sun","doi":"10.1016/j.jmsy.2025.11.008","DOIUrl":"10.1016/j.jmsy.2025.11.008","url":null,"abstract":"<div><div>Strip crown is a critical quality indicator in hot-rolled strip, as inaccurate prediction often leads to downstream flatness defects and reduced production efficiency. Traditional physical models and individual machine learning (ML) algorithms struggle to achieve stable and reliable performance under the noisy and imbalanced conditions of industrial production. To address this challenge, this study proposes an adaptive hybrid prediction framework (A-HPF) based on Dempster-Shafer evidence theory. The framework integrates multiple ML, incorporates the support vector machine synthetic minority over-sampling technique to mitigate class imbalance, and introduces an adaptive conflict resolution mechanism with fuzzy affiliation functions to dynamically optimize evidence fusion. To ensure transparency and trustworthiness, SHapley Additive exPlanations combined with a causal network is employed to interpret the A-HPF’s decision logic and trace potential root causes. Validated on a 2160 mm hot rolling line, the proposed method improves classification accuracy by 5.9–15.6 %, reduces misclassification in edge categories by 63.6 %, and achieves an overall accuracy exceeding 0.93 across eight major steel grades. These improvements are further embedded into an industrial digital platform, enabling real-time quality prediction, interpretable analysis, and decision support, providing a practical solution for intelligent quality management in hot strip rolling.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 878-903"},"PeriodicalIF":14.2,"publicationDate":"2025-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-region robotic grinding with adaptive toolpath planning and force control for point clouds of complex curved workpieces 基于自适应刀路规划和力控制的复杂曲面工件点云跨区域机器人磨削

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-14 DOI: 10.1016/j.jmsy.2025.11.009

Ziling Wang , Lai Zou , Wenxi Wang , A.Y.C. Nee , S.K. Ong

The robotic multi-region grinding method is used to machine curved workpieces with uneven surface allowance to further improve their profile accuracy. However, in this method, when the robot executes toolpaths across adjacent grinding regions, force changes and non-uniform grinding often occur. To address the problem, a novel cross-region robotic grinding method that incorporates force control and toolpath planning across adjacent regions is proposed. In this method, a toolpath planning method, with consideration of multiple grinding regions with different expected grinding forces, is developed to generate cutter-contact (CC) points in each toolpath curve based on the point clouds of workpieces, and ensure that there are CC points near the boundary between two adjacent grinding regions. Furthermore, a novel model predictive control scheme with an environment observer is designed to track the grinding force in a single grinding region. In addition, the adaptive impedance model with a novel adaptive update rate is introduced into the control scheme to reduce the changes in the grinding force along the toolpaths across two adjacent regions. Robotic grinding experiments are conducted to verify the superiority of the proposed grinding method. The surface accuracy of the curved workpiece is improved by some 26 %.

采用机器人多区域磨削方法加工曲面余量不均匀的曲面工件，进一步提高其轮廓精度。然而，在这种方法中，当机器人在相邻的磨削区域执行刀具轨迹时，往往会发生力的变化和不均匀的磨削。为了解决这一问题，提出了一种结合力控制和刀具轨迹规划的跨区域机器人磨削方法。该方法提出了一种考虑多个期望磨削力不同的磨削区域的刀路规划方法，根据工件的点云在每条刀路曲线上生成刀具接触点，并保证相邻两个磨削区域边界附近有刀具接触点。在此基础上，设计了一种新的带环境观测器的模型预测控制方案，用于跟踪单个磨削区域内的磨削力。此外，在控制方案中引入了具有新颖自适应更新速率的自适应阻抗模型，以减小两相邻区域沿刀具轨迹的磨削力变化。通过机器人磨削实验验证了所提磨削方法的优越性。曲面工件的表面精度提高了26% %。

{"title":"Cross-region robotic grinding with adaptive toolpath planning and force control for point clouds of complex curved workpieces","authors":"Ziling Wang , Lai Zou , Wenxi Wang , A.Y.C. Nee , S.K. Ong","doi":"10.1016/j.jmsy.2025.11.009","DOIUrl":"10.1016/j.jmsy.2025.11.009","url":null,"abstract":"<div><div>The robotic multi-region grinding method is used to machine curved workpieces with uneven surface allowance to further improve their profile accuracy. However, in this method, when the robot executes toolpaths across adjacent grinding regions, force changes and non-uniform grinding often occur. To address the problem, a novel cross-region robotic grinding method that incorporates force control and toolpath planning across adjacent regions is proposed. In this method, a toolpath planning method, with consideration of multiple grinding regions with different expected grinding forces, is developed to generate cutter-contact (CC) points in each toolpath curve based on the point clouds of workpieces, and ensure that there are CC points near the boundary between two adjacent grinding regions. Furthermore, a novel model predictive control scheme with an environment observer is designed to track the grinding force in a single grinding region. In addition, the adaptive impedance model with a novel adaptive update rate is introduced into the control scheme to reduce the changes in the grinding force along the toolpaths across two adjacent regions. Robotic grinding experiments are conducted to verify the superiority of the proposed grinding method. The surface accuracy of the curved workpiece is improved by some 26 %.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 856-877"},"PeriodicalIF":14.2,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IM-Chat: A multi-agent LLM framework integrating tool-calling and diffusion modeling for knowledge transfer in injection molding industry IM-Chat：一个集成了注塑行业知识转移的工具调用和扩散建模的多智能体LLM框架

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-12 DOI: 10.1016/j.jmsy.2025.11.007

Junhyeong Lee , Joon-Young Kim , Heekyu Kim , Inhyo Lee , Seunghwa Ryu

The injection molding industry faces critical challenges in preserving and transferring field knowledge, particularly as experienced workers retire and multilingual barriers hinder effective communication. This study introduces IM-Chat, a multi-agent framework based on large language models (LLMs), designed to facilitate knowledge transfer in injection molding. IM-Chat integrates both limited documented knowledge (e.g., troubleshooting tables, manuals) and extensive field data modeled through a data-driven process condition generator that infers optimal manufacturing settings from environmental inputs such as temperature and humidity, enabling robust and context-aware task resolution. By adopting a retrieval-augmented generation (RAG) strategy and tool-calling agents within a modular architecture, IM-Chat ensures adaptability without the need for fine-tuning. Performance was assessed across 100 single-tool and 60 hybrid tasks for GPT-4o, GPT-4o-mini, and GPT-3.5-turbo by domain experts using a 10-point rubric focused on relevance and correctness, and was further supplemented by automated evaluation using GPT-4o guided by a domain-adapted instruction prompt. The evaluation results indicate that more capable models tend to achieve higher accuracy, particularly in complex, tool-integrated scenarios. In addition, compared with the fine-tuned single-agent LLM, IM-Chat demonstrated superior accuracy, particularly in quantitative reasoning, and greater scalability in handling multiple information sources. Overall, these findings demonstrate the viability of multi-agent LLM systems for industrial knowledge workflows and establish IM-Chat as a scalable and generalizable approach to AI-assisted decision support in manufacturing. To support reproducibility and practical adoption, supplementary materials including prompts, evaluation data, and video demonstrations are made available.

注塑行业在保存和转移领域知识方面面临着严峻的挑战，特别是随着有经验的工人退休和多语言障碍阻碍了有效的沟通。本研究介绍了IM-Chat，一个基于大型语言模型（llm）的多智能体框架，旨在促进注塑成型中的知识转移。IM-Chat集成了有限的文档知识（例如，故障排除表，手册）和广泛的现场数据，通过数据驱动的过程条件生成器建模，从温度和湿度等环境输入推断出最佳的制造设置，从而实现强大的上下文感知任务解决方案。通过在模块化体系结构中采用检索增强生成（retrieve -augmented generation， RAG）策略和工具调用代理，IM-Chat确保了无需微调的适应性。领域专家对gpt - 40、gpt - 40 -mini和GPT-3.5-turbo的100个单工具和60个混合任务的性能进行了评估，并采用了10分标准，重点关注相关性和正确性，并进一步辅以使用gpt - 40进行的自动化评估，该评估由一个适应领域的指令提示引导。评估结果表明，能力越强的模型往往能获得更高的精度，特别是在复杂的、工具集成的场景中。此外，与经过微调的单代理LLM相比，IM-Chat显示出更高的准确性，特别是在定量推理方面，并且在处理多个信息源方面具有更大的可扩展性。总的来说，这些发现证明了多智能体LLM系统在工业知识工作流中的可行性，并将IM-Chat建立为制造业中人工智能辅助决策支持的可扩展和可推广的方法。为了支持可重复性和实际采用，还提供了包括提示、评估数据和视频演示在内的补充材料。

{"title":"IM-Chat: A multi-agent LLM framework integrating tool-calling and diffusion modeling for knowledge transfer in injection molding industry","authors":"Junhyeong Lee , Joon-Young Kim , Heekyu Kim , Inhyo Lee , Seunghwa Ryu","doi":"10.1016/j.jmsy.2025.11.007","DOIUrl":"10.1016/j.jmsy.2025.11.007","url":null,"abstract":"<div><div>The injection molding industry faces critical challenges in preserving and transferring field knowledge, particularly as experienced workers retire and multilingual barriers hinder effective communication. This study introduces IM-Chat, a multi-agent framework based on large language models (LLMs), designed to facilitate knowledge transfer in injection molding. IM-Chat integrates both limited documented knowledge (e.g., troubleshooting tables, manuals) and extensive field data modeled through a data-driven process condition generator that infers optimal manufacturing settings from environmental inputs such as temperature and humidity, enabling robust and context-aware task resolution. By adopting a retrieval-augmented generation (RAG) strategy and tool-calling agents within a modular architecture, IM-Chat ensures adaptability without the need for fine-tuning. Performance was assessed across 100 single-tool and 60 hybrid tasks for GPT-4o, GPT-4o-mini, and GPT-3.5-turbo by domain experts using a 10-point rubric focused on relevance and correctness, and was further supplemented by automated evaluation using GPT-4o guided by a domain-adapted instruction prompt. The evaluation results indicate that more capable models tend to achieve higher accuracy, particularly in complex, tool-integrated scenarios. In addition, compared with the fine-tuned single-agent LLM, IM-Chat demonstrated superior accuracy, particularly in quantitative reasoning, and greater scalability in handling multiple information sources. Overall, these findings demonstrate the viability of multi-agent LLM systems for industrial knowledge workflows and establish IM-Chat as a scalable and generalizable approach to AI-assisted decision support in manufacturing. To support reproducibility and practical adoption, <span><span>supplementary materials</span></span> including prompts, evaluation data, and video demonstrations are made available.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 839-855"},"PeriodicalIF":14.2,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cyber-physical internet enabled hierarchical attention network based reinforcement learning for order dispatch in fast fashion manufacturing 基于层次关注网络的强化学习在快时尚制造业订单调度中的应用

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-12 DOI: 10.1016/j.jmsy.2025.10.014

Yanying Wang , Zhiheng Zhao , Yujie Han , Ying Cheng , George Q. Huang

Fast fashion platforms such as SHEIN coordinate thousands of small, nearby garment factories to fulfil large numbers of small-lot, fast-switch orders. Dispatching each order operation to the most suitable factory while respecting process routes creates a Flexible Job Shop Scheduling Problem with sequence-dependent setup times (FJSP-SDST), which is NP-hard and must be solved repeatedly as new batches arrive. Current end-to-end deep reinforcement learning (DRL) schedulers either reschedule every batch from scratch or disregard setup costs, which undermines efficiency. We introduce a Cyber-Physical Internet (CPI) scheduling framework that provides routers for every factory and the company, enabling them to cache solved schedules and broadcast real time factory states. This approach skips redundant computations and supplies fresh setup time data. Within this framework, we have developed a Hierarchical Attention Network based Reinforcement Learning (HANRL) scheduler to model the interactions between orders and factories, as well as factory competition and setup costs. Experiments on synthetic and public benchmarks demonstrate that HANRL reduces makespan and improves generalization over state-of-the-art DRL baselines, all while retaining sub-second decision times. This proves the suitability of HANRL for large scale social manufacturing environments.

像SHEIN这样的快时尚平台协调数千家附近的小型服装厂，以完成大量小批量、快速切换的订单。在尊重工艺路线的情况下，将每个订单操作分配到最合适的工厂会产生一个具有序列相关设置时间的柔性作业车间调度问题（FJSP-SDST），该问题是np困难的，必须在新批次到达时反复解决。当前的端到端深度强化学习（DRL）调度器要么从头开始重新安排每个批处理，要么忽略设置成本，这会降低效率。我们引入了一个网络物理互联网（CPI）调度框架，为每个工厂和公司提供路由器，使它们能够缓存解决的调度和广播实时工厂状态。这种方法跳过了冗余计算并提供了新的设置时间数据。在这个框架内，我们开发了一个基于分层注意网络的强化学习（HANRL）调度程序，以模拟订单和工厂之间的相互作用，以及工厂竞争和设置成本。在综合和公共基准测试上的实验表明，HANRL在保持亚秒级决策时间的同时，减少了最长时间，提高了最先进的DRL基线的泛化能力。这证明了HANRL在大规模社会制造环境中的适用性。

{"title":"Cyber-physical internet enabled hierarchical attention network based reinforcement learning for order dispatch in fast fashion manufacturing","authors":"Yanying Wang , Zhiheng Zhao , Yujie Han , Ying Cheng , George Q. Huang","doi":"10.1016/j.jmsy.2025.10.014","DOIUrl":"10.1016/j.jmsy.2025.10.014","url":null,"abstract":"<div><div>Fast fashion platforms such as SHEIN coordinate thousands of small, nearby garment factories to fulfil large numbers of small-lot, fast-switch orders. Dispatching each order operation to the most suitable factory while respecting process routes creates a Flexible Job Shop Scheduling Problem with sequence-dependent setup times (FJSP-SDST), which is NP-hard and must be solved repeatedly as new batches arrive. Current end-to-end deep reinforcement learning (DRL) schedulers either reschedule every batch from scratch or disregard setup costs, which undermines efficiency. We introduce a Cyber-Physical Internet (CPI) scheduling framework that provides routers for every factory and the company, enabling them to cache solved schedules and broadcast real time factory states. This approach skips redundant computations and supplies fresh setup time data. Within this framework, we have developed a Hierarchical Attention Network based Reinforcement Learning (HANRL) scheduler to model the interactions between orders and factories, as well as factory competition and setup costs. Experiments on synthetic and public benchmarks demonstrate that HANRL reduces makespan and improves generalization over state-of-the-art DRL baselines, all while retaining sub-second decision times. This proves the suitability of HANRL for large scale social manufacturing environments.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 784-799"},"PeriodicalIF":14.2,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GenPattern: dual-graph enhanced sewing pattern generation via multimodal large language model GenPattern：通过多模态大语言模型生成双图增强缝制图案

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-12 DOI: 10.1016/j.jmsy.2025.11.005

Hongquan Gui , Zhanpeng Yang , Arjun Rachana Harish , Cheng Ren , Yishu Yang , Ming Li

Customized garment production is hindered by the expert-dependent nature of sewing pattern generation—a skill-intensive process requiring years of training. While recent approaches aim to translate user intent into sewing patterns, they often struggle to interpret multimodal inputs such as text and images. Multimodal large language models (MLLMs) offer a promising path forward, as they can naturally understand diverse user intents. Yet, applying MLLMs to sewing pattern generation is challenging because conventional tokenization methods often lose the structural information of sewing patterns. To address this issue, we propose GenPattern, a novel framework that integrates structured graph modeling with MLLMs to enable more accurate sewing pattern generation. We introduce a scalable vector graphics (SVG)-style pattern tokenizer, which encodes sewing patterns into structured token sequences. Furthermore, we present SewGraphFuser, a dual-graph module that explicitly models geometric and semantic dependencies to inject structural information into MLLMs. This module combines a structure graph convolution module and a sequence graph convolution module to jointly capture multi-scale spatial and sequential features via a geometric consistency graph and a semantic dependency graph. Finally, to bridge the gap between digital design and physical fabrication, our framework drives a human-robot collaborative cutting platform, enabling expert-free, on-demand garment customization. This innovation empowers human-robot collaboration in pattern production, enhancing scalability in real-world manufacturing. Experimental results show that GenPattern achieves 86.7 % stitch accuracy and reduces panel vertex L2 error to 2.9 cm, demonstrating its potential to democratize custom fashion by enabling non-experts to reliably produce physical garments directly from their ideas.

定制服装生产受到缝纫模式生成依赖专家的特性的阻碍——这是一个需要多年培训的技能密集型过程。虽然最近的方法旨在将用户意图转化为缝纫图案，但它们往往难以解释文本和图像等多模式输入。多模态大型语言模型（mllm）提供了一条很有前途的发展道路，因为它们可以自然地理解不同的用户意图。然而，由于传统的标记化方法往往会丢失缝制图案的结构信息，因此将mlm应用于缝制图案生成具有挑战性。为了解决这个问题，我们提出了GenPattern，这是一个将结构化图建模与mlm集成在一起的新框架，可以更准确地生成缝纫图案。我们引入了一个可伸缩矢量图形（SVG）风格的模式标记器，它将缝纫模式编码为结构化的标记序列。此外，我们提出了SewGraphFuser，这是一个双图模块，可以显式地建模几何和语义依赖，从而将结构信息注入到mllm中。该模块结合结构图卷积模块和序列图卷积模块，通过几何一致性图和语义依赖图共同捕获多尺度空间和序列特征。最后，为了弥合数字设计和物理制造之间的差距，我们的框架驱动人机协作切割平台，实现无专家，按需定制的服装。这一创新增强了模式生产中的人机协作，增强了实际制造中的可扩展性。实验结果表明，GenPattern实现了86.7 %的缝制精度，并将面板顶点L2误差降低到2.9 cm，这表明它有潜力实现定制时尚的民主化，使非专家也能直接根据自己的想法可靠地生产出实物服装。

{"title":"GenPattern: dual-graph enhanced sewing pattern generation via multimodal large language model","authors":"Hongquan Gui , Zhanpeng Yang , Arjun Rachana Harish , Cheng Ren , Yishu Yang , Ming Li","doi":"10.1016/j.jmsy.2025.11.005","DOIUrl":"10.1016/j.jmsy.2025.11.005","url":null,"abstract":"<div><div>Customized garment production is hindered by the expert-dependent nature of sewing pattern generation—a skill-intensive process requiring years of training. While recent approaches aim to translate user intent into sewing patterns, they often struggle to interpret multimodal inputs such as text and images. Multimodal large language models (MLLMs) offer a promising path forward, as they can naturally understand diverse user intents. Yet, applying MLLMs to sewing pattern generation is challenging because conventional tokenization methods often lose the structural information of sewing patterns. To address this issue, we propose GenPattern, a novel framework that integrates structured graph modeling with MLLMs to enable more accurate sewing pattern generation. We introduce a scalable vector graphics (SVG)-style pattern tokenizer, which encodes sewing patterns into structured token sequences. Furthermore, we present SewGraphFuser, a dual-graph module that explicitly models geometric and semantic dependencies to inject structural information into MLLMs. This module combines a structure graph convolution module and a sequence graph convolution module to jointly capture multi-scale spatial and sequential features via a geometric consistency graph and a semantic dependency graph. Finally, to bridge the gap between digital design and physical fabrication, our framework drives a human-robot collaborative cutting platform, enabling expert-free, on-demand garment customization. This innovation empowers human-robot collaboration in pattern production, enhancing scalability in real-world manufacturing. Experimental results show that GenPattern achieves 86.7 % stitch accuracy and reduces panel vertex L2 error to 2.9 cm, demonstrating its potential to democratize custom fashion by enabling non-experts to reliably produce physical garments directly from their ideas.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 822-838"},"PeriodicalIF":14.2,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Self-diagnosis service to support analysis of production performance, monitoring and optimisation activities 自我诊断服务，支持生产性能分析，监控和优化活动

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-11 DOI: 10.1016/j.jmsy.2025.11.010

José Joaquín Peralta Abadía , Fabio Marco Monetti , Sylvia Nathaly Rea Minango , Angela Carrera-Rivera , Miriam Ugarte Querejeta , Mikel Cuesta Zabaljauregui , Felix Larrinaga Barrenechea , Miren Illarramendi Rezabal , Antonio Maffei

Self-diagnosis functionalities, as integral components of advanced manufacturing services within cyber–physical systems (CPSs), are made possible through cloud computing technologies and machine learning techniques. These services play a crucial role in enhancing the autonomy of CPSs and introducing cost-efficient and scalable solutions. Despite the promising outlook, a gap exists in the literature regarding the lack of clear architectural frameworks and requirements for implementing self-diagnosis services in industrial settings. This paper addresses this gap by presenting a comprehensive requirement set and developing a high-level architecture tailored for self-diagnosis services. The proposed approach is validated through a detailed case study of a cloud-based self-diagnosis service, demonstrating alignment with the established architecture and requirements. The anticipated outcome of this research is to offer concrete implementation guidelines to support researchers, engineers, and practitioners in deploying CPS-based self-diagnosis services and improving production processes and system performance.

自我诊断功能作为网络物理系统（cps）中先进制造服务的组成部分，通过云计算技术和机器学习技术成为可能。这些服务在增强cps的自主性和引入具有成本效益和可扩展的解决方案方面发挥着至关重要的作用。尽管前景光明，但在文献中存在关于缺乏明确的体系结构框架和在工业环境中实施自我诊断服务的要求的差距。本文通过提出一个全面的需求集和开发一个为自诊断服务量身定制的高级体系结构来解决这一差距。通过对基于云的自诊断服务的详细案例研究验证了所建议的方法，证明了与已建立的体系结构和需求的一致性。本研究的预期结果是提供具体的实施指南，以支持研究人员、工程师和从业人员部署基于cps的自我诊断服务，并改善生产过程和系统性能。

{"title":"Self-diagnosis service to support analysis of production performance, monitoring and optimisation activities","authors":"José Joaquín Peralta Abadía , Fabio Marco Monetti , Sylvia Nathaly Rea Minango , Angela Carrera-Rivera , Miriam Ugarte Querejeta , Mikel Cuesta Zabaljauregui , Felix Larrinaga Barrenechea , Miren Illarramendi Rezabal , Antonio Maffei","doi":"10.1016/j.jmsy.2025.11.010","DOIUrl":"10.1016/j.jmsy.2025.11.010","url":null,"abstract":"<div><div>Self-diagnosis functionalities, as integral components of advanced manufacturing services within cyber–physical systems (CPSs), are made possible through cloud computing technologies and machine learning techniques. These services play a crucial role in enhancing the autonomy of CPSs and introducing cost-efficient and scalable solutions. Despite the promising outlook, a gap exists in the literature regarding the lack of clear architectural frameworks and requirements for implementing self-diagnosis services in industrial settings. This paper addresses this gap by presenting a comprehensive requirement set and developing a high-level architecture tailored for self-diagnosis services. The proposed approach is validated through a detailed case study of a cloud-based self-diagnosis service, demonstrating alignment with the established architecture and requirements. The anticipated outcome of this research is to offer concrete implementation guidelines to support researchers, engineers, and practitioners in deploying CPS-based self-diagnosis services and improving production processes and system performance.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 800-821"},"PeriodicalIF":14.2,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robotic inspection of fastener holes with hybrid visual and ultrasonic motion control 基于视觉和超声混合运动控制的紧固件孔机器人检测

IF 14.2 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Journal of Manufacturing Systems

Pub Date : 2025-11-10 DOI: 10.1016/j.jmsy.2025.11.003

Yanghao Wu, Paul D. Wilcox, Anthony J. Croxford

Fasteners are widely used in mechanical structures, where stress concentrations around fastener holes can lead to crack initiation and fatigue failures. In the aerospace industry, routine fastener hole inspections are critical to ensure structural integrity. Ultrasonic testing is one of the main inspection approaches. Conventionally, it involves a single-element probe that must be manually placed at multiple locations and orientations so that the ultrasound beam insonifies the area around the hole from different angles. The received ultrasonic time-domain signals at each location are analyzed, which is time-consuming, operator-dependent, and prone to inconsistencies. 2D ultrasonic array probes enable 3D volumetric images of fastener hole defects to be obtained from a single probe position, offering the potential for more efficient automated inspection and data interpretation. To achieve this, the 2D array probe must be accurately located over the centre of the hole and the ultrasonic coupling with the component must be consistent over the entire probe contact surface. This paper presents an automated robotic system for ultrasonic fastener hole inspection, that is designed to address these issues. A 7 degree-of-freedom robot arm is used with a vision module, and a customized probe adapter integrates a 2D ultrasonic array and coupling block into the robot end effector. A novel hybrid probe manipulation method is proposed, which combines camera-based visual localization with real-time ultrasound signal feedback to ensure accurate probe alignment and consistent coupling. The whole inspection workflow is scheduled and a graphical user interface is developed to demonstrate this automatic inspection. Experimental validation demonstrates that the robotic system performs accurate, repeatable inspections, significantly enhancing efficiency and reliability compared to manual techniques. The proposed approach addresses key challenges in robotic ultrasonic inspection and offers a scalable solution for intelligent maintenance in aerospace and other high-reliability industries.

紧固件广泛应用于机械结构中，紧固件孔周围的应力集中可能导致裂纹萌生和疲劳失效。在航空航天工业中，常规紧固件孔检查对于确保结构完整性至关重要。超声检测是主要的检测手段之一。传统上，它包括一个单元件探头，必须手动放置在多个位置和方向上，以便超声波光束从不同角度对孔周围的区域进行干扰。对每个位置接收到的超声时域信号进行分析，这是耗时的，依赖于操作员，并且容易出现不一致。2D超声阵列探头可以从单个探头位置获得紧固件孔缺陷的3D体积图像，从而提供更有效的自动检测和数据解释。为了实现这一点，二维阵列探头必须精确地位于孔的中心，并且与组件的超声波耦合必须在整个探头接触面上保持一致。本文提出了一种用于超声波紧固件孔检测的自动化机器人系统，旨在解决这些问题。7自由度的机械臂配有视觉模块，定制探头适配器将二维超声阵列和耦合块集成到机器人末端执行器中。提出了一种将基于摄像机的视觉定位与实时超声信号反馈相结合的新型混合探针操作方法，以保证探针的精确对准和一致耦合。整个检测工作流程是预定的，并开发了一个图形用户界面来演示这种自动检测。实验验证表明，与人工技术相比，机器人系统执行准确，可重复的检查，显着提高了效率和可靠性。提出的方法解决了机器人超声检测中的关键挑战，并为航空航天和其他高可靠性行业的智能维护提供了可扩展的解决方案。

{"title":"Robotic inspection of fastener holes with hybrid visual and ultrasonic motion control","authors":"Yanghao Wu, Paul D. Wilcox, Anthony J. Croxford","doi":"10.1016/j.jmsy.2025.11.003","DOIUrl":"10.1016/j.jmsy.2025.11.003","url":null,"abstract":"<div><div>Fasteners are widely used in mechanical structures, where stress concentrations around fastener holes can lead to crack initiation and fatigue failures. In the aerospace industry, routine fastener hole inspections are critical to ensure structural integrity. Ultrasonic testing is one of the main inspection approaches. Conventionally, it involves a single-element probe that must be manually placed at multiple locations and orientations so that the ultrasound beam insonifies the area around the hole from different angles. The received ultrasonic time-domain signals at each location are analyzed, which is time-consuming, operator-dependent, and prone to inconsistencies. 2D ultrasonic array probes enable 3D volumetric images of fastener hole defects to be obtained from a single probe position, offering the potential for more efficient automated inspection and data interpretation. To achieve this, the 2D array probe must be accurately located over the centre of the hole and the ultrasonic coupling with the component must be consistent over the entire probe contact surface. This paper presents an automated robotic system for ultrasonic fastener hole inspection, that is designed to address these issues. A 7 degree-of-freedom robot arm is used with a vision module, and a customized probe adapter integrates a 2D ultrasonic array and coupling block into the robot end effector. A novel hybrid probe manipulation method is proposed, which combines camera-based visual localization with real-time ultrasound signal feedback to ensure accurate probe alignment and consistent coupling. The whole inspection workflow is scheduled and a graphical user interface is developed to demonstrate this automatic inspection. Experimental validation demonstrates that the robotic system performs accurate, repeatable inspections, significantly enhancing efficiency and reliability compared to manual techniques. The proposed approach addresses key challenges in robotic ultrasonic inspection and offers a scalable solution for intelligent maintenance in aerospace and other high-reliability industries.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"83 ","pages":"Pages 770-783"},"PeriodicalIF":14.2,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145516963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0