Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
This study introduces electromagnetic dynamic self-piercing riveting(ED-SPR),an innovative technique that integrates electromagnetic riveting principles with static self-piercing riveting(S-SPR)for highperformance str...This study introduces electromagnetic dynamic self-piercing riveting(ED-SPR),an innovative technique that integrates electromagnetic riveting principles with static self-piercing riveting(S-SPR)for highperformance structural joints.A dedicated methodology and experimental apparatus for ED-SPR were systematically designed and validated.Quantitative comparative analyses between ED-SPR and S-SPR were conducted on three critical material combinations:CFRP/Al,low-strength steel HC340 LA/Al,and high-strength steel DP590/Al.Key findings demonstrate that the electromagnetic-driven process reduces installation resistance by 60%and achieves a 30%larger interlock distance at the joint base compared to S-SPR.These quantitative advantages directly contribute to an approximately 30%increase in load-bearing capacity and superior damage tolerance in ED-SPR joints,as evidenced by tensile-shear testing of single-lap joints.Furthermore,distinct failure modes were observed:ED-SPR joints exhibited top plate pull-out failure in CFRP/Al and DP590/Al configurations,contrasting with the predominant rivet pull-out failure in S-SPR counterparts.Surface morphology and damage evolution were characterized via scanning electron microscopy(SEM)on post-assembly and tensile-failed specimens.The study establishes a foundation for optimizing electromagnetic-driven riveting parameters to mitigate CFRP delamination and further enhance joint reliability in vehicle body and aircraft fuselage structures.展开更多
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金sponsored by National Natural Science Foundation of China(Nos.52305146 and 52275165)Natural Science Foundation of Chongqing,China(No.cstb2022nscqmsx1290)+1 种基金the financial support from the Major Special Project for Technological Innovation and Application Development of Chongqing(No.CSTB2024TIAD-STX0015)the Key Laboratory Project of Shaanxi Province(No.2025SYS-SYSZD-064)。
文摘This study introduces electromagnetic dynamic self-piercing riveting(ED-SPR),an innovative technique that integrates electromagnetic riveting principles with static self-piercing riveting(S-SPR)for highperformance structural joints.A dedicated methodology and experimental apparatus for ED-SPR were systematically designed and validated.Quantitative comparative analyses between ED-SPR and S-SPR were conducted on three critical material combinations:CFRP/Al,low-strength steel HC340 LA/Al,and high-strength steel DP590/Al.Key findings demonstrate that the electromagnetic-driven process reduces installation resistance by 60%and achieves a 30%larger interlock distance at the joint base compared to S-SPR.These quantitative advantages directly contribute to an approximately 30%increase in load-bearing capacity and superior damage tolerance in ED-SPR joints,as evidenced by tensile-shear testing of single-lap joints.Furthermore,distinct failure modes were observed:ED-SPR joints exhibited top plate pull-out failure in CFRP/Al and DP590/Al configurations,contrasting with the predominant rivet pull-out failure in S-SPR counterparts.Surface morphology and damage evolution were characterized via scanning electron microscopy(SEM)on post-assembly and tensile-failed specimens.The study establishes a foundation for optimizing electromagnetic-driven riveting parameters to mitigate CFRP delamination and further enhance joint reliability in vehicle body and aircraft fuselage structures.
