Regular fastener detection is necessary to ensure the safety of railways.However,the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways.Existing supervised inspect...Regular fastener detection is necessary to ensure the safety of railways.However,the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways.Existing supervised inspectionmethods have insufficient detection ability in cases of imbalanced samples.To solve this problem,we propose an approach based on deep convolutional neural networks(DCNNs),which consists of three stages:fastener localization,abnormal fastener sample generation based on saliency detection,and fastener state inspection.First,a lightweight YOLOv5s is designed to achieve fast and precise localization of fastener regions.Then,the foreground clip region of a fastener image is extracted by the designed fastener saliency detection network(F-SDNet),combined with data augmentation to generate a large number of abnormal fastener samples and balance the number of abnormal and normal samples.Finally,a fastener inspection model called Fastener ResNet-8 is constructed by being trained with the augmented fastener dataset.Results show the effectiveness of our proposed method in solving the problem of sample imbalance in fastener detection.Qualitative and quantitative comparisons show that the proposed F-SDNet outperforms other state-of-the-art methods in clip region extraction,reaching MAE and max F-measure of 0.0215 and 0.9635,respectively.In addition,the FPS of the fastener state inspection model reached 86.2,and the average accuracy reached 98.7%on 614 augmented fastener test sets and 99.9%on 7505 real fastener datasets.展开更多
The effect of the fastener's failure in a railway track on the dynamic forces produced in the wheel-rail contact is studied using the simulation software VAMPIRE to assess the derailment risk of two different vehicle...The effect of the fastener's failure in a railway track on the dynamic forces produced in the wheel-rail contact is studied using the simulation software VAMPIRE to assess the derailment risk of two different vehicles in two curves with distinct characteristics. First, a 3D-FEM model of a real track is constructed, paying special attention to fasteners, and calibrated with displacement data obtained experimentally during a train passage. This numerical model is subsequently used to determine the track vertical and lateral stiffness. This study evidences that although the track can practically lose its lateral stiffness as a consequence of the failure of 7 consecutive fasteners, the vehicle stability would not be necessarily compromised in the flawed zone. Moreover, the results reveal that the uncompensated acceleration and the distance along which the fasteners are failed play an important role in the dynamic behavior of the vehicle-track system, influencing strongly the risk of derailment.展开更多
基金supported in part by the National Natural Science Foundation of China (Grant Nos.51975347 and 51907117)in part by the Shanghai Science and Technology Program (Grant No.22010501600).
文摘Regular fastener detection is necessary to ensure the safety of railways.However,the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways.Existing supervised inspectionmethods have insufficient detection ability in cases of imbalanced samples.To solve this problem,we propose an approach based on deep convolutional neural networks(DCNNs),which consists of three stages:fastener localization,abnormal fastener sample generation based on saliency detection,and fastener state inspection.First,a lightweight YOLOv5s is designed to achieve fast and precise localization of fastener regions.Then,the foreground clip region of a fastener image is extracted by the designed fastener saliency detection network(F-SDNet),combined with data augmentation to generate a large number of abnormal fastener samples and balance the number of abnormal and normal samples.Finally,a fastener inspection model called Fastener ResNet-8 is constructed by being trained with the augmented fastener dataset.Results show the effectiveness of our proposed method in solving the problem of sample imbalance in fastener detection.Qualitative and quantitative comparisons show that the proposed F-SDNet outperforms other state-of-the-art methods in clip region extraction,reaching MAE and max F-measure of 0.0215 and 0.9635,respectively.In addition,the FPS of the fastener state inspection model reached 86.2,and the average accuracy reached 98.7%on 614 augmented fastener test sets and 99.9%on 7505 real fastener datasets.
文摘The effect of the fastener's failure in a railway track on the dynamic forces produced in the wheel-rail contact is studied using the simulation software VAMPIRE to assess the derailment risk of two different vehicles in two curves with distinct characteristics. First, a 3D-FEM model of a real track is constructed, paying special attention to fasteners, and calibrated with displacement data obtained experimentally during a train passage. This numerical model is subsequently used to determine the track vertical and lateral stiffness. This study evidences that although the track can practically lose its lateral stiffness as a consequence of the failure of 7 consecutive fasteners, the vehicle stability would not be necessarily compromised in the flawed zone. Moreover, the results reveal that the uncompensated acceleration and the distance along which the fasteners are failed play an important role in the dynamic behavior of the vehicle-track system, influencing strongly the risk of derailment.