语义数据标注的轻量化轨道扣件故障检测方法  

Lightweight Rail Fastener Fault Detection Method Based on Improved MobileVit and Grad⁃Cam

作　　者：姚德臣 王琰亮[1,2] 杨建伟 徐立新 张帆[1,2] YAO Dechen;WANG Yanliang;YANG Jianwei;XU Lixin;ZHANG Fan(School of Machine-Electricity and Automobile Engineering,Beijing University of Civil Engineering and Architecture Beijing,100044,China;Beijing Key Laboratory of Performance Guarantee on Urban Rail Transit Vehicles,Beijing University of Civil Engineering and Architecture Beijing,100044,China;Chen Gai Sluice Management Office,Water Supply Bureau of Dongping Lake Administration Bureau Taian,271599,China)

机构地区：[1]北京建筑大学机电与车辆工程学院,北京100044 [2]北京建筑大学城市轨道交通车辆服役性能保障北京市重点实验室,北京100044 [3]东平湖管理局供水局陈垓闸管理所,泰安271599

出　　处：《振动．测试与诊断》2024年第1期52-59,196,共9页Journal of Vibration,Measurement & Diagnosis

基　　金：国家自然科学基金面上资助项目(51975038,52272385);国家自然科学基金青年科学基金资助项目(52205083);北京市自然科学基金资助项目(L211008,L221027,L211007);北京市自然科学基金青年基金资助项目(3214042);北京建筑大学青年教师科研能力提升计划资助(X21055)。

摘　　要：针对常规深度学习网络规模大、对现场设备硬件要求高且人工标注位置数据复杂费时等问题,提出了一种语义数据标注的轻量化轨道扣件故障检测方法。该方法仅对训练数据做语义标注,改进轻量化Transformer模型,嵌入梯度加权类激活映射(gradient-weighted class activation mapping,简称Grad-CAM)模块对模型输出的特征图权重作映射处理,可将模型对轨道扣件检测效果可视化。将获得的激活图进行二值化定位检测目标位置,实验结果表明,在真实铁路环境下,改进的轻量化轨道扣件模型的准确率为94.31%。In response to the challenges of the large scale of conventional deep learning networks,high hardware demands for field devices,and the intricate and labor-intensive process of manually annotating location data,this paper introduces an innovative approach to rail fastener fault detection.This method only makes semantic annotation for training data,improves the lightweight Transformer model.Further,incorporating the gradient-weighted class activation mapping(Grad-CAM)module can visualize the weight distribution of the feature map output generated by the model.This visualization provides insights into the model performance in rail fastener detection.Subsequently,the resulting activation map is binarized to precisely pinpoint and identify the target location.Experimental results demonstrate that the improved lightweight model for track fastener detection achieves an impressive accuracy rate of 94.31%in real-world railway environments.

关 键 词：轨道扣件 智能故障诊断 深度学习 轻量化网络 

分 类 号：U216.3[交通运输工程—道路与铁道工程] TH17[机械工程—机械制造及自动化]