基于边缘AI计算的轨道扣件状态定量化检测方法  

Quantitative Detection of Rail Fasteners Based on Edge AI Computing

作　　者：白堂博 段嘉明 杨建伟 许贵阳[1,2] BAI Tangbo;DUAN Jiaming;YANG Jianwei;XU Guiyang(School of Mechanical,Electrical and Vehicle Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044,China;Beijing Key Laboratory of Performance Guarantee on Urban Rail Transit Vehicles,Beijing 100044,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

出　　处：《中国铁道科学》2025年第1期60-69,共10页China Railway Science

基　　金：国家自然科学基金资助项目(52272385);北京市自然科学基金资助项目(L211007,L221027)。

摘　　要：针对轨道扣件车载实时定量检测中检测的速度与精度难以平衡以及设备空间有限的问题,提出一种基于边缘AI计算的改进YOLOv8(You Only Look Once version 8)轨道扣件定量检测方法,并进行了部署和测试。首先,为实现轻量化部署,优化YOLOv8网络结构,嵌入移动神经网络V3(MobileNetV3)轻量化网络,引入压缩激励(SE)注意力机制,并重构颈部网络,加入可变形卷积;其次,结合推理引擎加速方法优化重构的网络模型,并将其部署在Jetson AGX Xavier边缘AI计算设备上;最后,对分割结果进行像素级提取,引入最小外接矩阵,定量分析扣件的断裂程度和偏转角度,并优化检测结果。结果表明:改进后的轻量化网络参数数量减少了22%;在边缘AI计算设备上的帧率相对原YOLOv8模型提升了80%,达到58帧·s^(-1);通过定量分析结果对模型进行修正,平均精度达到了97.0%,满足检测车辆所需的最低45帧·s^(-1)检测要求,实现了轨道扣件的定量化实时检测。The aim of this study is to address the challenges of balancing detection speed and accuracy of rail fasteners in real-time on-board quantitative detection,as well as the limitations posed by equipment space.The proposed solution is an enhanced YOLOv8 quantitative detection method for rail fasteners,utilising edge AI computing.This method has been tested and deployed.Firstly,to achieve lightweight deployment,the YOLOv8 network structure is optimised by embedding the MobileNetV3 lightweight network,introducing the Squeeze-and-Excitation(SE)attention mechanism,and reconstructing the neck network to incorporate deformable convolution.Secondly,the reconstructed network model is further optimised using the Jetpack-TensorRT acceleration method and deployed on a Jetson AGX Xavier edge AI computing device.Finally,the segmentation results are extracted at the pixel level,and a minimum outer join matrix is introduced to quantify the fracture degree and deflection angle of the fasteners,thereby optimising the detection results.The results demonstrate that the number of parameters of the enhanced lightweight network is reduced by 22%;the frame rate on the edge AI computing device is enhanced by 80%relative to the original YOLOv8 model,reaching 58 frames per second(fps).By refining the model based on quantitative analysis results,the average accuracy reaches 97.0%,which meets the minimum detection requirement of 45 fps for vehicles.Thus,quantitative real-time detection for rail fasteners is achieved.

关 键 词：边缘AI计算 扣件 轻量化 定量化检测 YOLOv8 

分 类 号：U216.3[交通运输工程—道路与铁道工程]