基于集成式部分卷积网络的轮轨踏面缺陷识别方法  

Identification method for wheel/rail tread defects based on integrated partial convolutional network

作　　者：程翔 何静[2] 张昌凡[2] 贾林[2] CHENG Xiang;HE Jing;ZHANG Changfan;JIA Lin(College of Physical Sciences and Technology,Central China Normal University,Wuhan,Hubei 430079,China;School of Railway Transportation,Hunan University of Technology,Zhuzhou,Hunan 412000,China)

机构地区：[1]华中师范大学物理科学与技术学院,湖北武汉430079 [2]湖南工业大学轨道交通学院,湖南株洲412000

出　　处：《机车电传动》2024年第5期139-150,共12页Electric Drive for Locomotives

基　　金：国家自然科学基金项目(52172403);湖南省自然科学基金资助项目(2023JJ60232);湖南省教育厅资助科研项目(23B1018)。

摘　　要：轮对是铁路车辆走行部的重要组件,轮对踏面损伤检测是列车检修的重要项目,然而,由于采样设备不统一和采样环境不确定,常导致踏面损伤检测数据集掺杂暗照度图像,使得微小踏面损伤难以充分识别。针对上述问题,文章提出一种集成式部分卷积网络的轮轨踏面缺陷识别方法 (I-PCNet)。该方法设计了一种稠密暗照度自校正网络(D-SCNet),将该模块拼接在识别模型的首层,以期在提取特征之前对暗照度样本进行自校正,以突出更多细节特征;考虑到微小轮对损伤难以准确识别的问题,提出一种增量式检测方法(E-ASFF);为进一步轻量化模型,引入一种部分卷积网络(P-Conv)技术,设计了轻量化主干网络(FasterNet);为更好地集成所提的多种策略,提高检测模型对样本的聚焦程度,设计了新型损失函数,并对其原理进行了说明。试验表明,在实际轮轨踏面数据集上,文章所提的策略优于传统踏面缺陷检测算法。此外,通过对比试验、可视化分析和泛化试验,进一步验证了文章所提方法的有效性和普适性。Wheelsets are critical components of the running gears in railway vehicles,making damage detection on wheel treads a key focus in train maintenance.However,the lack of standardized sampling equipment and the variability of sampling environments often result in detection datasets that contain underexposed images,which hinder the effective identification of minor tread damages.To address this challenge,an integrated partial convolutional network(I-PCNet)method was proposed for identifying wheel-rail tread de-fects.This method incorporated a dense underexposure self-correction network(D-SCNet)integrated into the initial layer of the identifi-cation model.The aim was to self-correct underexposed samples before feature extraction,thereby revealing more detailed features.Giv-en the difficulties associated with accurately detecting minor wheelset damages,an enhanced adaptive spatial feature fusion(E-ASFF)de-tection approach was introduced.Furthermore,a partial convolutional network(P-Conv)technique was implemented for the lightweight purpose,resulting in the design of a lightweight backbone network termed FasterNet.Additionally,the design incorporated a novel loss function to improve the integration of the proposed strategies and enhance the model's focus on the samples,with its principles clearly explained.Experiments using actual wheel-rail tread datasets demonstrated that the proposed strategies outperformed traditional tread defect detection algorithms.The effectiveness and generalizability of the proposed method were further validated through comparative experiments,visualization analysis,and generalization tests.

关 键 词：踏面缺陷 故障检测 神经网络 目标检测 

分 类 号：U270.331.1[机械工程—车辆工程]