湖南大学学报（自然科学版）2026，Vol.53Issue(4)：29-40,12.DOI:10.16339/j.cnki.hdxbzkb.2026264
基于轻量化线性自注意力反向知识蒸馏网络的TEDS图像缺陷检测研究
Research on TEDS image defect detection based on lightweight linear self-attention reverse knowledge distillation network
摘要
Abstract
The trouble of moving electric multiple units dynamic image detection system(TEDS)needs to detect components with diverse shapes and sizes,which leads to high false positive and missed detection rates in the existing detection methods.Therefore,a pseudo anomaly multi-head depth separable self-attention reverse knowledge distillation network is proposed to achieve anomaly detection on TEDS images.Firstly,the self-attention head vector is generated by replacing the matrix with depthwise separable convolution,and the sharp distribution of similarity is adjusted with a focus function.The constructed multi-head depthwise separable linear self-attention enjoys linear computational complexity.Secondly,a lightweight attention teacher-student model based reverse knowledge distillation network is constructed using a bottleneck residual module and a multi-head depth separable linear self-attention module,which improves the network's feature extraction ability while reducing the number of trainable parameters,and accelerates the detection speed.Projection layers are set after each module of the teacher network.Meanwhile,the Simplex and random cropping pseudo-defect mechanisms are employed to simulate pseudo-defect samples during training.Through multi-loss guidance,the projection layers are pushed away from the normal feature space to exclude defect information,forcing them to focus on exploring deeper representations of normal features and restricting the flow of defect information to the student network,resulting in greater feature differences between the teacher and student networks for anomaly.Research shows that the improved network can effectively enhance the anomaly detection capability of TEDS images;the evaluation metrics of image-Auroc,pixel-Auroc,and Aupro reach 94.6%,91.71%,80.1%,respectively.Compared with other algorithms,these metrics show improvements of 3.3,3.8,4 percentage points,respectively.This method can achieve a detection speed of 0.37 s per sheet,meeting the real-time requirements of TEDS systems.关键词
动车组运行故障动态图像检测系统/知识蒸馏/缺陷检测/多头深度可分离线性自注意力/伪缺陷Key words
trouble of moving electric multiple units dynamic image detection system(TEDS)/knowledge distil-lation/anomaly detection/multi-head depth separable linear self-attention/pseudo-defects分类
交通工程引用本文复制引用
王登飞,苏宏升,葛磊蛟,王少飞,殷文福..基于轻量化线性自注意力反向知识蒸馏网络的TEDS图像缺陷检测研究[J].湖南大学学报（自然科学版）,2026,53(4):29-40,12.基金项目
甘肃省教育厅高校教师创新基金项目(2024B-056),University Teacher Innovation Fund of Gansu Provincial Department of Edu-cation(2024B-056) （2024B-056）
甘肃省科技厅科技重大专项(22ZD6GA063),Major Science and Technology Projects of Gansu Province(22ZD6GA0 63) （22ZD6GA063）
兰州交通大学-西南交通大学联合创新基金(LH2024027),Lanzhou Jiaotong University-Southwest Jiaotong University Joint Innovation Fund(LH2024027) （LH2024027）
