基于注意力反向知识蒸馏的车轮踏面异常检测

Wheel Tread Anomaly Detection Based on Attentional ReverseKnowledge Distillation

车轮是铁路列车走行部的重要部件,车轮踏面上产生的缺陷严重危害着铁路列车的安全运行。由于实际中车轮踏面缺陷样本有限,有监督检测模型对缺陷的检测不具有鲁棒性。针对此问题,提出使用无监督的知识蒸馏异常检测模型实现对车轮踏面的异常检测任务。首先,使用UNet对踏面区域进行分割,减少非踏面区域对异常检测模型的影响;然后,在多尺度特征聚合之后添加一个注意力机制,提升反向知识蒸馏结构中学生网络对正常特征的重建能力,增强学生网络对正常特征重建的效果。实验结果表明:在铁路车轮踏面数据集上,改进后的模型能够达到93.8%的受试者工作特性曲线下的面积、82.3%的精准率、95.4%的召回率、87.0%的准确率。与原模型相比,改进后的模型检测性能得到提升。

Wheels are an essential part of railway trains;thus,defects on the wheel tread present serious risk regarding the safety of railway trains.Due to the limited samples of wheel tread defects in practice,the corresponding supervised detection model is insufficient.To solve this problem,an unsupervised knowledge distillation anomaly detection model is proposed to detect wheel tread anomalies.Accordingly,UNet is employed to segment the tread region and reduce the influence of non-tread regions on the anomaly detection model.An attention mechanism is then added after the multiscale feature fusion to improve the ability of the student network to reconstruct normal features in the reverse knowledge distillation structure,as well as enhance the reconstruction of normal features.From the experimental results,the improved model achieves the performance indexes of 93.8%area under receiver operating characteristic curve,82.3%precision,95.4%recall,and 87.0%accuracy considering the railway wheel tread dataset.Compared with the original model,the detection performance of the model is improved.