Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network

Surface defect recognition of train wheelset is crucial for the safe operation of the train wheel system. However, due to the diversity and complexity of such defects, it is difficult for existing algorithms to make rapid and accurate recognitions. To solve this problem, an improved spiking neural network (SNN) based defect recognition method for train wheelset tread is proposed. Specifically, a hybrid convolutional encoding module is first designed to conduct image-to-spike conversion and to create multi-scale sparse representations of the features. Second, a residual spiking convolutional neural network is implemented to extract spiking features optimally, and a multi-scale structure is adopted to enhance the SNN’s ability to handle details. A channel attention module is then incorporated to re-calibrate the weights of four-dimensional spiking feature maps. Finally, effective spiking features are obtained according to the recognition decisions which are made. The experimental results showed that the proposed method improved the accuracy of defect recognition. The recognition time of a single image is only 0.0195 s on average. The overall performance of the proposed method is noticeably superior to current mainstream algorithms.