Advanced Defect Detection in High-Speed Train Wheel Treads Using Nanoelectronic Systems

Abstract

Detecting defects on the wheel tread of high-speed trains is crucial for ensuring train safety. However, the challenge lies in acquiring sufficient defect data for effective detection. To address this, we propose a novel multi-similarity based few-shot segmentation network (MSFSNet), which employs different architecture for training and detection. Taking advantage of the principle of feature tensor similarity, MSFSNet enables precise extraction tread defects. In the training phase, the network comprises three branches: query branch, support branch, and task discrimination branch. To enhance defect detection efficiency, the detection phase employs an alternative architecture, where the support branch is replaced with a database of extracted defect feature tensors. The support branch provides tread defect information to the query branch, which employs the Multi-Similarity (MS) module to integrate for defect segmentation and detection. This integration effectively mitigates the overfitting issue caused by a scarcity of tread defect images. To ensure the effectiveness of defect information from the support branch, a task discrimination branch is constructed to discriminate tasks on query images and select similar support images. The Query Segmentation Module (QSM) is devised to achieve precise detection across various tread defect scales, enabling accurate segmentation amidst background noise. Experimental testing of MSFSNet on public datasets and the collected Wheel Tread Defect Dataset (WTDD) shows promising results: on FSSD-12 dataset, MSFSNet improves few-shot segmentation mIoU by 8.9% (1-shot) and 7.0% (5-shot); its capability for few-shot defect detection was confirmed on industrial dataset industrial-5i; and achieves 99.63% accuracy in detecting wheel tread defects on WTDD.