Hybrid convolution and transformer network for coupler fracture failure pattern segmentation recognition in heavy-haul trains

Couplers are an important component of heavy-haul trains. Effective failure analysis and fracture surface pattern recognition of the fractured coupler are of great significance for improving the safety of railway transportation. An end-to-end hybrid convolution and transformer (HCT) segmentation network for automatic semantic segmentation recognition of fracture surface failure patterns in metal couplers is proposed in this study. To achieve local modeling, the proposed method replaces handcrafted features with a pre-trained convolutional network for automatic feature extraction from the coupler's input image. Further, an HCT module is proposed for feature fusion and global modeling to improve the accuracy of different failure pattern semantic segmentation. A multi-scale loss function (MS-Loss) is proposed to improve the network performance while accelerating the convergence of the network. The experimental results show that the proposed HCT network achieves the highest mean intersection over union (mIoU) on the DJTUSeg (91.28 %) and DWTT-Seg (86.37 %) datasets and achieves a detection speed of 51 fps on a single GPU. The proposed method can detect in real-time while avoiding contamination from human subjective factors. It provides a new pattern recognition method for the brittle fracture inspection of heavy-haul train couplers and even the whole metal material fracture measurement solution, offering promising applications.