Identifying Coexisting Defects on Heavy-Haul Train Wheelset Treads via Dual-Branch United Image-Graph Network

Identifying wheelset tread defects for heavy-haul trains is an increasingly valued yet challenging task. These defects are usually characterized by irregular shapes, wide coverage, and high codependency under prolonged heavy loads. Frequently, multiple correlated defects are observed to coexist and intertwine within the same field of view, posing substantial difficulties for fine-grained identification. Although recent methods have progressed much, they neglect interlabel dependencies and cannot distinguish well between coexisting tread defects. To this end, we explore for the first time the importance of interlabel dependencies in identifying coexisting tread defects of heavy-haul trains. Concretely, we propose a novel multilabel classification framework based on a dual-branch united image-graph network to effectively recognize the three most concerning coexisting defects on heavy-haul train wheelset treads: crack, exfoliation, and spalling. To the best of our knowledge, this is the first work to consider multilabel learning for fine-grained tread defect identification. In the image-oriented branch, we design a pyramid feature re-extractor (PFrE) and a semantic attention guider (SAG) to excavate expressive feature representation and ensure effective multiscale fusion. In the graph-oriented branch, we construct graph convolutional networks to exploit sufficient label dependency priors. Further, a multilevel merging mechanism between label embeddings and image features (M3LI) is proposed to enhance the complementation between image and graph domains. Experiment results demonstrate superior performance than other competitive methods in identifying coexisting tread defects for heavy-haul trains. Additionally, the proposed method shows good generalization ability in similar industrial inspection scenes for rail surface defects and aluminum profile defects.