Aiming to assess the problems of low detection accuracy, poor reliability, and high cost of the manual inspection method for conveyor-belt-surface defect detection, in this paper we propose a new method of conveyor-belt-surface defect detection based on knowledge distillation. First, a data enhancement method combining GAN and copy–pasting strategies is proposed to expand the dataset to solve the problem of insufficient and difficult-to-obtain samples of conveyor-belt-surface defects. Then, the target detection network, the YOLOv5 model, is pruned to generate a mini-network. A knowledge distillation method for fine-grained feature simulation is used to distill the lightweight detection network YOLOv5n and the pruned mini-network YOLOv5n-slim. The experiments show that our method significantly reduced the number of parameters and the inference time of the model, and significantly improves the detection accuracy, up to 97.33% accuracy, in the detection of conveyor belt defects.

The catenary is an important part of the railway power supply system, and the good health of its key components is an important condition for the operation of high-speed trains. Due to the complex composition of catenary components and the large size difference between components, it is very difficult to implement the positioning and detection of all components. It severely limits the subsequent failure analysis of catenary components. Aiming at the problem of the difficult positioning of multiple components, this paper proposes a catenary complex component locating method based on the improved YOLO algorithm named CCL-YOLO. Firstly, based on the YOLO baseline method, a framework for locating complex components of railway catenary is proposed, which achieves the accurate locating of 40 catenary components and paves the way for subsequent fault detection. Furthermore, a novel "Gather-and Distribute" mechanism is introduced, which improves the original feature fusion method and its global feature fusion capability and effectively improves the positioning accuracy of complex catenary components. In addition, the Wasserstein distance loss is also applied to improve the detection capability of small objects. Finally, the comprehensive experimental results show that the proposed method for locating complex components of railway catenary can achieve a mean intersection over union of 94.1% for 40 components of different sizes. Meanwhile, it reduces the number of parameters and the complexity of the algorithm to a certain extent, thus paving the way for subsequent fault detection, which is of important application value.

Anomaly detection of catenary support components (CSCs) is an important component in railway condition monitoring systems. However, because the abnormal features of CSCs loosening are not obvious, and the current CNN models and visual Transformer models have problems such as limited remote modeling capabilities and secondary computational complexity, it is difficult for existing deep learning anomaly detection methods to effectively exert their performance. The state space model (SSM) represented by Mamba is not only good at long-range modeling, but also maintains linear computational complexity. In this paper, using the state space model (SSM), we proposed a new visual state space reconstruction network (VSM-UNet) for the detection of CSC loosening anomalies. First, based on the structure of UNet, a visual state space block (VSS block) is introduced to capture extensive contextual information and multi-scale features, and an asymmetric encoder–decoder structure is constructed through patch merging operations and patch expanding operations. Secondly, the CBAM attention mechanism is introduced between the encoder–decoder structure to enhance the model’s ability to focus on key abnormal features. Finally, a stable abnormality score calculation module is designed using MLP to evaluate the degree of abnormality of components. The experiment shows that the VSM-UNet model, learning strategy and anomaly score calculation method proposed in this article are effective and reasonable, and have certain advantages. Specifically, the proposed method framework can achieve an AUROC of 0.986 and an FPS of 26.56 in the anomaly detection task of looseness on positioning clamp nuts, U-shaped hoop nuts, and cotton pins. Therefore, the method proposed in this article can be effectively applied to the detection of CSCs abnormalities.