Defects Detection of Catenary Suspension Device Based on Image Processing and CNN

摘要

Catenary suspension device (CSD) is a critical part of the pantograph-catenary system, which is a fundamental power equipment to supply electricity to urban rail transit vehicles. Whether the CSD is in a normal state is of great significance to the safe operation of operating vehicles. Therefore, it is important to detect the defects of CSD in time and automatically. In this paper, innovative and intelligent methods using image processing technologies and convolutional neural network (CNN) are proposed. Firstly, the insulators and bolts of CSD are extracted in the detected images using template matching algorithm. After that, an improved Bag of Features (BOF) model is proposed for the defect detection of CSD. Furthermore, in order to further improve the detection efficiency, AlexNet is trained for the defect detection and identification of CSD. The experimental results show that the proposed methods can detect the defects of CSD in time, with high robustness and accuracy.