Arc Detection and Recognition in the Pantograph-Catenary System Based on Multi-Information Fusion

Abstract

The pantograph-catenary system is critical to high-speed railways. Electric arcs in the pantograph-catenary system indicate possible damages to the whole railway system, and detecting them in time has been a critical task. In this paper, a fusion method for the pantograph-catenary arc detection based on multi-type videos is proposed. First, convolutional neural network (CNN) is employed to detect arcs in visible light images, and a threshold method is applied to identify arcs in infrared images. Second, the CNN-based environment perception model is established on visible light images. It obtains the dynamical adjustment of the reliability weights for different scenarios where trains usually work. Finally, the information fusion model based on evidence theory uses those weights and integrates the detection results on visible light images and infrared results. The experimental results demonstrate the fusion method can avoid misjudgments of the two individual detection methods in certain scenarios, and perform better than each of them. This approach can adapt to the complex environments of high-speed trains.