A New Contactless Fault Diagnosis Approach for Pantograph-Catenary System Using Pattern Recognition and Image Processing Methods

Abstract

Comfort and safety of railway transport has become more important as train speeds continue to increase. In electrified railways, the electrical current of the train is produced by the sliding contact between the pantograph and catenary. The quality of the current depends on the reliability of contact between the pantograph and catenary. So, pantograph inspection is very important task in electrified railways and it is periodically made for preventing dangerous situations. This inspection is operated manually by taking the pantograph to the service for visual anomalies. However, this monitoring is impractical because of time consuming and slowness, as locomotive remains disabled. An innovative method based on image processing and pattern recognition is proposed in this paper for online monitoring of the catenary-pantograph interaction. The images are acquired from a digital line-scan camera. Data are simultaneously processed according to edge detection and Hough transform, and then the obtained features are provided to a D-Markov based state machine, and the pantograph related faults, such as overheating of the pantograph strip, bursts of arcing, and irregular positioning of the contact line are diagnosed. The proposed method is verified by real faulty and healthy pantograph videos.