Pantograph Catenary Performance Detection of Energy High-Speed Train Based on Machine Vision

Abstract

With the rapid development of high-speed rail in China, addressing the issue of safety assurance during the operation of the train is very important. A very important part of a train’s power supply system is the pantograph and catenary system, which consists of a pantograph and a catenary. Failure of the pantograph-catenary system can cause significant damage to the normal operation of the train. The dynamic performance of the pantograph-catheter system must be detected in real time during the operation of the train. This paper is based on the study and analysis of pantograph-catheter dynamic performance parameters and developed a system for real-time detection of pantograph-catheter dynamic performance parameters based on a car visual system. The results are as follows: based on this detection method, the visual error is low and the accuracy is high. The machine-based directional height detection module developed in this paper has a good detection effect and high test accuracy; the arcing detection module designed in this paper can effectively detect the arcing and store the arcing pictures and can display the duration of single arcing and the arcing rate of the section in real-time. The practical application effect is good. The results show that the focal length of the camera lens is 16 mm, and the error of the machine vision system is low. The system designed in this paper may make a great contribution to the operation condition monitoring and fault diagnosis of the pantograph-catenary system of a high-speed train in the future.

Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research

“…The monitoring targets are presented in Table 3 and include everything that is part of the catenary system, including "contact point" and "contact force", although these targets are on the boundary between the catenary system and the pantograph system. Only monitoring targets which occurred in more than two references are included in their own category, other monitoring targets, such as the bird nest [17] and catenary guide height [18], have been categorized as "other monitoring targets". The classification resulted in 10 terms (except the "other monitoring targets"), as shown in Table 4.…”

Health detection of high-speed train pantograph based on deep belief network

“…However, the analysis condition was single and the simulation environment was not considered. Yang Heng [8] designed the detection program and data processing program of the LabVIEW visual development platform, and analyzed and verified various errors that may cause the detection system through experiments. However, random background noise generated during the testing process can affect the algorithm.…”