Fault Pattern Recognition of Axle Box Bearings for High-speed EMU Based on Onboard Real-time Temperature Data

Abstract

Axle box bearing a very vulnerable mechanical component because of its heavy load and unpleasant working environment. Once a fault occurs, it will develop rapidly and seriously threaten the safety of train operation. Therefore, fault pattern recognition of axle box bearing is of great significance. The traditional diagnosis method of axle box bearing is based on vibration signal processing technology and trackside acoustic diagnosis, while the axle box bearing of high-speed EMU in China has not been equipped with acceleration sensors and not every line has been equipped with trackside acoustic diagnosis equipment. Therefore, this paper establishes a fault pattern recognition method based on onboard real-time temperature data of axle box bearing, which can effectively recognize the abnormal condition of a high-speed EMU axle box bearing or an axle box bearing sensor failure.