Online monitoring fault diagnosis system and method of train power system

Abstract

The invention belongs to the field of train fault diagnosis, and particularly relates to an online monitoring fault diagnosis system and method of a train power system. The system mainly comprises a train power device, a signal detection unit, a signal processing unit and a fault diagnosis unit. According to the method, the related state quantity of each device of the power system is obtained through sensors; a signal conditioning board of the power system conducts digital filtering and wavelet de-noising on signals so as to complete elimination of the noise signals and extract the useful signals; a wavelet algorithm is used for completing feature extraction of the wavelet energy spectrum, and the feature quantity of each subsystem is input into a corresponding sub-network to undergo fault diagnosis; the diagnosis results of all the sub-networks are fused at a central node, and fault diagnosis is completed initially; finally, fuzzy fusion is conducted on the diagnosis results of all the sub-networks so as to complete final positioning and diagnosis of faults. The online monitoring fault diagnosis system and method of the train power system have the advantages of being rapid, efficient, high in accuracy rate, high in reliability and high in network automation degree.

Description

technical field [0001] The invention belongs to the field of train fault diagnosis, and in particular relates to a system and method for on-line monitoring fault diagnosis of a train power system. Background technique [0002] With the rapid development of urban rail transit, how to ensure the safe and stable operation of trains has become an important issue, and the power system is a key subsystem of the train. Real-time monitoring of various state quantities of the train power system and system failure Diagnosis is the key to ensure the reliable operation of trains. However, most of the traditional fault diagnosis methods are manually diagnosed, which is time-consuming, labor-intensive, and has low accuracy and reliability, which affects the maintenance, debugging and replacement of the system. Moreover, the train system is intricate, and there are gaps between subsystems and equipment. The interference makes the detection signal distorted by noise interference, which can...

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to propose a system and method for on-line monitoring and fault diagnosis of train power systems for the problems of low accuracy and low efficiency of current train fault diagnosis

Images