Non-intrusive fault diagnosis method for vehicle-mounted electrical system of unmanned train

Abstract

The invention discloses a non-intrusive fault diagnosis method for a vehicle-mounted electrical system of an unmanned train. The non-intrusive fault diagnosis method comprises the following steps: collecting multiple groups of modeling data under different known fault types; based on a deep learning model taking the total voltage and total current time sequence as an input vector and taking the voltage and current time sequence of each electrical device as an output vector, obtaining a trained deep learning model; extracting power features; determining a feature selection method and a classifier; collecting multiple groups of measured data, inputting a total voltage time sequence and a total current time sequence corresponding to the measured data as the input vector into the deep learning model, extracting electric power features in each output vector output after the measured data passes through the deep learning model, selecting the electric power features corresponding to the measured data, inputting the selected electric power features into the classifier, and allowing the classifier to output the fault type of an electrical system to be diagnosed. The method is high in power load decomposition accuracy, high in power feature analysis performance, high in fault diagnosis result accuracy and good in timeliness.

Description

Technical field[0001]The present invention belongs to the technical field of fault diagnosis, and in particular, the present invention relates to a non-invasive diagnosis method of automatic vehicle in-vehicle electrical system failure.Background technique[0002]With the development of the times, rail transit plays an increasingly important role in global public transportation. The urgent needs of government and society have made increasing demands on the safety, efficiency and operational cost of rail transit. Rail transit intelligence is one of the cores of current and future rail transit industries. Unmanned railway vehicles is an important embodiment of the intelligent level of the rail transit industry and the core representative. For unmanned smart trains, the electrical system is to ensure the safety and comfort of the entire train.[0003]In order to improve the capacity of transportation, improve transportation quality, improve transportation efficiency, and ensure that passen...

AI Technical Summary

Problems solved by technology

[0011] In order to solve the technical problem of low accuracy of power load decomposition existing in the existing non-invasive electrical system fault diagnosis method, the technical solution adopted in the present invention is:

Images