A non-invasive diagnosis method for on-board electrical system faults of unmanned trains

Abstract

The invention discloses a non-intrusive diagnosis method for faults in an on-board electrical system of an unmanned train, which includes: collecting multiple sets of modeling data under different known fault types; The voltage and current time series of electrical equipment are used as the deep learning model of the output vector, and the trained deep learning model is obtained; the power feature is extracted; the feature selection method and classifier are determined; multiple sets of measured data are collected, and the total voltage time corresponding to the measured data is The sequence and total current time series are input into the deep learning model as input vectors, the power features in each output vector output by the measured data after passing through the deep learning model are extracted, the power features corresponding to the measured data are selected, and they are input into the classifier for classification. The device outputs the fault type of the electrical system to be diagnosed. The invention has high electric load decomposition accuracy, high power characteristic analysis performance, high accuracy of fault diagnosis results and good timeliness.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis, and in particular relates to a non-invasive diagnosis method for a fault in an on-board electrical system of an unmanned train. Background technique [0002] With the development of the times, rail transit is playing an increasingly important role in the field of global public transportation. The urgent needs of the government and society put forward higher and higher requirements for the safety, efficiency and operating cost of rail transit. Rail transit intelligence is one of the cores of the current and future rail transit industry development. Unmanned railway vehicles are an important embodiment and core representative of the intelligence level of the rail transportation industry. For unmanned smart trains, the electrical system is the core component to ensure the safety and comfort of the entire train operation. [0003] In order to improve transportation safety assurance capabil...

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