Intelligent rail unmanned vehicle fault gene identification method and system

Abstract

The invention discloses an intelligent rail unmanned vehicle fault gene identification method and system. The method comprises the following steps of: acquiring historical vibration data of a train by adopting an incremental web crawler-based method; preprocessing the vibration amplitude EA and the vibration period ET of the vibration data, and outputting a new X; taking the X as the input of a fault detection module, and outputting fault sequence data E after detecting a fault sequence; taking the fault sequence data E as input of a dimension reduction model, and outputting encodable gene sequences I1, I2, I3 and I4; integrating the encodable gene sequences I1, I2, I3 and I4 into a DNA sequence S=S1, S2, S3,..., SN, extracting base characteristics of the DNA sequence, and permuting and combining the base characteristics to form a predictable pre-judged candidate vehicle part fault gene Vs; and training a bidirectional long-short-term memory network deep learning model by using the candidate vehicle part fault gene to obtain a classification model. The method can accurately identify the position and the type of the vehicle fault.

Description

technical field [0001] The invention relates to the field of fault identification, in particular to a fault gene identification method and system for an intelligent rail driverless vehicle. Background technique [0002] With the development of key technologies for road and vehicle construction, high-speed rail has become the mainstay of my country's transportation. In recent years, the operating speed of high-speed rail and the improvement of automated driving have put forward higher requirements for its safety. Train safety has become the focus of international traffic. At present, the unmanned driving level of most high-speed railways in China has reached GOA2 (supervised train automatic driving). If the failure of the train's component modules can be diagnosed in time or even in advance, it can play an important role in guaranteeing the safety of the train. [0003] At this stage, fault identification methods for unmanned trains mainly include manual diagnosis, dismantl...

AI Technical Summary

Problems solved by technology

The above methods generally determine whether a component is faulty by setting a certain threshold. These methods have certain limitations, including insufficient fault judgment accuracy and small fault judgment range, which seriously affect the fault identification accuracy.

Images