A rail transit fault identification method and system based on improved Bayesian

Abstract

The invention discloses a rail transit fault identification method and system based on improved Bayesian. The method is as follows: 1) Determine various failure modes and corresponding monitoring quantities of each transportation equipment according to the circuit structure of the transportation equipment, and establish a failure model for each failure mode and corresponding monitoring quantities; The parent-child relationship between the monitoring data is obtained to obtain the standard fault sample data; 3) The standard fault sample data is used to train the Bayesian algorithm to obtain the fault identification model; the weight of the parent node in the fault identification model of each fault mode is Greater than the weight of the sub-node; 4) Real-time monitoring and collection of various monitoring quantities of traffic equipment, and record their time series; 5) Use the fault identification model to identify the data and determine the corresponding fault. The invention improves the accuracy of fault identification, shortens the time for repairing faults, enables fault self-diagnosis of equipment, and ensures driving safety from two aspects of operation and maintenance and equipment.

Description

technical field [0001] The invention provides a rail transit fault identification method and system improvement based on improved Bayesian, and relates to technical fields such as railway signal data, railway communication data, railway knowledge data, system alarm data, machine learning, Bayesian, etc., to solve Problems faced by data analysis of rail transit monitoring data. Background technique [0002] At present, there are three main types of monitoring and maintenance products in the field of rail transit (state-owned railways, enterprise railways and urban rail transit): CSM (Centralized Signal Monitoring System), various equipment maintenance machines, and communication network management systems. In order to improve the modern maintenance level of my country's railway signal system equipment, since the 1990s, TJWX-I and TJWX-2000 have been independently developed and continuously upgraded signal centralized monitoring CSM systems. At present, most of the stations h...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems of large workload, low efficiency and high risk in the manual diagnosis of railway signal system faults in the prior art, the present invention provides a rail transit fault classification and identification method and system based on improved Bayesian

Images