Fault detection method and system for turnout switching equipment based on multiple algorithms

Abstract

The invention discloses a fault detection method and system for turnout switching equipment based on multiple algorithms, and the method comprises the steps: storing three-phase current data collectedby a three-phase current collection system on the turnout switching equipment into a database, wherein the three-phase current data is a complete representation of one action period of the turnout conversion equipment; applying the extracted feature data to the training of SVM, KNN, decision tree and neural network models to obtain and store each model; feeding the test set to each model obtainedby training; finally determining whether the turnout switching equipment is abnormal or not and fault reasons by selecting the turnout equipment in the system and selecting the obtained optimal model, and the health condition of the turnout switching equipment is judged. The data is processed, and the optimal model is trained; The real-time data of the turnout conversion equipment of the companyis input into a fault detection system of the turnout conversion equipment to obtain whether a fault occurs, a fault phenomenon and a fault reason.

Description

technical field [0001] The invention relates to the technical field of fault detection and analysis of rail transit turnout switching equipment, in particular to the fault detection and analysis of various algorithm models. Background technique [0002] With the rapid development of my country's rail transit, the huge high-speed railways and the subway systems of major cities have put forward higher requirements for the safety, reliability and maintenance efficiency of equipment after maintenance. As an important part of the signal system, the switch switching equipment is the key equipment for changing the direction of the train while it is moving. The fault analysis of turnout switching equipment has become the premise of daily maintenance and repair. Through the efficient algorithm detection method and system, instead of time-consuming and labor-intensive human fault analysis, the pass rate of turnout equipment maintenance and the success rate of maintenance have been gre...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem of low efficiency and blindness of manual fault diagnosis and the differences of turnout switching equipment in major cities, the present invention provides a fault detection method and system for turnout switching equipment based on multiple algorithms

Images