ZPW-2000A type uninsulated track circuit fault diagnosis method

Abstract

The invention provides a ZPW-2000A type uninsulated track circuit fault diagnosis method based on a DBM-SVM. The ZPW-2000A type uninsulated track circuit fault diagnosis method based on the DBM-SVM isused for solving the problems of randomness, low diagnosis precision, large error and long period of manual detection. The diagnosis method comprises the following steps: dividing original data intoa training sample set and a test sample set; taking training sample set data as input data of the DBN; extracting features of track circuit fault original data, training a binary tree type support vector machine multi-class classifier by adopting the extracted features of the track circuit fault original data, and sending a test sample set into the binary tree type support vector machine multi-class classifier for classification to obtain a diagnosis result. According to the invention, based on the DBM-SVM model, fault diagnosis is carried out on the ZPW-2000A uninsulated track circuit, the diagnosis performance is stable, the precision is high, the error is small, the work period is short, and the fault diagnosis efficiency of the uninsulated track circuit is improved.

Description

technical field [0001] The invention belongs to the field of rail transit safety and troubleshooting, in particular to a ZPW-2000A non-insulated rail circuit fault diagnosis method based on a Deep Belief Network (DBN) and a Support Vector Machine (SVM) model. Background technique [0002] With the expansion of city scale and the improvement of people's living standards, urban rail transit plays an increasingly important role in people's daily life and communication, and the safe operation of rail transit is even more important. In the safe operation of rail transit, the normal operation of the track circuit is the prerequisite for ensuring the safety of the train. However, due to the complex structure of the track circuit, the harsh working environment, and prone to failures, the safe operation of the train cannot be effectively guaranteed. [0003] In the rail transit system, China's ZPW-2000A non-insulated track circuit is a track circuit developed on the basis of the Fre...

AI Technical Summary

Problems solved by technology

[0005] In order to improve the detection efficiency of the track circuit and overcome the problems of randomness, low diagnostic accuracy, large error and long cycle in manual detection, the present invention provides a ZPW-2000A non-insulated track circuit fault diagnosis method, which overcomes the traditional manual fault characteristics Uncertainties and errors brought about by extraction can realize high-precision diagnosis of track circuit faults and ensure safe operation of trains

Images