Intelligent track circuit fault diagnosis method based on a BP neural network

The invention relates to the technical field of track circuit fault diagnosis, and discloses an intelligent track circuit fault diagnosis method based on a BP neural network, and the method comprises the steps: 1, monitoring the variable of a track circuit section in real time; 2, dividing a training sample and a test sample; 3, performing normalization processing on the training sample data set and the test sample data set; 4, training a BP neural network net1; and 5, diagnosing a track circuit fault by using the BP neural network net1. According to the method, 29 kinds of fault data in the track circuit are tested through the BP neural network, and the test accuracy is high; when a fault occurs, the position where the fault occurs can be rapidly positioned firstly, the accuracy rate can reach 99.9%, meanwhile, the fault type can be specifically judged, and the accuracy rate is 97.13%-99.4%; guidance can be provided for field maintenance personnel, the maintenance time is reduced, and the reliability of a si