Urban rail transit 1500V DC switch trip fault intelligent classification

This paper introduces a classification of 1500V DC switch trip fault based on K-means algorithm. According to the trip duration at the time of the trip fault and the change of electrical volume, scatter diagram is drawn by Matlab, and the Euclidean distance from each point to each cluster center is calculated to complete the classification by comparing the distance sum between the new cluster center and the last round of cluster center. The proposed method aims to classify the DC switch trip faults of rail transit in detail and meet the requirements of rapid maintenance better. Through experimental comparison, it is concluded that when K=7, the SC coefficient of K-means performance index is 0.8326, which is the closest to 1 and the classification is complete compared with other K values, and the effect is good.