Research on Identification Method of Track Circuit State of Urban Rail Vehicles Based on CEEMDAN-SVM

Real time identification of the running state of the track circuit of urban rail vehicles is of great significance to the safe operation of trains. In this paper, a SVM based method for identifying the running state of urban rail vehicle track circuit is proposed. According to the real-time monitoring data of each sensor of the track circuit of the urban rail vehicle, the method of collective empirical mode decomposition is used to extract the features of the voltage signal. Finally, the running state of the track circuit is divided into three states: normal, mild failure and failure.