In this paper, a method of identifying the short-circuit fault current in DC traction power supply system based on local mean decomposition (LMD) and time-frequency entropy is proposed. Firstly, the feeder current signal of DC traction power supply system is analyzed by means of LMD, by which the LMD time-frequency distribution can be obtained. Secondly, the LMD time-frequency plane is divided into time-frequency blocks with equal area. Finally, the time-frequency entropy of the time-frequency plane is obtained, which can serve as the feature vector to distinguish the oscillation current and the short-circuit fault current in DC traction power supply system. According to the simulation analysis, it can be found out that the simulation results conform to the theoretical analysis. Moreover, the calculation results of the measured data show that the proposed method is capable of distinguishing the oscillation current and the short-circuit fault current in DC traction power supply system.