The wheel hub motor is the power source of the four-wheel independent drive system of the electric vehicle, and its operating state is directly related to the safety of the whole vehicle. In order to gradually realize the monitoring of the running state of the wheel hub motor, a new method, the order self-separation method, is proposed to adapt to its complex and varied driving conditions. The method overcomes the limitation that the traditional order tracking method needs to simultaneously collect the rotational speed signal and the vibration signal, only studies the rotational speed signal, and extracts the abnormal fluctuation components contained therein, and learns the non-stationary time domain by referring to the traditional order tracking method. The signal processing method performs angular domain resampling and Fourier transform on the wave components, highlighting the fault characteristics contained in the speed signal, and further solving the fault diagnosis of the wheel hub motor. Combined with MATLAB simulation analysis and wheel motor leakage test, the results show that the order self-separation method can effectively identify the wheel hub motor leakage fault characteristics.