In order to effectively monitor the operation state of in-wheel motor used in the electric vehicle and ensure the safety of the whole vehicle, an intelligent diagnosis method based on Weibull mixture model (WMM) and hidden Markov model (HMM) is proposed for bearing faults of in-wheel motor, that is simply known as a WMM-HMM diagnosis method. First, vibration signals of in-wheel motor are extracted for sensitive symptom parameters (SPs) which are used to characterize the bearing’s operation state and establish the observation sequence. Second, WMM is used to expand the limited observation sequence under various operating conditions of in-wheel motor to obtain sufficient observation sequence as the training sample set of HMM, and HMM parameters are determined through combination of supervised and unsupervised learning algorithm. Then the WMM-HMM diagnosis models are constructed under low and medium speed conditions respectively. Finally, the corresponding fault in-wheel motors were customized and the test bench was built to verify the proposed method. The results show that the proposed method can accurately identify the bearing faults of in-wheel motor under different conditions and has good generalization and applicability in the comparison with different methods.