As an important bridge between the rectification module and the high-frequency inverter module in the wireless charging system of electric vehicles, the power factor correction(PFC) device not only has a serious impact on the power grid, but also causes irreversible damage to the back-end high-frequency inverter module. Therefore, fast and accurate fault detection is needed. Traditional fault detection methods have long detection time and low detection accuracy. Therefore, a fault detection method of PFC device in the wireless charging system of EVs based on hidden Markov model(HMM) is proposed. Firstly, the model is initialized. Then Baum-Welch algorithm is used for fault model training. Finally, Viterbi algorithm is used for fault detection. Simulation results show that the accuracy of PFC device fault detection using HMM is about 40% higher than that of neural network and support vector machine, which is a fast and accurate method. Therefore, HMM is used to effectively identify the type of PFC device fault in the wireless charging system of electric vehicles.