Open AccessPFC fault detection method for EV wireless charging system based on hidden markov model
Author(s) -
Changfu Xu,
Bing Bo,
Ruoyin Wang,
Ming Zhang,
Xu Jun
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1311/1/012005
Subject(s) - hidden markov model , fault (geology) , viterbi algorithm , computer science , wireless , rectifier (neural networks) , inverter , real time computing , engineering , speech recognition , artificial intelligence , electrical engineering , telecommunications , artificial neural network , voltage , stochastic neural network , seismology , recurrent neural network , geology
The PFC device serves as an important bridge between rectifier module and high-frequency inverter module in the wireless charging system of electric vehicle (EV). Once this device fails, it will not only have a serious impact on the power grid, but also cause irreversible damage to the back-end high-frequency inverter module. Traditional fault diagnosis methods are difficult to meet the requirements of complex systems. In this paper, HMM which has unique advantages in training model and fault identification is used for fault diagnosis of PFC device of EV wireless charging system. Firstly, the model is initialized and the initial values of HMM are determined. Then, Baum-Welch algorithm is used for iterative training. Finally, Viterbi algorithm is used for fault diagnosis. The test results show that the PFC fault diagnosis accuracy of EV wireless charging system using HMM is about 25% higher than the traditional method, and the recognition speed is significantly improved.