Author(s)

Qian Wang, Huida Zheng, Shiyao Ren

Corresponding Author

Qian Wang

ABSTRACT

In order to improve the capacity of soft fault diagnosis for analog circuit, a Wavelet Neural Network (WNN) diagnosis method based on Unscented Kalman Filter (UKF) algorithm is proposed. To overcome the shortcoming of the traditional BP algorithm of WNN, UKF algorithm is introduced to optimize the parameters of WNN, completing the training of WNN. The simulation shows that the proposed modeling algorithm has the better diagnosis capacity. This also verifies the feasible and effectiveness of proposed method.

KEYWORDS

Wavelet, neural network, unscented Kalman filter, fault diagnosis, analog circuit