论文信息 - Research on Soft Fault Diagnosis of Wavelet Neural Network Based on UKF Algorithm for Analog Circuit

Research on Soft Fault Diagnosis of Wavelet Neural Network Based on UKF Algorithm for Analog Circuit

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.

Qian Wang | Shiyao Ren | Huida Zheng

[1] Jeffrey K. Uhlmann,et al. Reduced sigma point filters for the propagation of means and covariances through nonlinear transformations , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[2] He Yigang. The State-of-the-Art of Fault Diagnosis of Analog Circuits and Its Prospect , 2004 .

[3] Tao Xie,et al. Fault Diagnosis of Analog Circuit Based on High-Order Cumulants and Information Fusion , 2014, J. Electron. Test..

[4] Zhou Jing-jin. Research on analog circuit fault diagnosis based on neural network method , 2015 .

[5] Qinghua Zhang,et al. Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[6] Bojan Stopar,et al. Wavelet Neural Network employment for continuous GNSS orbit function construction: Application for the Assisted-GNSS principle , 2013, Appl. Soft Comput..