WNN Fault Diagnosis Model with Modified Parameter Initialization for Analog Circuit
Download as PDF
DOI: 10.23977/icamcs.2018.047
Author(s)
Yanming Wei, Baohua Zhang, Jingjuan Sun
Corresponding Author
Yanming Wei
ABSTRACT
To diagnose the fault in analog circuit correctly, a Wavelet Neural Network (WNN) method is proposed with improvement of parameter initialization. Considering the shortcoming of traditional randomization method of WNN initialization, a new initialization method is introduced to improve the capability of WNN model, which considers not only the initialization of connection weights, but also the initialization of the expansion factor and translation factor. The simulation shows that the proposed method has a good diagnosis capability for the fault in analog circuit.
KEYWORDS
Wavelet neural network, parameter initialization, analog circuit, fault diagnosis