Paper Title:

Performance Assessment on Two Kinds of GA-Based Neural Networks in Fault Diagnosis

Periodical Advanced Materials Research (Volumes 403 - 408)
Main Theme MEMS, NANO and Smart Systems
Edited by Li Yuan
Pages 3090-3094
DOI 10.4028/www.scientific.net/AMR.403-408.3090
Citation Xiao Gang Jian et al., 2011, Advanced Materials Research, 403-408, 3090
Online since November, 2011
Authors Xiao Gang Jian, Jian Gxin Huang
Keywords BPNN, Fault Diagnosis, GA, PNN, Transformer
Price US$ 28,-
Article Preview
View full size
Abstract

In this paper, we analyze characteristics of two kinds of GA-Based neural networks. For large scale neural networks, it is necessary to optimize the initial network parameters. Using the global optimum ability of GA(Genetic Algorithm), we optimize the initial weights and biases of BPNN (Back-Propagation Neural Networks), which can avoid the local minimum. And we also optimize the spread coefficient of Gaussian Radial Basis Function of PNN (Probabilistic Neural Networks). Then the results in transformer fault diagnosis are compared. Experimental results based on Matlab show that the method of GA-Based greatly increases the reliability of diagnosis.