Applleation of Improved Neural Network Model in Fault Diagnosis
Haihua Zhu · Microcomputer applications · 2010
Considering the reduction ability of rough set theory and the adaptive and self-learning abilities of neural network,a rough set-neural network combinatorial fault diagnosis model is constructed,and Elman and BP neural network are designed and compared in this paper.The simulation results show that the combinatorial method with BP can more simplify the structure of neural network,shorten the training time of the network and improve the diagnostic accuracy.