Contrast analysis of hysteresis curve fitting between optimized GRNN and BP neural network

HE Han-lin1， MENG Ai-hua1， ZHU Jia-ming1， SONG Hong-xiao2
（1. College of Mechanical Engineering， Hangzhou Dianzi University， Hangzhou 310018， China；  2. Hangzhou Zhejiang University Jingyi Electromechanical Technology Engineering Co.， Ltd.， Hangzhou 310000， China）

Abstract： Aiming at the nonlinear hysteresis curve of the giant magnetostrictive material（GMM），the generalized regression neural network（GRNN）and feed-forward BP neural network were applied to approach it. With the training and prediction of the networks，as well as comparing with the Jiles-Atherton（J-A）model，the approaching effect of the networks was analyzed，which guides the applying of the GMM well. Between them，the GRNN was trained by cross-validation method in order to enlarge the sample capacity. The best radial basis function expansion coefficient（SPREAD）was found out using circulation，and the conventional GRNN was optimized. The results indicate that the accuracy on the hysteresis curve predicted by optimized GRNN is obviously higher than the one done by BP.
Key words： giant magnetostrictive material（GMM）； generalized regression neural network（GRNN）； BP neural network； hysteresis curve fitting