基于遗传神经网络的漏磁非线性回归分析  

Nonlinear regression analysis of the leakage field based on neural networks and genetic algorithms

作　　者：王群京[1] 鲍晓华[1] 钱吉吉 倪有源[1] 

机构地区：[1]合肥工业大学电气与自动化工程学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2005年第9期1053-1056,共4页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(50077005)

摘　　要：文章针对人工神经网络易陷入局部极小、收敛速度慢的缺点,而遗传算法具有全局寻优的特点,将二者结合起来形成一种遗传神经网络的混合算法;通过实例分析和统计学检验,表明该算法可以运用于爪极发电机漏磁非线性回归分析中,并且遗传神经网络非线性回归是准确和高效的。In order to overcome the shortcomings of the artificial neural network（ANN） that it is usually trapped to a local optimum and has a low rate of convergence,considering the advantage of global optimal searching of the genetic algorithm（GA）, a combining algorithm for neural network training is formed by combining the ANN and the GA. The results of real examples and statistical tests show that this algorithm can be effective and reliable for nonlinear regression analysis.

关 键 词：人工神经网络 遗传算法 非线性回归 爪极发电机 

分 类 号：TM301[电气工程—电机]