长沙理工大学学报：自然科学版2012，Vol.9Issue(4)：53-57,5.
SA-LM优化WNN及其在模拟电路故障诊断中的应用
SA-LM optimized WNN and its aplication in analog circuit diagnosis
摘要
Abstract
To solve the continuous and compact wavelet neural network(WNN)'s slow con- vergence speed problem, the Levenberg-Marquardt (LM) algorithm is proposed to improve the WNN, and in order to overcome the LM-WNN's shortcomings that it has too fast con- vergence speed, which make it easily trapped in local minimum points and platform, simu- lated annealing (SA)algorithm is used to optimize the parameters of the wavelet neural net- work, which results a group of approximate solution. The approximate solution is put as the initial value of weights and threshold matrix of the LM-WNN ,to ensure that the LM- WNN converge to the global minimum point. Apply the SA-LM-WNN in analog circuit fault diagnosis problem, simulation results show that the algorithm can quickly converge to the global minimum, and the simulation effect is good.关键词
模拟退火/Levenberg-Marquardt连续型小波神经网络/模拟电路故障诊断Key words
simulated annealing/Levenberg-Marquardt WNN/analog circuit fault diagnosis分类
计算机与自动化引用本文复制引用
欧伦伟,刘辉,张杰,彭善华..SA-LM优化WNN及其在模拟电路故障诊断中的应用[J].长沙理工大学学报：自然科学版,2012,9(4):53-57,5.基金项目
湖南省科技厅科研资助项目 （）
