计算机应用研究2012，Vol.29Issue(1)：72-74,111,4.DOI:10.3969/j.issn.1001-3695.2012.01.019
基于PSO-RBF神经网络的模拟电路诊断
Analog circuit diagnosis based on particle swarm optimization radial basis function network
摘要
Abstract
In order to improve the speed and accuracy of analog circuit fault diagnosis using radial basis funtion neural network (RBFNN) , this paper proposed a new fault diagnosis method based on RBFNN optimized by particle swarm optimization (PSO). Trained RBFNN by the PSO algorithm which overcame the shortcomings that structure and parameters of neural network were hard to be set. Preprocessed the response signals of analog circuit by wavelet packet transform as the fault feature. The simulation result shows that this method which has higher diagnostic accuracy and faster convergence speed is effective for fault location.关键词
模拟电路/故障诊断/径向基神经网络/粒子群算法/小波包分解Key words
analog circuit/ fault diagnosis/ radial basis function network/ particle swarm optimization/ wavelet packet分类
信息技术与安全科学引用本文复制引用
宋丽伟,彭敏放,田成来,沈美娥..基于PSO-RBF神经网络的模拟电路诊断[J].计算机应用研究,2012,29(1):72-74,111,4.基金项目
国家自然科学基金资助项目(60973032,60673084) （60973032,60673084）
湖南省自然科学基金重点资助项目(10JJ2045) （10JJ2045）
