摘要
为了获得理想的模拟电路故障诊断效果,提出一种改进粒子群算法选择特征和神经网络参数的模拟电路故障诊断模型.对模拟电路故障诊断问题进行分析,提取模拟电路故障诊断特征,采用改进粒子群算法对故障特征和RBF神经网络的学习速率、动量因子进行优化和选择,建立模拟电路故障诊断分类器.通过应用实例对模型性能进行了对比分析,结果表明,相对于经典的模拟电路故障诊断模型,改进模型的模拟电路故障诊断率大幅度提高,故障诊断效率也得到相应的改善.
In order to obtain ideal fault diagnosis results,this paper presents a fault diagnosis model based on improved particle swarm algorithm to select features and parameters of neural network.Fault diagnosis situation of analog circuit is analysis and extract feature of analog circuit,and secondly,improved particle swarm optimization algorithm selects the features and parameters of RBF neural network to establish fault diagnosis classifier of analog circuits.The application experiment test the performance and the results show that compared with the classical fault diagnosis models,fault correct rate of the proposed model is greatly improved,and analog circuit fault efficiency has been improved.
出处
《内蒙古师范大学学报（自然科学汉文版）》
CAS
北大核心
2016年第1期55-59,共5页
Journal of Inner Mongolia Normal University(Natural Science Edition)
基金
广西教育厅高校科研项目(YB2014486
201204LX556)
关键词
模拟电路
故障诊断
RBF神经网络
混沌理论
粒子群优化算法
analog circuit
fault diagnosis
RBF neural network
chaos theory
particle swarm optimization algorithm
