您的位置:首页  > 论文页面

基于多维变换的模拟电路故障诊断的神经网络方法

发表时间:2010-07-31  浏览量:1525  下载量:769
全部作者: 祝文姬,何怡刚
作者单位: 湖南大学电气与信息工程学院
摘 要: 提出一种基于电路双线性函数在多维空间的变换与神经网络相结合的非线性模拟电路故障诊断新方法。该法不仅可以用于线性电路单故障、双故障及多故障的诊断,同时,非线性元件经分段线性化(piece�wise linear,PWL)后,多维变换的方法也可推广应用于非线性电路的诊断。在充分考虑基于多维变换的故障诊断方法基础上,采用神经网络融合粒子群(particle swarm optimization,PSO)的方法进行非线性模拟电路故障诊断。详述其诊断原理及诊断步骤,并给出诊断实例。
关 键 词: 模拟电路;神经网络;故障诊断;粒子群算法;双线性变换;多维变换
Title: Nonlinear analog fault diagnosis method based on transformation in multidimensional spaces and neural network
Author: ZHU Wenji, HE Yigang
Organization: College of Electrical and Information Engineering, Hunan University
Abstract: Based on a bilinear transformation in multidimensional spaces, a neural�network based nonlinear analog fault diagnostic system for actual circuits is proposed. This approach allows diagnosing single, double, and multi�faults in linear circuits. For nonlinear circuit, after the nonlinear component substituting by their piece�wise linear (PWL) models, the method can be used in nonlinear circuit fault diagnosis. Under considering the characteristics of the transformation in multidimensional space, the particle swarm optimization (PSO) algorithm�based BP neural network is applied to diagnose faults. Finally, the realization of the proposed strategy is expounded by using two examples.
Key words: analog circuits; neural network; fault diagnosis; particle swarm optimization; bilinear transformation; multidimensional transfo
发表期数: 2010年7月第14期
引用格式: 祝文姬,何怡刚. 基于多维变换的模拟电路故障诊断的神经网络方法[J]. 中国科技论文在线精品论文,2010,3(14):1492-1505.
 
0 评论数 0
暂无评论
友情链接