| 电力电子主电路故障诊断方法研究 |
| |
| 引用本文： | 郑连清,邹涛,娄洪立.电力电子主电路故障诊断方法研究[J].高电压技术,2006,32(3):84-86,98. |
| |
| 作者姓名： | 郑连清 邹涛 娄洪立 |
| |
| 作者单位： | 重庆大学电气工程学院,重庆,400044 |
| |
| 基金项目： | 重庆大学高电压与电工新技术教育部重点实验室访问学者资助项目 |
| |
| 摘 要： | 提出了采用小波分析和神经网络诊断电力电子装置故障诊断的方法,分析了三相桥式可控整流电路的故障波形特点,将利用小波变换模极大值和多尺度分析理论提取的故障特征输入神经网络诊断故障。归纳了故障诊断需知的3个条件以实现控制角的检测、故障的分类和定位。仿真表明该方法有效。
|
| 关 键 词： | 多尺度分析 频带能量分析 神经网络 故障诊断 |
| 文章编号： | 1003-6520（2006）03-0084-03 |
| 收稿时间： | 2005-03-09 |
| 修稿时间： | 2005-03-09 |
Fault Diagnosis of Power Electronic Circuits Based on Wavelet Transform and Neural Network |
| |
| ZHENG Lianqing,ZOU Tao,LOU Hongli.Fault Diagnosis of Power Electronic Circuits Based on Wavelet Transform and Neural Network[J].High Voltage Engineering,2006,32(3):84-86,98. |
| |
| Authors: | ZHENG Lianqing ZOU Tao LOU Hongli |
| |
| Affiliation: | College of Electrical Engineering, Chongqing University, Chongqing 400044, China |
| |
| Abstract: | Based on wavelet transform and neural network theory,a new fault diagnosis method for power electronic main circuits is presented.In this paper,the fault diagnosis of three-phase SCR rectifier circuit will be taken as an example to illustrate the method: analyzing the fault cases,drawing out the fault characteristics as the inputs of neural network to realize fault diagnosis based on module maximum of wavelet transform and multi-scale analysis. The paper induces fault diagnosis conditions,analyzes triggering angel detection,classifies and localizes circuit fault.This method is demonstrated to be valid with the simulation results. |
| |
| Keywords: | multi-scale analysis energy analysis in frequency bands neural network fault diagnosis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
