|
|
中国电机工程学报 2008, 28(24) 70-74 DOI:
ISSN: 0258-8013 CN: 11-2107/TM |
|
|
|
|
本期目录 |
下期目录 |
过刊浏览 |
高级检索
[打印本页]
[关闭] |
|
| 电力电子与电力传动 |
|
|
基于新型粒子群算法的电力电子装置在线故障诊断方法 |
|
|
陈如清 |
|
|
嘉兴学院机电工程学院 |
|
|
摘要：
分析了12脉波可控整流电路的294种故障模式，根据整流电压畸变波形提出一种特殊的故障分类方法。通过对故障电压波形的逻辑预处理得出12维故障向量及相应的故障编码。为改善粒子群算法(particle swarm optimization，PSO)的性能提出一种改进的带扰动项粒子群算法。引入进化速度因子，当粒子进化速度低于一定值时在粒子速度更新方程中添加一扰动项，算法的搜索效率和全局优化性能显著提高。将改进算法用于神经网络故障诊断建模，实验结果表明该系统具有诊断速度快、精度高的特点。适用于复杂电力电子设备或系统的故障诊断场合。 |
|
|
关键词：
逻辑预处理
故障模式
带扰动项粒子群算法
在线故障诊断
|
|
|
A Novel PSO Based On-line Fault Diagnosis Approach for Power Electronic System |
|
|
CHEN Ru-qing |
|
|
|
|
|
Abstract:
294 fault patterns of 12-pulse waveform controlled rectifier circuit were studied. A special fault classification method according to the rectifier aberrant voltage waveforms was presented. 12-dimension fault vectors and their corresponding fault codes were obtained through logically preprocessing the fault voltage waveforms. An improved particle swarm optimization (PSO) with disturbance (DPSO) was put forward to enhance the performance of PSO by introducing an evolution speed factor in standard PSO. A disturbance would be added to the velocity update equation when the factor decreased under a certain value. It enhanced the searching efficiency and improved the global optimization quality effectively. DPSO was applied in neural network fault diagnosis modeling. Experiment study demonstrates that the proposed technique is low time consuming with high fault identification rate. It is suitable for the fault diagnosis of complex power electronic devices or systems. |
|
|
Keywords:
logical preprocessing
fault pattern
particle swarm optimization with disturbance
on-line fault diagnosis
|
|
|
收稿日期 2007-04-04 修回日期 1900-01-01 网络版发布日期 |
|
|
DOI: |
|
|
基金项目:
|
|
|
通讯作者: 陈如清 |
|
|
作者简介: |
|
作者Email: ruqing2002@163.com |
|
|
| 参考文献： |
|
| 本刊中的类似文章 |
|
| Copyright by 中国电机工程学报 |
