期刊文献+

基于PSO—RBF监测预测模型的电力电子电路 预览

Fault Condition Monitoring Power Electronic Circuits Based Prediction Technique of on PSO-RBF Neural Network
在线阅读 下载PDF
收藏 分享 导出
摘要 针对现有电力电子电路故障状态预测技术的不足,提出将电路特征性能参数与粒子群算法(PS0)优化的径向基函数(RBF)神经网络相结合,对电力电子电路进行故障状态监测预测.以电源电路中Buck电路为例,选择电路输出电压作为监测信号,提取输出电压平均值及纹波电压值作为电路特征性能参数,并利用改进后的RBF神经网络实现状态预测.结果表明,利用PSO改进后的RBF神经网络对电路输出平均电压和纹波电压的预测比单纯RBF神经网络预测的结果更加精准,能够跟踪电源电路状态特征性能参数的变化趋势,有效实现电力电子电路状态监测和预测. Aiming at the issue of fault condition monitoring prediction technique of power electronic circuits, a method based on characteristic parameter data and particle swarm optimization(PSO) radial basis function (RBF) neural network for the fault condition monitoring prediction of power electronic circuits was proposed. The Buck converter circuit was taken as an example, then the average voltage was extracted as characteristic parameters, the fault prediction of power electronic circuits was achieved. The output voltage was selected as monitoring signal, then the average voltage was extracted as characteristic parameters. PSO-RBF neural network was used to predict the Buck converter circuit. The experimental results showed that the PSO-RBF neural network was more accurate in predicting than that of the only RBF neural network. The new method could trace the characteristic parameters' trend and could be effectively applied in fault condition monitoring prediction of power electronic circuits.
作者 王绅宇 陈丹江 叶银忠 WANG Shenyu , CHEN Danjiang , YE Yinzhong (1. School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai 201418, China;2. School of Electronic Information, Zhejiang Wanli University, Ningbo 315100, Zhejiang,China)
出处 《上海应用技术学院学报:自然科学版》 2015年第2期162-166,172共6页 Journal of Shanghai Institute of Technology: Natural Science
基金 国家自然科学基金资助项目(61374132)
关键词 故障状态预测 RBF神经网络 粒子群算法 电力电子电路 condition monitoring prediction RBF neural network particle swarm optimization(PSO) power electronic circuits
作者简介 王绅宇(1988-),男,硕士生,主要研究方向为故障诊断与容错控制.E—mail:Wangshenyu00@163.com 通信作者:叶银忠(1964-),男,教授,博士生导师,主要研究方向为控制理论与控制工程、系统仿真技术等.E—mail:yzye@sit.edu.cn
  • 相关文献

参考文献16

  • 1李娟,周东华,司小胜,陈茂银,徐春红.微小故障诊断方法综述[J].控制理论与应用,2012,29(12):1517-1529. 被引量:55
  • 2Demetriou M A, Polycarpou M M. Incipient fault diagnosis of dynamical systems using online approxi- mators[J]. IEEE Transactions on Automatic Con- trol, 1998, 43(11): 1-3. 被引量:1
  • 3Chen S, Wolfgang A, Harris C J, et al. SymmetricRBF classifier for nonlinear detection in multiple-an- tenna-aided systems[J~. IEEE Transactions on Neu- ral Networks, 2008,19(5) : 735-745. 被引量:1
  • 4Gonzalez J, Rojas I, Ortega J, et al. Multi-objective evolutionary optimization o[ the size, shape, and position parameters of radial basis function networks for function approximation[J]. IEEE Transactions on Neural Networks, 2003, 14(6): 1477-1496. 被引量:1
  • 5MISHRA S, PECHT C. In-situ sensors for product reliability monitoring[JS. Proceedings SPIE, 2002, 4755 : 10-18. 被引量:1
  • 6Li J, Tang G Y. Fault diagnosis for networked con- trol systems with delayed measurements and inputs [J]. IET Control Theory ~ Applications, 2010, 4 (6) : 1047-1054. 被引量:1
  • 7Hwang I, Sungwan K, Youdan K, et al. A survey of fault detection, isolation and reconfiguration methods l-J]. IEEE Transactions on Control Systems Technol- ogy, 2010, 18(3): 636-653. 被引量:1
  • 8Yang J B, Liu J, Xu D L, et al. Optimization modds for training belief-rule-based systems [J~. IEEE Transac- tions on Systems, Man, and Cybernetics, Part A: Sys- tems and Humans, 2007, 37(4): 569-585. 被引量:1
  • 9XuZ B, XuanJ P, Shi T L, et al. Application of a modified fuzzy ARTMAP with feature-weight learn- ing for the fault diagnosis of bearing[J]. Expert Sys- tems with Applications, 2009, 36(6).- 9961-9968. 被引量:1
  • 10叶世伟 史忠植译.神经网络原理[M].北京:机械工业出版社,2004.. 被引量:40

二级参考文献85

共引文献333

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈