基于粒子群优化SVM的电能质量复合扰动分类的研究  

A Research about Classification of Power Quality Multi-Disturbances Based on PSO-SVM

作　　者：胡坤[1] 余健明[1] 

机构地区：[1]西安理工大学自动化与信息工程学院,陕西西安710048

出　　处：《西安理工大学学报》2012年第3期352-355,共4页Journal of Xi'an University of Technology

摘　　要：针对暂态电能质量复合扰动的问题,提出了基于希尔伯特-黄变换和粒子群优化多分类支持向量机的暂态电能质量复合扰动检测分类的方法。利用希尔伯特-黄变换提取分类所需的特征向量作为训练数据输入粒子群参数优化的支持向量机,实现了对多种复合的暂态电能质量扰动问题分类。从仿真结果可以看出,该方法可以对常见的复合暂态电能质量扰动信号进行检测和分类,且结果精确。Detection method based on Hilbert-Huang transformation and PSO-SVM is in the aim of power quality multi-disturbances,suggested to make the classification and recognition of the disturbances of power quality in this paper.Hilbert-Huang transform is used to extract the significant feature vectors needed for classification which can be used as trained data input into the PSO-SVM so as to achieve the classification of multi-compound instant power quality disturbance problem.It can be seen from the simulation results that this method can be used to delect and classify the common compound instant power quality disturb signals with the accurate results.

关 键 词：暂态电能质量复合扰动 分类 希尔伯特-黄变换 支持向量机 粒子群优化算法 

分 类 号：TM712[电气工程—电力系统及自动化]