一种基于PSO-SVM的电能质量扰动识别与分类的新方法  

A New Method of Power Quality Disturbance Identification and Classification Based on the PSO- SVM

作　　者：杨宁霞[1] 孙晧[1] 公政 高建成 

机构地区：[1]山东科技大学电气与自动化工程学院,山东青岛266590 [2]山东电力潍坊市供电公司,山东潍坊261000 [3]山东电力新泰市供电公司,山东泰安271200

出　　处：《电测与仪表》2014年第16期17-20,共4页Electrical Measurement & Instrumentation

基　　金：山东省自然科学基金资助项目(ZR2012EEM021);山东省科技发展计划资助项目(2012G0020503);山东科技大学研究生创新基金资助项目(YC140213)

摘　　要：针对目前电网电能质量扰动识别与分类中采用的SVM分类器参数难以选择的问题,提出了一种基于粒子群(PSO)优化SVM的电能质量扰动识别新方法。利用MATLAB软件对实际电网中常见的5种扰动信号进行建模,将检测到的电压信号经复小波变换后作为PSO-SVM的输入样本进行训练和测试。仿真结果表明,该方法能够快速、可靠地对电能质量扰动进行识别与分类,对电网的电能质量监测具有较高的应用价值。Aiming at the current difficulty in choosing the classifier parameter of SVM for the power quality disturbance identification and classification, the paper put forward a new method of power quality disturbance identification based on the particle swarm optimization （PSO） SVM. Five kinds of common power quality disturbance signals were modeled by means of the MATLAB software, and the detected voltage signals were used as the input samples of the PSO-SVM training and testing after complex wavelet transform. The simulation results showed that the method could identify and classify the power quality disturbance quickly and reliably, and it had a high application value for power quality monitoring of the power grid.

关 键 词：电能质量扰动 SVM分类器 PSO 复小波变换 电能质量监测 

分 类 号：TM76[电气工程—电力系统及自动化]