• HOME
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • Chinese
Site search        
文章摘要
基于SVM的电能质量扰动分类
Research of Power Quality Disturbance classification Based On SVM
Received:June 03, 2014  Revised:June 03, 2014
DOI:
中文关键词: 电能质量 分类 支持向量机 网格搜索法
英文关键词: Power quality, Classification ,SVM, grid search method
基金项目:吉林省科技发展计划项目(20130206049GX);吉林省教育厅项目(2014339);吉林省教育厅项目(2013297);吉林省自然科学项目(20130101052JC)
Author NameAffiliationE-mail
zhanghong* changchun instituet of technology ccitjessica@126.com 
leizhiguo Jilin Province Power Supply Company  
jinyue changchun instituet of technology  
Tanwanyu changchun institute of technology ccitjessica@126.com 
Hits: 1671
Download times: 597
中文摘要:
      电能质量扰动信号数据庞大,数据提取较难。本文对常见的电能质量扰动及其组合的复合扰动进行离散小波分解,提取PQ(Power Quality)扰动信号能量差作为特征向量,以此降低扰动分类的数据量。利用MATLAB软件产生PQ扰动训练和测试样本,并在扰动样本中加入SNR=25dB的高斯白噪声,利用SVM对扰动样本进行分类,提出两步网格搜索法对SVM的参数进行优化。仿真实验结果表明,此分类方法具有较高识别率,证明该算法的准确性和鲁棒性。
英文摘要:
      There are many electrical power quality signals in power system, It is difficult to extract disturbance signal data. This paper adopts a method of discrete wavelet transformation to extract the power quality disturbance signals; This paper extracts the subtraction of energy on each of the frequency bands as the signal feature vector. decreasing classification of disturbance data.The software of MATLAB is used to generate the disturbance signal samples and the signal-noise ratio of 25dB (SNR=25 dB) Gauss white noise was added in the samples. The libsvm is used to solve multi-class SVM classification problems and a two-step grid search method is presented to optimize SVM parameters. The simulation results show the correct identification and classification of the presented method has a higher rate and it also verifies the correctness and effectiveness of this method.
View Full Text   View/Add Comment  Download reader
Close
  • Home
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • 中文页面
Address: No.2000, Chuangxin Road, Songbei District, Harbin, China    Zip code: 150028
E-mail: dcyb@vip.163.com    Telephone: 0451-86611021
© 2012 Electrical Measurement & Instrumentation
黑ICP备11006624号-1
Support:Beijing Qinyun Technology Development Co., Ltd