• 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
Ip-iq谐波检测中三角基函数神经网络快速滤波方法的研究
Study of the fast filtering based on trigonometrically-activated neural networks in the ip-iq harmonic detection
Received:December 12, 2013  Revised:January 08, 2014
DOI:
中文关键词: ip-iq谐波检测法  低通滤波器  实时检测  三角基函数神经网络
英文关键词: the ip-iq harmonic detection ,low-pass filter (LPF), Real time detection,trigon ometrically-activated neural network
基金项目:上海市高校教师创新基金(1S10302020),上海市高等学校内涵建设资助项目(2012085)
Author NameAffiliationE-mail
wang xin-sheng* University of Shanghai for Science and Technology thankyou1203@126.com 
Hits: 1802
Download times: 791
中文摘要:
      瞬时无功功率的ip-iq 谐波检测多以低通滤波器为基础,须采取大量数据才可以实现稳定输出,且响应与采集的数据量相关。现在也有很多谐波分析采用神经网络,但都是基于在已经存在数据直接导入,实时性无法体现。本文基于上述两种方式的不足结合分析提出一种用三角基函数神经网络替代低通滤波器的实时检测法,不在对固定的数值滤波分析,而是在simulink中编写S程序,封装成模块,做到其实时性检测效果,而且同样可以缩短响应时间,减小相对误差。运用MATLAB对两者进行仿真比较,结果表明三角基函数神经网络可以完全代替低通滤波器,且响应速度快,相对误差小,输出更稳定。
英文摘要:
      Most of ip-iq harmonic detection of the instantaneous reactive power based on the low-pass filter (LPF), in order to achieve stable output, it need to collect large amounts of data, the response is associated with the amount of data. Many of the existing harmonic analysis using neural network, but it is based on the data directly into already exists, the real-time cannot reflect. In this paper advanced the real-time detection method of the trigonometrically activated neural networks instead of LPF based on the above two methods’s defect , Not in the analysis of numerical filter fixed ,write a S function in Simulink and encapsulated into modules, shorten the response time, reduce the relative error; By comparing the MATLAB simulation results, it show that the trigonometrically-activated neural networks can completely replace the low pass filter, quick response, the relative error of relatively small, and stable output.
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