电气工程学报 ›› 2017, Vol. 12 ›› Issue (7): 26-32.doi: 10.11985/2017.07.005

• • 上一篇    下一篇

基于Hilbert-Huang变换与支持向量机的故障电弧检测研究

张湛1,杨光2,张峰2   

  1. 1. 中国电力工程顾问集团中南电力设计院 武汉 430071
    2. 上海交通大学电子信息与电气工程学院 上海 200240
  • 收稿日期:2016-08-29 出版日期:2017-07-25 发布日期:2019-11-25
  • 作者简介:张 湛 男 1966年生,本科,工程师,研究方向为电力系统设计和电力系统智能技术。|杨 光 男 1989年生,博士研究生,研究方向为电工理论与新技术、故障诊断与检测技术和现代轨道交通技术等。

Research of Arc Fault Detecting Based on Hilbert-Huang Transformation and Support Vector Machine

Zhang Zhan1,Yang Guang2,Zhang Feng2   

  1. 1. Central Southern China Electric Power Design Institute of China Power Engineering Consulting Group Wuhan 430071 China
    2. Shanghai Jiao Tong University Shanghai 200240 China
  • Received:2016-08-29 Online:2017-07-25 Published:2019-11-25

摘要:

随着国内用电设备增多,电气火灾的发生率也有所升高,故障电弧检测的研究成为当今热点。本文提出一种Hilbert-Huang变换与支持向量机相结合的方法,其中采用Hilbert-Huang变换对不同负载电流波形进行时域分解,从而提取各模态分量的特征值。然后采用支持向量机的自适应分类方法,通过学习不同负载下Hilbert-Huang变换得到的特征值,自适应地区分正常运行状态与故障电弧运行状态。本文以调光灯、电吹风高档、电吹风低档、电风扇和电水壶等5种类型的常用负载作为研究对象,验证算法的正确性。

关键词: 故障电弧检测, 故障电弧断路器, Hilbert-Huang变换, 支持向量机

Abstract:

With the increasing consumption of electric equipment, the occurring rates of electrical fires also rise in a high speed. This paper proposes a method combine Hilbert-Huang Transformation (HHT) and Support Vector Machine (SVM). We adopt the HHT to decompose the current waveform in different kinds of loads, and analyze the Intrinsic Mode Function from time domain and frequency domain. The SVM learns characteristic value in different loads, thus identification of normal condition and arc fault condition can be done in an adaptive way. This paper takes five kinds of common loads (dimmer, drier with high power, drier with low power, fan, heater, etc.) for the research object to verify the validity of the proposed method.

Key words: Arc detecting, arc fault circuit interrupter, Hilbert-Huang transformation, support vector machine

中图分类号: