摘要
针对电能质量分析中的电能质量扰动信号快速精确检测及分类重要内容,提出基于小波变换结合改进S变换的电能质量扰动分类方法.通过小波变换得到高低频分量,并选取低频分量做改进的S变换提取特征向量,既保持原信号特征,且得到的S变换模矩阵维数只有原信号直接做S变换的模矩阵维数的1/4.通过概率神经网络(probabilistic neural network,PNN)对信号进行分类.仿真结果证明,所提方法有效,能很好实现分类,且减少分类时间.
Rapid and accurate detection and classification of power quality disturbance signals are particularly important in power system. This paper proposes a new classification method based on wavelet transform combined with improved S-transform （IST）. The high and low frequency components were obtained by wavelet transform first, and then the low frequency component was selected to extract the feature vectors through IST. In this way, the characteristics of the original signal are retained, and the size of modulus matrix of this low frequency component after IST is only a quarter of that of the original signal after direct IST. Finally the probabilistic neural network （PNN） was employed to classify the signals. Simulation results show that the proposed method reduces greatly the time of classification, it is fast and effective.
出处
《深圳大学学报（理工版）》
EI
CAS
北大核心
2014年第1期23-29,共7页
Journal of Shenzhen University(Science and Engineering)
基金
国家自然科学基金资助项目(51177102)
深圳市基础研究计划资助项目(JCYJ20120613113140920)~~
关键词
电力系统
电能质量
小波变换
改进的S变换
概率神经网络
扰动分类
信号分析
power system
power quality
wavelet transform
improved S-transform
probabilistic neural network
disturbance classification
signal analysis
