希尔伯特–黄变换在变压器局部放电脉冲识别中的应用  

Application of Hilbert-Huang Transform in Pattern Recognition for Partial Discharge of Transformers

作　　者：刘双宝[1] 吕超[1] 于继来[1] 王立欣[1] 

机构地区：[1]哈尔滨工业大学电气工程及自动化学院,黑龙江省哈尔滨市150001

出　　处：《中国电机工程学报》2008年第31期114-119,共6页Proceedings of the CSEE

基　　金：黑龙江省自然科学基金项目(E2004-07)。

摘　　要：时频分析方法是变压器局部放电特征提取的有效手段。讨论利用小波变换方法分析非平稳信号的局限性,介绍希尔伯特–黄变换(Hilbert-Huang transform,HHT)的理论体系,并分别应用2种时频分析方法得到不同类型局放信号的幅值谱,从中提取了时频熵向量作为用于模式识别的特征量,模糊聚类结果显示,由希尔伯特–黄变换得到的时频熵向量具有优于小波变换的聚类特性。因此,希尔伯特–黄变换是目前变压器局放信号特征提取的有效方法。Time-frequency analysis is an efficient method in feature extraction for transformer partial discharge. The shortcomings of wavelet transform were discussed firstly as approaches to analyze non-stationary signals; then the theoretical framework of Hilbert-Huang transform was introduced; finally, the time-frequency spectrums were obtained through the two methods mentioned above and timefrequency entropy vectors were extracted from them as the features for pattern recognition. The result of fuzzy clustering shows that the clustering characteristic of HHT entropy vectors are better than those of wavelet transform, so HHT is a more efficient way to extract features of partial discharge pulses for transformers.

关 键 词：变压器 局部放电 希尔伯特-黄变换 小波变换 

分 类 号：TM85[电气工程—高电压与绝缘技术]