摘要
针对局部放电特高频(ultra-high frequency,UHF)信号畸变导致模式识别准确率下降的问题,提出了基于时频分布图像纹理特征的特征参数提取方法。首先对局部放电UHF信号进行s变换得到时频分布图像,然后采用灰度共生矩阵(gray-level co-occurrence matrix,CLCM)算法,从时频分布图像中提取出纹理特征参数。采用主成分分析(principal component analysis,PCA)法对由纹理特征参数构成的特征向量进行降维处理,得到局部放电UHF信号特征参数及特征向量,并输入到支持向量机(support vector machine,SVM)分类器中进行模式识别。结果表明,该特征参数可以有效识别4种典型变压器内部局部放电UHF信号,识别准确率最高达到97.50%。
In order to solve reduction of pattern recognition accuracy when partial discharge ultra-high frequency （UHF） signal is distorted, a novel feature parameters extraction method based on textural features in time-frequency （TF） representation image is proposed. Firstly, the TF representation image of partial discharge UHF signal can be obtained by the s-transform. Secondly, the textural features of TF image can be extracted by the gray-level co- occurrence matrix （GLCM） method. Through the principal component analysis （PCA） method, the eigenvector consisted by textural features can be dimensionality reduced. The feature parameters and eigenvector of par- tial discharge UHF signal can be obtained and inputted into the support vector machine （SVM） classifier for pat- tern recognition. The test and recognition results show that the proposed feature parameters can be used to recog- nize 4 types of typical partial discharge UHF signal in transformer, and the highest recognition accuracy reached 97.50%.
出处
《高压电器》
CAS
CSCD
北大核心
2017年第7期30-37,44,共9页
High Voltage Apparatus
基金
广州供电局有限公司科技项目(GZHKJ00000008)~~
关键词
局部放电
UHF信号
时频分布
纹理特征
特征参数
模式识别
partial discharge
UHF signal
time-frequency representation
textural features
feature parameters
pattern recognition
作者简介
田妍（1988-），女，工程师，研究方向为电气设备故障诊断。
