基于小波变换和支持向量机的电能质量扰动识别  

Power Quality Disturbances Identification Using Decision Tree and Support Vector Machine

作　　者：陈华丰[1] 乔磊[1] 柳双林[1] 

机构地区：[1]西南交通大学电气工程学院,成都610031

出　　处：《电气技术》2013年第2期14-18,共5页Electrical Engineering

摘　　要：电能质量扰动识别时,采用小波变换提取能量分布特征时小波分解层数通常缺乏理论依据,且采用支持向量机(SVM)分类时训练样本通常只含某一种信噪比(SNR)的噪声。针对以上两个问题,利用小波变换对电能质量扰动信号进行多分辨率分析时,根据扰动信号的采样率来确定小波分解层数,提取小波能量分布差特征作为SVM的输入向量,减少了计算量和特征维数;采用信噪比在较大范围内分布较均匀的训练样本来训练SVM,增强了SVM的范化能力。仿真实验表明,该方法提高了电能质量扰动识别准确率;在20dB噪声条件下,该方法对6种电能质量扰动的识别准确率仍达到95.20%。In the process of power quality disturbances identification, the wavelet decomposition level usually lack theoretical basis when using wavelet transform to extract energy difference distribution features and training samples for support vector machine （SVM） are usually in one condition of signal-noise ratio （SNR）. For the above two questions, the wavelet decomposion level is decided by signal sampling rate when using wavelet doing multi-resolution analysis, which reduces the calculation time and the number of characteristic dimension, then the extracted energy distribution features are used as the input vector of SVM to train a SVM based classifier; Uniform SNR distribution is employed for training samples and enforces the generalization ability of SVM. The simulation results indicate that this improved method can accurately classify 6 types of PQ disturbances and the accuracy can still reach 95.20% even the SNR is 20dB.

关 键 词：电能质量 扰动识别 小波变换 能量分布 支持向量机 

分 类 号：TM714[电气工程—电力系统及自动化] TN911.7[电子电信—通信与信息系统]