基于双密度双树小波变换的电能质量扰动识别方法

Power Quality Disturbances Identification Based on Double-density Dual-tree Discrete Wavelet Transform

针对电能质量扰动的识别问题,提出一种基于双密度双树小波变换(DD-DT DWT)小波熵和支持向量机的扰动信号识别方法。该方法首先对电能信号进行DD-DT DWT变换,然后分别提取其小波能量熵和小波系数Shannon熵以描述不同扰动信号的特征,最后采用二元树结构支持向量机分别对提取的两类小波熵特征向量进行分类。仿真实验表明:所提出的基于DD-DT DWT小波熵的特征提取方法能有效识别常见的8种扰动信号,并具有正确识别率高及噪声鲁棒性强的优点。

A method based on double-density dual-tree discrete wavelet transform （DD-DT DWT） wavelet entropy and support vector machine （SVM） is proposed to identify power quality disturbances. Firstly, the simulated power signals are processed by using DD-DT DWT, then wavelet energy entropy and wavelet coefficients Shannon entropy are calculated respectively. At last, a binary tree of SVM is adopted to classify the power quality disturbances. The simulation results indicate that the proposed method can effectively classify the common eight kinds of disturbance signals with high recognition accuracy and high robustness to noise.