基于小波和进化网络的电能质量动态扰动自动识别

Auto recognition of power quality disturbance based on wavelet and genetic net

提出了一种基于小波和进化网络的电能质量动态扰动自动识别方法。首先应用Ｄａｕｂｅｃｈｉｅｓ ４小波对扰动波形进行分解,得到各个尺度上的小波系数,然后进行特征提取:采用遗传算法设计的模式特征分类器对扰动进行分类。实验表明该方法具有分类准确、网络学习速度快及收敛效果好等显著特点。

A novel approach to detect and classify various types of power quality disturbances is presented in this paper. The wavelet Daubechies 4 is used to decompose the signals containing disturbances. The character vectors are extracted through the wavelet coefficients in five scales. Using the Genetic Algorithm (GA) based on the neural network the pattern characters can be classified by the mode classifier. Computation results show that the proposed method has good performance both in speed and in accuracy.