基于小波和ANN的电能质量分类方法

Power quality classification based on wavelet and artificial neural network

为了对电能质量进行有效的治理,以提高用电效率,有必要对电能质量进行快速的检测和准确的分类.基于小波的时频分析特点和人工神经网络(ANN)的学习能力,提出一种电能质量实用分类方法.利用正交小波对信号进行多分辨率分析,将一定时间长度内的信号的能量映射到多个频段内,通过与标准正弦信号各频段能量的比较,提取各类电能质量的能量变化特征;利用ANN对输入特征矢量进行识别,完成电能质量的自动分类.仿真实验证明,该方法可以有效地区分电压的上升、下降、闪变以及谐波畸变、暂态等5种电能质量问题.

To improve the power efficiency, it is necessary to detect the power quality signals sensitively, classify them accurately and clarify them effectively. This paper develops a novel method to classify power quality variations, which combines the aptitude of wavelet transform in analyzing non-stationary signals with the classification capabilities of artificial neural network (ANN). Power quality signals are decomposed with wavelet multi-resolution analysis and the feature vectors are extracted through the coefficients at different levels. Then ANN is used for automatic conversion of the power quality signals the feature vectors. Test results show that this method can effectively classifies voltage swell, voltage sag, voltage flicker, harmonic distortion and transient.