摘要
为了对电能质量进行有效的治理,以提高用电效率,有必要对电能质量扰动进行准确的分类。基于小波的时频分析特点和一种新型的小波神经网络,提出了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,提取各类电能质量变化的能量特征;利用小波神经网络对输入特征矢量进行识别,完成对电能质量的自动分类。研究表明,该方法能有效地区分电压骤降、电压骤升、电压中断、脉冲暂态4种电能质量问题。
To improve the power efficiency, it is necessary to classify the power quality signals accurately and clarify them effectively. This paper develops a practical method to classify power quality variations, which combines the trait of wavelet transform in analyzing non-stationary signals with a novel neural network named wavelet network. Power quality signals were decomposed with wavelet multi-resolution analysis and the feature vectors were extracted from the power variation of power quality. Then wavelet network was used for automatic conversion of the power quality. Research shows this method can effectively classifies voltage sag, voltage swell, voltage interruption, and transient.
出处
《电气技术》
2007年第9期56-58,共3页
Electrical Engineering
