短时电能质量扰动波形的识别

提出一种新的基于瞬时无功功率理论和小波-神经网络技术对电能质量进行辨识的方法。首先对各种电能质量信号进行时域和幅值分析,将在幅值上有显著特征的短期电能质量扰动信号识别出来;再对其余的信号进行小波变换,提取与信号频域相关的特征量来表征不同电能质量信号。将这些特征量作为神经网络(ANN)的输入可以实现电能质量的辨识。计算结果表明了该方法的有效性和准确性。

Short-Time Power Quality Disturbances Waveform Recognition

This paper suggests a method to classify short-time power quality using the wavelet transformation and ANN based on instantaneous reactive power theory.To begin with,the power quality signals of various kinds was decomposed in time domain and amplitude,and the signals of short-term power quality disturbance featured on the amplitudes are identified.And then the rest of signals are processed using the wavelet transform,and the features related to frequency band domain extracted are used to indicate the signals of different power qualities,and these features can be used as the input vector of ANN to classify the short-time power quality signals.The efficiency and validity of this method is verified by the calculation results.