提出一种基于广义S变换的短时电能质量扰动信号分类方法。首先对短时电能质量扰动信号进行广义S变换,得到模矩阵,再从模时频矩阵中提取5种统计量特征值,然后利用决策树对扰动信号进行归类,从而实现对短时电能质量扰动信号的自动分类。仿真结果表明,该方法识别正确率高,且对噪声不敏感,适用于实际电网电能质量扰动信号的分析。
Based on generalized S-transform, a classification method for short-time power quality disturbance signals is proposed. First, the generalized S-transform is applied to short-time power quality disturbance signals to obtain modulus matrix; then five kinds of statistic eigenvalues are extracted from the modulus matrix; and then by use of decision tree, the subsumption of disturbance signals is performed to implement automatic classification of short-time power quality disturbance signals. Simulation results show that it is not sensitive to noises and its recognition rate is high, so it is suitable to the analysis of power quality disturbance signals in actual power systems.