基于S变换和决策树算法的电能质量扰动识别

提出一种基于S变换和数据挖掘中决策树算法的电能质量扰动识别的方法.该方法首先用S变换对电能质量扰动波形进行时频分析,并使用统计方法提取相关特征量,然后用决策树算法对提取的特征量样本进行分类,并获得明确的分支规则.仿真结果表明,该方案正确率高,抗噪声能力强,训练样本少,响应速度快.

Electricity quality disturbance identification method based on Stockwell-transform and decision tree

An electricity quality disturbances identification method based on the Stockwell-transform and decision tree algorithm in data mining is proposed.The time-frequency analysis of electricity quality disturbance waveform is carried out by using Stockwell-transform; and 5 related features are extracted with statistical methods; and then the characteristics samples are classified with the decision tree algorithm; finally,the clear branch rules are obtained.The simulation results show that the electricity quality disturbance classification based on Stockwell-transform possesses the following features:high accuracy rate of identification,strong resistance to noises,less training samples and quick response.