基于Hoeffding Tree的电能质量在线扰动分类

Online power quality disturbance classification based on Hoeffding Tree

为满足电能质量扰动事件的在线分类需求,提出了一种基于Hoeffding Tree的电能质量扰动在线分类方法。对电能质量在线扰动分类中的关键技术进行了研究,提出用小波变换和离散傅里叶变换相结合的判别方法检测电能质量扰动,该算法采用自适应滑动数据窗算法,能够根据扰动持续时间提取完整的扰动事件。以小波信号能量以及基波有效值构成特征向量,利用Hoeffding Tree算法构建增量式分类训练模型。仿真结果表明,所提方法的准确度和效率均满足电能质量扰动事件在线检测和分类的要求。

An online classification method based on Hoeffding Tree is proposed for the online classification of PQD（Power Quality Disturbance）. The key technologies used in the online PQD classification based on power quality data stream are researched and a PQD detection method combining the wavelet transform and the DFF（Diserete Fourier Transform） is proposed,which adopts an adaptive sliding window to extract a complete PQD event according to its duration. The characteristic vector and the fundamental RMS and the Hoeffding Tree algorithm is is composed of the wavelet energy applied to build the incremental classification training model. Simulative results show that,the accuracy and efficiency of the proposed method meet the requirements of online PQD detection and classification.