Power quality disturbance classification based on time-frequency domain multi-feature and decision tree  

作　　者：Wenjing Zhao Liqun Shang Jinfan Sun 

机构地区：[1]School of Electrical and Control Engineering,Engineering,Xi’an University of Science and Technology,No.58,Yanta Road,Bei Lin District,Xi’an,Shaanxi Province,China [2]Shaanxi Power Generation co.,LTD.Weihe Thermal Power Plant,Xianyang,712000,China

出　　处：《Protection and Control of Modern Power Systems》2019年第1期349-354,共6页现代电力系统保护与控制（英文）

基　　金：supported by Natural Science Basic Research Plan in Shaanxi Province of China (Program No. 2019JM-544).

摘　　要：Accurate classification of power quality disturbance is the premise and basis for improving and governing power quality. A method for power quality disturbance classification based on time-frequency domain multi-feature and decision tree is presented. Wavelet transform and S-transform are used to extract the feature quantity of each power quality disturbance signal, and a decision tree with classification rules is then constructed for classification and recognition based on the extracted feature quantity. The classification rules and decision tree classifier are established by combining the energy spectrum feature quantity extracted by wavelet transform and other seven time-frequency domain feature quantities extracted by S-transform. Simulation results show that the proposed method can effectively identify six types of common single disturbance signals and two mixed disturbance signals, with fast classification speed and adequate noise resistance. Its classification accuracy is also higher than those of support vector machine (SVM) and k-nearest neighbor (KNN) algorithms. Compared with the method that only uses S-transform, the proposed feature extraction method has more abundant features and higher classification accuracy for power quality disturbance.

关 键 词：Power quality Disturbance classification WAVELET transform S-TRANSFORM Decision tree Classification rules 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]