基于广义S变换和DE-ELM的电能质量.docVIP

基于广义S变换和DE-ELM的电能质量 扰动信号分类* 张卫辉1，，，，（1. ， 132012；2.；3.， 253000） 摘要：本文了一种基于。通过新 关键词：；；； 中图分类号：TM 文献标识码： 文章编号：1001-1390（201）00-0000-00 quality disturbances classification based on generalized S-transform and differential evolution extreme learning machine Zhang Weihui1, Huang Nantian1, Yang Jincheng2, Yang Yongjian2, Wang Xinku3 (1. College of Electrical Engineering, Northeast Dianli University, Jilin 132012, Jilin, China. 2. Electric Power Research Institute, Xinjiang Power Company, Urumqi 830000, China.3. Dezhou Power Supply Company, Shandong Power Company, Dezhou 253000, Shandong, China.) Abstract：The classification of power quality disturbance is of great importantance for the comprehensive evaluation of power quality and the management of disturbance source location. In this paper, a classification method for power quality disturbance based on generalized S-transform and differential evolution extreme learning machine (DE-ELM) is proposed. Firstly, window width factors of different frequency area in the S-transform is changed to improve the performance of features. Secondly, the DE-ELM is used as the disturbance classifier, which adopts the differential evolution algorithm with global optimization. The Differential Evolution Extreme Learning Machine optimizes the input weight and bias of hidden layer nodes to enhance the generalization ability of extreme learning machine, and further improves the classification accuracy. As simulation experiments shown, comparing with the support vector machine and extreme learning machine, the new method can get higher accuracy and stronger noise resistance, so it is suitable for the identification of power quality disturbances. Keywords：differential evolution, extreme learning machine 0　引 言 Support Vector Machine，SVM）[5]、决策树[6,7]、贝叶斯分类器[8]和极限学习机（Extreme Learning Machine，ELM）[9]等。其中：Extreme Learning Algorithm，DE-ELM）的电能质量扰动信号分类辨识方法。首先，在深入分析扰动信号特点之后，通过窗宽因子调整S变换的高斯窗宽，得到更具针对性的时频分辨率，从而获得更好的时