于志勇,张卫辉,王新库,黄南天,黄喜旺.基于GA和ELM的电能质量扰动识别特征选择方法[J].电测与仪表,2016,53(23):. Yu Zhiyong,ZhangWeihui,WangXinku,HuangNantian,Huang Xiwang.A Method of Power Quality Disturbances Recognition Feature Selection Based on GA and ELM[J].Electrical Measurement & Instrumentation,2016,53(23):.
基于GA和ELM的电能质量扰动识别特征选择方法
A Method of Power Quality Disturbances Recognition Feature Selection Based on GA and ELM
Analysis and management of massive transient disturbance in power system need take efficiency and accuracy of disturbance classification into consideration. Since existing disturbance identification methods are lacked of rational feature selection process and the classifier too complicated to meet the need of efficient classification. In this paper,a new method with feature selection of power quality disturbance is proposed. Firstly, the original signal is preprocessed by S transform and extracting 25 kinds of disturbance signal features which are representative to build the original feature set. Secondly, based on extreme learning machine recognition accuracy rate,fitness function of genetic algorithm used to the disturbance feature selection is built. And finally using genetic algorithms to iterative and determining the optimal set of features. Experiments show that the new method can effectively remove redundant features, reduce classifier complexity and improve efficiency classification with ensuring the accuracy of classification.
