期刊文献+

基于小波变换和GA-LSSVM的电能质量扰动识别与分类 被引量:3

Identification and classification of power qualifications based on wavelet transform and GA-LSSVM
下载PDF
导出
摘要 电力系统的负荷需求迅速增加,使得电能质量问题频繁出现,而电能质量扰动的有效识别对提高电网电能质量起到至关重要的作用。为此,提出一种基于遗传算法优化最小二乘支持向量机(GA-LSSVM)的电能质量扰动源识别与分类方法。首先应用小波变换对电能质量扰动信号进行多尺度分析,在Matlab仿真平台利用库函数提取信号的数据特征集,再利用机器学习及其优化分类器算法GA-LSSVM实现电能质量扰动的分类识别。仿真试验证明,该方法能够识别不同的5种电能质量扰动信号,并且具有较高的分类准确度和抗干扰能力。 With the rapid development of China's modern smart grid,the types of power equipment in the distribution network become more diverse,which makes the load demand of the original power system increase rapidly,making power quality problems occur frequently.Effective identification of power quality disturbances plays a vital role in improving the power quality of the grid.This paper proposes a method of power quality disturbance source identification and classification based on genetic algorithm optimized least squares support vector machine(GA-LSSVM).First,wavelet transform is applied to multi-scale analysis of power quality disturbance signals,library functions are used to extract the data feature set of signals under Matlab simulation platform,and then machine learning and its optimized classifier algorithm GA-LSSVM are used to achieve the classification and identification of power quality disturbances.The simulation results show that this method can identify five different power quality disturbance signals,and has high classification accuracy and anti-interference ability.
作者 彭宇文 李瑞 李沁雪 杨国荣 陈晓华 许海文 PENG Yuwen;LI Rui;LI Qinxue;YANG Guorong;CHEN Xiaohua;XU Haiwen(School of Automation,Guangdong University of Technology,Guangzhou 510006,China;School of Ship and Ocean Engineering,Guangzhou Maritime University,Guangzhou 510700,China)
出处 《黑龙江电力》 CAS 2023年第1期1-9,共9页 Heilongjiang Electric Power
基金 国家自然科学基金——青年科学基金项目(项目编号:62006052)。
关键词 电能质量 电力系统 扰动识别 机器学习 GA-LSSVM power quality power system disturbance identification machine learning GA-LSSVM
  • 相关文献

参考文献14

二级参考文献201

共引文献2159

同被引文献24

引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部