基于Hilbert-huang变换和RVM的电能质量检测与分类  

Power quality detection and classification based on Hilbert Huang transform and RVM

作　　者：何晓丽 刘立群[1] HE Xiaoli;LIU Liqun(School of Electronic and Information Engineering, Taiyuan University of Science and technology,Shanxi Taiyuan 030024, China)

机构地区：[1]太原科技大学电子信息工程学院,山西太原030024

出　　处：《工业仪表与自动化装置》2021年第1期123-127,共5页Industrial Instrumentation & Automation

基　　金：山西省重点研发计划(高新)(201803D121106);山西省应用基础研究计划(201901D111252);太原科技大学教学改革创新项目(JG201913);太原科技大学大学生创新创业训练计划(XJ2019020)。

摘　　要：由于电力系统非常复杂,电能质量对电力系统的影响很大,为了提取电能质量的扰动参数及其对扰动类型的判别,在常规电能质量检测的基础上,利用Hilbert-huang变换(HHT)算法对集总经验模态分解(EEMD)产生的有效分量进行变换,将扰动频率数量、扰动持续时间、电压扰动幅值与相位这四个特征量从得到的曲线中提取,同时结合相关向量机(RVM)的分类特性,对特征值进行提取,处理后输入到粒子群优化相关向量机(PSO-RVM)分类器中进行扰动问题分类。最终在Matlab仿真平台上进行验证,该方法可以准确地识别各个扰动的特征量,与现有的扰动分类方法进行对比,表明PSO-RVM有较高的分类准确性,且参数简单,具有一定的抗噪性。Due to the complexity of power system,power quality has a great impact on power system.In order to extract power quality disturbance parameters and distinguish the types of disturbance,on the basis of conventional power quality detection,the Hilbert-Huang Transform Algorithm is used to transform the effective components of the collective empirical mode decomposition(EEMD),the number of disturbance frequency,the duration of disturbance,the amplitude and phase of voltage disturbance are extracted from the obtained curve,and the relevance vector machine is classified according to the disturbance problem,this is processed and entered into the particle swarm optimization relevance vector Machine(PSO-RVM)classifier.Finally,the accuracy of the algorithm is verified on the Matlab simulation platform.The method can accurately identify the characteristic quantity of each disturbance,and is compared with the existing disturbance classification methods,and it's noise-resistant.

关 键 词：电能质量 Hilbert-huang变换(HHT) 粒子群优化相关向量机(PSO-RVM) 检测分类 

分 类 号：TM711[电气工程—电力系统及自动化]