|本期目录/Table of Contents|

[1]何晓丽,刘立群.基于Hilbert-huang变换和RVM的电能质量检测与分类[J].工业仪表与自动化装置,2021,(01):123-127.[doi:1000-0682(2021)01-0000-00]
 HE Xiaoli,LIU Liqun.Power quality detection and classification based on Hilbert Huang transform and RVM[J].Industrial Instrumentation & Automation,2021,(01):123-127.[doi:1000-0682(2021)01-0000-00]
点击复制

基于Hilbert-huang变换和RVM的电能质量检测与分类

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年01期
页码:
123-127
栏目:
出版日期:
2021-02-15

文章信息/Info

Title:
Power quality detection and classification based on Hilbert Huang transform and RVM
作者:
何晓丽刘立群
太原科技大学 电子信息工程学院,山西 太原 030024
Author(s):
HE XiaoliLIU Liqun
School of Electronic and Information Engineering, Taiyuan University of Science and technology, Shanxi Taiyuan 030024,China
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
Keywords:
power quality Hilbert–Huang Transform(HHT) particle swarm optimization relevance vector machine (PSO-RVM) detection classification
分类号:
TM711
DOI:
1000-0682(2021)01-0000-00
文献标志码:
A
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。
Abstract:
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.

参考文献/References:

[1] 储珺,马建伟.基于小波变换的电能质量扰动信号的检测[J].电力系统保护与控制,2009,37(05):34-36+64.

[2] REDDY M Jaya Bharata, RAGHUPATHY Rama Krishnan, VENKATESH K P ,et al. Power quality analysis using Discrete Orthogonal S-transform (DOST)[J]. Digital Signal Processing,2013,23(2).
[3] 李天云,赵妍,李楠,等.基于HHT的电能质量检测新方法[J].中国电机工程学报,2005(17):52-56.
[4] 胡晓曦,刘含露,熊婷婷,等.基于希尔伯特-黄变换的复杂电能质量信号检测技术[J].电气技术,2012(05):6-10.
[5] 李晓娜. 基于Hilbert-Huang变换的电能质量扰动检测与识别研究[D].北京:中国矿业大学,2017.
[6] 刘伟伟,蒋晓宇,蔡华,等.基于Hilbert变换和分类树的电能质量扰动分类辨识[J].电测与仪表,2010,47(11):22-26+35.
[7] 李庚银,王洪磊,周明.基于改进小波能熵和支持向量机的短时电能质量扰动识别[J].电工技术学报,2009,24(04):161-167.
[8] 田振果,傅成华,吴浩,等.基于HHT的电能质量扰动定位与分类[J].电力系统保护与控制,2015,43(16):36-42.
[9] 李晓娜,沈兴来,薛雪,等.基于改进HHT和决策树的电能质量扰动辨识[J].电力建设,2017,38(02):114-121.
[10] 钟佑明,秦树人,汤宝平.Hilbert-Huang变换中的理论研究[J].振动与冲击,2002(04):15-19+119-120.
[11] GAI Guanghong. The processing of rotor startup signals based on empirical mode decomposition[J]. Mechanical Systems and Signal Processing,2006,20(1).
[12] 李子旋. 基于自适应互补LMD和RVM的电能质量检测与分类[D].北京:中国矿业大学,2018.
[13] 雷亚国.基于改进Hilbert-Huang变换的机械故障诊断[J].机械工程学报,2011,47(05):71-77.
[14] Detection of time varying pitch in tonal languages: an approach based on ensemble empirical mode decomposition[J].Journal of Zhejiang University-Science C(Computers & Electronics),2012,13(02):139-145.
[15] 吴新忠,邢强,陈明,等.采用改进互补集总经验模态分解的电能质量扰动检测方法[J].浙江大学学报(工学版),2017,51(09):1834-1843.
[16] 张鑫磊,李根.基于IEEMD与LS-SVM组合的短期风电功率多步预测方法[J].电测与仪表,2020,57(06):52-60.
[17] 杨国鹏,周欣,余旭初.稀疏贝叶斯模型与相关向量机学习研究[J].计算机科学,2010,37(07):225-228.
[18] 彭炜文.基于PSO-RVM的异步电动机转子断条故障诊断[J].电气应用,2019,38(09):109-114.
[19] 颜学龙,陈卓.PSO优化多核RVM的模拟电路故障预测[J].计算机工程与应用,2019,55(12):140-144.

相似文献/References:

[1]董瑞,李晓英.飞轮电池对风光互补发电系统电压波动的改善研究[J].工业仪表与自动化装置,2013,(05):117.
[2]韩向可,段立霞.基于DSP的风电场电能质量监测系统设计[J].工业仪表与自动化装置,2014,(06):50.
 HAN Xiangke,DUAN Lixia.Design of wind farm power quality monitoring system based on DSP[J].Industrial Instrumentation & Automation,2014,(01):50.
[3]李俊秀,李明旭.基于DSP电压闪变在线检测方法及仿真[J].工业仪表与自动化装置,2015,(05):117.
 LI Junxiu,LI Mingxu.The Research of the Voltage flicker detection methods online based on the DSP[J].Industrial Instrumentation & Automation,2015,(01):117.
[4]吴丽珍,王晓婷,刘腾飞.微电网电能质量改善与控制方法综述[J].工业仪表与自动化装置,2018,(03):16.
 WU Lizhen,WANG Xiaoting.Review of power quality improvement and control methods for microgrid[J].Industrial Instrumentation & Automation,2018,(01):16.
[5]崔慧明,王 程,陈振勇,等.基于MEEMD的复合电能质量扰动检测方法研究[J].工业仪表与自动化装置,2018,(06):12.[doi:1000-0682(2018)06-0000-00]
 CUI Huiming,WANG Cheng,CHEN Zhenyong,et al.Research on compound power quality disturbance detection method based on MEEMD[J].Industrial Instrumentation & Automation,2018,(01):12.[doi:1000-0682(2018)06-0000-00]

备注/Memo

备注/Memo:
收稿日期:2020-08-24
基金项目:
山西省重点研发计划(高新)(201803D121106);?/div>
山西省应用基础研究计划(201901D111252);?/div>
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)
作者简介:
何晓丽(1993),女,山西孝义人,硕士研究生,主要研究方向为新能源发电与并网技术。
更新日期/Last Update: 1900-01-01