GIS Partial Discharge Pattern Recognition Based on IWOA-SVM Algorithm

Author:

Wang Jiayi,Fang Yuan,Kou Jianqiang,Xia Yankun,Zhou Dianbo,Dong Hanbin

Abstract

Abstract To effectively recognize partial discharge (PD) types in gas-insulated switchgear (GIS) equipment, a novel PD pattern recognition method is proposed. This method leverages an improved whale optimization algorithm (IWOA) to optimize the support vector machine (SVM). Firstly, typical PD defects were simulated in the GIS chamber. The PRPS results demonstrated significant differences among four PD defects. Secondly, multiple feature values of PD results were calculated for feature extraction. Finally, the IWOA-SVM algorithm was employed for the recognition of PD patterns in GIS. Experimental results indicate that the IWOA-SVM algorithm can effectively recognize different PD types and the predicted accuracy rate can reach 99.1667%, which is much higher than SVM and WOA-SVM algorithms, providing information to construction units for maintenance.

Publisher

IOP Publishing

Reference12 articles.

1. A mobile nets convolutional neural network for GIS partial discharge pattern recognition in the ubiquitous power Internet of things context: optimization, comparison, and application;Wang;IEEE Access,2019

2. Analysis and detection of fault for substation GIS insulating part based on integrated automation system data;Liu;Journal of Physics: Conference Series. IOP Publishing,2022

3. Severity evaluation of UHF signals of partial discharge in GIS based on semantic analysis;Meng;IEEE Transactions on Power Delivery,2022

4. Application of ANFIS and ANN for partial discharge localization in oil through acoustic emission;Hashim;IEEE Transactions on Dielectrics and Electrical Insulation,2023

5. Partial discharge pattern recognition via sparse representation and ANN;Majidi;IEEE Transactions on Dielectrics and Electrical Insulation,2015

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3