Research on mechanical state identification method of multi-type disconnectors based on difference curve and SVM

Author:

Yang Tao,Wang Bing,Xu Ji-Yong,Zhu Qi-Long,Niu Bo-Rui,Liu Yu-Fei,He Song

Abstract

Abstract There are various types of high-voltage isolating switches and frequent mechanical defects, but it is difficult to meet engineering needs by detecting the mechanical state of a single isolating switch. Currently, most of the research only takes the GW4 disconnector as the research object, and the practicability of related diagnostic methods remains to be verified. In this paper, the difference curve is obtained as the sample to be identified by comparing the travel curve of the isolating switch to be diagnosed and its historical standard curve. With further elimination of the travel curve difference caused by the isolating switch model, extraction of the relevant time domain feature quantity, and combination of the support vector, the algorithm uses half of the data of each model in each state as the training sample and the other half of the data as the test sample, and the recognition accuracy rate is 100%. The GW4 and GW23 data are used as the training samples, the GW7 and GW36 data are used as the test samples, and the recognition accuracy is accurate. The rate was 87.5%. It is verified that the method of segmental extraction of difference curve features, combined with the support vector machine algorithm, can realize the intelligent identification of the mechanical state of different types of disconnectors, in which the degree of fault directly affects the spatial distribution of the samples and has a great impact on the accuracy of the identification results.

Publisher

IOP Publishing

Subject

Computer Science Applications,History,Education

Reference30 articles.

1. Impact assessment of remote control and preventive maintenance on the failure rate of a disconnector population[J];Jürgensen;IEEE Transactions on Power Delivery,2018

2. Failure frequencies for high-voltage circuit breakers, disconnectors, earthing switches, instrument transformers, and gas-insulated switchgear[J];Runde;IEEE Transactions on Power Delivery,2013

3. Cause Analysis and Treatment of Common Faults of Outdoor High-voltage Disconnector[J];Mingxue;High Voltage Apparatus,2010

4. Failure Analysis and Countermeasures for GW5-126 Disconnector Contacts Burning[J];Zongwei;High Voltage Apparatus,2011

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