{"title":"利用极端学习机分析双回路输电线路故障情况的智能方法","authors":"Hongmei Gu, Qingqing Zhang, Lei Wang","doi":"10.1007/s00202-024-02621-3","DOIUrl":null,"url":null,"abstract":"<p>Existing fault situation frameworks conventionally use different ABC-domain or sequence network equivalent circuits for different fault types. The environmental conditions lead to changes in the parameters of the double-circuit transmission lines, and these incorrect parameters cause errors in the fault situation frameworks. The best tool for fault situation and protection of double-circuit transmission lines is the use of frameworks that work independently of the line parameters. In this article, fault situation for double-circuit transmission lines is implemented based on the measured voltage and current of each line, utilizing an Extreme Learning Machine capable of identifying nonlinear equations between measured values and fault situation. First, all types of faults were simulated at different distances in a power grid with a double-circuit transmission line. Then, the information obtained is utilized to train intelligent tools. Finally, the fault situations for different distances and resistances are estimated to assess the suggested method. To assess the superiority of the suggested framework over other intelligent frameworks, the outcomes of this article are compared with the outcomes obtained from two intelligent tools, artificial neural networks and support vector machines, which show more precision and reliability of the Extreme Learning Machine than other tools.</p>","PeriodicalId":50546,"journal":{"name":"Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An intelligent method for fault situation in double-circuit transmission lines utilizing extreme learning machine\",\"authors\":\"Hongmei Gu, Qingqing Zhang, Lei Wang\",\"doi\":\"10.1007/s00202-024-02621-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Existing fault situation frameworks conventionally use different ABC-domain or sequence network equivalent circuits for different fault types. The environmental conditions lead to changes in the parameters of the double-circuit transmission lines, and these incorrect parameters cause errors in the fault situation frameworks. The best tool for fault situation and protection of double-circuit transmission lines is the use of frameworks that work independently of the line parameters. In this article, fault situation for double-circuit transmission lines is implemented based on the measured voltage and current of each line, utilizing an Extreme Learning Machine capable of identifying nonlinear equations between measured values and fault situation. First, all types of faults were simulated at different distances in a power grid with a double-circuit transmission line. Then, the information obtained is utilized to train intelligent tools. Finally, the fault situations for different distances and resistances are estimated to assess the suggested method. To assess the superiority of the suggested framework over other intelligent frameworks, the outcomes of this article are compared with the outcomes obtained from two intelligent tools, artificial neural networks and support vector machines, which show more precision and reliability of the Extreme Learning Machine than other tools.</p>\",\"PeriodicalId\":50546,\"journal\":{\"name\":\"Electrical Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-07-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electrical Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s00202-024-02621-3\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electrical Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s00202-024-02621-3","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
An intelligent method for fault situation in double-circuit transmission lines utilizing extreme learning machine
Existing fault situation frameworks conventionally use different ABC-domain or sequence network equivalent circuits for different fault types. The environmental conditions lead to changes in the parameters of the double-circuit transmission lines, and these incorrect parameters cause errors in the fault situation frameworks. The best tool for fault situation and protection of double-circuit transmission lines is the use of frameworks that work independently of the line parameters. In this article, fault situation for double-circuit transmission lines is implemented based on the measured voltage and current of each line, utilizing an Extreme Learning Machine capable of identifying nonlinear equations between measured values and fault situation. First, all types of faults were simulated at different distances in a power grid with a double-circuit transmission line. Then, the information obtained is utilized to train intelligent tools. Finally, the fault situations for different distances and resistances are estimated to assess the suggested method. To assess the superiority of the suggested framework over other intelligent frameworks, the outcomes of this article are compared with the outcomes obtained from two intelligent tools, artificial neural networks and support vector machines, which show more precision and reliability of the Extreme Learning Machine than other tools.
期刊介绍:
The journal “Electrical Engineering” following the long tradition of Archiv für Elektrotechnik publishes original papers of archival value in electrical engineering with a strong focus on electric power systems, smart grid approaches to power transmission and distribution, power system planning, operation and control, electricity markets, renewable power generation, microgrids, power electronics, electrical machines and drives, electric vehicles, railway electrification systems and electric transportation infrastructures, energy storage in electric power systems and vehicles, high voltage engineering, electromagnetic transients in power networks, lightning protection, electrical safety, electrical insulation systems, apparatus, devices, and components. Manuscripts describing theoretical, computer application and experimental research results are welcomed.
Electrical Engineering - Archiv für Elektrotechnik is published in agreement with Verband der Elektrotechnik Elektronik Informationstechnik eV (VDE).