Development for Electrical Fault Detection and Classification Analysis Model based on Machine Learning Algorithms
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Junho | - |
dc.contributor.author | Sim, Sunhwa | - |
dc.contributor.author | Kim, Seokjun | - |
dc.contributor.author | Cho, Seokheon | - |
dc.contributor.author | Han, Changhee | - |
dc.date.accessioned | 2024-08-09T06:30:17Z | - |
dc.date.available | 2024-08-09T06:30:17Z | - |
dc.date.issued | 2024-04 | - |
dc.identifier.issn | 2640-6829 | - |
dc.identifier.issn | 2640-6810 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/28851 | - |
dc.description.abstract | With the development of industry and technology in modern society, many industries and houses require a sufficient electricity supply. As demand for electricity increases, rapid detection of the type and location of electrical faults within the power system is critical to ensure the reliable operation of power systems. Since the traditional fault detection method has low accuracy and takes much time to detect the fault type and location, we propose a new electrical fault detection model based on machine learning algorithms. MATLAB Simulink collects the line current and bus voltage data during power system fault events. We consider two machine learning algorithms, Random Forest and K-Nearest Neighbor (K-NN) algorithms, as electrical fault detection and classification models. The data collected from the power system simulation is processed in various ways and then applied to the machine learning algorithms. As a result, we verify that the learning model based on the Random Forest algorithms, using the peak-to-peak value of the line current and bus voltage as training data, shows the best performance for detecting and predicting electrical faults. | - |
dc.format.extent | 7 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE | - |
dc.title | Development for Electrical Fault Detection and Classification Analysis Model based on Machine Learning Algorithms | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/SusTech60925.2024.10553405 | - |
dc.identifier.scopusid | 2-s2.0-85197249144 | - |
dc.identifier.wosid | 001256474400001 | - |
dc.identifier.bibliographicCitation | 2024 IEEE CONFERENCE ON TECHNOLOGIES FOR SUSTAINABILITY, SUSTECH, pp 50 - 56 | - |
dc.citation.title | 2024 IEEE CONFERENCE ON TECHNOLOGIES FOR SUSTAINABILITY, SUSTECH | - |
dc.citation.startPage | 50 | - |
dc.citation.endPage | 56 | - |
dc.type.docType | Proceedings Paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Science & Technology - Other Topics | - |
dc.relation.journalResearchArea | Energy & Fuels | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Hardware & Architecture | - |
dc.relation.journalWebOfScienceCategory | Green & Sustainable Science & Technology | - |
dc.relation.journalWebOfScienceCategory | Energy & Fuels | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | SYSTEMS | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | electrical fault | - |
dc.subject.keywordAuthor | fault detection | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
350-27, Gumi-daero, Gumi-si, Gyeongsangbuk-do, Republic of Korea (39253)054-478-7170
COPYRIGHT 2020 Kumoh University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.