[논문]열화상 이미지 분석을 통한 배전 설비 공정능력지수 감지 시스템 개발

이형근; 홍용민; 강성우

doi:10.7469/jksqm.2021.49.3.327

[국내논문] 열화상 이미지 분석을 통한 배전 설비 공정능력지수 감지 시스템 개발
Identifying Process Capability Index for Electricity Distribution System through Thermal Image Analysis 원문보기

品質經營學會誌 = Journal of Korean society for quality management, v.49 no.3, 2021년, pp.327 - 340

이형근 (인하대학교 산업경영공학과) , 홍용민 (인하대학교 산업경영공학과) , 강성우 (인하대학교 산업경영공학과)

Abstract ▼ AI-Helper

Purpose: The purpose of this study is to propose a system predicting whether an electricity distribution system is abnormal by analyzing the temperature of the deteriorated system. Traditional electricity distribution system abnormality diagnosis was mainly limited to post-inspection. This research presents a remote monitoring system for detecting thermal images of the deteriorated electricity distribution system efficiently hereby providing safe and efficient abnormal diagnosis to electricians. Methods: In this study, an object detection algorithm (YOLOv5) is performed using 16,866 thermal images of electricity distribution systems provided by KEPCO(Korea Electric Power Corporation). Abnormality/Normality of the extracted system images from the algorithm are classified via the limit temperature. Each classification model, Random Forest, Support Vector Machine, XGBOOST is performed to explore 463,053 temperature datasets. The process capability index is employed to indicate the quality of the electricity distribution system. Results: This research performs case study with transformers representing the electricity distribution systems. The case study shows the following states: accuracy 100%, precision 100%, recall 100%, F1-score 100%. Also the case study shows the process capability index of the transformers with the following states: steady state 99.47%, caution state 0.16%, and risk state 0.37%. Conclusion: The sum of caution and risk state is 0.53%, which is higher than the actual failure rate. Also most transformer abnormalities can be detected through this monitoring system.

Keyword

표/그림 (14)

그림 Figure 1. Status of Fire Damaged Cost and Deaths
표 Table 1. Process Capability Index
그림 Figure 2. Methodology Process
그림 Figure 3. Object Detection Algorithm using YOLOv5
그림 Figure 4. Preprocessing
표 Table 2. Process Capability Index
표 Table 3. Confusion Matrix
그림 Figure 5. Summary of Experimental Process
그림 Figure 6. Example of Original Image and Thermal Image
그림 Figure 7. Example of Detected Electricity Distribution System
그림 Figure 8. Evaluation of YOLOv5 with 100 epochs
표 Table 4. Optimal Hyperparameters for Each Algorithm
표 Table 5. Used Algorithm and Evaluation Value
표 Table 5. Process Capability Index and Evaluation Value

참고문헌 (19)

Cho. 2017. An Experimental Study on the Detection Characteristic of Draft Ice by Thermography System. Korea Academy Industrial Cooperation Society. 302-307.
Choi K, Chai H, and Moon J. 2016. A Study on Failure Rate Extraction of Distribution System Equipment considering Regional Characteristics. The Transactions of the Korean Institute of Electrical Engineers 65P(3):199-203.

원문보기 상세보기
Choi S and Hur J. 2020. Optimized-XG Boost Learner Based Bagging Model for Photovoltaic Power Forecasting.Transactions of the Korean Institute of Electrical Engineers 69(7):978-84

상세보기
Kim J, Choi K, and Kang S. 2021. Infrared thermal image-based sustainable fault detection for electrical facilities. Sustain 13(2):1-16. doi:10.3390/su13020557.

상세보기
Kong J, Ha T, and Lee Y. 2020. Study of an Oil Whip and Oil Whip Initial State Detect in Rotating Machine Using by Convolution Neural Network. KSFM J Fluid Mach 23(3):5-12. doi:10.5293/kfma.2020.23.3.005.

상세보기
Korea Infrastructure Safety Corporation. General inspection criteria for electrical facilities are organized. http://sunhome.pe.kr/apt/pdf/11jgjg.pdf.
Korean Statistical Information Service. 2020. Monthly property damage due to ignition factors. https://kosis.kr/statHtml/statHtml.do?orgId156&tblIdDT_15601N_008&conn_pathI2.
Korean Statistical Information Service. 2021. Status of casualties by location for ignition factors. https://kosis.kr/statHtml/statHtml.do?orgId156&tblIdDT_15601N_008&conn_pathI2.
Ku K, Kwon J, and Jin H. 2019. A Study on Searching Stabled EMI Shielding Effectiveness Measurement Point for Military Communication Shelter Using Support Vector Machine and Process Capability Analysis. Journal of the Korea Academia-Industrial cooperation Society 20(2):321-328.

원문보기 상세보기
Lee H and Kim W. 2020. Quantitative Analysis on Phase Contrast of Defect Detection Mechanism by Wavelet Infrared Thermography. J Korean Soc Nondestruct Test 40(2):85-90. doi:10.7779/jksnt.2020.40.2.85.

상세보기
Lee H. 2020. Analysis of partial discharge in medium-voltage cables using IR(Infra Red) camera. The Korean Institute of Electrical Engineers. 2170-2171.
Lee K and Kim S. 2020. Thermo-physical Properties of the Asphalt Pavement by Solar Energy. J Korea Acad Coop Soc. 21(1):717-724. doi:10.5762/KAIS.2020.21.1.717.
Lee S, Yoon Y, and Jung J. 2020. A Machine Learning Model for Predicting Silica Concentrations through Time Series Analysis of Mining Data. J Korean Soc Qual Manag. 48(3):499-508.
Lee Y, Lee H, Jang H. 2021. Development of a New Similarity Index to Compare Time-series Profile Data for Animal and Human Experiments. J Korean Soc Qual Manag. 49(2):145-159.
Min B, Yoo J and Kim S. 2021. Network Intrusion Detection with One Class Anomaly Detection Model based on Auto Encoder. Journal of Internet Computing and Services 22(1):13-22.
Oh D. 2021. A Failure Prediction Algorithm of the Distribution Facility based on the Weather Correlation Analysis. Journal of the Korean Institute of Illuminating and Electrical Installation Engineers 31(11):75-81.

상세보기
Shi X, Hu J, and Lei X. 2021. Detection of Flying Birds in Airport Monitoring Based on Improved YOLOv5. 2021 IEEE 6th Int Conf Intell Comput Signal Process ICSP 2021(Icsp):1446-1451. doi:10.1109/ICSP51882.2021.9408797.
Woo S, Jung C, and Kim J. 2018. Assessment of climate change impact on aquatic ecology health indices in Han river basin using SWAT and random forest. J Korea Water Resour Assoc. 51(10):863-874. doi:10.3741/JKWRA.2018.51.10.863. %3CGo%0Ato.
Yiqi L. 2021. Density Adaptive Grid-based k-Nearest Neighbor Regression Model for Large Dataset. J Korean Soc Qual Manag. 49(2):201-211.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증