차원축소 기법을 이용한 전력용 변압기 건전도 지수 평가에관한 연구
A Study on Power Transformer Health Index Evaluation Using Dimensionality Reduction
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
건전도 지수는 유지보수 및 교체의 우선순위를 산정하기 위한 전력설비의 상태를 하나의 지표로 나타내는 방법이다. 머신러닝을사용하여 건전도 지수의 산정 알고리즘을 개발할 때 다종의 입력파라미터를 사용하기 때문에 대규모의 데이터양이 필요하고, 데이터 간 거리가 멀어져 군집 추출에 정확도가 떨어지거나 과적합 현상이 발생하는 문제가 있다. 따라서 본 논문에서는 차원축소기법을이용한 새로운 머신러닝 기반 건전도 지수 산정 알고리즘을 제안한다. 제안된 방식에서는 FMEA 및 진단 교차 매트릭스를 통해 입력파라미터를 선정하고, 차원축소 방식을 통해 입력 데이터의 차원을 축소하여 머신러닝 모델에 적용 및 비교하였다.
Abstract
The health index quantifies power equipment condition into a single indicator, guiding maintenance andreplacement priorities. Developing a machine learning-based health index algorithm requires extensive data due tothe wide range of input parameters. However, issues such as low clustering accuracy and overfitting can occur dueto data sparsity and distance. To address this, this paper proposes a novel soundness index calculation methodthat employs dimensionality reduction. Key parameters are selected via FMEA and diagnostic cross-matrix, anddimension reduction techniques are applied to input data, enhancing model performance.
참고문헌 (17)
- Ahmed E. B. Abu-Elanien, "Asset management techniques for transformers", Electric Power Systems Research, 80(4), pp.456~464 (2010)[DOI]
- Tsang, A. H. C., "Data management for CBM optimization", Journal of Quality in Maintenance Engineering, 12(1), pp.37~51 (2006)[DOI]
- Romaimi, Khamis, "Health index assessment for power transformer strategic asset management in electrical utilities", International Journal of Strategic Engineering Asset Management, 4, pp.81~99 (2023)[DOI]
- T. Hjartarson, "Predicting Future Asset Condition Based on Current Health Index and Maintenance Level", ESMO 2006~2006 IEEE 11th International Conference on Transmission &Distribution Construction, Operation and Live-Line Maintenance (2006)
- Brandtzæg, Georg, "Health indexing of Norwegian power transformers", MS, pp.2015
- H. Manninen, "Health Index Prediction of Overhead Transmission Lines : A Machine Learning Approach", IEEE Transactions on Power Delivery, 37(1), pp.50~58 (2022)[DOI]
- Li, S, "Review of Transformer Health Index from the Perspective of Survivability and Condition Assessment", Electronics (2023)[DOI]
- Alqudsi, Alhaytham, "Application of machine learning in transformer health index prediction", Energies, 12(14) (2019)[DOI]
- Leauprasert, Kunanya, "Intelligent machine learning techniques for condition assessment of power transformers", 2020 International Conference on Power, Energy and Innovations (ICPEI) (2020), IEEE
- Sarajcev, Petar, "Wide & Deep Machine Learning Model for Transformer Health Analysis", 2019 4th International Conference on Smart and Sustainable Technologies (SpliTech) (2019), IEEE
- Verleysen, Michel, "The curse of dimensionality in data mining and time series prediction", International work-conference on artificial neural networks (2005), Springer Berlin Heidelberg
- "IEEE Std C57.140", ~
- "EPRI – Equipment Failure Model and Data for Substation Transformer", ~
- "CIGRE TB-642", ~
- Pearson, Karl, "LIII. On lines and planes of closest fit to systems of points in space", The London, Edinburgh, and Dublin philosophical magazine and journal of science, 2(11), pp.559~572 (1901)[DOI]
- Hinton, Geoffrey E., "Stochastic neighbor embedding", Advances in neural information processing systems, 15 (2002)
- Van der Maaten, Laurens, "Visualizing data using t-SNE", Journal of machine learning research, 9(11) (2008)