Enhancing power transformer insulation assessment using gradient boosted decision trees and 2-FAL analysis
Tóm tắt: 138
| 
PDF: 62 
##plugins.themes.academic_pro.article.main##
Author
Từ khóa:
Power transformers
Dissolved Gas Analysis
insulation aging
health index
2-furfuraldehyde
Gradient Boosted Decision Trees
remaining useful life
Tóm tắt
This study presents an empirical model for predicting the degree of polymerization (DP) and estimating the remaining useful life (RUL) of transformer insulation based on 2-furfuraldehyde (2-FAL) concentrations. Using 125 samples collected from multiple credible sources, a Gradient Boosted Decision Trees (GBDT) model was developed to improve prediction accuracy. Compared with existing models such as Chengdong, Burton, and Heisler, the proposed GBDT achieved superior performance, with lower Mean Absolute Error (MAE = 38.65) and Root Mean Squared Error (RMSE = 63.04). Graphical analyses confirmed a strong agreement between predicted and measured DP values, effectively capturing the nonlinear relationship between 2-FAL and DP. Sensitivity analysis showed that the model responds notably to small variations in 2-FAL at early degradation stages. The results enhance transformer diagnostics and enable proactive asset management through accurate, non-invasive, and data-driven monitoring of insulation aging.
Tài liệu tham khảo
-
[1] H. V. Tran, K. A. Nguyen, and D. D. Le, “Impact of data balancing algorithms on the accuracy of power transformer fault diagnosis based on dissolved gas analysis”, in Proc. 2nd Int. Conf. on Green Solutions for Emerging Technologies and Sustainability (GSETS 2025), Ho Chi Minh City, Vietnam, Apr. 2025, pp. 851–863.
[2] D. Feng, Z. Wang, and P. Jarman, “Transmission power transformer assessment using furan measurement with the aid of thermal model”, in Proc. 2012 IEEE Int. Conf. Condition Monitoring and Diagnosis (CMD), Sep. 2012, pp. 521–524.
[3] Y. Wang, S. Gong, and S. Grzybowski, “Reliability evaluation method for oil–paper insulation in power transformers”, Energies, vol. 4, no. 9, pp. 1362–1377, 2011. https://doi.org/10.3390/en4091362
[4] X. Chendong, F. Qiming, and X. Shiheng, “To estimate the ageing status of transformers by furfural concentration in the oil”, in Proc. of the CIGRE Study Committee 33 Colloquium, Leningrad, Moscow, 1991.
[5] A. Heisler, A. Banzer, and R. Ilgen, “Zustandsbeurteilung von Transformatoren mit Furfurol-Bestimmung”, EW – Magazin für die Energiewirtschaft, vol. 102, no. 16, pp. 58–59, 2003.
[6] A. D. Pablo, “Interpretation of furanic compounds analysis–degradation models”, CIGRÉ Working Group D1, Tech. Brochure 15-01, 1997.
[7] A. D. Pablo, “Furfural and ageing: How are they related”, in IEE Colloquium on Insulating Liquids (Ref. No. 1999/119), May 1999, pp. 5–1. IET.
[8] M. Dong, Z. Yan, and G. J. Zhang, “Comprehensive diagnostic and aging assessment method of solid insulation in transformer”, in Proc. 2003 Annu. Rep. Conf. Electrical Insulation and Dielectric Phenomena (CEIDP), Oct. 2003, pp. 137–140. IEEE.
[9] R. D. Stebbins, D. S. Myers, and A. B. Shkolnik, “Furanic compounds in dielectric liquid samples: Review and update of diagnostic interpretation and estimation of insulation ageing”, in Proc. 7th Int. Conf. Properties and Applications of Dielectric Materials (ICPADM), 2003, pp. 921–926.
[10] B. Pahlavanpour, M. Eklund, and N. Naphthenics, “Thermal ageing of mineral insulating oil and kraft paper”, in Proc. TechCon, Oct. 2003.
[11] P. J. Burton, “Applications of liquid chromatography to the analysis of electrical insulating materials”, CIGRÉ Technical Brochure 15-8, 1988.
[12] H. Vaurchex, I. Höhlein, and A. J. Kachler, “Transformer aging research on furanic compounds dissolved in insulating oil”, in Proc. Large High Voltage Electrical Systems Conf., Paris, France, Aug. 2002, pp. 25–30.
[13] C. Lin, B. Zhang, and Y. Yuan, “The aging diagnosis of solid insulation for oil-immersed power transformers and its remaining life prediction”, in Proc. 2010 Asia-Pacific Power and Energy Engineering Conf. (APPEEC), Mar. 2010, pp. 1–3. IEEE.
[14] A. Teymouri, B. Vahidi, and P. van der Wielen, “A novel methanol-based DP estimation method with a new methanol peak detector index for aging assessment of power transformer insulation paper”, IEEE Trans. Dielectr. Electr. Insul., vol. 29, no. 4, pp. 1506–1513, 2022.
[15] B. A. Thango, J. A. Jordaan, and A. F. Nnachi, “Assessment of transformer cellulose insulation life expectancy based on oil furan analysis (case study: South African transformers)”, Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 6, pp. 29–33, 2021.
[16] S. Ghoneim, “The degree of polymerization in a prediction model of insulating paper and the remaining life of power transformers”, Energies, vol. 14, art. no. 670, 2021.
[17] P. C. K. Guri and K. Najdenkoski, “Transformer remaining life calculation based on degree of polymerization (DP)”, Journal of Multidisciplinary Engineering Science and Technology, vol. 4, no. 11, pp. 16779–16786, 2024.
[18] H. Park, E. Kim, B. S. Kwak, T. Jun, R. Kawano, and S. H. Pyo, “Selective aqueous extraction and green spectral analysis of furfural as an aging indicator in power transformer insulating fluid”, Separations, vol. 10, no. 7, pp. 381, 2023.
[19] International Electrotechnical Commission (IEC), “Insulating liquids – Determination of acidity – Part 2: Colourimetric titration”, IEC 62021-2, 2007.
[20] A. C. I. U. Ancuța-Mihaela, M. C. NIȚU, M. Nicola, C. I. Nicola, and F. Lăzărescu, “Complementary analysis of the degree of polymerization based on chemical markers 2-furaldehyde and methanol using fuzzy logic”, in Proc. 21st Int. Symp. Electrical Apparatus & Technologies (SIELA), Jun. 2020, pp. 1–6. IEEE.
[21] R. Soni and B. Mehta, “Review on asset management of power transformer by diagnosing incipient faults and faults identification using various testing methodologies”, Engineering Failure Analysis, vol. 128, no. 2, pp. 105634, 2021.
[22] D. Kanumuri, V. Sharma, and O. P. Rahi, “Analysis using various approaches for residual life estimation of power transformers”, International Journal on Electrical Engineering & Informatics, vol. 11, no. 2, pp. 389–407, 2019.
[23] K. Guri, “Correlation between degree of polymerization and data from transformer oil analysis”, Electrotechnica & Electronica (E+E), vol. 59, no. 1, pp. 24–32, 2024.
[24] H. V. Tran, K. A. Nguyen, D. D. Le, and D. H. Dinh, “Improving the reliability of oil-immersed power transformer fault diagnosis based on the evaluation of dissolved gas component input vectors”, in Proc. 2025 8th Int. Conf. on Circuits, Systems and Simulation (ICCSS 2025), Ho Chi Minh City, Vietnam, May 2025, pp. 109–114. https://doi.org/10.1109/ICCSS65911.2025.11081708
[25] C. Bentéjac, A. Csörgő, and G. Martínez-Muñoz, “A comparative analysis of gradient boosting algorithms”, Artificial Intelligence Review, vol. 54, pp. 1937–1967, 2021. https://doi.org/10.1007/s10462-020-09896-5
[26] A. A. Adekunle, I. Fofana, P. Picher, E. M. Rodriguez-Celis, and O. H. Arroyo-Fernandez, “Analyzing transformer insulation paper prognostics and health management: A modeling framework perspective”, IEEE Access, vol. 12, pp. 58349–58377, 2024.
[27] B. A. Thango and P. N. Bokoro, “Prediction of the degree of polymerization in transformer cellulose insulation using the feedforward backpropagation artificial neural network”, Energies, vol. 15, no. 12, pp. 4209, 2022.
Xem thêm
##plugins.themes.academic_pro.article.sidebar##
Đã Xuất bản
Sep 30, 2025
Download
Cách trích dẫn
Tran, H. V., K. A. Nguyen, và D. D. Le. “Enhancing Power Transformer Insulation Assessment Using Gradient Boosted Decision Trees and 2-FAL Analysis”. Tạp Chí Khoa học Và Công nghệ - Đại học Đà Nẵng, vol 23, số p.h 9B, Tháng Chín 2025, tr 49-55, doi:10.31130/ud-jst.2025.23(9B).503E.
