Research on application of artificial intelligence in diagnosis of potential failures in transformers by dissolved gas analysis method
Abstract: 458
| 
PDF: 197 
##plugins.themes.academic_pro.article.main##
Author
Keywords:
Transformer
DGA
Artificial intelligence
Machine learning
FastTreeOva
Abstract
Dissolved gas analysis in insulating oil is a popular method for monitoring the condition of oil-immersed transformers. International standards organizations and researchers have developed many methods such as Doernenburg ratio, Roger ratio, IEC ratio, Duval triangle, and Duval pentagon to diagnose faults based on the composition of combustible gases produced in insulating oil: H2, CH4, C2H4, C2H6, C2H2, CO, and CO2 [1]. However, these methods have certain limitations, reducing the reliability of the diagnosis results. To overcome this, the authors applied the FastTreeOva machine learning model, developed by Microsoft, to predict potential failures in transformers. Using the ML.NET Framework and FastTree regression technique, this model achieved a prediction accuracy of 99.5%. Combined with the database from the transformers on the Central and Central Highlands power grids from 2002 to present, the software "DGA DIAGNOSTIC TOOL" was built to support analysis and diagnosis.
References
-
[1] Li, L. Wang, and B. Song, “Fault diagnosis of power transformers with membership degree”, IEEE Access, vol. 7, pp. 28791–28798, 2019, doi: 10.1109/ACCESS.2019.2902299.
[2] B. M. Taha, S. Ibrahim, and D. E. A. Mansour, “Power transformer fault diagnosis based on DGA using a convolutional neural network with noise in measurements”, IEEE Access, vol. 9, pp. 111162–111170, 2021, doi: 10.1109/ACCESS.2021.3102415.
[3] Hu, X. Ma, and Y. Shang, “A novel method for transformer fault diagnosis based on refined deep residual shrinkage network”, IET Electr Power Appl, vol. 16, no. 2, pp. 206–223, Feb. 2022, doi: 10.1049/elp2.12147.
[4] Suwarno, H. Sutikno, R. A. Prasojo, and A. Abu-Siada, “Machine learning based multi-method interpretation to enhance dissolved gas analysis for power transformer fault diagnosis”, Heliyon, vol. 10, no. 4, Feb. 2024, doi: 10.1016/j.heliyon.2024.e25975.
[5] Benmahamed, O. Kherif, M. Teguar, A. Boubakeur, and S. S. M. Ghoneim, “Accuracy improvement of transformer faults diagnostic based on DGA data using SVM-BA classifier”, Energies (Basel), vol. 14, no. 10, May 2021, doi: 10.3390/en14102970.
[6] IEEE Guide for the Interpretation of Gases Generated in Mineral Oil-Immersed Transformers, C57.104-2019. Transformers Committee of the IEEE Power and Energy Society, 2019.
[7] A. Thango, “On the Application of Artificial Neural Network for Classification of Incipient Faults in Dissolved Gas Analysis of Power Transformers”, Mach Learn Knowl Extr, vol. 4, no. 4, pp. 839–851, Dec. 2022, doi: 10.3390/make4040042.
[8] Mineral oil-filled electrical equipment in service – Guidance on the interpretation of dissolved and free gases analysis, IEC60599, 4th ed. Internationanl electrotechniccal commission, 2022.
[9] Duval and A. dePablo, “Interpretation of Gas-In-Oil Analysis Using New IEC Publication 60599 and IEC TC 10 Databases”, IEEE Electrical Insulation Magazine, vol. 17, no. 2, pp. 31–41, 2001.
[10] Duval and L. Lamarre, “The duval pentagon-a new complementary tool for the interpretation of dissolved gas analysis in transformers”, IEEE Electrical Insulation Magazine, vol. 30, no. 6, pp. 9–12, Nov. 2014, doi: 10.1109/MEI.2014.6943428.
[11] Van Le, “Application of artificial intelligence in diagnosis of power transformer incipient faults”, 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). IEEE, Da Nang, 2013. doi: 10.1109/CCECE.2013.6567700.
[12] Agrawal and A. K. Chandel, “Transformer incipient fault diagnosis based on probabilistic neural network”, in 2012 Students Conference on Engineering and Systems, SCES 2012, 2012. doi: 10.1109/SCES.2012.6199110.
[13] E. Gouda, S. H. El-Hoshy, and H. H. E. L. Tamaly, “Condition assessment of power transformers based on dissolved gas analysis”, IET Generation, Transmission and Distribution, vol. 13, no. 12, pp. 2299–2310, Jun. 2019, doi: 10.1049/iet-gtd.2018.6168.
[14] Chalupnik, K. Bialas, I. Jozwiak, and M. Kedziora, Acquiring and Processing Data Using Simplified EEG-based Brain-Computer Interface for the Purpose of Detecting Emotions. 2021.
[15] Van Hieu and D. T. T. Ha, “A system for dianosing autism based on the decision tree”, The University of Danang - Journal of Science and Technology, vol. 1, no. 11, pp. 101–104, 2015.
[16] M. et al. Magaji, “Fast Tree Model for Predicting Network Security Incidents”, in 2022 5th Information Technology for Education and Development (ITED). IEEE, 2022, pp. 1–6.
[17] Nanfak, S. Eke, C. H. Kom, R. Mouangue, and I. Fofana, “Interpreting dissolved gases in transformer oil: A new method based on the analysis of labelled fault data”, IET Generation, Transmission and Distribution, vol. 15, no. 21, pp. 3032–3047, Nov. 2021, doi: 10.1049/gtd2.12239.
[18] Odongo, R. Musabe, and D. Hanyurwimfura, “A multinomial dga classifier for incipient fault detection in oil-impregnated power transformers”, Algorithms, vol. 14, no. 4, Apr. 2021, doi: 10.3390/a14040128.
[19] Liu, B. Song, L. Wang, J. Gao, and R. Xu, “Power transformer fault diagnosis based on dissolved gas analysis by correlation coefficient-DBSCAN”, Applied Sciences (Switzerland), vol. 10, no. 13, Jul. 2020, doi: 10.3390/app10134440.
[20] Regulations for operation and repair. National Power Transmission Corporation, 2018.
[21] M. Hoang, “Power Transformer operation condition diagnosis using DGA ang artificial intelligence on Python platform”, Eng. Dissertation, Dept. Electrical and Electronic Engineering, Ho Chi Minh City University of Technology, Ho Chi Minh, 2021.
[22] Van Nga, “Report on the application of DGA Diagnostic Tool software at CPCETC”, Central electrical testing company limited, Da Nang, Nov. 2023.
[23] Q. Huy and V. K. Truong, “Report on the application of DGA Diagnostic Tool software at NPCETC”, Northern Electrical Tesing one member Company Limited, Northern Electrical Tesing one member Company Limited, Ha Noi, Mar. 2024.
[24] T. N. Tuan, “Report on the application of DGA Diagnostic Tool software at ETCHCM”, Ho Chi Minh City Electrical Testing Company, Ho Chi Minh, Mar. 2024.
Read more
##plugins.themes.academic_pro.article.sidebar##
Published
Oct 31, 2024
Download
How to Cite
Nguyễn Văn Ngà, Ngô Huy Chiến, Đào Trực, Trần Đình Thọ, Nguyễn Văn Lục, and Trần Huy Vũ. “Research on Application of Artificial Intelligence in Diagnosis of Potential Failures in Transformers by Dissolved Gas Analysis Method”. The University of Danang - Journal of Science and Technology, vol. 22, no. 10, Oct. 2024, pp. 30-40, https://jst-ud.vn/jst-ud/article/view/9362.
