THE USE OF ARTIFICIAL INTELLIGENCE ALGORITHMS FOR THE DIAGNOSIS AND CATEGORIZATION OF WINDING DEFECTS IN POWER TRANSFORMERS
Keywords:
Engineering, Artificial Intelligence, Diagnosis, Power TransformersAbstract
The power transformer is the piece of equipment that plays the most important role in the power system. Enormous power transformers are among the components of any power system that are both the most expensive and the most strategic. The generation and transmission of electric power must have a reliable and consistent operation in order to be economically viable. Failures of transformers brought on by an unexpected or unanticipated power loss are one of the most expensive and costly of all events. As a result, a suitable maintenance strategy is essential in order to prevent unanticipated outages. Because of this, there is a pressing need for further research on detection and diagnosis techniques that are able to determine the state of the equipment. At the generating plants, the transformers are responsible for a significant role. The greatest producing capacity in India is 765 kilovolts, and the locations of the generating stations are often rather far from the load sites. So, the voltage needs to be stepped up to an extremely high value at various stages in order to convey electricity with minimal losses, and it needs to be stepped down to distribution voltage levels at substations. As a result, electricity is delivered in many stages at a variety of different system voltages. When seen from this perspective, the transformer is regarded as the most expensive asset of electricity utilities. In most cases, the estimated service life of a transformer falls anywhere between 20 and 30 years. The goal of the utilities company is to maximize the operating life of the transformer while minimizing the risk of it failing or breaking down. When the transformer insulation ages, the insulation paper shrinks, which results in a loss of clamping pressure and, ultimately, mechanical strength. The essential components of a transformer that are susceptible to failure are the insulation.
References
AJ, Christina & Salam, M. & Rahman, Quazi& Wen, Fushuan& Ang, Swee&Voon, William. “Causes of transformer failures and diagnostic methods – A review”, Renewable and Sustainable Energy Reviews, Volume.82, Part 1, 2017.
Shayan Tariq Jan, Raheel Afzal, and Akif Zia Khan “Transformer Failures, Causes & Impact”, International Conference Data Mining, Civil and Mechanical Engineering Feb. 1-2, 2015.
William H. Bartley, HSB, “Failure Analysis of Power Transformers,” Proceedings of the Thirty-Six Annual Conference, Stockholm, 2003.
Akbari Mohsen, P. Khazaee and P. KarimifardSabetghadam, "Failure Modes and Effects Analysis (FMEA) for Power Transformers", Power Transmission & Distribution Research CenterNiroo Research Institute (NRI) Tehran Iran. 28th international power system conference Iran, pp. 1-7, November 2013.
Guide for LIFE Management Techniques for Power Transformer, CIGRE Working Group A2.18, no. 227, June 2003.
“IEEE Guide for Transformer Impulse Tests," in IEEE Std C57.98-1993, vol., no., pp.1-59, 11 Nov. 1994,
Y. Yang, Q. Wang, C. Gao, J. Pu, X. Zhang and J. Li, "Study of Comparison of Voltage Distribution in Transformer under Different Lightning Impulse Voltages," 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE), 2020, pp. 1-4,
Luna López, Z., Gómez, P., Espino-cortes, F.P., & Peña-Rivero, R. (2017). Modeling of Transformer Windings for Fast Transient Studies: Experimental Validation and Performance Comparison. IEEE Transactions on Power Delivery, 32, 1852-1860.
F. K. W. Grover, “Inductance Calculations, Working Formulae and Tables”, Dover Publications, 180 Varick Publication, Newyork.
Y. Li, J. Du, X. Li and D. Li, "Calculation of capacitance and inductance parameters based on FEM in high-voltage transformer winding," 2011 International Conference on Electrical Machines and Systems, 2011, pp. 1-4.
Hosseini, Seyed Mohammad Hassan et al. “Using the finite element method to calculate parameters for a detailed model of transformer winding for partial discharge research.” Turkish Journal of Electrical Engineering and Computer Sciences 23 (2015): 709-718.
Banaszak S, Gawrylczyk KM, Trela K, Bohatyrewicz P. The Influence of Capacitance and Inductance Changes on Frequency Response of Transformer Windings. Applied Sciences. 2019; 9(5):1024.
IEEE Guide for the Application and Interpretation of Frequency Response Analysis for Oil-Immersed Transformers," in IEEE Std C57.149-2012, vol., no., pp. 1-72, 8 March 2013.
Alsuhaibani, S.H., Khan, Y., Beroual, A., & Malik, N.H. (2016). A Review of Frequency Response Analysis Methods for Power Transformer Diagnostics. Energies, 9, 879-895.
Cigre, W.G. Mechanical Condition Assessment of Transformer Windings using Frequency Response Analysis (FRA); Brochure 342; CIGRE: Paris, France, 2008.
Sharma, V. (2022). A Study on Data Scaling Methods for Machine Learning. International Journal for Global Academic & Scientific Research, 1(1), 31–42. https://doi.org/10.55938/ijgasr.v1i1.4
Kaushik, P. (2023). Deep Learning Unveils Hidden Insights: Advancing Brain Tumor Diagnosis. International Journal for Global Academic & Scientific Research, 2(2), 01–14. https://doi.org/10.55938/ijgasr.v2i2.45
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Amar Saraswat, Rajiv Mishra, Ashwini S Shivannavar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author(s) hold complete right on the content of this article.