การใช้โครงข่ายประสาทเทียมช่วยในการวิเคราะห์กำลังสูญเสียของหม้อแปลงไฟฟ้าระบบจำหน่ายในสภาวะโหลดปกติและโหลดเกิน
Keywords:
Artificial neural network, Distribution transformer, Temperature, Power lossesAbstract
This research paper presents power loss analysis in a 3-phase distribution transformer of 100 kVA 22 kV-400/230 V in normal load and overload conditions using a neural network technique. This method can analyze power loss in the transformer quicker and use fewer variables than the power loss calculation using various parameters obtained from transformer manufacturers. Seventy thousand sets of current tests ranging from 1%-140% at temperatures of 35oC, 45oC, 55oC, 65oC and 75oC were experimentally measured, then power losses are calculated. Fifty-six thousand sets of those were used for training of the neural network to find the parameters and the other 14,000 sets were used for the input data to find power losses. In addition, the power losses obtained from the artificial neural network were compared with calculated power losses by using parameters from transformer manufacturers. The error percentage value no more than 1.06 was at a satisfactory level suggestingthat this method can be applied in the designing of electrical power loss test for transformers in the future.
References
Souza AN, Silva IN, Souza CFLN, Zago MG. Using artificial neural networks for identification of electrical losses in transformers during the manufacturing phase. Proceedings of the 2002 International Joint Conference on Neural Networks Vol.2; 2002 May 12-17; Honolulu, HI, USA. 2002. p. 1346-50
Suechoey B. Estimating the economically optimal size of distribution transformer to suitable the load and reduce electrical power losses. Kasem Bundit Engineering Journal 2024;14(1):48-61. (In Thai)
Suttisinthong N, Pothisarn C. Analysis of Electrical Losses in Transformers using Artificial Neural Networks. Proceedings of the International MultiConference of Engineers and Computer Scientists 2014 Vol II (IMECS 2014); 2014 Mar 12-14, 2014; Hong Kong. p. 705-8
Basheer IA, Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. Journal of Microbiological Methods 2000;43(1):3-31.
Suechoey S, Siriporananon S, Pringsakul N, Thongrak A. Implementation of load cycle simulation for studies of loss energy and lifetime of oil-immersed transformers. Proceedings of the 10th International Conference on Sciences, Technology and Innovation for Sustainable Well-Being (STISWB 2018); 2018 May 9-11; Vientiane, Laos. p. 202-7.
Siriporananon S, Suechoey B. Power losses analysis in a three-phase distribution transformer using artificial neural networks. The ECTI Transactions on Electrical Engineering, Electronics, and Communications 2020;18(2):130-6.
Siriporananon S, Suechoey B, Pringsakul N. Performance testing of transformers used in distribution systems. Proceedings of the 10th International Conference on Sciences, Technology and Innovation for Sustainable Well-Being (STISWB 2018); 2018 May 9-11; Vientiane, Laos. p. 196-201.
International Electrotechnical Commission. IEC60076-2. Power transformer part 2: temperature rise for liquid-immersed transformers. Geneva, Switzerland: International Electrotechnical Commission; 2011.
Grainger JJ, Stevenson WD. Power system analysis. Newyork, USA: McGraw-Hill; 1994.
Provincial Electricity Authority Thailand (PEA). Three-phase transformer for 22 kV and 33 kV distribution systems with ability to withstand short circuit, specification No. RTRN-035/2558. Bangkok, Thailand: Provincial Electricity Authority Thailand; 2015.
Hagan MT, Demuth HB, Beale M. Neural network design. Boston, USA: PWS Publishing Company; 1996.
Demuth H, Beale M. Neural network toolbox user’s guide. Natick, MA: The Mathwork; 1998.
Souza KN, Castro TN, Pereira TM, Pontes RST, Braga APS. Prediction of core losses on a three-phase transformer using neural network. Proceeding of the International Symposium on Circuits and Systems (ISCAS 2011); 2011 May 15-19; Rio de Janeiro, Brazil. p.1105-8.
Yadav AK, Azeem A, Singh A, Malik H, Rahi OP. Application research based on Artificial Neural Network (ANN) to predict no-load for transformer’s design. Proceeding of the 2011 International Conference on Communication Systems and Network Technologies; 2011 Jun 3-5; Katra, India. p.180-3.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Kasem Bundit University
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
*Copyright
The article has been published in Kasem Bundit Engineering Journal (KBEJ) is the copyright of the Kasem Bundit University. Do not bring all of the messages or republished except permission from the university.
* Responsibility
If the article is published as an article that infringes the copyright or has the wrong content the author of article must be responsible.
