Determination of leakage reactance in monophase transformers using by cascaded neural network

Year 2016, Volume: 4 Issue: 2, 89 - 96, 30.09.2016

Selcuk Nogay

Abstract

In this study, the artificial neural networks method was used in order to determine the leakage induction coefficient using known constants of the transformer. It is important to reach the leakage reactance through guessing. For this purpose, two types of ANN models were used in the study and were compared to one another. These two ANN models are cascaded ANN model and the conventional model. Testing data were used to measure the efficiency of these two models. Testing data are the same for both models. When the models were compared to each other, it was concluded that Cascaded ANN model was more successful. However, it is a fact that both models produce estimation around 99%. The main reason why the ANN model is used in the study is to ensure a more practical and quicker attainment of leakage reactance or leakage induction coefficient by looking at the fixed and measurable values of the transformer than calculation method.

Keywords

Transformator, Leakage Induction Coefficient, Cacaded Neural Network, Backpropagation Learning Algorithm

References

• [1] L. Andriušienė, A. Kairys, P. Kostrauskas, “Mathematical Modeling of External Characteristics of Power Transformers” , Electronics and Electrical Engineering. – Kaunas: Technologija, No. 5, 40, 2002 [2] P. Raitsios, “Leakage field of a transformer under conventional and superconducting condition”, Journal of Materials Processing Technology, 108. 246-252. 2001. [3] R. Doebbelin, C. Teichert, M. Benecke, and A. Lindemann, “Computerized Calculation of Leakage Inductance Values of Transformers”, Piers Online, Vol. 5, No. 8, 2009. [4] M. A. Tsili, A. G. Kladas, S. Georgilakis, “Computer aided analysis and design of power transformers”, Computers in Industry, 59, pp. 338–350, 2008 [5] A. G. Leal, J. A. Jardini, L. C. Magrini, S. U. Ahn, “Distribution Transformer Losses Evaluation, A New Analytical Methodology and Artificial Neural Network Approach”, IEEE Transactions on Power System, Vol. 24, No. 2, MAY 2009. [6] M. Tripathy, R. P. Maheshwari and H.K. Verma, “Probabilistic neuralnetwork- based protection of power transformer”,IET Electr. Power Appl. 1, (5), pp. 793–798, 2007. [7] A. Stadler, M. Albach, S. Chromy, “The Optimization of High Frequency Operated Transformers for Resonant Converters”, Dresden EPE , 2005 [8] O. İkizli, Distribution, Losses and Warm up on Electrical Machines - Elektrik Makinalarında Dağılma, Kayıplar ve Isınma, Library of Istanbul Technical University, 1962, No 482, pp. 15-18 [9] M. Tsili, A. Kladas, P. Georgilakis, A. Souflaris, D. Paparigas, “ Numerical techniques for design and modeling of distribution transformers”, Journal of Materials Processing Technology, 161. 320– 326, 2005. [10] J. Kondoh, I. Ishii, “Fault Current Limiting Transformer With Variable Reactance”, IEEE Transactions on applied superconductivity, Vol. 14, No. 2, June 2004. [11] Jan Reynders, “The prediction of fault currents in a large multi-winding reactor transformer”, IEEE Bologna PowerTech Conference, June 23- 26, Bologna, Italy, 2003. [12] L. Fausett, Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Prentice Hall. 1994. [13] H. Yurtoglu, Yapay Sinir Ağları Metodolojisi ile Öngörü Modellemesi: Bazı Makroekonomik Değişkenler için Türkiye Örneği, DPT Dissertion, DPT:2683, pp 1-7. Feb. 2005 [14] H. S. Nogay, “Prediction of Internal Temperature in Stator Winding of Three-Phase Induction Motors with ANN”, European Transactions on Electrical Power. 20:1–9. DOI: 10.1002. 2010. [15] T. Kohonen, “State Of The Art In Neural Computing”, IEEE First International Conference on Neural Networks, 1. 79-90, 1987. [16] Z. Aydogmus, “A neural network-based estimation of electric fields along high voltage insulators”, Expert Systems with Applications, 36, 8705–8710. 2009. [17] T.M. Hagan, H.B. Demuth, M. Beale, Neural Network Design, PWS Publishing Company, Boston 2-44, 1996. [18] B. Ciylan, “Determination of Output Parameters of a Thermoelectric Module using Artificial Neural Networks”, Electronics and Electrical Engineering. – Kaunas: Technologija, no:10, 116, 2011 [19] G.E.P Box., G. Jenkins, Time Series Analysis, Forecasting and Control, Golden-Day, San Francisco, CA, 1970. [20] M. Islam, A. Sattar, F. Amin, X. Yao, and K. Murase, “A New Constructive Algorithm for Architectural and Functional Adaptation of Artificial Neural Networks”, IEEE Transactions on Systems , Man. And Cybernetics – Part B, Vol. 39, No 6, Dec. 2009. [21] B. Jena, D. Swain, and A. Tyagi, “Application of Artificial Neural Networks for Sea-Surface Wind-Speed Retrieval From IRS-P4”, (MSMR), Brightness Temperature IEEE Geoscience and Remote Sensing Letters, Vol. 7, No. 3, 567. July 2010. [22] Khaled Shaban, Ayman El-Hag, Andrei Matveev, “ A Cascade of Artificial Neural Networks to Predict Transformers Oil Parameters”, IEEE Transactions on Dielectrics and Electrical Insulation ,Vol. 16, No. 2; April 2009. [23] A. Kazemi, M. T. Hassanzadeh, A. Gholami, “Artificial Neural Network for Insulator Leakage Currents Prediction from Environmental Data”, 2nd IEEE International Conference on Power and Energy (PECon 08), Johor Baharu, Malaysia, December 1-3, 2008 [24] T.C. Akinci. “Short Term Wind Speed Forecasting with ANN in Batman, Turkey” , Electronics and Electrical Engineering, Vol.107, No.1, 2011.