Estimation of Permanent Magnet Synchronous Generator Performance with Artificial Neural Network Models

Abstract

The interest in renewable energy sources has grown with the increase of environmental pollution and the decrease of fossil fuels. It is possible to provide energy supply security and diversity by using renewable energy sources. In this regard, wind energy, which is one of the renewable energy sources whose share in energy production increases day by day, emerges as a local and environmentally friendly solution. Many different types of generators are used in wind turbines and these have advantages and disadvantages according to each other. Permanent magnet synchronous generators (PMSG) are preferred because of their advantages such as high efficiency, high power density and being used directly in wind turbines without the need for gear system. In this study, the performance of the 2,5 kW PMSG, with a 14-pole surface placement, internal rotor, suitable for use in wind turbines, has been examined by changing the physical structure of the magnet. For this purpose, performance parameters such as total magnet consumption, efficiency, power loss have been successfully estimated using single and double hidden layered multi layer neural network (MLNN), elman neural network (ENN) and radial basis function neural network (RBFNN).

Keywords

• multilayer neural network,elman neural network,radial basis function neural network,permanent magnet synchronous generator

Sabit Mıknatıslı Senkron Generatör Performansının Yapay Sinir Ağı Modelleri ile Kestirimi

Abstract

Çevre kirliliğinin artması ve fosil yakıtların azalması ile yenilenebilir enerji kaynaklarına ilgi artmıştır. Yenilenebilir enerji kaynaklarını kullanarak enerji arz güvenliğini ve çeşitliliğini sağlamak mümkündür. Bu bağlamda, enerji üretiminde payı her geçen gün artan yenilenebilir enerji kaynaklarından biri olan rüzgâr enerjisi, yerel ve çevre dostu bir çözüm olarak ortaya çıkmaktadır. Rüzgâr türbinlerinde birçok farklı tipte jeneratör kullanılmaktadır ve bunlar birbirlerine göre avantaj ve dezavantajlara sahiptir. Sabit mıknatıslı senkron generatörler (SMSG) yüksek verim, yüksek güç yoğunluğu ve dişli sistemine gerek olmadan direkt olarak rüzgâr türbinlerinde kullanılma gibi avantajlarından dolayı tercih edilmektedirler. Bu çalışmada, rüzgâr türbinlerinde kullanıma uygun 14-kutuplu yüzey yerleştirmeli, içten rotorlu, 2,5 kW SMSG’nin performansı mıknatısın fiziksel yapısı değiştirilerek incelenmiştir. Bu amaçla toplam kullanılan mıknatıs miktarı, verim, güç kaybı gibi performans parametreleri tek ve iki gizli katmana sahip çok katmanlı sinir ağı (MLNN), elman sinir ağı (ENN) ve radyal tabanlı fonksiyon sinir ağı (RBFNN) kullanılarak başarılı bir şekilde kestirilmiştir.

Keywords

• çok katmanlı sinir ağı,elman sinir ağı,radyal tabanlı fonksiyon sinir ağı,sabit mıknatıslı senkron generatör

References

1. [1] V. Khare, S. Nema, and P. Baredar, “Solar–wind hybrid renewable energy system: A review”, Renewable and Sustainable Energy Reviews, vol. 58, pp. 23-33, 2016.
2. [2] E. Delihasanlar, E. K. Yaylacı and A. Dalcalı, “Solar Energy potential in the world and Turkey, current status, incentives, installation cost analysis-Karabuk province sample”, Electronic Letters on Science & Engineering, vol. 15, no. 1, pp. 12-20, 2019.
3. [3] “Elektrik üretim iletim istatistikleri raporu”, [Online]. https://www.teias.gov.tr/tr-TR/turkiye-elektrik-uretim-iletim-istatistikleri. [Erişim: 10.04.2020].
4. [4] “Gerçek zamanlı üretim”, [Online]. https://seffaflik.epias.com.tr/transparency/uretim/gerceklesen-uretim/gercek-zamanli-uretim.xhtml. [Erişim: 10.04.2020].
5. [5] H. Polinder, F.F.A. van der Pijl, G.J. de Vilder and P. Tavner, “Comparison of direct-drive and geared generator concepts for wind turbines”, Proc. International Conference on Electric Machines and Drives, 2005, pp. 543-550.
6. [6] O, Lyan, V. Jankunas, E. Guseınoviene, A. Pasilis, A. Senulis, A. Knolis and E Kurt, “Exploration of a permanent magnet synchronous generator with compensated reactance windings in parallel rod configuration”, Journal of Electronic Materials, pp. 1-7, 2018.
7. [7] A. Dalcalı, E. Kurt, E. Çelik and N. Öztürk, “Cogging Torque Minimization Using Skewed and Separated Magnet Geometries”, Journal of Polytechnic, vol. 23, no. 1, pp. 223-230, 2020.
8. [8] A. Dalcalı, M. Akbaba, “Optimum pole arc offset in permanent magnet synchronous generators for obtaining lowest voltage harmonics”, Scientia Iranica D, vol. 24, no. 6, pp. 3223-3230, 2017.

9. [9] K.M. Vishnu Murthy, Computer-Aided Design of Electrical Machines. BS Publications, Hyderabad, 2008.
10. [10] G. Lee, S. Min and J.P. Hong, “Optimal Shape design of rotor slot in squirrel-cage induction motor considering torque characteristics”, IEEE Transactions on Magnetics, vol.49, no.5, pp. 2197-2200, 2013.
11. [11] A. Dalcalı, M. Akbaba, “Comparison of 2D and 3D magnetic field analysis of single-phase shaded pole induction motors”, Engineering Science and Technology, an International Journal, vol.19, no. 1, pp. 1-7, 2016.
12. [12] S.L. Ho and W.N. Fu, “Review and future application of finite element methods in induction motors,” Electric Machines & Power Systems, vol. 26, no. 2, pp. 111-125, 1998.
13. [13] M. Akbaba and S. Q. Fakhro, "An ımproved computational technique of the inductance parameters of the reluctance augmented shaded-pole motors using finite element method," IEEE Transactions on Energy Conversion, vol. 7, no. 2, pp. 308–314, 1992.
14. [14] A. Dineva, A. Mosavi, S. F. Ardabili, I. Vajda, S. Shamshirband, T. Rabczuk and K. W. Chau, “Review of soft computing models in design and control of rotating electrical machines”, Energies, vol. 12, no. 1049, pp. 1-28, 2019.
15. [15] A. Dalcalı, O. Çetin, C. Ocak and F. Temurtaş, “Prediction of the force on a projectile in an electromagnetic launcher coil with multilayer neural network”, Sakarya University Journal of Computer and Information Sciences, vol. 1, no. 3, pp. 1-10, 2018.
16. [16] E. Çelik, H. Gör, N. Öztürk and E. Kurt, “Application of artificial neural network to estimate power generation and efficiency of a new axial flux permanent magnet synchronous generator”, Int. J. Hydrogen Energy, vol. 42, pp. 17692–17699, 2017.
17. [17] M. Ehsani, Y. Gao, and S, Gay, “Characterization of electric motor drives for traction applications”, Proc. 29th Annual Conference of the IEEE Industrial Electronics Society, USA, 2003.
18. [18] H. W. Jun, J. W. Lee, G.H. Yoon and J. Lee, J. “Optimal design of the PMSM retaining plate with 3-D barrier structure and eddy-current loss-reduction effect, IEEE Transaction on Industrial Electronics, vol. 65, no. 2, pp. 1808-1818, 2018.
19. [19] B.O. Zala and V. Pugachov, “Methods to reduce cogging torque of permanent magnet synchronous generator used in wind power plants”, Elektronika Ir Elektrotechnika, vol. 23, no.1, pp. 43-48, 2017.
20. [20] Y. Duan, “Method for design and optimization of surface mount permanent magnet machines and induction machines” Ph. D. Thesis, Georgia Institute of Technology, pp. 8-24, 2010.
21. [21] C. Ocak, “Doğrudan tahrikli asansör sistemlerinde kullanılan sabit mıknatıslı senkron motorlarda mıknatıs geometrisinin motor performansı ve maliyeti üzerindeki etkilerinin incelenmesi”, Mühendislik Bilimleri ve Tasarım Dergisi, vol. 7, no. 4, pp. 825-834, 2019.
22. [22] F. Temurtas, R. Gunturkun, N. Yumusak, and H. Temurtas, “Harmonic detection using feed forward and recurrent neural networks for active filters,” Electr. Power Syst. Res., vol. 72, no. 1, pp. 33–40, 2004.
23. [23] O. Çetin and F. Temurtaş, “Classification of magnetoencephalography signals by multilayer and radial based artificial neural networks,” Elec Lett Sci Eng, pp. 32–38, 2018.
24. [24] M. F. Moller, “A scaled conjugate gradient algorithm for fast supervised learning,” Neural Networks, vol. 6, pp. 525–533, 1993.
25. [25] A. Gulbag and F. Temurtas, “A study on quantitative classification of binary gas mixture using neural networks and adaptive neuro-fuzzy inference systems,” Sensors Actuators, B Chem., vol. 115, no. 1, pp. 252–262, 2006.
26. [26] A. Gulbag and F. Temurtas, “A study on transient and steady state sensor data for identification of individual gas concentrations in their gas mixtures,” Sensors and Actuators B, vol. 121, no. 1, pp. 590–599, 2007.
27. [27] A. Gulbag, F. Temurtas, C. Tasaltin, and Z. Z. Öztürk, “A study on radial basis function neural network size reduction for quantitative identification of individual gas concentrations in their gas mixtures,” Sensors Actuators, B Chem., vol. 124, no. 2, pp. 383–392, 2007.