A Neural Network Controller For The Direct Power Control Of Doubly Fed Induction Generator

Authors

  • Rodrigo Andreoli de Marchi State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil
  • Paulo S. Dainez State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil
  • Fernando J. Von Zuben State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil
  • Edson Bim State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil

DOI:

https://doi.org/10.18618/REP.2013.3.10381046

Keywords:

constant switching frequency, Direct Power Control, Doubly-Fed Induction Generator, Multilayer perceptron, Neural Network Controller

Abstract

In this paper a direct power control strategy for a doubly-fed induction generator by using an artificial neural network controller with the multilayer perceptron structure is presented. The control variables direct- and quadrature-axis rotor voltage signals are directly generated by proposed controller from both stator current and voltage that are measured by Hall sensors. The input variables of the control system are the rotor speed, the active and reactive power references and their respective errors. The proposed control strategy allows that the converter connected to the rotor terminals operates with constant switching frequency which simplifies the design of the AC harmonic filter and as well as prevents their power losses. To validate the proposed control strategy, digital simulation and experimental tests are performed for a 2.25\,kW doubly-fed induction generator. A TMS320F2812 DSP is used to implement the neural network controller.

Downloads

Download data is not yet available.

Author Biographies

Rodrigo Andreoli de Marchi, State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil

received the B.S. degree (2008) in electrical engineering from Methodist University of Piracicaba, Brazil, the M.S. degree (2011) from State University of Campinas, Brazil and currently he is working toward the Ph.D. degree at the State University of Campinas. His current research interests include AC drives and neural networks control applied to squirrel cage and doubly fed induction machines.

Paulo S. Dainez, State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil

received the B.Sc. degree in electrical engineering from Federal University of Santa Catarina, Brazil, in 1994, the M.Sc. degree in electrical engineering from State University of Santa Catarina, Brazil, in 2010. From 1994 to 2011, he was an Electrical Engineer in the Whirlpool Compressor Unit - Brazil. Since 2011, he is working toward the Ph.D. degree in electrical engineering from State University of Campinas, Brazil. His current research interest include control and simulation of electrical machines, Multiphase motor and AC drives.

Fernando J. Von Zuben, State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil

received his Dr.E.E. degree from the University of Campinas (Unicamp), Campinas, SP, Brazil, in 1996. He is currently the header of the Laboratory of Bioinformatics and Bioinspired Computing (LBiC), and an Associate Professor at the Department of Computer Engineering and Industrial Automation, School of Electrical and Computer Engineering, University of Campinas (Unicamp). The main topics of his research are computational intelligence, bioinspired computing, multivariate data analysis, and machine learning. He coordinates open-ended research projects in these topics, tackling real-world problems in the areas of information technology, decision-making, pattern recognition, and discrete and continuous optimization. He has concluded the supervision of more than 40 graduate students, and has published more than 60 full research papers and more than 200 conference papers. Fernando J. Von Zuben is IEEE Senior Member and also a member of the Evolutionary Computation Technical Committee of the IEEE Computational Intelligence Society.

Edson Bim, State University of Campinas - UNICAMP - School of Electrical and Computer Engineering - P.O. Box 6101 - 13083-852 Campinas Brazil

received the B.S., M.S., and Ph.D. degrees, in electrical engineering from the State University of Campinas (UNICAMP), Campinas, São Paulo, Brazil, in 1976, 1981, and 1993, respectively. Since 1977 he has been Professor with the Faculty of Electrical and Computer Engineering, University of Campinas (Unicamp) and he is currently an Associate Professor. He has written one book (Portuguese language, 2nd Edition), secured one Brazil patent and published technical papers. Much of his current research focuses on predictive adaptive and neural networks control applied to three-phase and multiphase induction machines.

References

B. H. Chowdhury and S. Chellapilla.Double-fedinduction generator control for variable speed windpower generator.Electric Power System Research,76:786-800, 2006. https://doi.org/10.1016/j.epsr.2005.10.013 DOI: https://doi.org/10.1016/j.epsr.2005.10.013

I. Cardici and M. Ermis.Double-output inductiongeneratoroperatingatsubsynchronousandsupersynchronous speeds:steady-state performanceoptimization and wind-energy recovery.IEE ProceedingsB, 139:429-442, 1992. https://doi.org/10.1049/ip-b.1992.0053 DOI: https://doi.org/10.1049/ip-b.1992.0053

R. Datta and V. T. Rangathan.Variable-speed windpower generation using doubly fed wound rotor inductionmachine - a comparison with alternative schemes.IEEETrans. Energy Conversion, 17:414-421, 2002. https://doi.org/10.1109/TEC.2002.801993 DOI: https://doi.org/10.1109/TEC.2002.801993

F. Blaabjerg and F. Iov. Wind power - a power sourcernow enabled by power electronics. InBrazilian PowerElectronics Conference, pages 1-16, 2007.

R. G. de Oliveira, J. L. da Silva, and S. R. Silva.Desenvolvimento de uma nova estratégia de controlede potência reativa em gerador de inducão de duplaalimentacão para turbinas eólicas.Eletrônica dePotência, 13(4):207-284, Nov. 2008. https://doi.org/10.18618/REP.2008.4.277284 DOI: https://doi.org/10.18618/REP.2008.4.277284

S. T. Jou, S. B. Lee, Y. B. Park, and K. B. Lee. Directpower control of a dfig in wind turbines to improvedynamics responses.Journal of Power Electronics,9(4):781-790, Sept. 2009. https://doi.org/10.6113/JPE.2009.9.5.781

A. Petersson, L. Harnefors, and T. Thiringer. Evaluationof current control methods for wind turbines usingdoubly-fed induction machines.IEEE Trans. PowerElectron., 20:2270-2281, 2005. https://doi.org/10.1109/TPEL.2004.839785 DOI: https://doi.org/10.1109/TPEL.2004.839785

F. K. de A. Lima, E. H. Watanabe, P. Rodriguez, andA. Luna. Controle de gerador de inducão duplamentealimentado diante de afundamentos de tensão.Eletrônicade Potência, 3(14):189-199, 2009. https://doi.org/10.18618/REP.2009.3.189199 DOI: https://doi.org/10.18618/REP.2009.3.189199

R. Datta and V.T. Ranganathan. Direct power control ofgrid-connected wound rotor induction machine withoutrotor position sensors.IEEE Trans. Power Electron.,16:1058-1066, 2001. https://doi.org/10.1109/63.923772 DOI: https://doi.org/10.1109/63.923772

I. Takahashi and T. Noguchi. A new quick-response andhigh-efficiency control strategy of an induction motor.IEEE Transactions Industry Applications, 22:820-827,1986. https://doi.org/10.1109/TIA.1986.4504799 DOI: https://doi.org/10.1109/TIA.1986.4504799

Lie Xu and P. Cartwright. Direct active and reactivepower control of dfig for wind energy generation.IEEETrans. Energy Conversion, 21(3):750-758, Sept. 2006. https://doi.org/10.1109/TEC.2006.875472 DOI: https://doi.org/10.1109/TEC.2006.875472

D. Zhi and L. Xu. Direct power control of dfig withconstant switching frequency and improved transientperformance.IEEE Trans. Energy Conversion, 22:110-118, 2007. https://doi.org/10.1109/TEC.2006.889549 DOI: https://doi.org/10.1109/TEC.2006.889549

R. V. Jacomini and E. Bim. Direct power control of adoubly fed induction generator by using a neuro-fuzzycontroller.Eletrônica de Potência, 16(4):330-338, Nov.2011. https://doi.org/10.18618/REP.20114.330338 DOI: https://doi.org/10.18618/REP.20114.330338

O. Barambones, J. M. G. Durana, and E. Kremers.A neural network based wind speed estimator fora wind turbine control.15th IEEE MediterraneanEletrotechnical Conference, pages 1383-1388, 2010. https://doi.org/10.1109/MELCON.2010.5476008 DOI: https://doi.org/10.1109/MELCON.2010.5476008

A. F. Santos, F. A. S. Neves, R. R. B. Aquino, andM. C. Cavalcanti. Application of artificial neural networkin the efficient control of three-phase induction motor.Eletrônica de Potência, 15(2):87-96, May 2010. https://doi.org/10.18618/REP.2010.2.087096 DOI: https://doi.org/10.18618/REP.2010.2.087096

O. Soares, H. Gonçalves, A. Martins, and A. Carvalho.Nonlinear control of the doubly-fed induction generatorin wind power systems.Renewable and Energy,35:1662-1670, 2010. https://doi.org/10.1016/j.renene.2009.12.008 DOI: https://doi.org/10.1016/j.renene.2009.12.008

L. Li and K. Wang. Doubly-fed generation system basedon neural network inverse control.Second InternationalSymposium on Knowledge Acquisition and Modeling,pages 147-150, 2009. https://doi.org/10.1109/KAM.2009.128 DOI: https://doi.org/10.1109/KAM.2009.128

Edson Bim."Máquinas Elétricas e Acionamento".Elsevier Publications, 2012.

W. T. Miller, R. S. Sutton, and P. J. Werbos."NeuralNetworks for Control". Bradford Book, 1995.

K. Hornik, M. Stinchkombe, and H. White. Multilayerfeedforward networks are universal approximators.Neural Networks, 2(5):359-366, Febr. 1989. https://doi.org/10.1016/0893-6080(89)90020-8 DOI: https://doi.org/10.1016/0893-6080(89)90020-8

V. Cherkassky and F. Mulier."Learning from Data:Concepts, Theory, and Methods". Wiley, 2007. https://doi.org/10.1002/9780470140529 DOI: https://doi.org/10.1002/9780470140529

L. A. C. Meleiro, F. J. Von Zuben, and R. MacielFilho. Constructive learning neural network applied toidentification and control of a fuel-ethanol fermentationprocess.Engineering Applications of ArtificialIntelligence, 22:201-215, 2009. https://doi.org/10.1016/j.engappai.2008.06.001 DOI: https://doi.org/10.1016/j.engappai.2008.06.001

T. M. Mitchell."Machine Learning". McGraw-Hill,1997.

S. Haykin."Neural Networks and Learning Machines".Wiley, 2008.

R. V. Jacomini, A. França, and E. Bim.Simulationand experimental studies on double-fed inductiongenerator power control operating at subsynchronousoperation speed.Power Electronics and Drive Systems.International Conference on, pages 1421-1424, 2009. https://doi.org/10.1109/PEDS.2009.5385924 DOI: https://doi.org/10.1109/PEDS.2009.5385924

E. P. dos Santos and F. J. Von Zuben. Improved second-order training algorithms for globally and partiallyrecurrent neural networks.Proceedings of the IEEEInternational Joint Conference on Neural Networks,3:1501-1506, 1999. https://doi.org/10.1109/IJCNN.1999.832591 DOI: https://doi.org/10.1109/IJCNN.1999.832591

M. F. Moller. A scaled conjugate gradient algorithm forfast supervised learning.Neural Networks, 6:525-533,1993. https://doi.org/10.1016/S0893-6080(05)80056-5 DOI: https://doi.org/10.1016/S0893-6080(05)80056-5

K. Najarian. On learning of sigmoid neural networks.Complexity, 6(4):39-45, Jun. 2001. https://doi.org/10.1002/cplx.1041 DOI: https://doi.org/10.1002/cplx.1041

Downloads

Published

2013-08-31

How to Cite

[1]
R. A. de Marchi, P. S. Dainez, F. J. V. Zuben, and E. Bim, “A Neural Network Controller For The Direct Power Control Of Doubly Fed Induction Generator”, Eletrônica de Potência, vol. 18, no. 3, pp. 1038–1046, Aug. 2013.

Issue

Vol. 18 No. 3 (2013)

Section

Original Papers

License

Copyright (c) 2013 Revista Eletrônica de Potência

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC