Artificial Intelligence Based Vector Control of Induction Generator Without Speed Sensor for Use in Wind Energy Conversion System

Abstract

Indirect field oriented control (IFOC) of squirrel-cage induction generator (SCIG) with full capacity power converter used in wind energy conversion system (WECS) is presented in this paper. In order to improve WECS reliability robust IFOC algorithm using artificial intelligence (AI) for speed estimation was developed. Estimated speed is used for realization of maximum power tracking algorithm (MPPT). Practical testing and validation of considered estimation techniques is performed using advance laboratory prototype of WECS. Extensive experimentation is conducted in order to verify efficiency and reliability of proposed speed-sensorless control technique under realistic WECS operating conditions.

Keywords

• wind energy; induction generator; rotor speed estimation; MRAS algorithm; artificial intelligence

References

1. IM using MRAS observer with ANN for given set of parameters. Proposed technique obviously leads the estimated signal to a finite steady state response, but the noise and oscillations make this signal unacceptable. As proposed by the theoretical discussion, to lessen the adverse effect learning coefficient should be η << 1. By manual tuning of the parameter, optimal learning coefficient is found to be η = 0.00009, while keeping the momentum term at the same value. Increment of the adjustable weight coefficient
2. A. Belhamadia, M. Mansor, M. A. Younis, “A Study on Wind and Solar Energy Potentials in Malaysia”, International Journal of Renewable Energy Research – IJRER, Vol.4, No.4, pp. 1042-1048, 2014.
3. N. S. Patil, Y. N. Bhosle, “A Review On Wind Turbine Generator Topologies”, International Conference on Power, Energy and Control (ICPEC) , pp.625-629, 6-8 Feb. 2013. doi: 10.1109/ICPEC.2013.6527733
4. A. G. Aissaoui, A. Tahour, M. Abid, N. Essounbouli, F. Nollet, M. I. Chergu, “Variable Structure Control Applied in Wind Turbine Based on Induction Generator”, International Journal of Renewable Energy Research – IJRER, Vol.2, No.4, pp. 600-607, 2012.
5. B. Wu, Y. Lang, N. Zagari, S. Kouro, Power Conversion and Control of Wind Energy Systems, John Wiley and Sons, IEEE Press, USA, 2011, ch. 5, ch. 7.
6. R. Teodorescu, M. Liserre, P. Rodriguez Grid Converters for Photovoltaic and Wind Power Systems, John Wiley and Sons, IEEE Press, USA, 2011, ch. 6.
7. J. B. Alaya, A. Khedher, M. F. Mimouni, “Speed- Sensorless DFIG Wind Drive Based on DTC Using Sliding Mode Rotor Flux Observer”, International Journal of Renewable Energy Research –IJRER, Vol.2, No.4, pp. 736-745, 2012.
8. P. Vas, Sensorless Vector and Direct Torque Control, Oxford Univ. Press, NY, 1998, ch. 4.

9. M. Hinkkanen, J. Luomi, “Parameter sensitivity of full- order flux observers for induction motors”, IEEE Transactions on Industry Applications, vol.39, no.4, pp.1127-1135, July-Aug. 2003.
10. J.A. Santisteban, R.M. Stephan, “Vector control methods for induction machines: an overview”, IEEE Transactions on Education, vol.44, no.2, pp.170-175, May 2001.
11. F. Blaabjerg F. Iov, T. Kerekes, R. Teodorescu, “Trends in Power Electronics and Control of Renewable Energy Systems”, 14th International Conference of Power Electronics and Motion Control, K1-K19, EPE- PEMC 2010.
12. M. Wang, E. Levi, “Evaluation of Steady-State and Transient Behavior of a MRAS Based Sensorless Rotor Flux Oriented Induction Machine in the Presence of Parameter Detuning“, Electric Machines and Power Systems, Vol. 27, no. 11, pp. 1171 – 1190, 1999.
13. B. Dumnic, V. Katic, V. Vasic, D. Milicevic, M. Delimar, “An Improved MRAS Based Sensorless Vector Control Method for Wind Power Generator” Journal of Applied Research and Technology – JART, Vol. 10. no. 5, pp. 687-697, October 2012.
14. P. Vas, Artificial-Intelligence-based Electrical Machines and Drives: Application of Fuzzy, Neural, Fuzzy-neural, and Genetic-algorithm-based Techniques, Oxford University Press, 1999, ch. 5.
15. B. Yegnanarayana, Artificial Neural Network s, Prentice-Hall of India, New Delhi, 2005, ch. 1.
16. J. M. Zaruda, Introduction to Artificial Neural Systems, Jaico Publishing House, 2005, ch. 4.
17. B. Dumnic, D. Milicevic, B. Popadic, V. Katic, Z. Corba, “Advanced laboratory setup for control of electrical drives as an educational and developmental tool“, EUROCON, pp. 903-909, Zagreb, Croatia, July dSpace manual, Modular Systems – Hardware Installation and Configuration Reference, dSpace gmbh, F. Iov, A. D. Hansen, P. Sorensen, F. Blaabjerg “Wind Turbine Blockset in Matlab/Simulink,” UNI. PRINT Aalborg University, March 2004.