Artificial Intelligence control applied in wind energy conversion system

This work presents a field oriented control (FOC) of active and reactive power applied on Doubly Fed Induction Machine (DFIM) integrated in wind energy conversion system (WECS). The main objective of this work is to compare the performances of energy produced by the use of two types of controllers ( PI regulator and the neural network regulator (NN)) in order to control the wind power conversion system to compare their precision & robustness against the wind fluctuation and the impact on the quality of produced energy .A field oriented control of DEFIG stator is also presented to control the active and reactive power. To show the efficiency of the performances and the robustness of the two control methods those were analyzed and compared by simulation using Matlab/Simulink software. The results described the favoured method.

[1]  Hicham Chaoui,et al.  Comparative Study of PI, RST, Sliding Mode and Fuzzy Supervisory Controllers for DFIG based Wind Energy Conversion System , 2015 .

[2]  Yonghua Song,et al.  Application of fuzzy logic in power systems. II. Comparison and integration with expert systems, neural networks and genetic algorithms , 1998 .

[3]  Swati A. Barbade.  Neural network based control of Doubly Fed Induction Generator in wind power generation. , 2012 .

[4]  David J. Atkinson,et al.  Stator-flux-oriented control of a doubly-fed induction machine with and without position encoder , 2000 .

[5]  F. Poitiers,et al.  Dynamic performances of a doubly-fed induction machine for a variable-speed wind energy generation , 2002, Proceedings. International Conference on Power System Technology.

[6]  Tayeb Allaoui,et al.  Hybrid Fuzzy Sliding Mode Control of a DFIG Integrated into the Network , 2013 .

[7]  J.J. Brey,et al.  Integration of renewable energy sources as an optimised solution for distributed generation , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[8]  G. Tapia,et al.  Modeling and control of a wind turbine driven doubly fed induction generator , 2003 .

[9]  Mamadou Lamine Doumbia,et al.  Direct active and reactive power control of DFIG based WECS using PI and sliding mode controllers , 2014, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society.

[10]  Messaoud Hamouda,et al.  Impedance model for diagnosis of water management in fuel cells using artificial neural networks methodology , 2016 .

[11]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[12]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[13]  K. Viswanadha S Murthy,et al.  A performance comparison of DFIG using power transfer matrix and direct power control techniques , 2014 .

[14]  Lennart Söder,et al.  An overview of wind energy-status 2002 , 2002 .

[15]  F. Poitiers,et al.  Advanced control of a doubly-fed induction generator for wind energy conversion , 2009 .

[16]  Kevin Warwick,et al.  Artificial intelligence techniques in power systems , 1997 .

[17]  F.-C. Chen,et al.  Back-propagation neural networks for nonlinear self-tuning adaptive control , 1990, IEEE Control Systems Magazine.