Adaptive neural output regulation control of a solar power plant

Abstract This work proposes an indirect adaptive nonlinear control scheme based on a recurrent neural network and the output regulation theory. The neural model is first trained off-line, being further improved by means of an on-line learning strategy using the Lyapunov and nonlinear observation theories. The regulation problem is solved by an iterative strategy, formulated as an eigenvalue assignment problem, ensuring the convergence of the regulation equations. The strategy was tested on a distributed collector field of a solar power plant (Plataforma Solar de Almeria, Spain). Experimental results, collected on the solar power plant, show the effectiveness of the proposed approach.

[1]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[2]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .

[3]  Jose C. Principe,et al.  Neural and adaptive systems : fundamentals through simulations , 2000 .

[4]  Manuel Berenguel,et al.  Neural identification applied to predictive control of a solar plant , 1998 .

[5]  B. Castillo,et al.  Asymptotic output tracking for SISO nonlinear discrete systems , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.

[6]  J. Henriques,et al.  Adaptive neural model-based predictive control of a solar power plant , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[7]  Wei Wang,et al.  Modeling Dynamic System by Recurrent Neural Network with State Variables , 2004, ISNN.

[8]  F. Thau.  Observing the state of non-linear dynamic systems† , 1973 .

[9]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[10]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[11]  Soteris A. Kalogirou,et al.  Artificial Intelligence in Energy And Renewable Energy Systems , 2006 .

[12]  Alberto Cardoso,et al.  Supervision and c-Means clustering of PID controllers for a solar power plant , 1999, Int. J. Approx. Reason..

[13]  Donald C. Wunsch,et al.  Advanced architecture and training algorithms for recurrent neural networks , 2006 .

[14]  Ali Saberi,et al.  On output regulation for linear systems , 2001 .

[15]  Jie Huang,et al.  Neural-Network-Based Approximate Output Regulation of Discrete-Time Nonlinear Systems , 2007, IEEE Transactions on Neural Networks.

[16]  Suwat Pattamavorakun,et al.  A Comparison of Selected Training Algorithms for Recurrent Neural Networks , 2006, PRICAI.

[17]  En Sup Yoon.  The 5th International Symposium on Process Systems Engineering : proceedings of the PSE '94, Kyongju, Korea, 30 May-3 June, 1994 , 1994 .

[18]  Anita C. Faul,et al.  Non-linear systems , 2006 .

[19]  Aldo Cipriano,et al.  Fuzzy predictive control of a solar power plant , 2005, IEEE Transactions on Fuzzy Systems.

[20]  R. Pickhardt,et al.  Application of a nonlinear predictive controller to a solar power plant , 1998, Proceedings of the 1998 IEEE International Conference on Control Applications (Cat. No.98CH36104).

[21]  Eduardo F. Camacho,et al.  Self-Tuning PI Control of a Solar Power Plant , 1990 .

[22]  D. Normand-Cyrot,et al.  Minimum-phase nonlinear discrete-time systems and feedback stabilization , 1987, 26th IEEE Conference on Decision and Control.

[23]  Wilson J. Rugh,et al.  On output regulation for discrete-time nonlinear systems , 1997, Autom..

[24]  S. Monaco,et al.  Nonlinear regulation for a class of discrete-time systems , 1993 .

[25]  Edoardo Mosca,et al.  Adaptive control of a solar energy plant : Exploiting accessible disturbances , 1997 .

[26]  E.F. Camacho,et al.  Self-tuning control of a solar power plant with a distributed collector field , 1992, IEEE Control Systems.

[27]  Tariq Samad,et al.  Intelligent optimal control with dynamic neural networks , 2003, Neural Networks.

[28]  W. Rugh,et al.  Stabilization on zero-error manifolds and the nonlinear servomechanism problem , 1992 .

[29]  Manuel Berenguel,et al.  Advanced control of solar plants , 1997 .

[30]  A. L. Cardoso,et al.  Fuzzy supervisor and feedforward control of a solar power plant using accessible disturbances , 1999, 1999 European Control Conference (ECC).

[31]  Manuel Berenguel,et al.  A survey on control schemes for distributed solar collector fields. Part I: Modeling and basic control approaches , 2007 .

[32]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[33]  Riyanto T. Bambang,et al.  Nonlinear active noise control using EKF-based recurrent fuzzy neural networks , 2007, Int. J. Hybrid Intell. Syst..

[34]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[35]  D. Luenberger.  An introduction to observers , 1971 .

[36]  Eduardo F. Camacho,et al.  CONTROL DE CAMPOS DE COLECTORES SOLARES , 2006 .

[37]  Madan M. Gupta,et al.  Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory , 2003 .

[38]  F. Mazenc.  Differentiable lyapunov function and center manifold theory , 2001 .

[39]  Mahdi Jalili-Kharaajoo.  Predictive Control of a Solar Power Plant with Neuro-Fuzzy Identification and Evolutionary Programming Optimization , 2004 .

[40]  W. Rugh,et al.  An approximation method for the nonlinear servomechanism problem , 1992 .

[41]  Manuel Berenguel,et al.  A survey on control schemes for distributed solar collector fields. Part II: Advanced control approaches , 2007 .

[42]  Kumpati S. Narendra,et al.  Gradient methods for the optimization of dynamical systems containing neural networks , 1991, IEEE Trans. Neural Networks.

[43]  Wilson J. Rugh,et al.  Output regulation with derivative information , 1995, IEEE Trans. Autom. Control..

[44]  B. Castillo,et al.  Output regulation of non-linear systems with more inputs than outputs , 1993 .

[45]  Jun Wang,et al.  Recurrent neural networks for nonlinear output regulation , 2001, Autom..

[46]  Robin De Keyser,et al.  APPLICATION of a SMITH PREDICTOR based NONLINEAR PREDICTIVE CONTROLLER to a SOLAR POWER PLANT , 2007 .