A NEW APPROACH OF THE NEURAL PREDICTIVE CONTROL APPLIED IN A THERMOELECTRIC MODULE

Adhemar de Barros Fontes, Pablo Amorim, Márcio Ribeiro da Silva Garcia

Abstract

This article presents an efficient solution for predictive control based on neural networks with feedfoward multilayer, as a model for a thermoelectric module. It is shown the capability of a neural network to learn the entire nonlinear dynamics and the advantage of using these nonlinear models for the calculation of the predicted variables. It is also suggested a new control law capable of minimize the cost function using the Newton-Raphson and the descendent gradient optimization rules. For this application it is shown that a significant reduction in the number of iterations and application in real-time systems when compared to other optimization techniques.

References

  1. (1999). Theromeletric coolers and accessories. Corporation, first edition.
  2. Almeida, L. A. L. (2003). Modelo de Histerese para Transica˜o Semicondutor-Metal em Filmes Finos de VO2. PhD thesis, Universidade Federal de Campina Grande.
  3. Almeida, L. A. L. (2004). Modelo dinmico na˜o-linear para módulo termoelétrico. In XV Congresso Brasileiro de Automtica.
  4. Camacho, E. F. and Bordons, C. (2004). Model predictive control. Springer-Verlag Limited.
  5. Clarke, D. W. (1994). Advanced in model-based predictive control. Oxford Univesity Press.
  6. Fontana, M. (2001). Caracterizaca˜o e modelagem das propriedades ópticas de sensores de dióxido de vanádio. Master's thesis, Universidade Federal de Campina Grande.
  7. Fontes, A. B., Dorea, C. E. T., and Garcia, M. R. S. (2008). An iterative algorithm for constrained mpc with stability of bilinear systems. In 16th Mediterranean Conference on Control and Automation, pages 1526-1531.
  8. Garcia, M. R. S. (2008). Controle preditivo por realimentaca˜o de estado de sistemas bilineares sob restrico˜es aplicado a um módulo termoelétrico. Master's thesis, Universidade Federal da Bahia.
  9. Goodhart, S. G., Burnham, K. J., and James, D. J. G. (1994). Bilinear self-tuning control of a high temperature heat treatment plant. IEE Proc.-Control Theory Appl., 141(1):12-18.
  10. Hagan, M. T. and Menhaj, M. (1994). Trainning feedforward networks with the marquadt algorithm. IEEE Transactions on Neural Networks, 5(6):989-993.
  11. Hao, J., Tan, S., and Vandewalle, J. (1993). One step ahead predictive control of nonlinear systems by neural networks. In Proceedings of 1993 International Joint Conference on Neural Networks.
  12. Lee, J. H. and Ricker, N. L. (1994). Extended kalman filter based nonlinear model predictive control. Ind. Eng. Chem. Res., 33(6):1530-1541.
  13. Li, W. C. and Biegler, L. T. (1988). Process control strategies for constrained nonlinear systems. Ind. Eng. Chem. Res., (27):1421-1433.
  14. Lima, J. S. (2007). Técnicas de controle preditivo bilinear aplicado a um módulo termoelétrico. Master's thesis, Universidade Federal da Bahia.
  15. Propoi, A. I. (1963). Use of lp methods for synthesizing sampled-data automatic systems. Automn Remote Control, 24.
  16. Santana, M. J. C. (2008). Controle preditivo multimodelo aplicado a um módulo termoelétrico: Uma nova métrica. Master's thesis, Universidade Federal da Bahia.
  17. Sobrinho, M. O. S. L., Lima, J. S., Souza, V. O. S. T., Fontes, A. B., and Almeida, L. A. L. (2006). Caracterizaca˜o de um módulo termoelétrico por modelo paramétrico bilinear. Congresso Brasileiro de Automtica.
  18. Soloway, D. and Halcy, P. J. (1996). Neural generalized predictive control, a newton-raphason implementation. In Symposium on Intelligent Control.
  19. Zamarreo, J. M. and Vega, P. (1999). Neural predictive control. application to a highly non-linear system. Engineering Applications of Artificial IntelligenceJapan, (12):149-158.
Download


Paper Citation


in Harvard Style

de Barros Fontes A., Amorim P. and Ribeiro da Silva Garcia M. (2009). A NEW APPROACH OF THE NEURAL PREDICTIVE CONTROL APPLIED IN A THERMOELECTRIC MODULE . In Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 978-989-8111-99-9, pages 189-194. DOI: 10.5220/0002193001890194


in Bibtex Style

@conference{icinco09,
author={Adhemar de Barros Fontes and Pablo Amorim and Márcio Ribeiro da Silva Garcia},
title={A NEW APPROACH OF THE NEURAL PREDICTIVE CONTROL APPLIED IN A THERMOELECTRIC MODULE},
booktitle={Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2009},
pages={189-194},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002193001890194},
isbn={978-989-8111-99-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - A NEW APPROACH OF THE NEURAL PREDICTIVE CONTROL APPLIED IN A THERMOELECTRIC MODULE
SN - 978-989-8111-99-9
AU - de Barros Fontes A.
AU - Amorim P.
AU - Ribeiro da Silva Garcia M.
PY - 2009
SP - 189
EP - 194
DO - 10.5220/0002193001890194