Real time identification and control of dynamic systems using recurrent neural networks

  • Mohammad Mehdi Korjani
  • Omid Bazzaz
  • Mohammad Bagher Menhaj
Article

Abstract

Recently, several recurrent neural networks for solving constraint optimization problems were developed. In this paper, we propose a novel approach to the use of a projection neural network for solving real time identification and control of time varying systems. In addition to low complexity and simple structure, the proposed neural network can solve wider classes of time varying systems compare with other neural networks that are used for optimization such as Hopfield neural networks. Simulation results demonstrate the effectiveness and characteristics of the proposed neural network compared with a Hopfield neural network.

Keywords

Recurrent neural network Real time identification Real time control 

References

  1. Bouzerdoum A, Pattison TR (1993) Neural network for quadratic optimization with bound constraints. IEEE Trans Neural Netw 4: 293–304CrossRefGoogle Scholar
  2. Chamseddine A, Noura H, Ouladsine M (2006) Sensor fault detection, identification and fault tolerant control: application to active suspension. In: Proceedings of the 2006 American control conference Minneapolis, Minnesota, USAGoogle Scholar
  3. Chu SR, Shoureshi R, Tenorio M (1990) Neural networks for system identification. IEEE Control Syst 10: 31–33CrossRefGoogle Scholar
  4. Ferris MC, Pang JS (1997) Engineering and economic applications of complementarity problems. Soc Ind Appl Math (SIAM) Rev 39: 669–713MATHMathSciNetGoogle Scholar
  5. Hopfield JJ, Tank DW (1985) Neural computation of decisions in optimization problems. Biol Cybern 52: 141–152MATHMathSciNetGoogle Scholar
  6. Hu X, Wang J (2006) Solving pseudomonotone variational inequalities and pseudoconvex optimization problems using the projection neural network. IEEE Trans Neural Netw 17(6): 1487–1499CrossRefGoogle Scholar
  7. Jamesand ES, Balakrishnan SN (1994) Use of Hopfield neural networks in optimal guidance. IEEE Trans Aerosp Electron Syst 30(1): 287–293CrossRefGoogle Scholar
  8. Karam M, Zohdy MA, Ferinwata SS (2001) Robust optimal control using recurrent dynamic neural network. In: Proceedings of the 2001 IEEE international symposium on intelligent control, Mexico City, Mexico, pp 331–336Google Scholar
  9. Kennedy MP, Chua LO (1988) Neural networks for nonlinear programming. IEEE Trans Circuits Syst II 35: 554–562CrossRefMathSciNetGoogle Scholar
  10. Kinderlehrer DA, Stampacchia G (1980) An introduction to variational inequalities and their applications. Academic Press, New YorkMATHGoogle Scholar
  11. Leyva R, Martinez-Salamero L, Jammes B, Marpinard JC, Guinjoan F (1997) Identification and control of power converters by means of neural networks. IEEE Trans Circuits Syst I Fundam Theory Appl 44(8): 735–742MATHCrossRefGoogle Scholar
  12. Liu Q, Wang J (2008) A one-layer recurrent neural network with a discontinuous hard-limiting activation function for quadratic programming. IEEE Trans Neural Netw 19(4): 558–570CrossRefGoogle Scholar
  13. Maa CY, Shanblatt MA (1992) Linear and quadratic programming neural network analysis. IEEE Trans Neural Netw 3: 580–594CrossRefGoogle Scholar
  14. Mestre N, Silva MP, Cardeira C, Botto MA (2007) Identification and control of an autonomous mobile robot. ROBÓTICA 2007, 7th Conference on Mobile Robots and Competitions Centro Paroquial de Paderne, Albufeira, PortugalGoogle Scholar
  15. Mingai L, Xiaogang R (2004) Dynamic tracking optimization by continuous Hopfield neural network. In: Proceedings of the 5th World congress on intelligent control and automation, Hangzhou, China, pp 2598–2602, JuneGoogle Scholar
  16. Rodríguez-Vázquez A, Domínguez-Castro R, Rueda A, Huertas JL, Sánchez-Sinencio E (1990) Nonlinear switched-capacitor ‘neural networks’ for optimization problems. IEEE Trans Circuits Syst II 37: 384–397CrossRefGoogle Scholar
  17. Shen J, Balakrishnan SN (1998) A class of modified Hopfield networks for control of linear and nonlinear systems. In: Proceedings of the American control conference, Philadelphia, Penn, USA, pp 964–969, JuneGoogle Scholar
  18. Tao Q, Cao JD, Xue MS, Qiao H (2001) A high performance neural network for solving nonlinear programming problems with hybrid constraints. Phys Lett A 288(2): 88–94MATHCrossRefMathSciNetGoogle Scholar
  19. Wang J, Wu G (1996) A multilayer recurrent neural network for on-line synthesis of minimum-norm linear feedback control systems via pole assignment. Automatica 32(3): 435–442MATHCrossRefMathSciNetGoogle Scholar
  20. Xia YS (1996) A new neural network for solving linear and quadratic programming problems. IEEE Trans Neural Netw 7: 525–529CrossRefGoogle Scholar
  21. Xia YS, Wang J (2001) A dual neural network for kinematic control of redundant robot manipulators. IEEE Trans Syst Man Cybern B 31: 147–154CrossRefGoogle Scholar
  22. Xia YS, Wang J (2004) A general projection neural network for solving monotone variational inequalities and related optimization problems. IEEE Trans Neural Netw 15: 824–852CrossRefMathSciNetGoogle Scholar
  23. Xia YS, Leung H, Wang J (2002) A projection neural network and its application to constrained optimization problems. IEEE Trans Circuits Syst II 49: 447–458CrossRefMathSciNetGoogle Scholar
  24. Xiaogang R (1997) Linear quadratic dynamic optimization with Hopfield network for discrete-time systems. In: Proceedings of the 2nd World congress on intelligent control and automation, Xian, China, pp 1880–1883Google Scholar
  25. Yoshikawa T (1990) Foundations of robotics: analysis and control. MIT Press, Cambridge, MAGoogle Scholar
  26. Zhang CQ, Moore KL (1991) System identification using neural networks. In: Proceedings Of The 30th conference on decision and control, Bringhton, England, pp 3076–3087, DecGoogle Scholar
  27. Zhang S, Zhu X, Zou L-H (1992) Second-order neural networks for constrained optimization. IEEE Trans Neural Netw 3: 1021–1024CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2009

Authors and Affiliations

  • Mohammad Mehdi Korjani
    • 1
  • Omid Bazzaz
    • 1
  • Mohammad Bagher Menhaj
    • 1
  1. 1.Amirkabir University of TechnologyTehranIran

Personalised recommendations