Skip to main content
SpringerLink
Log in

Wavelet Neural Network Model Reference Adaptive Control Trained by a Modified Artificial Immune Algorithm to Control Nonlinear Systems

  • Research Article - Electrical Engineering
  • Published:
Arabian Journal for Science and Engineering Aims and scope Submit manuscript

Abstract

This paper presents a wavelet neural network (WNN)-based model reference adaptive control (WNNMRAC) scheme to control arbitrary complex nonlinear systems. As the training method for the WNN, a newly developed optimization technique, called the micro artificial immune system (Micro-AIS), is employed to find the optimal values for the WNN parameters. Two modifications were suggested to enhance the performance of the original Micro-AIS, resulting in a more powerful optimization algorithm. Utilizing the proposed control approach, it is not necessary to construct a pseudo-plant, which was a prerequisite in other works, for controlling the nonlinear systems. To demonstrate the effectiveness of the proposed direct WNNMRAC, three single-input single-output complex nonlinear systems are selected, including a non-minimum phase system, a time-delay system, and a minimum phase system. From several performance evaluation tests, the WNNMRAC has shown its effectiveness in terms of accurate control performance, applicability to different types of nonlinear systems, robustness to external disturbances, and good generalization ability. In addition, a simulation test to control nonlinear multi-input multi-output (MIMO) system has shown that the WNNMRAC can be extended to control nonlinear MIMO systems. Finally, from a comparative study, the WNNMRAC has confirmed its superiority over a conventional neural network model reference adaptive control.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Li S., Li J., Qiu J., Ji H., Zhu K.: Control design for arbitrary complex nonlinear discrete-time systems based on direct NNMRAC strategy. J. Process Control. 21(1), 103–110 (2011)

    Article  Google Scholar 

  2. Kadri M.B.: System identification of a cooling coil using recurrent neural networks. Arab. J. Sci. Eng. 37(8), 2193–2203 (2012)

    Article  Google Scholar 

  3. Yazdi M.R.S., Bagheri G.S., Tahmasebi M.: Finite volume analysis and neural network modeling of wear during hot forging of a steel splined hub. Arab. J. Sci. Eng. 37(3), 821–829 (2012)

    Article  Google Scholar 

  4. Aydin S., Kilic I., Temeltas H.: Using linde buzo gray clustering neural networks for solving the motion equations of a mobile robot. Arab. J. Sci. Eng. 36(5), 795–807 (2011)

    Article  Google Scholar 

  5. Ahmed M.S.: Neural-net-based direct adaptive control for a class of nonlinear plants. IEEE Trans. Autom. Control. 45(1), 119–124 (2000)

    Article  MATH  Google Scholar 

  6. Chen C.-H.: Intelligent transportation control system design using wavelet neural network and PID-type learning algorithms. Expert Syst. Appl. 38(6), 6926–6939 (2011)

    Article  Google Scholar 

  7. Huang A.-C.: Model reference adaptive control of a class of non-autonomous systems using serial input neuron. Neurocomputing. 51, 413–423 (2003)

    Article  Google Scholar 

  8. Ahmed M.S.: Neural net based MRAC for a class of nonlinear plants. Neural Netw. 13(1), 111–124 (2000)

    Article  Google Scholar 

  9. Kamalasadan S., Ghandakly A.A.: A Neural network parallel adaptive controller for dynamic system control. IEEE Trans. Instrum. Meas. 56(5), 1786–1796 (2007)

    Article  Google Scholar 

  10. Kumar M.V., Suresh S., Omkar S.N., Ganguli R., Sampath P.: A direct adaptive neural command controller design for an unstable helicopter. Eng. Appl. Artif. Intell. 22(2), 181–191 (2009)

    Article  Google Scholar 

  11. Cirrincione M., Pucci M.: Sensorless direct torque control of an induction motor by a TLS-based MRAS observer with adaptive integration. Automatica. 41(11), 1843–1854 (2005)

    Article  MATH  MathSciNet  Google Scholar 

  12. Farahani, M.: Intelligent control of SVC using wavelet neural network to enhance transient stability. Eng. Appl. Artif. Intel. In Press (2012)

  13. Wei S., Wang Y., Zuo Y.: Wavelet neural networks robust control of farm transmission line deicing robot manipulators. Comput. Stand. Interface. 34(3), 327–333 (2012)

    Article  Google Scholar 

  14. Wai R.-J., Chang H.H.: Backstepping wavelet neural network control for indirect field-oriented induction motor drive. IEEE Trans. Neural Netw. 15(2), 367–382 (2004)

    Article  Google Scholar 

  15. Wai R.-J., Duan R.-Y., Lee J.-D., Chang H.-H.: Wavelet neural network control for induction motor drive using sliding-mode design technique. IEEE Trans. Ind. Electron. 50(4), 733–748 (2003)

    Article  Google Scholar 

  16. Hsu C.-F.: Adaptive fuzzy wavelet neural controller design for chaos synchronization. Expert Syst. Appl. 38(8), 10475–10483 (2011)

    Article  Google Scholar 

  17. Sun T., Pei H., Pan Y., Zhang C.: Robust wavelet network control for a class of autonomous vehicles to track environmental contour line. Neurocomputing. 74(17), 2886–2892 (2011)

    Article  Google Scholar 

  18. Hsu C.-F., Cheng K.H., Lee T.T.: Robust wavelet-based adaptive neural controller design with a fuzzy compensator. Neurocomputing. 73(1–3), 423–431 (2009)

    Article  Google Scholar 

  19. Yoo S.J., Park J.B., Choi Y.H.: Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates. Inf. Sci. 177(15), 3074–3098 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  20. Li M., Liu D.: A novel adaptive self-turned PID controller based on recurrent-wavelet-neural-network for PMSM speed servo drive system. Procedia Eng. 15, 282–287 (2011)

    Article  Google Scholar 

  21. Kuo R.J., Tseng W.L., Tien F.C., Liao T.W.: Application of an artificial immune system-based fuzzy neural network to a RFID-based positioning system. Comput. Ind. Eng. 63(4), 943–956 (2012)

    Article  Google Scholar 

  22. Prakash A., Deshmukh S.G.: A multi-criteria customer allocation problem in supply chain environment: an artificial immune system with fuzzy logic controller based approach. Expert Syst. Appl. 38(4), 3199–3208 (2011)

    Article  Google Scholar 

  23. Li Z., Zhang Y., Tan H.-Z.: IA-AIS: An improved adaptive artificial immune system applied to complex optimization problems. Appl. Soft Comput. 11(8), 4692–4700 (2011)

    Article  Google Scholar 

  24. Herrera-Lozada J.C., Calvo H., Taud H.: A Micro artificial immune system. Polibits. 43, 107–111 (2011)

    Google Scholar 

  25. Ham F.M., Kostanic I.: Principles of neurocomputing for science and engineering. McGraw Hill, New York (2001)

    Google Scholar 

  26. Noriega J.R., Wang H.: A direct adaptive neural-network control for unknown nonlinear systems and its application. IEEE Trans. Neural Netw. 9(1), 27–34 (1998)

    Article  Google Scholar 

  27. Gao F., Wang F., Li M.: Predictive control for processes with input dynamic nonlinearity. Chem. Eng. Sci. 55(19), 4045–4052 (2000)

    Article  Google Scholar 

  28. Abiyev R.H.: Fuzzy wavelet neural network for control of dynamic plants. Int. J. Inf. Math. Sci. 1(2), 139–143 (2005)

    Google Scholar 

  29. Kim J.M., Park J.B., Choi Y.H.: Wavelet neural network controller for AQM in a TCP network: adaptive learning rates approach. Int. J. Control Autom. Syst. 6(4), 526–533 (2008)

    Google Scholar 

  30. Oussar Y., Rivals I., Personnaz L., Dreyfus G.: Training wavelet networks for nonlinear dynamic input–output modeling. Neurocomputing. 20(1–3), 173–188 (1998)

    Article  MATH  Google Scholar 

  31. Leung K., Cheong F., Cheong C.: Generating compact classifier systems using a simple artificial immune system. IEEE Trans. Syst. Man Cybern. B. 37(5), 1344–1356 (2007)

    Article  Google Scholar 

  32. Yildiz A.R.: A novel hybrid immune algorithm for global optimization in design and manufacturing. Robot Comput. Integr. Manuf. 25(2), 261–270 (2009)

    Article  Google Scholar 

  33. Zhang Q., Benveniste A.: Wavelet networks. IEEE Trans. Neural Netw. 3(6), 889–898 (1992)

    Article  Google Scholar 

  34. Narendra K.S., Parthasarathy K.: Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Netw. 1(1), 4–27 (1990)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Control and Systems Engineering Department, University of Technology, Baghdad, Iraq

    Omar Farouq Lutfy

Authors
  1. Omar Farouq Lutfy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Omar Farouq Lutfy.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lutfy, O.F. Wavelet Neural Network Model Reference Adaptive Control Trained by a Modified Artificial Immune Algorithm to Control Nonlinear Systems. Arab J Sci Eng 39, 4737–4751 (2014). https://doi.org/10.1007/s13369-014-1088-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13369-014-1088-5

Keywords

Search

Navigation