JJAP Conf. Proc. 4, 011612 (2016) doi:10.7567/JJAPCP.4.011612
Intelligent neural network design for nonlinear control using simultaneous perturbation stochastic approximation (SPSA) optimization
- 1Doctoral School of Applied Informatics and Applied Mathematics, Óbuda University, Budapest, Hungary
- 2Doctoral School of Computer Science, Universita’ degli Studi di Milano, Crema, Italy
- 3Institute of Mechatronics & Vehicle Engineering, Óbuda University, Budapest Hungary
- 4Department of Mathematics and Informatics, J. Selye University, Komarno, Slovakia
- 5Institute of Applied Mathematics, Óbuda University, Budapest, Hungary
- 6Department of Computer Science, Universita’ degli Studi di Milano, Crema, Italy
- Received September 27, 2015
- PDF (805 KB) |
Recently intelligent control systems using neural networks (NN) have been widely applied. NNs are used to approximate complicated mathematical functions of nonlinear systems. This paper considers the design of an intelligent NN controller for nonlinear systems where the neural network is trained with the simultaneous perturbation stochastic approximation (SPSA) algorithm instead of the classical training methods. The main contribution of the SPSA method that it requires only two objective function measurements per iteration regardless of the dimension of the optimization problem. The effectiveness of the proposed scheme is demonstrated by the adaptive control of the translational oscillator/rotational actuator (TORA) system. Results of numerical simulation substantiate that the suggested approach leads to a fast way of controller designs by providing acceptable performance.
Content from this work may be used under the terms of the Creative Commons Attribution 4.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
- 1 J. C. Spall and J. A. Cristion, Stat. Sin. 4, 1 (1994).
- 2 I. Nagy, Acta Polytechnica Hungarica 11, 39 (2014).
- 3 A. Vande Wouwer, C. Renotte, and M. Remy, Proc. of the Am. Contr. Conf., 1999, p. 388.
- 4 M. Ahmad, S. Azuma, and T. Sugie, Expert Syst. Appl. 41, 6361 (2014).
- 5 H. Patino, R. Carelli, and B. R. Kuchen, IEEE Trans. Neural Networks 13, 343 (2002).
- 6 Q. Song, J. C. Spall, Y. C. Soh, and J. Ni, IEEE Trans. Neural Networks 19, 817 (2008).
- 7 R. T. Bupp, D. S. Bernstein, and V. T. Copola, Int. J. Robust Nonlinear Control 8, 307 (1998).
- 8 A. Astolfi, D. Karagiannis, and R. Ortega, Nonlinear and Adaptive Control with Applications, Communications and Control Engineering (Springer, London, 2008) 1st ed.
- 9 J. F. Chen and A. C. Huang, IET Control Theory Appl. 6, 103 (2012).
- 10 A. Kulkarni and A. Kumar, Procedia Eng. 38, 1001 (2012).
- 11 A. Dineva, J. K. Tar, A. R. Várkonyi-Kóczy, and V. Piuri, IEEE 19th Int. Conf. Intelligent Engineering Systems (INES 2015), 2015, Bratislava, Slovakia, p. 135.
- 12 J. K. Tar, J. F. Bitó, and I. J. Rudas, 14th IEEE Int. Conf. Intelligent Engineering Systems 2010, Las Palmas of Gran Canaria, Spain, 2010, p. 231.
- 13 J. K. Tar, Proc. of the 2010 Mathematical Methods in Engineering International Symposium (MME 2010), 2010, Coimbra, Portugal.
- 14 J. K. Tar, J. F. Bitó, L. Nádai, and J. A. Tenreiro Machado, Robust Fixed Point Transformations in Adaptive Control using Local Basin of Attraction (Acta Polytechnica, Hungarica, 2009) Vol. 6, p. 21.