Proceedings of the International Conference on Information Systems Design and Intelligent Applications 2012 (INDIA 2012) held in Visakhapatnam, India, January 2012 pp 273-280 | Cite as
Intelligent Chaos Controller
Abstract
Recent developments have shown the possibility of constructing Bifurcation Diagrams for real-world chaotic system based on observed data. In the present work we demonstrate how the control can be achieved on the data-driven process/system based on the bifurcation diagram construction capability. In reality many physical and non-physical systems are very difficult to represent using a mathematical form; even if mathematical models exist, it would be a difficult task to build a controller which works in real-time. Moreover, if the considered system is chaotic in nature there are very few methods for are available controlling. On contrary there are large number of Chaos Control techniques when the considered system is/has a mathematical model. Based on the fundamental idea of these techniques, i.e. small perturbation at appropriate time is enough to control such a chaotic systems, the present method uses the global search capability of genetic algorithms to find a best perturbation to the control parameter at each step with a RNN model of the considered system as an objective function.
Keywords
Chaotic System Bifurcation Diagram Model Predictive Control Recurrent Neural Network Chaotic RegionPreview
Unable to display preview. Download preview PDF.
References
- 1.Fradkov, A.L., Evans, R.J.: Control of chaos: Survey 1997-2000. In: Preprints of 15th IFAC World Congress on Automatic Control. Plenary papers, Survey papers, Milestones, Barcelona, pp. 143–154 (July 2002)Google Scholar
- 2.Almeida, L.: Backpropagation in perceptrons with feedback. In: Eckmiller, R., der Malsburg, V. (eds.) Neural Computers, pp. 199–208. Springer, New York (1988)Google Scholar
- 3.Bengio, Y., Gingras, F.: Recurrent neural networks for missing or asynchronous data. In: Neural Information Proceesing Systems. MIT Press (1996)Google Scholar
- 4.Horne, B.G., Giles, C.: An experimental comparison of recurrent neural networks. In: Advances in Neural Information Processing Systems, p. 697. MIT Press (1995)Google Scholar
- 5.Boccaletti, S., Grebogi, C., Lai, Y.C., Mancini, H., Maza, D.: The control of chaos: Theory and applications. Physics Reports 329(3), 103–197 (2000)CrossRefMathSciNetGoogle Scholar
- 6.Andrievskii, B.R., Fradkov, A.L.: Control of chaos: Methods and applications. 2.applications. Automation and Remote Control 65(4), 505–533 (2003)CrossRefMathSciNetGoogle Scholar
- 7.Hilborn, R.C.: Chaos and Nonlinear Dynamics: An Introduction for Scientists and Engineers, 2nd edn. Oxford University Press, New York (2000)MATHGoogle Scholar
- 8.Christini, D.J., Collins, J.J.: Controlling neuronal chaos using chaos control, http://arxiv.org/abs/chao-dyn/9503003
- 9.Dattani, J., Blake, J.C., Hilker, F.M.: Target-oriented chaos control. Physics Letters A 375(45), 3986–3992 (2011), http://www.sciencedirect.com/science/article/pii/S0375960111011194 CrossRefGoogle Scholar
- 10.De Feo, O.: Self-emergence of chaos in the identification of irregular periodic behaviour. CHAOS 13(4), 1205–1215 (2003)CrossRefMATHMathSciNetGoogle Scholar
- 11.Doya, K.: Bifurcations in the learning of recurrent neural networks. In: Proc. IEEE Int. Symp. Circuits and Systems, pp. 2777–2780. IEEE (1992)Google Scholar
- 12.Elman, J.: Finding structure in time. Cognitive Science 6(2), 285–324 (1990)Google Scholar
- 13.Jones, A.J., Tsui, A., Oliveira, A.G.: Neural models of arbitrary chaotic systems: construction and the role of time delayed feedback in control and synchronization. Complexity International 9 (2002)Google Scholar
- 14.Aihara, K., Takabe, T., Toyoda, M.: Chaotic neural networks. Special Issue on Recurrent Networks for Sequence Processing 144(12), 333–340 (1990)MathSciNetGoogle Scholar
- 15.Krishnaiah, J., Kumar, C., Faruqi, M.A.: Modelling and control of chaotic processes through their bifurcation diagrams generated with the help of recurrent neural networks models: Part 1 - simulation studies. Journal of Process Control 16(1), 53–66 (2006)CrossRefGoogle Scholar
- 16.Kuo, J.M., Principe, J.C., de Vries, B.: Prediction of chaotic time-series using recurrent neural networks. Submitted to IEEE Workshop NN for SP (1992)Google Scholar
- 17.Fradkov, A.L., Evans, R.J.: Control of chaos: Survey 1997-2000. Survey paper. Univ. of Melbourne, St. Petersburg (2002)Google Scholar
- 18.Nayfeh, A.H., Balachandran, B.: Applied Nonlinear Dynamics: Analytical, Computational and Experimental Methods. John Willey and Sons, New York (1995)CrossRefMATHGoogle Scholar
- 19.de Oliveira, A.G., Tsui, A.P., Jones, A.J.: Using a neural network to calculate the sensitivity vectors in synchronisation of chaotic maps. In: Proceedings 1997 International Symposium on Nonlinear Theory and its Applications (NOLTA 1997), vol. 1, pp. 46–49. Research Society of Nonlinear Theory and its Applications, IEICE, Honolulu, U.S.A (1997)Google Scholar
- 20.Ott, E., Grebogi, C., Yorke, J.A.: Controlling of chaos. Phys. Rev. Lett. 64, 1192–1196 (1990)Google Scholar
- 21.Ott, E.: Chaos in Dynamical Systems. Cambridge University Press, Maryland (1993)MATHGoogle Scholar
- 22.Panzyak, A., Yu, W., Sanchez, E.: Identification and control of unknown chaotic systesm via dynamical neural networks. IEEE Trans. on Circuits and Systems 46(12), 1491–1495 (1999)CrossRefGoogle Scholar
- 23.Pineda, F.J.: Generalization of backpropagation to recurrent neural networks. Physical Review Letters 19, 2229–2232 (1987)CrossRefMathSciNetGoogle Scholar
- 24.Tsui, A.P.M., Jones, A.J.: Periodic response to external stimulation of a chaotic neural network with delayed feedback. Int. J. of Bifurcation and Chaos 9(4), 713–722 (1999)CrossRefMATHGoogle Scholar
- 25.Po-Feng, Chu, J.Z., Jang, S.S., Shieh, S.S.: Developing a robust model predictive control architecture through regional knowledge analysis of artificial neural networks. Journal of Process Control 13, 423–435 (2002)Google Scholar
- 26.Pyragas, K.: Continuous control of chaos by self-controlling feedback. Physics Letters A 170, 421–428 (1992)CrossRefGoogle Scholar
- 27.Rohwer, R., Forrest, B.: Training time-dependence in neural networks. In: Proceedings of the First IEEE International Conference on Neural Networks, San Diego, CA, vol. 2, pp. 701–708 (1987)Google Scholar
- 28.Schenk-Hoppé, K.R.: Bifurcations of the randomly perturbed logistic map - numerical study and visualizations, http://www.iew.unizh.ch/home/klaus/logistic/intro.html
- 29.Schöll, E.: Neural control: Chaos control sets the pace. Nature Physics (2010)Google Scholar
- 30.Lin, T., Horne, B.G., Tino, P., Giles, C.: Learning long–term dependencies in narx recurrent neural networks. IEEE Trans. on Neural Networks 7(6), 1329 (1996)CrossRefGoogle Scholar
- 31.Weeks, E.R., Burgess, J.M.: Evolving artificial neural networks to control chaotic systems. Physical Review E 56(2), 1531–1540 (1997)CrossRefGoogle Scholar
- 32.Ditto, W.L., Rauseo, S.N., Spano, M.L.: Experimental control of chaos. Phys. Rev. Lett. 65(26), 3211–3214 (1990)CrossRefGoogle Scholar
- 33.Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient is difficult. IEEE Transactions on Neural Networks 5(2), 157–166 (1994)CrossRefGoogle Scholar