Abstract
Choice of the architecture of the neural network makes it possible to find its optimal structure for the control of nonlinear multi-input multi-output (MIMO) systems using the linearization feedback.Genetic algorithm is proposed as the optimization method for finding the appropriate structure. The controller is based on the parameters of the obtained neural network. The error based criterion is applied as evaluation function for model identification procedure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bastian, A., Gasós, J.: A type i structure identification approach using feedforward neural networks. In: IEEE World Congress on Computational Intelligence: ICNN, Orlando, FL, USA, June 27 - July 02, pp. 3256–3260 (1994)
Helmicki, A.J., Jacobson, C.A., Nett, C.N.: Fundamentals of control-oriented system identification and their application for identification in h  ∞ . In: American Control Conference, Boston, MA, USA, pp. 89–99 (June 1991)
González-Olvera, M.A., Tang, Y.: Black-box identification of a class of nonlinear systems by a recurrent neurofuzzy network. IEEE Transactions on Neural Networks 21(4), 672–679 (2010)
Feil, B., Abonyi, J., Szeifert, F.: Determining the model order of nonlinear input-output systems by fuzzy clustering. In: Benitez, J.M., Cordon, O., Hoffmann, F., Roy, R. (eds.) Advances in Soft Computing, Engineering Design and Manufacturing, pp. 89–98. Springer, Heidelberg (2003)
Vassiljeva, K., Petlenkov, E., Belikov, J.: State-space control of nonlinear systems identified by anarx and neural network based sanarx models. In: WCCI 2010 IEEE World Congress on Computational Intelligence: IJCNN, Barcelona, Spain, pp. 3816–3823 (July 2010)
Vassiljeva, K., Petlenkov, E., Belikov, J.: Neural network based minimal state-space representation of nonlinear mimo systems for feedback control. In: 2010 the 11th International Conference on Control Automation, Robotics and Vision, Singapore, December 7-10, pp. 2191–2196 (2010)
Petlenkov, E., Nõmm, S., Kotta, Ü.: Nn-based anarx structure for identification and model-based control. In: The 9th International Conference on Control Automation Robotics and Vision, Singapore, pp. 2284–2288 (December 2006)
Petlenkov, E.: Nn-anarx structure based dynamic output feedback linearization for control of nonlinear mimo systems. In: The 15th Mediterranean Conference on Control and Automation, Athens, Greece, pp. 1–6 (June 2007)
Stanley, K., Miikkulainen, R.: Efficient reinforcement learning through evolving neural network topologies. In: Genetic and Evolutionary Computation Conference, San Francisco, CA, USA, pp. 569–577 (2002)
Stanley, K., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)
Grefenstette, J.J.: Optimization of control parameters for genetic algorithms. IEEE Transactions on Systems, Man and Cybernetics 16(1), 122–128 (1986)
Whitley, D.: Genetic algorithms and neural networks. In: Winter, G., Periaux, J., Galan, M., Cuesta, P. (eds.) Genetic Algorithms in Engineering and Computer Science, pp. 191–201. John Wiley, New York (1995)
Son, J.S., Lee, D.M., Kim, I.S., Choi, S.K.: A study on genetic algorithm to select architecture of a optimal neural network in the hot rolling process. Journal of Materials Processing Technology 153-154, 643–648 (2004)
Pothin, R., Kotta, Ü., Moog, C.: Output feedback linearization of nonlinear discrete-time systems. In: Proc. of the IFAC Conf. on Control System Design, Bratislava, pp. 174–179 (2000)
Kotta, Ü., Nõmm, S., Chowdhury, F.: On a new type of neural network-based input-output model: The anarma structure. In: The 5th IFAC Symposium on Nonlinear Control Systems NOLCOS, St. Petersbourg, Russia, pp. 1535–1538 (July 2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vassiljeva, K., Belikov, J., Petlenkov, E. (2011). Genetic Algorithm Based Structure Identification for Feedback Control of Nonlinear MIMO Systems. In: Bouchachia, A. (eds) Adaptive and Intelligent Systems. ICAIS 2011. Lecture Notes in Computer Science(), vol 6943. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23857-4_23
Download citation
DOI: https://doi.org/10.1007/978-3-642-23857-4_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23856-7
Online ISBN: 978-3-642-23857-4
eBook Packages: Computer ScienceComputer Science (R0)