Home | Issues | Profile | History | Submission | Review

Vol: 50(64) No: 1 / March 2005       Inverse Control Based on Neural Networks Octavian Prostean Department of Automation and Applied Informatics, "Politehnica" University of Timisoara, Faculty of Automation and Computers, V. Parvan no 2, Timisoara, Romania, phone: (0040) 256-403237 Ioan Filip Department of Automation and Applied Informatics, "Politehnica" University of Timisoara, Faculty of Automation and Computers, V. Parvan no 2, Timisoara, Romania Cristian Vasar Department of Automation and Applied Informatics, "Politehnica" University of Timisoara, Faculty of Automation and Computers, V. Parvan no 2, Timisoara, Romania, e-mail: cristian.vasar@aut.upt.ro, web: http://www.aut.upt.ro/~cristian.vasar/ Iosif Szeidert Department of Automation and Applied Informatics, "Politehnica" University of Timisoara, Faculty of Automation and Computers, V. Parvan no 2, Timisoara, Romania Keywords: artificial neural networks, training algorithm, inverse control strategies, forward controller. Abstract This paper describes the use of Artificial Neural Networks (ANN) for the control of plants based on inverse control strategies. The neural controller is trained to model the experimental inverse model of the plant using the generalized back propagation off-line algorithm. The inverse model of the plant is obtained by the offline training mechanism that uses experimental input and output data. After the training, the neural network is used as a forward controller. To improve the control performances, the neural controller is trained further using an online specialized method. The paper presents results of the experimental tests. The neural control algorithm is implemented on the computer and the performance of controller is evaluated under a set of experimental tests made to the active control of a considered plant. References [1] D. Psaltis, A. Sideris, and A. A. Yamamure, “A multilayered neural network controller”, Control Sys. Magazine, vol. 8, no. 2, pp. 17 – 21, 1988. [2] K. J. Hunt and D. Sbarbaro, “Neural networks for nonlinear Internal Model Control”, IEE Proceedings-D, vol. 138, no. 5, pp. 431 – 438, 1991. [3] M. Shafiq and M. Moinudden, “Adaptive inverse control using a multi layer perceptron neural network”, Proceedings of the 22nd IASTED International Conference on Modelling, Identification, and Control (MIC 2003), Innsbruck, Austria. IASTED/ACTA Press, pp. 595 – 599, 2003. [4] R. Fletcher, Practical Methods of Optimization, John Wiley & Sons, New York, 1987. [5] M. Nørgaard, O. Ravn, N. K. Poulsen, and L. K. Hansen, Neural Networks for Modelling and Control of Dynamic Systems, Springer-Verlag, London, 2000. [6] L. Ljung, System Identification – Theory for the User, Prentice-Hall, Englewood Cliffs, NJ, 1987. [7] A. Fasso, “Residual autocorrelation distribution in the validation data set”, Journal of Time Series Analysis, vol. 21, no. 2, pp. 143 – 153, 2000.