Intelligent Hybrid Adaptive Control Approach For Nonlinear Systems

This paper proposes a Gain Scheduling adaptive control scheme based on fuzzy systems, neural networks and genetic algorithms: an optimal fuzzy PI controller is developed, by a genetic algorithm, according to some design specifications, and a neural network is designed to learn and tune on-line the fuzzy controller parameters at different operating points from ones used in the learning process. Simulation results are shown to demonstrate the efficiency of the proposed structure for DC servomotor adaptive speed control design.413418Astrom, K.J., Wittenmark, B., (1995) Adaptive Control, , 2nd ed, Addison-WesleyIoannou, P.A., Sun, J., (1996) Robust Adaptive Control, , Prentice-HallChalam, V.V., (1987) Adaptive Control Systems: Techniques and Applications, , Marcel DekkerDillon, T., Khosla, R., (1997) Engineering Intelligent Hybrid Multi-Agent Systems, , Kluwer Academic PublishersGoonatilake, S., Khebbal, S., (1995) Intelligent Hybrid Systems, , Jhon Wiley & SonsSinha, N.K., Gupta, M.M., Intelligent Control Systems: Theory and Design (1996) IEEE PRESSMichalewicz, Z., (1996) Genetic algorithms + data structures = evolution programs, , 3rd ed, Springer-VerlagBottura, C.P., Serra, G.L.O., An optimal knowledge based PI controller (2003) Book series on frontiers in artificial intelligece and its applications, , IOS PRESS The Netherlands, NovemberVellasco, M.M., Tanscheit, R., Pacheco, M.A.C., A neuro-fuzzy-genetic system for automatic setting of control strategies (2001) 20th NAFIPS international conference and 9th IFSA world congress, 3, pp. 1553-155