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.