Fuzzy and Neural Adaptive Control of a Class of Nonlinear Systems

In this book, two types of direct adaptive control schemes for a class of nonlinear systems are proposed. Based on the feedback linearization theory, the architecture employs for the first approach the fuzzy logic reasoning of Takagi Sugeno (TS) type and uses for the second approach the strategy of neural network reasoning of radial basis function (RBF) type to approximate the feedback linearization control law. In each case, the parameters of the adaptive controller are adapted according to a law derived using Lyapunov stability theory. The adaptive controller is applied in simulation to control three nonlinear systems in both the fuzzy and the neural network methods.

Autorentext

Mohamed Bahita obtained his Ingénieur , his Master Degree and his Doctor ès Sciences Degree all in control Engineering from the University of Constantine, Algeria. He is currently with the University of BOUMERDES, Algeria. His main interests are in artificial intelligence (fuzzy and neural) and in adaptive control of nonlinear systems.