Backstepping-based genetic fuzzy-neural controller and its application in motor control with buck DC-DC converters

In this paper, a genetic adaptive fuzzy-neural control scheme is proposed for a class of multiple-input multiple-output (MIMO) nonlinear systems. The control scheme incorporates backstepping design into the genetic algorithm with a backstepping-based fitness function. Using the backstepping-based fitness function, the genetic algorithm can be used to adjust the parameters of the fuzzy-neural networks in order to instantaneously generate the appropriate control strategy. The genetic algorithm has a simplified procedure with the backstepping-based fitness function which is used to evaluate the real-time stability of the closed-loop systems. To illustrate the feasibility and applicability of the proposed method, simulation and experimental results are provided.