Tracking control of nonlinear systems using fourier neural network

A Fourier neural network (FNN) based control scheme is presented in this paper for tracking control of a class of unknown nonlinear systems. The FNN employs orthogonal complex Fourier exponentials as the basis functions, and therefore the FNN has a clear physical meaning and the network topology is easily determined. Due to the orthogonality of the basis functions, the FNN has a fast convergent speed and can avoid local minimum. Taking advantage of the FNN, the proposed FNN controller requires no priori knowledge of the system and is suitable for real time control. The stability analysis of the closed-loop system is based on the Lyapunov theory. Experimental results on a gearbox are given to show the effectiveness of the proposed controller