Adaptive radial basis function neural network based tracking control of Van der Pol oscillator

Abstract

In this paper an online adaptive Radial Basis Function (RBF) controller is designed and simulated for the tracking control of Van der Pol oscillator. Van der pol oscillator is a nonlinear oscillator which is used for the modeling of various laser, mechanical and electrical oscillatory systems. The control and adaptive laws for the RBF controller are designed based on the neural network approximation. Lyapunov stability criterion is used in order to analyze the stability of the designed control and adaptive laws. Matlab/Simulink tool is used for the simulation of the designed adaptive controller for the tracking control of Van der Pol oscillator. The designed controller performance is tested with the uncertain system parameters and in the presence of disturbance in the system. The results of simulation show better reference tracking of the oscillator with the designed adaptive controller having good set speed and control accuracy. The designed controller has good robustness against the system perturbations and disturbances.