Studies on RBF networks compensative control of chaotic system

In view of the property of nonlinear chaotic systems composed of a sum of a linear and nonlinear part, a compensative control method using radial basis function networks (RBFNs) is presented, the trained RBF networks can eliminate the nonlinear part of the chaotic system, the resulting system is dominated by the linear part. Then, a designed linear statefeedback controller is used to suppress the system to a desirable position. In addition to theoretical analysis, the computer simulations on the representative continuoustime chaotic system (Holmes nonlinear oscillator) show the effectiveness of the proposed method.4figs.,12refs.