Stable adaptive control for a class of nonlinear systems without use of a supervisory term in the control law

In this paper,a direct adaptive control scheme for a class of nonlinear systems is proposed. the architecture employs a gaussian radial basis function (rbf) network to construct an adaptive controller. the parameters of the adaptive controller are adapted and changed according to a law derived using lyapunov stability theory. the centres of the rbf network are adapted on line using the k-means algorithm. asymptotic lyapunov stability is established without the use of a supervisory (compensatory) term in the control law and with the tracking errors converging to a neighborhood of the origin. finally,a simulation is provided to explore the feasibility of the proposed neuronal controller design method. © school of engineering,taylor's university.