Neural networks based adaptive control for a class of uncertain nonlinear processes

In this paper, an adaptive neural controller design procedure for a class of nonlinear systems with incompletely known and time varying nonlinearities is presented. The unknown process dynamics is on-line identified using feedforward neural networks based estimators. Both the form of the controller and the adaptation laws of neural networks weights are derived from a Lyapunov stability property of the closed-loop system. The derived control method guarantees semiglobal uniform boundedness for adaptive system. In order to test the proposed method, the neural networks based adaptive control is applied in the case of a prototype fermentation bioprocess, for which kinetic dynamics is strongly nonlinear, time varying and not exactly known.