Modeling and control of drug delivery systems using adaptive neural control methods

This paper investigates the use of adaptive neural network techniques for modeling and control of mean arterial pressure through the intravenous infusion of sodium nitroprusside. A model reference based adaptive nonlinear control scheme with neural networks replacing the unknown nonlinearities is developed. In this formulation nonlinear estimators are used to augment the linear control law for improved performance. Computer simulations illustrate the ability of radial basis function (RBF) networks to model the unknown nonlinearities and improve the closed-loop system characteristics.