Many processes in the chemical industry have modest nonlinearities; i.e., l
inear dynamics play a dominant role in governing the process output behavio
r in the operating range of interest, but the linearization errors may be s
ignificant. For these types of processes, linear-based control may yield a
poor performance, while nonlinear-based control results in computation comp
lexity. We propose to model this type of process with a composite model con
sisting of a linear model (LM) and a multilayered feedforward neural networ
k (MFNN). The LM is used to capture the Linear dynamics, while the MFNN is
employed to predict the LM's residual errors, i.e., the process nonlinearit
ies. Effective off-line and on-line al,algorithms are proposed for the iden
tification of the composite model. With this model structure, it is shown t
hat a simple analytical predictive control law can be formulated to control
a nonlinear process. Simulation examples are also given to illustrate the
effectiveness of the model identification and the proposed predictive contr
ol.