A simple control law analogous to the linear generalized minimum variance (
GMV) control is presented for the general unknown nonlinear dynamic process
es. With this control law, the iterative search of the control input, which
is often encountered in the nonlinear control, can be eliminated, resultin
g in an efficient computation for real-time implementation. The implementat
ion of this control law requires two key quantities to be calculated: the i
nput-output sensitivity function and the quasi-one-step-ahead predictive ou
tput. The selection of a diagonal recurrent neural network (DRNN) as the pr
ocess identifier allows a direct estimation of these two quantities, result
ing in the proposed control law to be implemented in a straightforward mann
er. Both simulation and experiment are given to demonstrate the effectivene
ss of the proposed control algorithm. (C) 1999 Elsevier Science Ltd. All ri
ghts reserved.