A novel architecture for integrating neural networks with industrial contro
llers is proposed, for use in predictive control of complex process systems
. In the proposed method, a conventional controller, e.g., a proportional-i
ntegral (PI) controller, is used to control the process. In addition, a rec
urrent neural network is used in the form of a multistep-ahead predictor (M
SP) to model the process dynamics. The parameters of the PI controller are
tuned by a backpropagation-through-time (BTT)-like approach using "parallel
learning" to achieve acceptable regulation and stabilization of the contro
lled process. The advantage of such a formulation is the effective on-line
adaptation of the controller parameters while the process is in operation,
and the tracking of the different process operating regimes and variations.
The proposed method is used in the stabilization and transient control of
u-tube steam generator (UTSG) water level. Currently, available constant-ga
in PI controllers are unable to stabilize the UTSG at low operating powers,
necessitating manual operator control. The proposed predictive controller
stabilizes the process and improves its transient performance over the enti
re operating range. The adaptive PI controller can handle severe operationa
l transients in the presence of significant actuator noise and process para
meter drifts that could result from aging and other wear-and-tear effects.