OPTIMIZING CONTROL OF A CONTINUOUS STIRRED-TANK FERMENTER USING A NEURAL-NETWORK

Feedforward neural networks are a general class of nonlinear models th at can be used advantageously to model dynamic processes. in this inve stigation, a neural network was used to model the dynamic behaviour of a continuous stirred tank fermenter in view of using this model for p redictive control. In this system, the control setpoint is not known e xplicitly but it is calculated in such a way to optimize an objective criterion. The results presented show that neural networks can model v ery accurately the dynamics of a continuous stirred tank fermenter and , the neural model, when used recursively, can predict the state varia bles over a long prediction horizon with sufficient accuracy. In addit ion, neural networks can adapt rapidly to changes in fermentation dyna mics.