Predictive Control of a Multivariable Neutralisation Process Using Elman Neural Networks

This paper presents development and simulation results of a computationally efficient predictive control algorithm based on a recurrent Elman neural network. The considered process is a multivariable neutralisation reactor. Process modelling and control issues are thoroughly discussed. In particular, the discussed computationally efficient predictive control algorithm with on-line trajectory linearisation and quadratic optimisation is compared to the truly nonlinear scheme with nonlinear optimisation repeated of each sampling instant on-line.