A Comparison of Robust Model Predictive Control Techniques for a Continuous Bioreactor

Biotechnology industry is expanded rapidly due to the progress in the understanding of bio-systems and the increased demand for products. Since bioprocess dynamics are almost always affected by physical parameter variations and external disturbances, the need for robust control techniques is of major importance in order to ensure the desired behavior of the process. The overall process equilibrium is guaranteed if all quantities in the bioreactor remain into prescribed ranges. In recent years, closed-loop control methods have been used in order to cope with uncertainty and an important number of constraints imposed by the physical system. For this purpose, predictive control is a quite promising technique. In the present paper three robust model predictive control (RMPC) techniques are used in order to regulate the substrate concentration and the biomass production in a bioreactor. These techniques are applied to a continuous bioreactor in which the pH changes are considered as disturbances while the air pressure is ignored by the process model. For the simulation purposes a linearized model of the system has been used in which the uncertainty is described in the form of a disturbance term. The effectiveness of the methods is illustrated by means of simulation results.