A Neural Network Based Control of a Simulated Biochemical Process

This paper describes an application of feedforward neural networks for inverse plant control of a process with highly non-linear characteristics. A biochemical process was considered where the microorganism, Saccharomyces cerevisiae, a yeast, grows in a chemostat on a glucose substrate and produces ethanol as a product of primary energy metabolism. In this process, which is of immense interest to industries worldwide, three state variables were considered: microbial, substrate and product concentrations. The last one is the controlled variable, and the dilution rate is the manipulated variable. In the study, the quality of the control is analyzed for the case where all states are assumed to be measurable and the case where only the product concentration is available.