Optimal control of a fed-batch yeast fermentation process based on Least Square Support Vector Machine

Abstract

An optimal control algorithm is presented in this paper for application to a fed-batch yeast fermentation process. The algorithm utilises a non-linear model of the process that is developed using Least Square Support Vector Machine (LS-SVM). The model can be used as a software sensor to provide predictions of the unmeasured variables. Furthermore, this non-linear model is used within an optimal control law to regulate the productivity of the batch by manipulating the substrates that are fed into the fermentation vessel. The proposed control algorithm is successfully applied to an yeast fermentation process and its performance compared with the nominal control algorithm that has been applied to this application in the past. The proposed controller is found to compare favourably with the nominal algorithm.