Fed-batch Yeast Fermentation Process Research Articles

An Approach to Continuous Approximation of Pareto Front Using Geometric Support Vector Regression for Multi-objective Optimization of Fermentation Process

The approaches to discrete approximation of Pareto front using multi-objective evolutionary algorithms have the problems of heavy computation burden, long running time and missing Pareto optimal points. In order to overcome these problems, an approach to continuous approximation of Pareto front using geometric support vector regression is presented. The regression model of the small size approximate discrete Pareto front is constructed by geometric support vector regression modeling and is described as the approximate continuous Pareto front. In the process of geometric support vector regression modeling, considering the distribution characteristic of Pareto optimal points, the separable augmented training sample sets are constructed by shifting original training sample points along multiple coordinated axes. Besides, an interactive decision-making (DM) procedure, in which the continuous approximation of Pareto front and decision-making is performed interactively, is designed for improving the accuracy of the preferred Pareto optimal point. The correctness of the continuous approximation of Pareto front is demonstrated with a typical multi-objective optimization problem. In addition, combined with the interactive decision-making procedure, the continuous approximation of Pareto front is applied in the multi-objective optimization for an industrial fed-batch yeast fermentation process. The experimental results show that the generated approximate continuous Pareto front has good accuracy and completeness. Compared with the multi-objective evolutionary algorithm with large size population, a more accurate preferred Pareto optimal point can be obtained from the approximate continuous Pareto front with less computation and shorter running time. The operation strategy corresponding to the final preferred Pareto optimal point generated by the interactive DM procedure can improve the production indexes of the fermentation process effectively.

On-line evolutionary optimization of an industrial fed-batch yeast fermentation process

This paper presents two genetic algorithms based on optimization methods to maximize biomass concentration, and to minimize ethanol formation. The objective function is maximized according to the values of feed flow rate, using genetic search approaches. Five case studies were carried out for different initial conditions, which strongly influence the optimal profiles of feed flow rate for the fermentation process. The ethanol and glucose disturbance effects were examined to stress the effectiveness of proposed approaches. The proposed genetic approaches were implemented for an industrial scale baker’s yeast fermentor which produces Saccharomyces cerevisiae known as baker’s yeast. The results show that optimal feed flow rate was obtained in a satisfactory and successful way for fed-batch fermentation process.

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

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.

A COMPARATIVE STUDY OF SOFT-SENSING METHODS FOR FED-BATCH FERMENTATION PROCESSES

A comparative study of software sensors using Multiway Partial Least Squares and Extended Kalman Filters in an application to a fed-batch yeast fermentation process is presented. The MPLS theory is introduced firstly and then applied to a yeast fed-batch fermentation process to provide soft-sensing facilities. The soft-sensing capabilities of the MPLS approach are found to compare favourably with the results using EKF.

Optimization of fed-batch culture of recombinant yeast by using genetic algorithms

A simulation and experimental study on the on-line adaptive optimization of fed-batch yeast fermentation process has been performed using genetic algorithms. In simulation study, genetic algorithms based on three different strategies with no adaptation were developed and applied to obtain the optimal feed rate profiles for several initial conditions. The genetic algorithm showed better or similar results compared with an approach based on maximum principle and singular control theory. To confer adaptability on the optimization algorithm developed, an on-line model parameter estimation strategy based on genetic algorithm was developed and incorporated into it. In experimental study, the resulting adaptive optimization algorithm was applied to fed-batch cultures of a recombinant yeast producing calcitonin. It performed on-line model parameter update and optimal feed rate profile calculation simultaneously. It followed the process quite well and gave a much higher value of performance index (in this particular case, cell mass produced) than the simple genetic algorithm with no adaptability.