Mustafa Türker

Dynamic Neural-Network-Based Model-Predictive Control of an Industrial Baker's Yeast Drying Process

This paper presents dynamic neural-network-based model-predictive control (MPC) structure for a bakers yeast drying process. Mathematical model consists of two partial nonlinear differential equations that are obtained from heat and mass balances inside dried granules. The drying curves that are obtained from granule-based model were used as training data for neural network (NN) models. The target is to predict the moisture content and product activity, which are very important parameters in drying process, for different horizon values. Genetic-based search algorithm determines the optimal drying profile by solving optimization problem in MPC. As a result of the performance evaluation of the proposed control structure, which is compared with the model based on nonlinear partial differential equation (PDE) and with feedforward neural network (FFN) models, it is particularly satisfactory for the drying process of a bakers yeast.

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 bakers yeast fermentor which produces Saccharomyces cerevisiae known as bakers yeast. The results show that optimal feed flow rate was obtained in a satisfactory and successful way for fed-batch fermentation process.

Nonlinear predictive control of a drying process using genetic algorithms.

A nonlinear predictive control technique is developed to determine the optimal drying profile for a drying process. A complete nonlinear model of the bakers yeast drying process is used for predicting the future control actions. To minimize the difference between the model predictions and the desired trajectory throughout finite horizon, an objective function is described. The optimization problem is solved using a genetic algorithm due to the successful overconventional optimization techniques in the applications of the complex optimization problems. The control scheme comprises a drying process, a nonlinear prediction model, an optimizer, and a genetic search block. The nonlinear predictive control method proposed in this paper is applied to the bakers yeast drying process. The results show significant enhancement of the manufacturing quality, considerable decrease of the energy consumption and drying time, obtained by the proposed nonlinear predictive control.

Comparison of different estimation techniques for biomass concentration in large scale yeast fermentation

In this study, previously developed five different state estimation methods are examined and compared for estimation of biomass concentrations at a production scale fed-batch bioprocess. These methods are i. estimation based on kinetic model of overflow metabolism; ii. estimation based on metabolic black-box model; iii. estimation based on observer; iv. estimation based on artificial neural network; v. estimation based on differential evaluation. Biomass concentrations are estimated from available measurements and compared with experimental data obtained from large scale fermentations. The advantages and disadvantages of the presented techniques are discussed with regard to accuracy, reproducibility, number of primary measurements required and adaptation to different working conditions. Among the various techniques, the metabolic black-box method seems to have advantages although the number of measurements required is more than that for the other methods. However, the required extra measurements are based on commonly employed instruments in an industrial environment. This method is used for developing a model based control of fed-batch yeast fermentations.

Adaptive Neuro-Fuzzy-Based Control of Drying of Baker's Yeast in Batch Fluidized Bed

A control system was designed using adaptive neuro-fuzzy inference system (ANFIS) for industrial-scale batch drying of bakers yeast. The temperature and flow rate of inlet air were considered as the manipulated variables to control the temperature and dry matter of the product, respectively, resulting in two adaptive fuzzy controllers. The membership functions for all inputs were adjusted by a hybrid learning algorithm. The database used in this work comprises large quantities of industrial-scale data (about 570 batches) obtained under different working conditions over one year. This database was used for learning and testing phases of the ANFIS controller. The performance of the proposed controller demonstrates the effectiveness and potential of the proposed ANFIS-based controller.

Model Based Control of Large Scale Fed-Batch Baker's Yeast Fermentation

Abstract Abstract Two different control methods are applied to the technical scale (25 m 3 ) fed-batch bakers yeast fermentation. Feedback linearizing control design is used to manipulate the substrate feeding rate in order to maximize the biomass yield and minimizing the production of ethanol. Firstly, the specific growth rate controller is developed and applied to maintain the specific growth rate at specified trajectory. Secondly, the minimal ethanol controller is developed to maximize biomass productivity, by controlling specific growth rate just above the maximum oxidative growth rate by controlling ethanol concentration. The both controllers worked successfully and can be combined to follow required specific growth rate trajectory and respond successfully to disturbances in overflow fermentations such as Saccharomyces cerevisiae .