Application of hybrid models for prediction and optimization of enzyme fermentation process. A comparative study

• Autorzy: Plaskute V. , Levisauskas D.
• Języki publikacji: EN

Abstrakty

EN

The paper presents a comparison of the biotechnological process prediction and optimization results obtained by using different structure hybrid mathematical models for modeling of the same bioprocess. The hybrid models under investigation consist of the product mass balance equation in which different means - an artificial neural network, fuzzy-neural network and cell age distribution based calculation scheme - are incorporated for modeling the specific biosynthesis rate of a desired product. Experimental data from alpha -amylase laboratory and industrial fermentation processes are used for model parameter identification and the process prediction tests.

Słowa kluczowe

EN

mathematical models; bioprocess; hybrid models; fuzzy neural network; cell age distribution; biosynthesis rate; enzyme fermentation; industrial processes; optimization

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Systems Science
• Rocznik: 2001
• Tom: Vol. 27, nr 3
• Strony: 115--123
• Opis fizyczny: Bibliogr. 9 poz.

Twórcy

autor

Plaskute V.

• Kaunas University of Technology, Process Control Department, Studentu St. 50, LT-3031 Kaunas, Lithuania

autor

Levisauskas D.

• Kaunas University of Technology, Process Control Department, Studentu St. 50, LT-3031 Kaunas, Lithuania

Bibliografia

• [1] Biriukov V. V., Kantere V. M., Optimization of batch processes of microbiological synthesis Moscow, “Nauka”, 1985, 292, (in Russian).
• [2] KINOSHITA S., OKADA H., TERUI G., Kinetic studies of enzyme production by microbes. II Process kinetics of a-amylase production by Bacillus subtilis, J Ferment. Technol., Vol. 45, 1967, 504-510.
• [3] LEVISAUSKAS D., PLASKUTE V., Modeling and optimization of secondary metabolites production in fed-batch biotechnological processes based on physiologically active biomass concept, ISSN 1392- 124X, Information Technology and Control, Kaunas, Technology, No 1(10), 1999, 33-36.
• [4] PORTO V. W., FOGEL D. B., FOGEL L. J., Alternative neural network training methods, IEEE Expert, 1995, 16-22.
• [5] PREUSTING H., NOORDOVER J., SIMUTIS R., LUEBBERT A., The use of hybrid modeling for the optimization of the penicillin fermentation process, Chimia, Vol. 50(9), 1996, 416-417.
• [6] SIMUTIS R., DORS M., LUEBBERT A., Bioprocess optimization and control: application of hybrid modeling, J. Biotechnology, Vol. 42, 1995, 285-290.
• [7] SIMUTIS R., HAVLIK I., LUEBBERT A., Fuzzy aided neural network for real time state estimation and process prediction in a production scale beer fermentation, J. Biotechnology, Vol. 27, 1993, 203-215.
• [8] TERUI G., OKAZAKI M., KINOSHITA S., Kinetic studies on enzyme production by microbes: On kinetic models, J. Ferment. Technol., Vol. 45, 1967, 497-503.
• [9] WANG L. X., Adaptive fuzzy systems and control, Prentice Hall, Englewood Cliffs, 1996, 232.