Summary
In bioengineering processes, many complex and nonlinear biochemical reactions occur simultaneously, since a variety of microorganisms and enzymes are present in the system. Thus, it may be difficult to describe the process with conventional mathematical models and use such models for process control. Recently soft computing methods such as artificial neural networks, fuzzy reasoning, fuzzy neural networks, and the genetic algorithm, have been applied to the modeling and control of bioengineering processes. In this chapter, three applications to the Japanese sake making process are reviewed, and the manner in which soft computing methods can help in the interpretation and control of this process are discussed. Knowledge extraction from a sake brewing expert, called TOJI, was carried out with the aim of optimizing the temperature control of the mashing process using fuzzy reasoning and fuzzy neural networks. We also discuss the determination of optimum process temperature and humidity using artificial neural networks and genetic algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zadeh, L. A.: Fuzzy sets.: Information and Control, 8, 338–358 (1965).
Horikawa, S., Furuhashi, T., and Uchikawa, Y.: A study on fuzzy modeling using fuzzy neural networks. Proc. of IFES ‘81, 562–573 (1991).
Rumelhart, D. E., Hinton G. E., and Williams, R. J.: Learning representations by back-propagating errors. Nature, 323, 533–536 (1986).
Holland, J. H.: Adaptation in natural and artificial systems. University of Michigan Press, Michigan, USA (1975).
Sugimoto, Y. and Fujita, E.: Process control of sake fermentation. Hakkokogaku,65, 199–215 (1987). (In Japanese)
Oishi, K., Tominaga, M., Kawato, A., Abe, Y., Imayasu, S., and Nanba, A.: Application of fuzzy control theory to the sake brewing process. J. Ferment. Bioeng., 72, 115–121 (1991).
Oishi, K., Tominaga, M., Kawato, A., and Imayasu, S.: Analysis of the state characteristics of sake brewing with a neural network. J. Ferment. Bioeng., 73, 153–158 (1992).
Matsuura, K., Hirotsune, M., Nagata, F., and Hamaguchi, M.: A kinetic study on continuous sake fermentation. Hakkokogaku,69, 345–354 (1991). (In Japanese)
Nishida, Y., Fukaya, I., Takahashi, N., Hanai, T., Honda, H., and Kobayashi, T.: Construction of fuzzy rules based on statistically analyzed data for control of the sake (Ginjo) making process. Seibutsu-kogaku,72, 267–274 (1994). (In Japanese)
Hanai, T., Honda, H., Takahashi, N., Nishida, Y., Fukaya, I., and Kobayashi, T.: Framework rules for control of the sake (Ginjo) making process and their application in fuzzy control. Seibutsu-kogaku,72, 275–281 (1994). (In Japanese)
Hanai, T., Nishida, Y., Ohkusu, E., Honda, N., Fukaya, I., and Kobayashi, T.: Experimental Fermentations of Ginjo sake with two fuzzy controls. Seibutsu-kogaku,73, 283–289 (1995). (In Japanese)
Hanai, T., Katayama, A., Honda, H., and Kobayashi, T.: Automatic fuzzy modeling for Ginjo sake brewing process using fuzzy neural networks. J. Chem. Eng. JPN., 30, 94100 (1997).
Matsuura, K., Hirotsune, M. and Hamachi, M.: Cell density identification in alcohol fermentation by neural network. Seibutsu-kogaku,69, 463–469 (1991). (In Japanese)
Nishida, Y., Hanai, T., Katayama, A., Honda, H., Fukaya, I., and Kobayashi, T.: Experimental Ginjo-sake brewing by using fuzzy neural network. J. Brew. Soc. Japan,92, 447–451 (1997). (In Japanese)
Sugimoto, Y., Tanaka, N., Furukawa, A., Watanabe, K., Yoshida, T., and Taguchi, H.: Adaptive control strategies for the mashing process in sake brewing. J. Ferment. Technol., 64, 187–197 (1986).
Tsuchiya, Y., Koizumi, J., Suenari, K., Teshima, Y., and Nagai, S.: Construction of fuzzy rules and a fuzzy simulator based on the control techniques of Hiroshima toji (experts). Hakkokogaku,68, 123–129 (1990). (In Japanese)
Matsuura, K., Shiba, H., Hirotsune, M., and Hamachi, M.: Optimizing control of sensory evaluation in the sake mashing process by decentralized learning of fuzzy inferences using a genetic algorithm. J. Ferment. Bioeng., 80, 251–258 (1995).
Honda, H., Hanai, T., Katayama, A., Tohyama, H., and Kobayashi, T.: Temperature control of ginjo sake mashing process by automatic fuzzy modeling using fuzzy neural networks. J. Ferment. Bioeng., 85, 107–112 (1998).
Hanai, T., Ueda, N., Honda, H., Tohyama, H. and Kobayashi, T.: Decision of temperature course in mashing process using GA-FNN for quality control of Ginjo sake. Seibutsu-kogaku,76, 331–337 (1998). (In Japanese)
Nihon Jyouzou Kyoukai.: Saishin shuzou kouhon, p.60–82. Nihon Jyouzou Kyoukai, Tokyo (1991). (In Japanese)
Hanai, T., Honda, H., Ohkusu, E., Ohki, T., Tohyama, H., Murakami, T. and Kobayashi, T.: Application of an artificial neural network and genetic algorithm for determination of process orbit in the koji making process. J. Biosci. Bioeng., 87, 507512 (1999).
Shiraishi, H. and Nakahara, S: Application of fuzzy reasoning using genetic algorithm for control of an activated sludge process, Kagaku Kogaku Ronbunshu, 22, 1–6 (1996). (In Japanese)
Ishida, M. and Ohba, T.: Control by new policy and experience-driven neural network to follow a desired trajectory. J. Chem. Eng. Japan, 27, 137–138 (1994).
Hanai, T., Iwata, N., Furuhashi, T., Yoshikawa, Y., Honda, H., and Kobayashi, T.: Proposal of Confidence Function for reverse problem of fuzzy neural network. Proc. 63th Annual Meeting of Soc. Chem. Eng. Japan, 1, 61, Osaka, Japan (1998). (In Japanese)
Ito, K.: Studies on the mycelial growth of Aspergillus oryzae on rice grain. Seibutsukogaku, 71, 115–127 (1993). (In Japanese)
Inoue, T., Tanaka, J., and Mitsui, S.: Recent advances in Japanese brewing technology, p.13–27. Gordon and Breach, New York (1993).
Okazaki, N. and Sugiyama, S.: Growth estimation of Aspergillus oryzae cultured on solid media. J. Ferment. Technol., 57, 408–412 (1979).
Kitano, H.: Identeki alugolizumu, Sangyou Tosho, Tokyo (1993). (In Japanese)
Suga, T.: Tahenryou Kaiseki no Jissen,p.97–103. Gendai Sugaku Sha, Kyoto, Japan (1993) (In Japanese)
Nihon Jyouzou Kyoukai.: Seishu seizou gijyutsu,p.91–124. Nihon Jyouzou Kyoukai, Tokyo (1992). (In Japanese)
Shi, Z. and Shimizu, K.: Pattern recognition of the change in dissolved oxygen concentration by neural network in E. coli cultivation. Kagaku Kogaku Ronbunshu, 19, 692–694 (1993). (In Japanese)
Ye, K., Jin, S. and Shimizu, K.: Fuzzy neural network for the control of high cell density cultivation of recombinant E. coli. J. Ferment. Bioeng., 77, 663–673 (1994).
Yoshida, T. and Shioya, S. ed.: Application of knowledge engineering to bioprocess systems. Seibutsu-kogaku,74, 185–213 (1996). (In Japanese)
Horiuchi, J., Kamasawa, M., Miyakawa, H, and Kishimoto, M.: Phase control of fed-batch culture for a-amylase production based on culture phase identification using fuzzy inference. J Ferment. Bioeng., 76, 207–212 (1993).
Hanai, T., Ohki, T., Honda, H., and Kobayashi, T.: Estimation model of the butadiene quality from polymerization conditions using fuzzy neural network. Proc. 63th Annual Meeting of Soc. Chem. Eng. Japan, 1, 61, Osaka, Japan (1998). (In Japanese)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Hanai, T., Honda, H., Kobayashi, T. (2003). Application of Artificial Neural Networks, Fuzzy Neural Networks, and Genetic Algorithms to Biochemical Engineering. In: Cartwright, H.M., Sztandera, L.M. (eds) Soft Computing Approaches in Chemistry. Studies in Fuzziness and Soft Computing, vol 120. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-36213-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-36213-5_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-53507-9
Online ISBN: 978-3-540-36213-5
eBook Packages: Springer Book Archive