Open Access Open Access  Restricted Access Subscription or Fee Access

Hybrid Models for Biological Reactors: Performance and Possibilities


(*) Corresponding author


Authors' affiliations


DOI's assignment:
the author of the article can submit here a request for assignment of a DOI number to this resource!
Cost of the service: euros 10,00 (for a DOI)

Abstract


The complexity of microbial processes, coupled with the effects of incomplete mixing and the influx of noise, makes it difficult to describe quantitatively the behavior of bioreactors under realistic conditions. By circumventing the need for phenomenological equations, neural networks offer viable descriptions of such systems. However, such networks also require large amounts of carefully screened data and long training schedules. They also have limited extrapolation capability and poor physiological fidelity. Since phenomenological models are derived from physical descriptions of cellular processes, combinations of such models with neural networks, and sometimes also fuzzy logic, have provided good portrayals of nonideal bioreactor behavior while reducing the weaknesses of both approaches. However, like neural networks themselves, different architectures are possible for hybrid neural models. The rationale, architectures and illustrative applications of hybrid models for biological reactors are discussed here, with the possibility of combining them with cybernetic models, exploiting cellular intelligence, to develop self-evolving intelligent systems for optimization and control of microbial processes.
Copyright © 2018 Praise Worthy Prize - All rights reserved.

Keywords


Biological Reactors; Nonideal Conditions; Mathematical Models; Neural Networks; Hybrid Neural Models; Self-Evolving Intelligent Systems

Full Text:

PDF


References


H. Shimizu, Metabolic engineering: integrating methodologies of molecular breeding and bioprocess systems engineering, J. Biosci. Bioeng. 94 (2002) 563-573.

J.E. Haag, A. van de Wouwer, P. Bogaerts, Dynamic modeling of complex biological systems: a link between metabolic and macroscopic description, Math. Biosci. 193 (2005) 25-49.

T.M. Leib, C.J. Pereira, J. Villaden, Bioreactors: a chemical engineering perspective, Chem. Eng. Sci. 56 (2001) 5485-5497.

E. Carson, D.D. Feng, M.-N. Pons, R. Soncini-Sessa, G. van Straten, Dealing with bio- and ecological complexity: Challenges and opportunities, Ann. Revs. Control 30 (2006) 91-101.

P.R. Patnaik, External, extrinsic and intrinsic noise in cellular systems: analogies and implications for protein synthesis, Biotechnol. Mol. Biol. Revs. 1 (2006) 123-129.

C.-F. Mandenius, Recent developments in the monitoring, modeling and control of biological production systems, Bioprocess Biosyst. Eng. 26 (2004) 347-351.

D. Ramkrishna, On modeling of bioreactors for control, J. Process Contr. 13 (2003) 581-589.

L.Z. Chen, S.K. Nguang, X.M. Li, X.D. Chen, Soft sensors for on-line biomass measurements, Bioprocess Biosyst. Eng., 26 (2004) 191-195.

K.G. Gadkar, S. Mehra, J. Gomes, On-line adaptation of neural networks for bioprocess control, Comput. Chem. Eng. 29 (2005) 1047-1057.

P.R. Patnaik, Neural network designs for poly-(-hydroxybutyrate production optimization under simulated industrial conditions. Biotechnol. Lett. 27 (2005) 409-415.

H.J.L. van Can, H.A.B. te Braake, C. Helliga, K.Ch.A.M. Luyben, J.J. Heijnen, An efficient model development strategy for bioprocesses based on neural networks in macroscopic balances, Biotechnol. Bioeng. 54 (1997) 549-566.

S. Haykin, Neural networks: A comprehensive foundation (Prentice–Hall, Englewood Cliffs, N.J., 1998).

M. Agarwal, Combining neural and conventional paradigms for modelling, prediction and control. Int. J. Syst. Sci. 28 (1997) 65-81.

J. Schubert, R. Simutis, M. Dors, I. Havlik, A. Lubbert, Bioprocess optimization and control: Application of hybrid modeling, J. Biotechnol. 35 (1994) 51-68.

V. Galvanauskas, R. Simutis, A. Lubbert, Hybrid process models for process optimization, monitoring and control, Bioprocess Biosyst. Eng. 26 (2004) 393-400.

P.R. Patnaik, Neural and hybrid optimizations of the fed-batch synthesis of poly-(b-hydroxybutyrate by Ralstonia eutropha in a nonideal bioreactor, Bioremed. J. 12 (2008) 117-130.

O. Kahrs, W. Marquardt, The validity domain of hybrid models and its application in process optimization, Chem. Eng. Processing 46 (2007) 1054-1066.

P.R. Patnaik, The extended Kalman filter as a noise modulator for continuous yeast cultures under monotonic, oscillating and chaotic conditions, Chem. Eng. J. 108 (2005) 91-99.

D.C. Psichogis, L.H. Ungar, A hybrid neural network-first principles approach to process modeling, A.I.Ch.E.J. 38 (1992) 1499-1511.

J. Schubert, R. Simutis, M. Dors, I. Havlik, A. Lubbert, Hybrid modelling of yeast production processes–Combination of a priori knowledge on different levels of sophistication, Chem. Eng. Technol. 17 (1993) 10-20.

P. Linko, Y. Zhu, Neural network programming in bioprocess variable estimation and state prediction, J. Biotechnol. 21 (1991) 253-270.

M.N. Karim, S.L. Rivera, Artificial neural networks in bioprocess state estimation, Biochem. Eng. Biotechnol. 46 (1992) 1-33.

H.J.L. van Can, C. Helliga, K.Ch.A.M. Luyben, J.J. Heijnen, H.A.B. te Braake, Strategy for dynamic process modeling based on neural networks in macroscopic balances, A.I.Ch.E.J. 12 (1996) 3403-3418.

S. de Azevedo, B. Dahm, F.R. Oliviera, Hybrid modeling of biochemical processes: A comparison with the conventional approach, Comput. Chem. Eng. 21 Suppl. (1997) S751-S756.

R. Oliviera, Combining first principles modelling and artificial neural networks: a general framework, Comput. Chem. Eng. 28 (2004) 755-766.

B. Sonnleiter, O. Kappeli, Growth of Saccharomyces cerevisiae is controlled by its limited respiratory capacity: Formulation and verification of a hypothesis, Biotechnol. Bioeng. 28 (1986) 927-937.

K. Friehs, Plasmid copy number and plasmid stability, Adv. Biochem. Eng. Biotechnol. 86 (2004) 47-82.

P.R. Patnaik, Hybrid neural simulation of a fed-batch bioreactor for a nonideal recombinant fermentation, Bioprocess Biosyst. Eng. 24 (2001) 151-161.

P.R. Patnaik, Neural and hybrid neural modeling and control of fed-batch fermentation for streptokinase: Comparative evaluation under nonideal conditions. Can. J. Chem. Eng. 82 (2004) 599-606.

S. James, R. Legge, H. Budman, Comparative study of black-box and hybrid estimation methods in fed-batch fermentation, J. Process Control 12 (2002) 113-121.

K. Zuo, H.-P. Cheng, S.-C. Wu, W.-T. Wu, A hybrid model combining hydrodynamic and biological effects for the production of bacterial cellulose with a pilot scale airlift reactor, Biochem. Eng. J. 29 (2006) 81-90.

P.R. Patnaik, A hybrid simulator for improved filtering of noise from oscillating microbial fermentations, Biochem. Eng. J. 39 (2008) 389-396.

M. Beuse, R. Bartling, A. Kopman, H. Diekman, M. Thoma, Effect of dilution rate on the mode of oscillation in continuous cultures of Saccharomyces cerevisie, J. Biotechnol. 61 (1998) 15-31.

K.D. Jones, D.S. Kompala, Cybernetic model of the growth dynamics of Saccharomyces cerevisiae in batch and continuous cultures, J. Biotechnol. 71 (1999) 105-131.

W. Babel, J.-U. Ackerman, U. Breuer U., Physiology, regulation, and limits of the synthesis of poly(3HB), Adv. Biochem. Eng. Biotechnol. 71 (2001) 125-157.

A. Steinbuchel, PHB and other polyhydroxyalkanoates. In: H.J. Rehm, G. Reed (Eds.), Biotechnology (VCH, Weinheim, 1996, Vol. 6, Ch. 13).

S. Khanna, A.K. Srivastava, Recent advances in microbial polyhydroxyalkanoates, Process Biochem. 40 (2005) 607-619.

J.H. Lee, H.C. Lim, J. Hong, Application of nonsingular transformation to on-line optimal control of poly-(-hydroxybutyrate fermentation. J. Biotechnol. 55 (1997) 135-150.

P.R. Patnaik, Enhancement of PHB biosynthesis by Ralstonia eutropha in fed-batch cultures by neural filtering and control, Food Bioprod. Processing 84(C2) (2006) 150-156.

J. Peres, R. Oliviera, L.S. Serafim, P. Lemos, M.A. Reis, S.F. de Azevedo, Hybrid modelling of a PHA production process using modular neural networks, Comput. Aided Chem. Eng. 18 (2004) 733-738.

P.R. Patnaik, Intelligent models of the quantitative behavior of microbial systems, Food Bioprocess Technol. 2 (2008) 122-137.

L.F.M. Zorzetto, J.A. Wilson, Monitoring bioprocesses using hybrid models and an extended Kalman filter, Comput Chem. Eng. 20 Suppl. (1996) S689-S694.

J.-I. Horiuchi, Fuzzy modeling and control of biological processes, J. Biosci. Bioeng. 94 (2002) 574-578.

M. Cakmakci, Adaptive neuro-fuzzy modelling of anaerobic digestion of primary sedimentation sludge, Bioprocess Biosyst. Eng. 30 (2007) 349-357.

J.-I. Horiuchi, M. Kishimoto, Application of fuzzy control to industrial bioprocesses in Japan, Fuzzy Sets Syst. 128 (2002) 117-124.

P.F. van Lith, B.H.L. Betlem, B. Roffel, A structured modeling approach for dynamic hybrid fuzzy-first principles models, J. Process Control 12 (2002) 605-615.

M.J. Guardia, A. Gambhir, A.F. Europa, D. Ramkrishna, W.-S. Hu, Cybernetic modeling and regulation of metabolic pathways in multiple steady states of hybridoma cells, Biotechnol. Prog. 16 (2000) 847-853.

D. Ramakrishna, D.S. Kompala, G.T. Tsao, Are microbes optimal strategists? Biotechnol. Prog. 3 (1987) 121-126.

S. Arnold, T.Becker, A. Delgado, F. Emde, A. Enenkel, Optimizing high strength acetic acid bioprocess by cognitive methods in an unsteady state cultivation, J. Biotechnol. 97 (2002) 133-145.

J. Varner, D. Ramkrishna, Metabolic engineering from a cybernetic perspective. The aspartate family of amino acids, Metabol. Eng. 1 (1998) 88-116.

B.M. Kim, S.W. Kim, D.R. Yang, Cybernetic modeling of the cephalosporin C fermentation process by Cephalosporium acremonium, Biotechnol. Lett. 25 (2003) 611-616.

P.R. Patnaik, Cognitive optimization of microbial PHB production in an optimally dispersed bioreactor by single and mixed cultures. Bioprocess Biosyst. Eng. 32 (2009) 557-568.

P.R. Patnaik, Synthesizing cellular intelligence and artificial intelligence for bioprocesses, Biotechnol. Adv. 24 (2006) 129-133.

R.C. Giordano, J.R. Bertini, M. Nicoletti, R.L.C. Giodano, On-line filtering CO2 signals from a bioreactor gas outflow using a committee of constructive neural networks, Bioprocess Biosyst. Eng. 31 (2008) 101-109.


Refbacks

  • There are currently no refbacks.


Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2024 Praise Worthy Prize