An integrated hybrid neural system for noise filtering, simulation and control of a fed-batch recombinant fermentation☆

Abstract Fermentations employing genetically modified (recombinant) bacteria have complex metabolisms that are sensitive to the operating conditions. Therefore it is difficult to propose simple and accurate mathematical models suitable for industrial conditions. Under such a simulated condition, a fed-batch fermentation has been analyzed here for recombinant β-galactosidase production by Escherichia coli containing the plasmid pOU140. A previous study had shown that representing the bioreactor by an Elman neural network and coupling this to neural networks to filter the disturbances selectively and to control the fermentation generated more β-galactosidase than a well-mixed, noise-free fermentation. To overcome the limitations of large recurrent networks, the bioreactor has now been represented by a hybrid model which combines a partial mathematical model with two small Elman neural networks for the intra-cellular variables, an autoassociative network to filter the noise and a feedforward network as the controller. This integrated system permits more robust operation in the presence of disturbances and produces smoother profiles of the concentrations, improved gene expression and more β-galactosidase than previously achieved with an Elman network alone.

[1]  H J van Can,et al.  An efficient model development strategy for bioprocesses based on neural networks in macroscopic balances. , 1997, Biotechnology and bioengineering.

[2]  G. Montague,et al.  Enhanced supervision of recombinant E. coli fermentation via artificial neural networks , 1994 .

[3]  John Villadsen,et al.  Modeling fermentations with recombinant microorganisms: Formulation of a structured model , 1991, Biotechnology and bioengineering.

[4]  J Morris,et al.  Neural-network contributions in biotechnology. , 1994, Trends in biotechnology.

[5]  J Thibault,et al.  On‐line prediction of fermentation variables using neural networks , 1990, Biotechnology and bioengineering.

[6]  W. Johnston,et al.  Industrial control of recombinant E. coli fed-batch culture: new perspectives on traditional controlled variables , 2002, Bioprocess and biosystems engineering.

[7]  Predrag Horvat,et al.  Engineering approach to mixing quantification in bioreactors , 1992 .

[8]  P. R. Patnaik,et al.  A simulation study of dynamic neural filtering and control of a fed-batch bioreactor under nonideal conditions , 2001 .

[9]  Yuan Tian,et al.  Optimal control of a fed-batch bioreactor based upon an augmented recurrent neural network model , 2002, Neurocomputing.

[10]  J. F. Reid,et al.  A prototype neural network supervised control system for Bacillus thuringiensis fermentations , 1994, Biotechnology and bioengineering.

[11]  J. D. Díaz Ricci,et al.  Plasmid Effects on Escherichia coli Metabolism , 2000, Critical reviews in biotechnology.

[12]  Dale E. Seborg,et al.  Nonlinear control strategies for continuous fermenters , 1992 .

[13]  H. Bremer,et al.  Effect of the bacterial growth rate on replication control of plasmid pBR322 in Escherichia coli , 1986, Molecular and General Genetics MGG.

[14]  P. R. Patnaik,et al.  Incomplete mixing in large bioreactors — a study of its role in the fermentative production of streptokinase , 1996 .

[15]  P. Patnaik.  Enhancement of protein activity in a recombinant fermentation by optimizing fluid dispersion and initial plasmid copy number distribution , 2001 .

[16]  Ioan Dumitrache,et al.  Optimal De-Batch Bioprocess Control Via Intelligent System Based on Hybrid Techniques , 2001 .

[17]  A J Morris,et al.  Enhancing bioprocess operability with generic software sensors. , 1992, Journal of biotechnology.

[18]  Kazuyuki Shimizu,et al.  Fuzzy neural network for the control of high cell density cultivation of recombinant Escherichia coli , 1994 .

[19]  J. Keasling,et al.  A Monte Carlo simulation of plasmid replication during the bacterial division cycle , 2000, Biotechnology and bioengineering.

[20]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[21]  P. R. Patnaik.  Coupling of a neural filter and a neural controller for improvement of fermentation performance , 1999 .

[22]  P. R. Patnaik,et al.  Improvement of the microbial production of streptokinase by controlled filtering of process noise , 1999 .

[23]  W. Bentley,et al.  Plasmid‐encoded protein: The principal factor in the “metabolic burden” associated with recombinant bacteria , 1990, Biotechnology and bioengineering.

[24]  P. R. Patnaik.  Hybrid neural simulation of a fed-batch bioreactor for a nonideal recombinant fermentation , 2001 .

[25]  G W Luli,et al.  Comparison of growth, acetate production, and acetate inhibition of Escherichia coli strains in batch and fed-batch fermentations , 1990, Applied and environmental microbiology.

[26]  Rimvydas Simutis,et al.  Bioprocess optimization and control: Application of hybrid modelling , 1994 .

[27]  A sensitivity approach to manipulated variable selection for control of a continuous recombinant fermentation , 2001 .

[28]  Mark A. Kramer,et al.  Modeling chemical processes using prior knowledge and neural networks , 1994 .

[29]  K. Schügerl,et al.  Metabolic enhancement due to plasmid maintenance , 1994, Biotechnology Letters.

[30]  D. R. Baughman,et al.  An Expert Network for Predictive Modeling and Optimal Design of Extractive Bioseparations in Aqueous Two-Phase Systems , 1994 .

[31]  Rimvydas Simutis,et al.  Exploratory Analysis of Bioprocesses Using Artificial Neural Network‐Based Methods , 1997 .

[32]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[33]  P. Patnaik,et al.  Neural control of an imperfectly mixed fed-batch bioreactor for recombinant β-galactosidase , 1999 .

[34]  John Villadsen,et al.  Modelling of microbial kinetics , 1992 .

[35]  H. Noorman,et al.  Substrate gradients in bioreactors: origin and consequences , 1996 .

[36]  B. Glick.  Metabolic load and heterologous gene expression. , 1995, Biotechnology advances.

[37]  Patnaik.  Optimizing initial plasmid copy number distribution for improved protein activity in a recombinant fermentation. , 2000, Biochemical engineering journal.

[38]  W. Bentley,et al.  Investigation of subpopulation heterogeneity and plasmid stability in recombinant escherichia coli via a simple segregated model , 1993, Biotechnology and bioengineering.

[40]  Hisbullah,et al.  Comparative evaluation of various control schemes for fed-batch fermentation , 2002 .

[41]  P. R. Patnaik,et al.  A recurrent neural network for a fed-batch fermentation with recombinant Escherichia coli subject to inflow disturbances , 1997 .

[42]  P. Dhurjati,et al.  Improvement of product yields by temperature‐shifting of Escherichia coli cultures containing plasmid pOU140 , 1987, Biotechnology and bioengineering.

[43]  P. R. Patnaik,et al.  SENSITIVITY OF RECOMBINANT FERMENTATION WITH RUN-AWAY PLASMIDS: A STRUCTURED ANALYSIS OF THE EFFECT OF DILUTION RATE∗ , 1995 .