Neural control of an imperfectly mixed fed-batch bioreactor for recombinant β-galactosidase

The production of β-galactosidase in fed-batch fermentation by a recombinant strain of Escherichia coli was studied for on-line optimization by PID control and by an artificial neural network (ANN). The process was represented by an Elman ANN and the controller by a feed-forward network. Based on earlier work, the fermentation was carried out below a threshold temperature in an imperfectly mixed bioreactor. To mimic an industrial situation, data generated by a deterministic model were corrupted by adding 10% Gaussian noise. For dynamic optimal performance, the controller adjusted the mixing characteristics for each sampling interval on the basis of data for the previous interval. Application of neural control increased the maximum attainable concentration of β-galactosidase by 23.8% per gram of cell mass and by 51.1% per unit volume of the broth, compared with the uncontrolled fermentation; corresponding increases with adaptive PID control were 8.1% and 17.7%, respectively.

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

[2]  Julian Morris,et al.  Artificial neural networks in process estimation and control , 1992, Autom..

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

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

[5]  Anton Moser,et al.  Bioprocess Technology: Kinetics and Reactors , 1998 .

[6]  D. Dochain,et al.  On-Line Estimation and Adaptive Control of Bioreactors , 2013 .

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

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

[9]  Thomas F. Edgar,et al.  Adaptive control strategies for process control: A survey , 1986 .

[11]  K. Schügerl,et al.  Strategies for improving plasmid stability in genetically modified bacteria in bioreactors. , 1991, Trends in biotechnology.

[12]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

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

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

[16]  Kazuyuki Shimizu,et al.  Neuro-Fuzzy Control of Bioreactor Systems with Pattern Recognition , 1992 .

[17]  P. Patnaik.  Micromixing and the steady-state performance of bioreactors using recombinant bacteria--analysis through a reversed two-environment model. , 1994, Journal of chemical technology and biotechnology.

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

[19]  Patrick N. Royce,et al.  A Discussion of Recent Developments in Fermentation Monitoring and Control from a Practical Perspective , 1993 .

[20]  R. D. Tanner,et al.  The effect of imperfect mixing on an idealized kinetic fermentation model , 1985 .

[21]  G Lyberatos,et al.  Effect of cycling on final mixed culture fate , 1987, Biotechnology and bioengineering.

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

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

[24]  Qi Chen,et al.  Dynamic optimization of nonlinear processes by combining neural net model with UDMC , 1994 .

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

[26]  Wilfred D. Stein,et al.  Cell Shape: Determinants, Regulation, and Regulatory Role , 1989 .

[27]  K. Reardon,et al.  Parameters influencing the productivity of recombinant E. coli cultivations. , 1993, Advances in biochemical engineering/biotechnology.

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

[29]  P. Patnaik.  Dynamic sensitivity of a chemostat for a microbial reaction with substrate and product inhibition , 1994 .

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