Intelligent optimisation of batch fermentations' initial conditions

The paper considers the problems of initial conditions optimisation for a class of biotechnological processes called batch fermentations. The method called backpropagation through time of utility function is used as optimisation procedure and neural network model of the process under consideration is used for derivatives' calculation. The developed procedure was applied to pre-fermentation process for yogurt starter cultures cultivation. The simulation results confirm experimental experience and expert's opinion on the possible optimal decisions.

[1]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[2]  F. M. Driessen,et al.  Evidence that Lactobacillus bulgaricus in yogurt is stimulated by carbon dioxide produced by Streptococcus thermophilus , 1982 .

[3]  V. Marshall.  Lactic acid bacteria: starters for flavour , 1987 .

[4]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[5]  A. Hillier,et al.  Metabolism of Streptococcus thermophilus. 2. Production of CO2 and NH3 from urea , 1982 .

[6]  D. Lloyd,et al.  Amino acid fermentation in non‐starter Lactobacillus spp. isolated from Cheddar cheese , 2000, Letters in applied microbiology.

[7]  Wenbo Xu,et al.  Culture conditions optimization of hyaluronic acid production by Streptococcus zooepidemicus based on radial basis function neural network and quantum-behaved particle swarm optimization algorithm , 2009 .

[8]  W. Sandine,et al.  Influence of temperature on associative growth of Streptococcus thermophilus and Lactobacillus bulgaricus. , 1986, Journal of dairy science.

[9]  Rintu Banerjee,et al.  Optimization of culture parameters for extracellular protease production from a newly isolated Pseudomonas sp. using response surface and artificial neural network models , 2004 .

[10]  G. Kostov,et al.  Oxygen influence in the mutual metabolism of S. thermophilus and Lb. bulgaricus in yogurt starter cultures , 2009 .

[11]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[12]  P.J. Werbos,et al.  An overview of neural networks for control , 1991, IEEE Control Systems.

[13]  Imran A. Tasadduq,et al.  Response surface methodology: A neural network approach , 1997 .

[14]  M. Collins,et al.  DNA base composition, DNA-DNA homology and long-chain fatty acid studies on streptococcus thermophilus and Streptococcus salivarius. , 1984, Journal of general microbiology.

[15]  Ka Kit Cheung.  Neural networks for optimization , 2001 .

[16]  Rekha S. Singhal,et al.  Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: Case study of fermentative production of scleroglucan , 2008 .

[17]  G. Linden,et al.  Carbon dioxide fixation by cells and cell-free extracts of Streptococcus thermophilus , 1996, Journal of Dairy Research.

[18]  W. Sandine,et al.  Associative Growth and Differential Enumeration of Streptococcus thermophilus and Lactobacillus bulgaricus : A Review. , 1984, Journal of food protection.