L-lysine Neuro-Dynamic Optimal Control

Dr. Tatiana Ilkova; Dr. Mitko Petrov

Authors

Dr. Tatiana Ilkova
Dr. Mitko Petrov

Keywords:

dynamic programming, neural network, Llysine fermentation, optimal control

Abstract

In this paper Neuro-dynamic programming (NDP) is proposed as an alternative to alleviate the "curse of dimensionality" of the Dynamic programming (DP) for optimal control of a fed-batch fermentation process in the L-lysine production. The most effective and cheapest method for the Llysine biosynthesis (in biological active form) is the microbiological method via a direct fermentation. In this paper an optimization method of the L-lysine production from strain Brevibacterium flavum 22LD is used and that is NDP. The results show that the quality of L-lysine enhances at the end of the process. The proposed method is particularly simple to implement and can be applied for on-line optimization.

Downloads

How to Cite

L-lysine Neuro-Dynamic Optimal Control. (2011). Global Journal of Medical Research, 11(4), 55-60. https://medicalresearchjournal.org/index.php/GJMR/article/view/101784

Download Citation

References

D Bertsekas, J Tsitsiklis (1996) Neuro-dynamic programming: an overview. 1, 560-564.

Kurt Driessens, Sašo Džeroski (2004) Integrating Guidance into Relational Reinforcement Learning. 57(3), 271-304.

Andrew Barto, Steven Bradtke, Satinder Singh (1995) Learning to act using real-time dynamic programming. 72(1-2), 81-138.

R Sutton (1988) Learning to predict by the methods of temporal differences. 3, 9-44.

N Kaisare, J Lee, J Lee (2003) Simulation based strategy for nonlinear optimal control: application to a microbial cell reactor. 13, 347-363.

T Ilkova, M Petrov (2008) Dynamic and neurodynamic optimization of a fed-batch fermentation process. 5253, 365-369.

Savas Anastassiadis (2007) L-Lysine Fermentation. 1(1), 11-24.

A Soni, R Parker (2002) Fed-batch bioreactor control using a multi-scale model. 3, 2371-2376.

D Vlachos, A Mhadeshwar, N Kaisare (2006) Hierarchical multiscale model-based design of experiments, catalysts, and reactors for fuel processing. 30(10-12), 1712-1724.

J Lee, N Kaisare, J Lee (2006) Choice of approximator and design of penalty function for an approximate dynamic programming based control approach. 16, 135-156.

Zh Xiong, J Zhang (2005) Neural Network model-based on-line re-optimisation control of fedbatch processes using a modified iterative dynamic programming algorithm. 44, 477-484.