Optimization of Fermentation Medium for the Production of Lipopeptide Using Artifi cial Neural Networks and Genetic Algorithms

Abstract

Artifi cial neural networks and genetic algorithms were used to model and optimize fermentation conditions for the production of a novel lipopeptide by Bacillus subtilis MO–01. Experimental data reported in the literature were used to build the neural network model. Four process variables viz., sucrose (g/l), ammonium chloride (g/l), ferrous sulphate (μM), zinc sulphate (mM) served as inputs to the neural network model, and lipopeptide yield (g/l) served as an output of the model. Genetic algorithm was used to optimize the input space of the neural network model to fi nd the optimum values of the variables for maximum lipopeptide
yield. Using this procedure, artifi cial intelligence techniques have been effectively integrated to create a powerful tool for process modeling and optimization.