Dynamic simulation of phenol biodegradation in a fluidized bed bioreactor using genetic algorithm trained neural network

Abstract

The aim of this work is to simulate the dynamic behavior of a phenol biodegradation process in a fluidized bed bioreactor (FBR). Pseudomonas putida is used for the biodegradation of phenol. A mathematical model was developed to describe the dynamic behavior of the biodegradation process. The model equations describing the process have been solved, and the rate of biodegradation and the biofilm thickness at different points of time have been determined. The mathematical model has been directly mapped onto the network architecture. The network is used to find an error function. Minimization of error function with respect to the network parameters (weights and biases) has been considered as training of the network. A real-coded genetic algorithm has been used for training the network in an unsupervised manner. The system is tested for two different inlet concentrations of feed. The results obtained are then compared with the experimental results. It is found that there is a good agreement between the experimental results and the results obtained from the model