Simulation of biodegradation process in a fluidized bed bioreactor using genetic algorithm trained feedforward neural network

Abstract

Thebiodegradationprocessofphenolinafluidizedbedbioreactor(FBR)hasbeensimulatedusinggenetic algorithm trained feedforward neural network. Experiments were carried out using the microorganism Pseudomonas sp. on synthetic wastewater. The steady state model equations describing the biodegradation process havebeensolvedusingfeedforwardartificialneuralnetwork(FFANN)andgeneticalgorithm (GA). The mathematical modelhasbeendirectlymappedontothenetworkarchitectureandthenetwork has been used to find an error function (mean squared error criterion). The minimization of the error function with respect to network parameters (weights and biases) has been considered as training of the network. Real-coded genetic algorithm has been used for training the network in an unsupervised manner. The diffusivities of phenol and oxygen in biofilm obtained from the simulation have been compared with the literature values.