Modeling and optimization of biogas production on saw dust and other co-substrates using Artificial Neural network and Genetic Algorithm

The joint challenge of global pollution and depletion of fossil fuels is driving intense search into alternative renewable sources. This paper reports the modeling and optimization of biogas production on mixed substrates of saw dust, cow dung, banana stem, rice bran and paper waste using Artificial Neural Network (ANN) coupling Genetic Algorithm (GA). Data from twenty five mini-pilot biogas fermentations were used to train and validate a structured ANN with a topology of 5-2-1. The model served as fitness function for GA optimization process. An optimized substrate profile emerged with a predicted biogas performance of 10.144L. Evaluation of the optimal profile gave a biogas production of 10.280L, thus an increase of 8.64%, and an early biogas production initiated on the 3rd day of fermentation against the 8th day in non-optimized system. ANN coupling GA efficiently modeled the non-linear behavior of the process. A recipe for an optimum biogas production using the above co-substrates has been elucidated. ► We model and optimize biogas production process on mixed substrates. ► Artificial Neural Network (ANN) coupled Genetic Algorithm (GA) strategy is used. ► The validated optimal profile gave an 8.64% increase, and early biogas production. ► ANN coupling GA efficiently abstract complex non-linear bioprocess behavior.