19-08-2014, 03:05 PM
Biobriquette has the potential to meet the additional energy demands of urban and industrial sectors of developing countries like India. The various parameters to be taken into account for developing a model are compositions of biobriquettes and its properties like ash, volatile matter relative moisture and calorific value.
Biobriquette has the potential to meet the additional energy demands of urban and industrial sectors of developing countries like India. The various parameters to be taken into account for developing a model are compositions of biobriquettes and its properties like ash, volatile matter relative moisture and calorific value. Artificial Neural Networks (ANN) are effective in modeling of non-linear multi variable relationships and also referred as black box models. For modeling of shell and tube heat exchanger, ANN architecture has been optimized. In present work, multi layer perceptron (MLP) ANN with GDR based learning have been developed for estimation of properties of bio briquettes as a function of compositions. It is observed that ANN model with single hidden layers (4-15-4) has good level of accuracy (98-99.5%) for predicted values of training and test data set.
Keywords: Agricultural residues, ANN, Bio briquette