An artificial neural network (ANN) was developed on MATLAB platform for predicting the reaction furnace temperature. Three important variable of the reaction furnace: fuel gas spiking, air and acid gas temperature and H2S concentration were fed as input into the ANN model, separately, while the reaction furnace temperature was the output. A three layer feed forward artificial neural network (ANN) model having one input neurons, one output neuron and three hidden neurons was developed to predict the reaction furnace temperature. A good agreement between the measured and the predicted values was obtained. The resulting ANN shows satisfactory prediction of the reaction furnace temperature with R2 above the 9.06

Keywords