Ab s tract Prediction of hydrogen sulfide and carbon dioxide concentration in gas sweetening plant by developing artificial neural network model

Gas sweetening is an essential s tep in gas treatment processes for environmental and safety concerns. One of the mos t widely used and well-known solvents for gas sweetening is methyl diethanolamine (MDEA). One of the mos t important criteria for measuring the effectiveness of gas treatment units is the amount of acid gas treated with MDEA solution. In this s tudy, artificial neural network (ANN) method was used to predict hydrogen sulfide and carbon dioxide This model was built using the data set collected from a gas sweetening unit in the center of Iran, which was collected over a period of six months, and was used as input to the neural network. The data includes hydrogen sulfide and carbon dioxide concentration, inlet gas flow rate, gas temperature, pressure and inlet amine temperature. The designed ANN model showed good accuracy in modeling the process under inves tigation. The tes t results show a high coefficient of determination (R2) more than 0.95.