Author/Authors :
P. Valeh-e Sheyda Chemical Engineering Department, Faculty of Engineering, Razi University, Kermanshah, Iran , H. Rashidi Ammonia Plant, Process Eng. Dept., Kermanshah Petrochemical Industries Company, Kermanshah, Iran , J. Behin Chemical Engineering Department, Faculty of Engineering, Razi University, Kermanshah, Iran
چكيده لاتين :
This paper presents an artificial neural network (ANN) model for primary methane steam reformer (SMR) unit of Kermanshah Petrochemical Industries Company (KPIC). The main feature of the model is to provide a general, accurate and fast responding model for analysis of SMR unit. The industrial data were applied to train the multilayer feed forward neural network with thirteen inputs and four outputs with different algorithms and different numbers of neurons in the hidden layer. The results clearly depicts that the obtained model is a powerful tool to estimate the outlet compositions of reformer; moreover, the designed neural network can be used instead of approximate and complex analytical equations in optimization and process planning.
