Comparison between Backpropagation, Elman and Radial Basis Function (RBF) networks in modeling of Tehran refinery hydrocracking unit

Different Artificial Neural Networks for modeling the hydrocracking process were utilized and their abilities were compared. The input–output data for the training and simulation phases of the networks were obtained from the Tehran refinery ISOMAX unit. Backpropagation, Elman and Radial Basis Function (RBF) networks were used for modeling and simulation of the hydrocracking unit. For each network model several architectures were studied and the best parameters for each network were obtained. The trained networks predict the yields of products of the ISOMAX unit(diesel, kerosene, light naphtha and heavy naphtha) with good accuracy. The residual error (root mean squared difference), coefficient correlation and run time, are three criteria that have been used for selection of the best network for modeling the hydrocracking unit.

کلیدواژه ها:

Artificial neural networks ، Backpropagation ، Elman ، RBF ، Hydrocracking process