شماره ركورد كنفرانس :
5048
عنوان مقاله :
Product yields prediction of Tehran refinery hydrocracking unit using artificial neural networks
Author/Authors :
Kh ،Sharifi Department of Chemical Engineering - Iran University of Science and Technology - Narmak Street - Tehran, Iran , M ،Shirvani Department of Chemical Engineering - Iran University of Science and Technology - Narmak Street - Tehran, Iran , M ،Bahmani Department of Chemistry - Applied Chemistry Group - Tarbiat Moalem University - Dr. Mofatteh Street - Tehran, Iran
كليدواژه :
Artificial neural networks , Hydrocracking process , Product yields
عنوان كنفرانس :
ششمين كنگره بين المللي مهندسي شيمي
چكيده لاتين :
In this contribution Artificial Neural Network (ANN) modeling of the hydrocracking process is presented. The
input–output data for the training and simulation phases of the network were obtained from the Tehran refinery
ISOMAX unit. Backpropagation networks of different architectures were developed and the networks that best
simulated the plant data were retained. The trained networks predicted the yields of products of the ISOMAX unit
(diesel, kerosene, light naphtha and heavy naphtha) with only 4% error. The residual error (root mean squared
difference) between the model predictions and plant data indicated that the validated model could be reliably used to
simulate the ISOMAX unit. Such validated models are valuable tools for refineries for process optimization, control,
design, catalyst selection and a better understanding of the process operation.
