شماره ركورد كنفرانس :
3834
عنوان مقاله :
PREDICTION OF THE TRUE CRITICAL TEMPERATURE OF BINARY N-ALKANS MIXTURES BASED ON ARTIFICIAL NEURAL NETWORK
پديدآورندگان :
Movagharnejad Kamyar Faculty of Chemical Engineering, Babol University of Technology, P.O. Box, 484, Babol, Iran , Etebarian Seyyede Mahafarin etebarian2005@stu.nit.ac.ir Faculty of Chemical Engineering, Babol University of Technology, P.O. Box, 484, Babol, Iran;
كليدواژه :
critical point , prediction , artificial neural networks , normal alkane
عنوان كنفرانس :
نوزدهمين سمينار شيمي فيزيك ايران
چكيده فارسي :
The critical point calculation of multi-component mixtures, is very important to understand the phase behavior in high temperature and pressure. Hence providing a way to predict this point, in oil and related industries can be beneficial. Also, in many hydrocarbon processing operations for rational design of separation equipment and chemical reactors, the critical properties of mixtures are required. In this study, a network with two hidden layers based on the experimental data of n-alkanes mixtures including 877 points - data was used for training. The results show that the model created has a high resolution (99.87%) and has a good agreement with the experimental data.
