سال انتشار: ۱۳۸۶

محل انتشار: پنجمین کنگره بین المللی مهندسی شیمی

تعداد صفحات: ۸

نویسنده(ها):

Zahedi – Simulation and AI research canter, Department of Chemical Engineering, Faculty of Engineering, Razi University, Kermanshah, Iran
Khanalizadeh – Simulation and AI research canter, Department of Chemical Engineering, Faculty of Engineering, Razi University, Kermanshah, Iran

چکیده:

In this study, an Artificial Neural Network (ANN) modeling for estimation of vapor pressure is proposed. Different data from several pure materials have been collected. Temperature and acentric factor have been considered as network inputs. Vapor pressure is the network outputs. 70 percent of the data have been used for training of ANN. Among the multilayer feed-forward architectures a preprocessing and post processing network with 16 hidden neurons has been found as best feed-forward predictor. The result of network has successfully been validated with experimental data.