سال انتشار: ۱۳۹۱

محل انتشار: چهاردهمین کنگره ملی مهندسی شیمی ایران

تعداد صفحات: ۴

نویسنده(ها):

P Darvishi – Chemical Engineering Department, School of Engineering, Yasouj University, Yasouj, Iran
D Dehghan Baniani – Department of Materials Science and Engineering, Shiraz University, Shiraz,
M Lashkarbolooki – School of Chemical and Petroleum Engineering, Shiraz University, Shiraz, Iran
B Vaferi –

چکیده:

Understanding vapor liquid equilibrium (VLE) is one of the most important information for designing of process equipments. In this work, artificial neural network (ANN) was used to modelthe bubble point pressure and vapor phase composition of binary ethanol (C2H5OH) mixtures. The proposed ANN model has been constructed with VLE experimental data of nine different binary systems containing C2H5OH collected from various literatures. Optimal configuration of the ANNmodel has been determined using minimizing %AARD, MSE and suitable R2. By using thisprocedure a two-layer ANN model with twenty-three hidden neuron has been found as an optimal topology. The accuracy of our optimal two layers ANN model has been compared with the Peng–Robinson cubic equation of state. Comparison with available literatures data and Peng-Robinsonequation of state confirm that the present ANN model is more accurate than the other published works. The sensitivity errors analysis clarify that our ANN model could predict vapor phase composition and bubble point pressure with %AARD of 1.52% and 2.59% respectively