شماره ركورد كنفرانس :
4518
عنوان مقاله :
Prediction of the MMP by Using of Artificial Intelligence
Author/Authors :
Ebrahimi A Amirkabir University of Technology - Department of Chemical Eng , Tehran , H Rasouli Amirkabir University of Technology - Department of Chemical Eng , Tehran , Rashidi F Amirkabir University of Technology - Department of Chemical Eng , Tehran , E Khamehchi Amirkabir University of Technology - Department of Chemical Eng , Tehran
كليدواژه :
CO2–Oil MMP , Genetic Algorithm , Neural Network , BP , PSO , Intelligent Proxy
عنوان كنفرانس :
The 7th International Chemical Engineering Congress & Exhibition (IChEC 2011
چكيده لاتين :
An important factor in the design of gas injection projects is the minimum miscibility pressure (MMP). A new genetic algorithm (GA)-based correlation and two neural network models (one of them is trained by BP algorithm and another is trained by PSO algorithm) have been developed to estimate the CO2–oil MMP. The correlation and models use the following key input parameters: reservoir temperature, molecular weight of C5+, mole percentage of the volatiles and intermediate components (for the first time, the mole percentages are used as independent variables). Then results have been validated against experimental data and are finally compared with commonly used correlations reported in the literature;
The results show that the neural network model trained by BP algorithm and the correlation that has been developed by GA can be applied effectively and afford high accuracy and dependability for MMP forecasting.
