A neural computing strategy to estimate dew-point pressure of gas condensate reservoirs. (18th May 2020)

• Record Type: Journal Article
• Authors: Daneshfar, Reza; Keivanimehr, Farhad; Mohammadi-Khanaposhtani, Mohammad; Baghban, Alireza
• Is Part Of: Petroleum science and technology. Volume 38:Number 10(2020)
• Page Start: 706
• Page End: 712
• Publication Date: 2020-05-18
• Subjects: Dew-point pressure -- empirical correlation -- gas condensate reservoir -- MLP-ANN -- statistical analysis; Liquid fuels -- Periodicals; Petroleum -- Periodicals; 665.505
• DOI: 10.1080/10916466.2020.1780257
• Languages: English
• ISSNs: 1091-6466

Abstract

Abstract: A novel multilayer perceptron artificial neural network (MLP-ANN) model is proposed to estimate the dew-point pressure (DPP) of gas condensate reservoirs as a function of gas composition, reservoir temperature and, molecular weight and specific gravity of C7+ . For this purpose, a comprehensive database was prepared by reviewing literature and the results of MLP-ANN are graphically and statistically compared with these actual values. The R -squared ( R 2 ) and mean relative error are determined to be 0.9868 and 1.5%, respectively, which reveals that DPP values are well predicted by this model. Furthermore, the MLP-ANN model is compared with previous developed models.