Abstract:TX 75083-3836, U.S.A., fax 01-972-952-9435.
AbstractReservoir fluid properties data are very important in reservoir engineering computations such as material balance calculations, well testing, reserve estimates, and numerical reservoir simulations. Ideally, those data should be obtained experimentally. On some occasions, these data are not either available or reliable; then, empirically derived correlations are used to predict PVT properties. However, the success of such correlations in prediction depends mai… Show more
“…Based on their conclusion, they proposed a generalized regression neural network model for determining the viscosity of Kuwaiti crude. AlMarhoun and Osman (2002) have presented correlations for bubble point pressure and saturated OFVF using MLP trained by backpropagation with early stopping for Saudi Arabian crudes. They reported an average absolute relative error of 5.89% for bubble point pressure and 0.511% for saturated OFVF.…”
“…Based on their conclusion, they proposed a generalized regression neural network model for determining the viscosity of Kuwaiti crude. AlMarhoun and Osman (2002) have presented correlations for bubble point pressure and saturated OFVF using MLP trained by backpropagation with early stopping for Saudi Arabian crudes. They reported an average absolute relative error of 5.89% for bubble point pressure and 0.511% for saturated OFVF.…”
“…Nowadays, soft computing approaches are helpful robust tools which play a significant role in analyzing and unraveling challenging pitfalls in various scopes of science and engineering (for instance [35][36][37][38][39][40][41][42][43] in comparison to many published empirical and analytical solutions [44][45][46].…”
“…These data are basically extracted from PVT laboratory reports of bottom-hole samples. According to Al-Marhoun and Osman (Al-Marhoun and Osman, 2002) local models are superior to universal models in terms of accuracy and reliability. Therefore in order to build models for confident prediction of solution gas oil ratio for Iranian southwest oil fields, in this study 157 local unpublished PVT data sets from the region were used.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.