Current Approaches in Prediction of PVT Properties of Reservoir Oils

Abstract

Bubble point pressure Bubble point oil formation factor Crude oil.PVT (pressure-volume-temperature) properties of reservoir fluids in the oil and gas industry constitute an integral part of the required data for a thorough study of the reservoir, optimally compilation of oil production and operation schemes. In the absence of PVT data that measured in laboratory conditions, empirical correlation is used to evaluate these properties. These correlations cannot be applied universally due to the differences of crude oil composition, the working condition of geographical and oil environment. In the article widespread correlations and models was investigated in the field of prediction of PVT properties of reservoir oil from different regions. Their accuracy and productivity was thoroughly analyzed too.

Machine Learning Applied to Predict Key Petroleum Crude Oil Constituents

“…De Oliveira et al also used ANNs to predict flash point, cetane index, and sulfur content of diesel blends. To predict crude oil pressure volume temperature (PVT) properties, Al-Marhoun et al [8] and Nagi et al [9] proposed support vector machines, and Makrufa et al [10] used ANN. Oloso et al [11] developed an ensemble ML model for the prediction of dead oil, saturated and undersaturated viscosities.…”