Development of a new gas condensate viscosity model using artificial intelligence

Abstract

Accurate estimation of gas condensate fluid properties is a challenging task due to the evolving condensate liquid from the gas phase below the saturation pressure. Among the fluid properties, viscosity of condensate liquid has the largest prediction uncertainty. The existing literature methods cannot cope with the nonlinearity and physics of gas condensate mixture (transition from a single phase to two phases) below the saturation pressure. Hence, in this study based on the experimental condensate viscosity data, a simple linear equation as a function of pressure, temperature and solution gas to oil ratio was developed. For this purpose, a comprehensive data source of 1368 experimental data points acquired from open literature has been used. For developing the new condensate viscosity correlation, an artificial intelligence (AI) method known as the Takagi–Sugeno–Kang (TSK) fuzzy algorithm was utilized. The accuracy of the developed correlation was compared with five previously published literature models. The superiority of the new correlation over the existing literature models is confirmed by statistical parameters of a least root mean square error of 0.0194, a mean average error of 0.0163 and an average absolute relative deviation percentage of 7.123. The proposed condensate viscosity correlation is valid in a pressure range of 0.25–75.84 MPa), a temperature range of 303–443.15°K and Rs of 41.96–3496 scf/STB.The proposed correlation can be used as an alternative approach to the existing models for accurately estimating the gas condensate viscosity and for conducting reliable reservoir simulation studies.

Keywords

• Artificial Intelligence (AI)
• Condensate viscosity
• Fuzzy approach
• K–mean clustering
• Membership Functions (MFs)
• Takagi–Sugeno–Kang (TSK)