A new approach to rheological properties of waxy crude oils using the
tree-based machine learning methods
Abstract
In this work, the rheological behavior of three crude oils, with low,
middle and high wax content, in the absence/presence of polymeric and
aromatic flow improvers was investigated. The rheological data cover the
temperature range of 0 to 60 °C to include the wax appearance
temperature (WAT). The results indicated that EVA copolymer has
remarkable performance in change of flow behavior from non-Newtonian to
Newtonian even at temperatures below WAT. Moreover, the addition of
small quantities of asphaltene solvents such as toluene can improve
viscosity of crude oil with high wax content. In addition to
experimental and analytical modeling investigations, this work attempted
to model measured shear stress and viscosity of waxy crude oils using
tree-based machine learning methods and consider wax content and
additives concentration as input parameters of models. Amongst all
implemented techniques, Extra Trees model performed as a potential
predictor in waxy oils rheology studies.