(342e) Friction Theory & Free Volume Theory Coupled with Artificial Intelligence Algorithms to Estimate the Viscosity of Crude Oils

The Friction Theory (FT) and the Free Volume Theory (FVT) for viscosity modeling are applied to live oil characterized based on SARA TEST. Both of the theory-based models make a new model in combination with two equation of state (PR EoS and PC-SAFT EoS). The FT and FVT parameters for pseudo-components are obtained by tuning the viscosity at atmospheric pressure and temperatures of 10, 20, and 40^°C. A new fitting approach is suggested where the number of fitting parameters for both of the used equations of state is 17 and 12 for FT and FVT model, respectively. These parameters are tuned using the Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) and make eight new models. The results show that using PC-SAFT EoS provides viscosity predictions for all models with less deviation from experimental viscosity. The FT and FVT models have less error for crude oils with API>40 and API<40, respectively. The use of PC-SAFT+PSO to tunning parameters significantly improves the accuracy in viscosity modeling for both FT and FVT models. However, PSO can play a significant role even more than PC-SAFT, because PR+FVT+PSO has the overal AAD% rather than PC-SAFT+FT+GA.