Development and comparison of different artificial intelligence-based models for viscosity of in-situ cross-linked acids

The use of in-situ cross-linked acids (ICAs) is common in stimulating oil and gas reservoirs. However, their rheological models have not been widely incorporated into simulation software due to their complex behavior and lack of valid data. Accordingly, in this study, development of new models for estimation of viscosity of ICAs as a function of pH and shear rate was intended. For this purpose, 33 experimental data points were collected from literature and methods of genetic programming, neural network (NN), and fuzzy logic (FL) were used to develop models. In summary, all three models performed equally well and better than a previously published model, with an R2 = 0.99 and an average absolute percent error of 7%. In terms of computational costs, genetic programming correlation was found to be 76 and 786% faster than NN and FL, respectively. Therefore, the model developed by genetic programming was suggested to be used in numerical solvers for estimation the viscosity of ICAs as a function of pH and shear. Sensitivity analysis on temperature, pH, and shear rate showed that pH would have the highest impact on the apparent viscosity of the considered ICAs.