Designing drilling fluids, spacers, cement slurries and fracturing fluids are all often done by trial and error in the laboratory. In the first step, the required properties of these fluids are categorized and then efforts will be started with a rough idea of the optimum composition. This first guess usually depends on the experience of the lab analyst or fluid engineer. Afterwards, the trial and error testing starts and it continues until the fluid design gets closer to the desired fluid criteria. There are several tests data that would not be used in this method and it is hard to digest a plethora of information by user. Trial and error could be time consuming, very costly and misleading. Today, there is a need for an intelligent system which uses all the available data (Big Data), even if the data sets are not close to the desired goal, and comprehensivly offers insights for fluid designs.
This paper conducted a thorough study on the application of the machine leaning based methodologies including Artificial Neural Networks (ANN) and Gaussian Process Regression (GPR) to reduce the costs of testing, integrating available experimental data and eliminating the need for personnel supervision. These practical nonlinear regression methods empowers efficient and fast prediction tools which do not require including complex physics of the underlying system while integrating all available data from different sources. GPR which is also known as Kriging in Geostatistics literature has exceptional advantages over traditional regression methods since it does not require a known form for regression function and also has the capability of determining estimation error and confidence interval. This machine learning based tool offers comprehensive insights for intelligent fluid design and considerably reduces the cost.