On the prediction of filtration volume of drilling fluids containing different types of nanoparticles by ELM and PSO-LSSVM based models
Aleksander Lekomtsev, Amin Keykhosravi, Mehdi Bahari Moghaddam, Reza Daneshfar, Omid Rezvanjou
Abstract
There is a direct link between the extent of formation damage and the filtration volume of the drilling fluids in hydrocarbon reservoirs. The filtration volume can be diminished by adding different additives to the drilling fluids. Recently, nanoparticles have been extensively used for enhancing the filtration characteristics of the drilling fluids. However, there is no reliable model for investigating the influence of this class of additives on the performance of drilling fluids. Hence in this study, two powerful tools ELM (extreme learning machine) and PSO-LSSVM (particle swarm optimization-least square support vector machine) are applied to determine the effect of various nanoparticles on the filtration volume. The assessment of the models is carried out by computing the statistical parameters, and it is found that ELM has a greater ability to predict the filtration volumes, while PSO-LSSVM performs satisfactorily too. The model predictions and experimental results are in excellent agreement as suggested by the values of root mean squared error (RMSE = 0.2459), coefficient of determination (R2 = 0.999), and mean relative error (MRE = 2.028%) for the dataset. The statistical analysis shows that the suggested model can predict the filtration volume with great accuracy. Moreover, through sensitivity analysis of the input parameters, it is found that for a specified nanoparticle, the filtration volume is highly influenced by nanoparticle concentration and it is the essential variable for the optimization process.