Cuttings Transport Modeling in Wellbore Annulus in Oil Drilling Operation using Evolutionary Fuzzy System

Abstract

The process of cuttings transport in drilling operation is a complex problem that concerns the very drilling parameters. Accurate prediction of the cuttings concentration (hole cleaning efficiency) in the wellbore annulus as a function of operational drilling parameters such as wellbore geometry, pump rate, drilling fluid rheology and density, and maximum drilling rate is vital for optimizing these parameters. In this paper, a hybrid evolutionary fuzzy system (EFS) based on artificial intelligent (AI) techniques for estimation of cuttings concentration in oil drilling operation using operational drilling parameters is presented. The extraction of the Takagi–Sugeno–Kang (TSK) type fuzzy rule-based system for the EFS is carried out by means of an efficient genetic learning algorithm employing symbiotic evolution for fitness assignment. A determination coefficient (R2) of 0.877 together with a root mean square error (RMSE) of 1.4 between prediction and experimental data for test data implied a very satisfactory model performance. Results showed that the estimation accuracy of the proposed EFS is superior to other models such as adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and multiple linear regression (MLR).