Optimisation of Drilling Parameters for Directional and Horizontal Wells Using Genetic Algorithm

Abstract

In this paper, a modification of Bourgoyne and Young ROP model has been derived. Bourgoyne and Young recommend multiple regression method to determine unknown coefficients. However, applying multiple regressions leads to physically meaningless values in some situation. Although some new mathematical model methods have recently been developed to reach meaningful results. In order to reach a more accurate prediction and physically meaningful coefficient, genetic algorithm was used to determine the eleven unknown drilling parameters of the proposed model. The model was validated with field data obtained from randomly selected wells drilled in the offshore locations at Khangiran Iranian field. The proposed model was found to estimate the rate of penetration with an error of ±10%. In this study, a robust model has been developed, tested and found to give realistic penetration rate for roller cone bits in directional and horizontal wells. The model is a veritable tool that can be used to investigate the synergistic effect of several drilling parameters on the rate of penetration.