The effect of formation thickness on the performance of deterministic and machine learning models for rate of penetration management in inclined and horizontal wells

• Published in: Journal of petroleum science & engineering 2020-08, Vol.191, p.107160, Article 107160
• Main Authors: Najjarpour, Mohammad, Jalalifar, Hossein, Norouzi-Apourvari, Saeid
• Format: Article
• Language: English
• Subjects: Data-driven methods; Deterministic models; Machine learning; Particle swarm optimization algorithm; Rate of penetration; Trust-region method
• ISSN: 0920-4105; 1873-4715
• DOI: 10.1016/j.petrol.2020.107160

Rate of penetration (ROP) is one of the most important parameters in reducing drilling expenditure. In this paper, a ROP management study has been conducted for a well in Southwest of Iran. As a part of this study, the best approach for ROP prediction was determined by comparing the performance of several methods and particle swarm optimization (PSO) algorithm was implemented for optimization of ROP. This paper highlights the effects of formation thickness and the magnitude of working data-set on the performance of different algorithms which are being used for ROP management studies, especially in horizontal and inclined wells. This topic has special importance, when the results show a massive difference in thin and thick formations for some ROP prediction methods. Comparing the results of different ROP prediction methods showed that hybrid Bingham model has the best performance in ROP prediction; only if a powerful mathematical tool like trust-region method is being used for the determination of its unknown coefficients. This superiority was not generalized in all individual formations and there were different results in the cases of thin and thick formations; so, application of the bag-of-algorithms strategy by using the most accurate method in each formation is suggested for the prediction of ROP. Performing this ROP management project resulted in the prediction of ROP with a total relative error of 13.59% and also 48.30% improvement in ROP. •The magnitude of working data-set affects the performance of ROP management algorithms.•This study expands the coverage of ROP prediction methods to horizontal and inclined wells.•Hybrid Bingham model in combination with trust-region method shows the best performance in ROP prediction.•Application of the bag-of-algorithms strategy is suggested for the prediction of ROP.