Abstract
This paper presents an artificial intelligence (AI) solution for predicting time-dependent safe mud weight windows and polar charts for inclined wellbores. The AI agents, in the form of neural networks, are trained and tested on data generated from a poroelastic analytical solution. The results show that the trained neural networks are capable of predicting time-dependent mud weight windows and polar charts as accurately as the analytical solution. The AI solution achieves a mean squared error (MSE) of 0.107 and a coefficient of determination (R2) of 0.995 for collapse mud weights, and an MSE of 0.043 and an R2 of 0.998 for fracturing mud weights on test datasets. They are also significantly faster and less demanding in computing capacity than the analytical solution, consistently showing three-orders-of-magnitude speed-ups in computational speed tests. Evaluations on two case studies similarly demonstrate the AI solution's capabilities and benefits.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
