Integrated Drilling Geomechanics Analysis Using Poro-Elasto-Plastic Finite Elements and Machine Learning

Abstract

This study will deal with the essential weaknesses of traditional elastic models to predict wellbore instability that in most cases results in expensive drilling procedures. The aim of this study is to develop an integrated drilling geomechanics analysis using Poro-Elasto-Plastic finite elements and machine learning. The objectives are to, integrate drilling operations using a poro-elasto-plastic Finite Element Model; integrate drilling operations using machine learning algorithms. The analysis evolves a synthesized framework that combines a poro-elastoplastic Finite Element Model (FEM) and a Machine Learning (ML) to allow a dynamic and precise geomechanical analysis. A Drucker-Prager yield criterion has been used in the FEM to model the effects of plastic deformation and time-dependent effects of pore pressure around the wellbore in a realistic manner. Afterward, the ML surrogate models are trained using the outputs of the FEM in order to provide fast real-time predictions. Findings indicate that the hybrid model is able to properly measure the plastic yield zone and can give a dynamically updated safe mud weight window, which is much better than the traditional methods of doing so. The conclusion confirms that such integration forms a powerful digital twin, which allows making decisions in advance to increase the safety of drilling, streamline operations, and minimize non-productive time, thereby creating a new paradigm of wellbore stability management.