Poroelastic modeling of borehole breakouts for in-situ stress determination by finite element method

Abstract

Borehole breakouts are changes in borehole geometry in a cross section perpendicular to the borehole axis when rock subjected to in-situ stress experiences shear failure. By finite element modeling of borehole breakouts considering poroelasticity, the authors simulate the process of borehole breakouts in terms of initiation, propagation and stability in the condition of Mogi-Coulomb criteria, and can get the shape of borehole breakouts. It's desirable that this information of borehole breakouts can be used to determine in-situ stress by inverse analysis. Artificial neural network provides such a tool to establish the relationship between in-situ stress and shape on borehole breakouts, by which in-situ stress can be obtain according to different shape of borehole breakouts. In this paper, there are two steps to determinate in-situ stress by inverse analysis. First, Sets of finite element modeling provides sets of data on in-situ stress and borehole breakout measures, which will be used to train an artificial neural network that can eventually represent the relationship between the in-situ stress and borehole breakout measures. Second, for a given measure of borehole breakouts, the trained artificial neural network will be used to predict the corresponding in-situ stress. Results show that the inverse analysis based on finite element modeling of borehole breakouts and artificial neural network can effectively determine in-situ stress.