Abstract

Using the presented criteria for the breakdown pressure in which the breakdown pressure is related to the horizontal stress, the breakdown pressure in the hydraulic fracturing test is directly used in the estimation of the maximum horizontal in situ stress. However, the classical breakdown pressure criteria do not take into account the effects of near-wellbore stress field, so estimating the horizontal stress using them is accompanied by errors. A plane strain numerical model is presented to obtain the breakdown pressure, in which the effect of initial crack length are considered. In this model, it is assumed that the rock medium is impermeable and the breakdown occurs at the tip of two radially cracks. Thus, in this model, the effect of the initial crack length, which is not present in the classical models, is considered. The results obtained from the numerical model show the significant effect of the initial crack length on the breakdown pressure. Also, the comparison of the numerical model with the classical criteria shows that the condition of using the classical criteria to determine the breakdown pressure is that the ratio of the initial crack length to the borehole radius is very small. Using the numerical model, 1,456 datasets were prepared to train an artificial neural network to predict the maximum horizontal stress. Input parameters include breakdown pressure, minimum horizontal stress, initial crack length, and tensile strength. The evaluation of the results shows that the obtained neural network model has a good ability to predict the maximum horizontal stress.

Full Text
Published version (Free)

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 call