Prediction of Formation Pressure Relief by Using Neural Network

Abstract

Listen

Translate article

ABSTRACT: Accurate formation pressure relief prediction is crucial, especially in drilling operations technically and economically. Its prediction will save costs and time, and even the right decisions can be taken before problems occur. The available correlations for pore pressure prediction depend on logging data, formation characteristics, and a combination of logging and drilling parameters. The objective of this work is to apply BP neural networks (BPNN) models to estimate the formation pressure relief through the available drilling data. The used parameters include Gama (Gr), interval transit time (Dt), wave velocity, and resistivity(R10). A data set obtained from some vertical wells was utilized to develop the predictive model. A different set of data was utilized for validating the proposed artificial intelligence (AI) models. The models forecasted the output with a good correlation coefficient (R) for training and testing. Moreover, the mean relative Error (MRE) did not exceed 15.9%. By comparing and analyzing the formation pressure predicted by the traditional model Bowers, the BPNN model has better performance. The predicted results of the BPNN model are closer to the true pressure coefficient and have smaller errors. This study proves the reliability of the proposed models in estimating the formation pressure relief while drilling using drilling data. 1. INTRODUCTION Pore pressure prediction is very important for drilling operations. Pore pressure influences drilling efficiency and well operation costs, such as well designing, wellbore stability analysis, casing design, mud program designs, drilling operations, and structural optimization (Lee B Y et al., 1998). Accurate pore pressure determination is important for selective production and injection. The abnormal pressure is divided according to the size of the formation pressure coefficient (SONG Xianzhi et al., 2022), which is defined as the ratio of the measured formation pressure to the hydrostatic pressure at the same depth, which is a dimensionless quantity, which reflects the relative level of the formation pressure (LUO Ming et al., 2021). When the pressure coefficient is less than 0.8, it is abnormal low pressure, and when the pressure coefficient is between 0.8∼1.2, it is normal pressure. When the pressure coefficient is less than 0.8 or greater than 1.2, it is abnormal pressure. The normal pressure of pore pressure usually does not cause any drilling problems. Abnormal pressures need to be considered in the design of oil wells; Tubing, slurry density, cement planning, and casing solidification depth are all included in this. Many problems, such as kicking and bursting, shale uplifting, and differential pressure pipe adhesion, are thought to be the result of pressure abnormalities (Rock Mechanics, 1995).