ABSTRACT: Rock mechanical properties play a crucial role in fracturing design, wellbore stability and in-situ stresses estimation. Conventionally, there are two ways to estimate Young’s modulus, either by conducting compressional tests on core plug sample or by calculating it from well log parameters. The objective of this paper is to present an approach to develop a continuous Young’s modulus profile without the need for well logs and core data. The proposed approach is based on the use of drilling parameters such as weight on bit, rate of penetration and rotation speed. To investigate this approach, artificial neural network (ANN) machine learning algorithm was used. ANN is very common artificial intelligence method that could be used in regression or classification problems. 2288 data points were used to construct and test the model, while another 1667 data points were hidden from the algorithm and used later to validate the built models. These data cover different types of formations, carbonate, sandstone and shale. A good match between the actual and predicted Young’s modulus was achieved with correlation coefficients above 0.92 and average absolute percentage errors were less than 15% in training, testing and validation datasets. This model is presented in this paper as a white-box to be used with different datasets. According to these results, the estimation of elastic moduli from drilling parameters is promising and this approach could be investigated for other rock mechanical parameters.
Workflow to Build a Continuous Static Elastic Moduli Profile From the Drilling Parameters Using Artificial Intelligence
Siddig, O. M., and S. M Elkatatny. "Workflow to Build a Continuous Static Elastic Moduli Profile From the Drilling Parameters Using Artificial Intelligence." Paper presented at the ARMA/DGS/SEG International Geomechanics Symposium, Virtual, November 2021.
Download citation file: