Estimating Drilling Parameters for Diamond Bit Drilling Operations Using Artificial Neural Networks


INTERNATIONAL JOURNAL OF GEOMECHANICS, vol.8, no.1, 2008 (SCI-Expanded) identifier identifier


Diamond bit drilling is one of the most widely used and preferable drilling techniques because of its higher rate of penetration and core recovery in the hardest rocks, the ability to drill in any direction with less deviation, and the ability to drill with greater precision in coring and prospecting drilling. Conventional bit analysis techniques include mathematical methods such as specific energy and formation drillability. In this study, artificial neural network (ANN) analysis as opposed to conventional mathematical techniques is used to estimate major drilling parameters for diamond bit drilling, i.e., weight on bit, rotational speed, and bit type. The use of the proposed methodology is demonstrated using an ANN trained with information obtained from 45,000 m of diamond bit drilling operations conducted on several formations and locations in Turkey. The studied formations include shallow carbonates as well as sandstones in the Zonguldak hard coal basin. The neural network results are compared to those obtained from conventional methods such as specific energy analysis. It was observed that the proposed methodology provided satisfactory results both in relatively less documented and drilled formations as well as in well-known formations.