Real-Time Data-Driven Detection of the Rock-Type Alteration During a Directional Drilling

TLDR

During directional drilling, a bit can enter nonproductive rock layers due to a ~20 m gap between the bit and high‑fidelity rock‑type sensors, and the only timely way to detect lithotype changes is through MWD data, yet no general mathematical models exist that accurately reconstruct rock type from MWD data for the oil and gas industry. The study proposes a data‑driven method that uses MWD data to rapidly detect rock‑type changes by combining machine‑learning classification with novel change‑detection techniques. The method is applied to MWD data collected from a newly developed oilfield in northern western Siberia, employing machine‑learning classification of rock type and change‑detection algorithms. The approach reduces rock‑type change detection delay from 20 m to 1.8 m and cuts false‑positive alarms from 43 to 6 per well.

Abstract

During the directional drilling, a bit may sometimes go to a nonproductive rock layer due to the gap about 20m between the bit and high-fidelity rock type sensors. The only way to detect the lithotype changes in time is the usage of Measurements While Drilling (MWD) data. However, there are no general mathematical modeling approaches that both well reconstruct the rock type based on MWD data and correspond to specifics of the oil and gas industry. In this article, we present a data-driven procedure that utilizes MWD data for quick detection of changes in rock type. We propose the approach that combines traditional machine learning based on the solution of the rock type classification problem with change detection procedures rarely used before in the Oil\&Gas industry. The data come from a newly developed oilfield in the north of western Siberia. The results suggest that we can detect a significant part of changes in rock type reducing the change detection delay from $20$ to $1.8$ meters and the number of false-positive alarms from $43$ to $6$ per well.