Data-Driven Model for the Drilling Accidents Prediction

Antipova, Ksenia (Skolkovo Institute of Science and Technology, Digital Petroleum) | Klyuchnikov, Nikita (Skolkovo Institute of Science and Technology, Digital Petroleum) | Zaytsev, Alexey (Skolkovo Institute of Science and Technology, Digital Petroleum) | Gurina, Ekaterina (Skolkovo Institute of Science and Technology, Digital Petroleum) | Romanenkova, Evgenia (Skolkovo Institute of Science and Technology, Digital Petroleum) | Koroteev, Dmitry (Skolkovo Institute of Science and Technology, Digital Petroleum)



Majority of the accidents while drilling have a number of premonitory symptoms notable during continuous drilling support. Experts can usually recognize such symptoms, however, we are not aware of any system that can do this job automatically. We have developed a Machine learning algorithm which allows detecting anomalies using the drilling support data (drilling telemetry). The algorithm automatically extracts patterns of premonitory symptoms and then recognizes them during drilling.

The machine learning model is based on Gradient Boosting decision trees. The model analyzes real time drilling parameters within a sliding 4-hour window. For each measurement, the model calculates the probability of an accident and warns about anomaly of particular type, if the probability exceeds the selected threshold.

Our training sample comes from 20+ oilfields and consists of sections related to 80+ accidents of the following types: stuck pipe, mud loss, gas-oil-water show, washout of pipe string, failure of drilling tool, packing formation, that occurred while drilling, trip-in, trip-out, reaming; the sample also includes more than 700 sections without accidents.

We have designed the prediction model to work during drilling new wells and to distinguish the normal drilling process from the faulty one. One can configure the anomaly threshold to balance amount of false alarms and the number of missed accidents.

To evaluate quality of the model we measure data science metrics and check an industry-driven criterion. The model can identify 40 accidents from about 80 with high confidence, whereas for the others there is still a room for improvement. Our findings suggest that including more accidents of underrepresented types will improve quality. Other data science metrics also support aptitude of the model. Finally, having data from multiple heterogeneous oilfields, we expect that the model will generalize well to new ones.

This paper presents a good practice of development and implementation of a data-driven model for automatic supervision of continuous drilling. In particular, the model described in the paper will assist specialists with drilling accidents prediction, optimize their work with data and reduce the nonproductive time associated with the accidents by up to 20%.