Forecasting the abnormal events at well drilling with machine learning

TL;DR

This paper introduces a machine learning-based approach that uses time-series data from drilling telemetry to predict six types of drilling accidents in real-time, aiming to prevent accidents during well construction.

Contribution

The paper presents a novel Bag-of-features representation for time-series data combined with a physics-informed machine learning model for accident forecasting.

Findings

70% accident prediction accuracy

False positive rate of 40%

Effective partial prevention of drilling accidents

Abstract

We present a data-driven and physics-informed algorithm for drilling accident forecasting. The core machine-learning algorithm uses the data from the drilling telemetry representing the time-series. We have developed a Bag-of-features representation of the time series that enables the algorithm to predict the probabilities of six types of drilling accidents in real-time. The machine-learning model is trained on the 125 past drilling accidents from 100 different Russian oil and gas wells. Validation shows that the model can forecast 70% of drilling accidents with a false positive rate equals to 40%. The model addresses partial prevention of the drilling accidents at the well construction.