Forecasting the abnormal events at well drilling with machine learning
This work addresses partial prevention of drilling accidents during well construction, offering a domain-specific solution for the oil and gas industry.
The paper tackles the problem of predicting drilling accidents using a data-driven and physics-informed machine learning algorithm, achieving 70% forecasting accuracy with a 40% false positive rate on a dataset of 125 past accidents from 100 Russian oil and gas wells.
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.