Victor Makarov | Search arXiv

arXiv2019

Application of Machine Learning to accidents detection at directional drilling

We present a data-driven algorithm and mathematical model for anomaly alarming at directional drilling. The algorithm is based on machine learning. It compares the real-time drilling telemetry with one corresponding to past accidents and analyses the level of similarity. The model performs a time-series comparison using aggregated statistics and Gradient Boosting classification. It is trained on historical data containing the drilling telemetry of $80$ wells drilled within $19$ oilfields. The model can detect an anomaly and identify its type by comparing the real-time measurements while drilling with the ones from the database of past accidents. Validation tests show that our algorithm identifies half of the anomalies with about $0.53$ false alarms per day on average. The model performance ensures sufficient time and cost savings as it enables partial prevention of the failures and accidents at the well construction.

cs.LG↗

arXiv1999

Predicate Logic with Definitions

Predicate Logic with Definitions (PLD or D-logic) is a modification of first-order logic intended mostly for practical formalization of mathematics. The main syntactic constructs of D-logic are terms, formulas and definitions. A definition is a definition of variables, a definition of constants, or a composite definition (D-logic has also abbreviation definitions called abbreviations). Definitions can be used inside terms and formulas. This possibility alleviates introducing new quantifier-like names. Composite definitions allow constructing new definitions from existing ones.

cs.LO↗