Central Asian Research Index

Journal of Mathematics Mechanics and Computer Science, 2025, т. 126, № 2

PREDICTION OF DRILL STRING VIBRATIONS USING MACHINE LEARNING TOOLS

Askar Kudaibergenov, Askat Kudaibergenov, Togzhan Tileuberdi

Al-Farabi Kazakh National University, Almaty, Kazakhstan

Аннотация · Abstract

The objective of this work is to apply machine learning algorithms for the analysis of dynamic vibrations of drill strings. As part of the research, a mathematical model describing the vibrations of the drill string was developed; a finite difference scheme was implemented, and numerical modeling was carried out using the three-point sweep method. Based on the data obtained from the numerical solution, a machine learning model was created. The numerical modeling was implemented using C++, while data collection and the construction of the machine learning model were performed using the Python programming language. As a result, a predictive model was obtained, capable of accurately forecasting the dynamic vibrations of the drill string and determining optimal parameters, thereby improving the efficiency and safety of drilling operations.

Сведения · Details