Key words: drilling troubles, drilling mud loss, mud loss intensity, artificial neural network, parallel computations.
A problem of prediction for troubles during well drilling on the base of minimal information on earlier drilled wells has been considered. Methods for prediction have been developed and realized; they allow simulating dependence of troubles on spatial location of wells on the base on artificial neural networks and parallel computations.
References
1. Baymukhametov K.S., Viktorov P.F., Gaynullin K.Kh., Syrtlanov A.Sh., Geologicheskoe stroenie i razrabotka neftyanykh i gazovykh mestorozhdeniy Bashkortostana (Geological structure and development of oil and gas fields in Bashkortostan), Ufa: Publ. of RITs ANK “Bashneft'”, 1997, 424 p.
2. Vadetskiy Yu.V., Burenie neftyanykh i gazovykh skvazhin (Drilling of oil and gas wells), Moscow: Akademiya Publ., 2007, 352 p.
3. Haykin S., Neural networks – a comprehensive foundation, Pearson Education, 2005, 823 p.
4. Ezhov A.A., Shumskiy S.A., Neyrokomp'yuting i ego primenenie v ekonomike i biznese (Neurocomputing and its application in economics and business), Moscow: Publ. of Moscow Engineering Physics Institute, 1998, 224 p.
5. Lind Yu.B., Kabirova A.R., Iskusstvennyy intellekt - Artificial intelligence, 2012, no. 3, pp. 451-457.
СКОРБИМ
|
16.12.2025 г. ушел из жизни, известный российский инженер-геофизик, Заслуженный работник нефтяной и газовой промышленности РФ, Почетный нефтяник, большой друг нашего журнала
