Drilling

This study explores the use of autoencoder models with convolutional neural networks to present a framework and prototype for early and accurate kick detection during offshore oilwell drilling.
Operators aren’t rushing to drill, even as the closure of the Strait of Hormuz drives oil prices up.
The authors reach conclusions that the industry should define a standard testing method to improve swelling performance, including validation of repeatability, to complement existing guidelines.

Page 1 of 102