US 12,136,267 B2
Rig state detection using video data
Laetitia Shao, Menlo Park, CA (US); Suhas Suresha, Menlo Park, CA (US); Indranil Roychoudhury, Menlo Park, CA (US); Crispin Chatar, Menlo Park, CA (US); Soumya Gupta, Menlo Park, CA (US); and Jose Celaya Galvan, Menlo Park, CA (US)
Assigned to Schlumberger Technology Corporation, Sugar Land, AS (US)
Appl. No. 17/995,324
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
PCT Filed Apr. 5, 2021, PCT No. PCT/US2021/025757
§ 371(c)(1), (2) Date Oct. 3, 2022,
PCT Pub. No. WO2021/203090, PCT Pub. Date Oct. 7, 2021.
Claims priority of provisional application 63/004,542, filed on Apr. 3, 2020.
Prior Publication US 2023/0186627 A1, Jun. 15, 2023
Int. Cl. E21B 19/00 (2006.01); E21B 21/06 (2006.01); E21B 44/00 (2006.01); G06T 7/246 (2017.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 20/50 (2022.01)
CPC G06V 20/41 (2022.01) [E21B 19/00 (2013.01); E21B 21/065 (2013.01); E21B 44/00 (2013.01); G06T 7/248 (2017.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/50 (2022.01); E21B 2200/20 (2020.05); E21B 2200/22 (2020.05); G06T 2207/10016 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, from a first camera and a second camera positioned on a rig floor of a drilling rig, training images representing a shaker and a stick of the drilling rig over a first period of time;
associating individual training images of the training images with times at which the individual training images were captured;
determining a rig state at each of the times;
classifying the individual training images based on the rig state at each of the times, resulting in classified training images;
training a machine learning model to identify the rig state based on the classified training images, resulting in a trained machine learning model;
receiving additional images representing the shaker and the stick of the drilling rig over a second period of time; and
determining one or more rig states of the drilling rig during the second period of time using the trained machine learning model based on the additional images.