US 12,141,960 B2
Cutter analysis and mapping
William Brian Atkins, Houston, TX (US); Radompon Sungkorn, Katy, TX (US); and Michael Stephen Pierce, Spring, TX (US)
Assigned to Halliburton Energy Services, Inc., Houston, TX (US)
Appl. No. 17/594,147
Filed by Halliburton Energy Services, Inc., Houston, TX (US)
PCT Filed Jun. 10, 2019, PCT No. PCT/US2019/036343
§ 371(c)(1), (2) Date Oct. 4, 2021,
PCT Pub. No. WO2020/251534, PCT Pub. Date Dec. 17, 2020.
Prior Publication US 2022/0172338 A1, Jun. 2, 2022
Int. Cl. G06T 7/00 (2017.01); E21B 10/12 (2006.01); E21B 10/567 (2006.01); E21B 12/02 (2006.01); G01N 21/88 (2006.01); G01N 21/956 (2006.01); G01N 29/44 (2006.01); G05B 23/02 (2006.01); G06F 18/241 (2023.01); G06N 3/02 (2006.01); G06N 20/00 (2019.01); G06T 7/12 (2017.01); G06V 10/26 (2022.01); G06V 10/44 (2022.01); G06V 10/70 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/80 (2022.01); E21B 10/42 (2006.01)
CPC G06T 7/001 (2013.01) [E21B 10/12 (2013.01); E21B 10/567 (2013.01); G01N 21/8803 (2013.01); G01N 29/4418 (2013.01); G06F 18/241 (2023.01); G06N 3/02 (2013.01); G06N 20/00 (2019.01); G06T 7/0004 (2013.01); G06T 7/0008 (2013.01); G06T 7/12 (2017.01); G06V 10/26 (2022.01); G06V 10/454 (2022.01); G06V 10/70 (2022.01); G06V 10/764 (2022.01); G06V 10/768 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/80 (2022.01); E21B 10/42 (2013.01); E21B 12/02 (2013.01); E21B 2200/20 (2020.05); E21B 2200/22 (2020.05); G01N 2021/8854 (2013.01); G01N 2021/888 (2013.01); G01N 2021/95615 (2013.01); G01N 21/95684 (2013.01); G05B 23/0283 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30164 (2013.01); G06V 2201/06 (2022.01)] 10 Claims
OG exemplary drawing
 
1. A method comprising:
identifying a cutter on a drill bit based on a drill bit image and an object recognition model of a machine learning system, the machine learning system includes one or more neural networks;
assigning a grading value of the cutter based on a classification model of the machine learning system, wherein a neural network of the one or neural networks is trained using a set of training cutter images associated with drill bit characteristics indicators and a set of training classifications;
determining a surface parameter based on a surface of the cutter;
generating a comparison value based on the surface parameter; and
mapping a set of cutter information to the cutter on the drill bit, wherein the set of cutter information comprises the grading value and the comparison value.