US 12,078,048 B2
Field operations system with filter
Yingwei Yu, Katy, TX (US); Qiuhua Liu, Houston, TX (US); Richard John Meehan, Katy, TX (US); Sylvain Chambon, Clamart (FR); and Mohammad Khairi Hamzah, Petaling Jaya (MY)
Assigned to Schlumberger Technology Corporation, Sugar Land, TX (US)
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
Filed on Apr. 28, 2023, as Appl. No. 18/308,881.
Application 18/308,881 is a continuation of application No. 16/636,317, granted, now 11,674,375, previously published as PCT/US2018/061314, filed on Nov. 15, 2018.
Claims priority of provisional application 62/586,288, filed on Nov. 15, 2017.
Prior Publication US 2023/0272705 A1, Aug. 31, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. E21B 44/00 (2006.01); E21B 21/08 (2006.01); E21B 49/00 (2006.01); G01V 1/50 (2006.01); G01V 11/00 (2006.01); G06F 17/15 (2006.01); G06F 17/16 (2006.01); G06F 30/20 (2020.01); G06F 30/27 (2020.01); G06N 3/044 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2023.01); G06N 7/00 (2023.01); G06T 13/80 (2011.01)
CPC E21B 44/00 (2013.01) [E21B 49/003 (2013.01); G01V 1/50 (2013.01); G01V 11/00 (2013.01); G06F 17/15 (2013.01); G06F 17/16 (2013.01); G06F 30/20 (2020.01); G06F 30/27 (2020.01); G06N 3/044 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2013.01); G06N 7/00 (2013.01); E21B 21/08 (2013.01); G01V 2200/14 (2013.01); G01V 2200/16 (2013.01); G06T 13/80 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
training a deep neural network using time series data that represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment and models a pre-defined operational procedure as a temporal sequence of desired operational actions by the deep neural network;
receiving operation data from the equipment responsive to operation in the environment and outputting an actual operation as an actual sequence of actual operational actions by the deep neural network;
performing an operation-level comparison to evaluate the temporal sequence against the actual sequence using a comparison function in a latent space of the deep neural network, classifying one or more actual operation internal states by one or more activity labels from the pre-defined operational procedure, and outputting a score function that quantifies the comparison function in the latent space, wherein the comparison function in the latent space quantifies compliance of each of the actual operational actions with each of the desired operational actions; and
controlling a well construction operation based on the score function.