公开(公告)号：US12071844B2

公开(公告)日：2024-08-27

申请号：US17177897

申请日：2021-02-17

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Richard John Meehan ,  Cheolkyun Jeong ,  Velizar Vesselinov ,  Wei Chen ,  Yuelin Shen ,  Minh Trang Chau

IPC: E21B44/00 ,  E21B47/026 ,  E21B49/00 ,  E21B49/08

CPC classification number: E21B44/00 ,  E21B47/026 ,  E21B49/003 ,  E21B49/0875 ,  E21B2200/20 ,  E21B2200/22

Abstract: A method for drilling a well includes generating a plurality of proposed drilling actions using a plurality of working agents based on a working environment, simulating drilling responses to the proposed drilling actions using a plurality of validation agents in a validation environment that initially represents the working environment, determining rewards for the proposed drilling actions based on the simulating, using the validation agents, selecting one of the proposed drilling actions, and causing a drilling rig to execute the selected one of the proposed actions.

公开(公告)号：US20230419005A1

公开(公告)日：2023-12-28

申请号：US18251905

申请日：2021-11-08

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Cheolkyun Jeong ,  John Richard Meehan

IPC: G06F30/28

CPC classification number: G06F30/28 ,  E21B2200/20 ,  E21B41/00

Abstract: A method can include receiving a location from a process guided by an agent, where the process intends to reach a target; assigning uncertainty to the process; performing multiple simulation runs, guided by agent output, from the location with an intent to reach the target, where the multiple simulation runs account for the uncertainty; and generating output based on the multiple runs that characterizes an ability of the agent to reach the target in view of the uncertainty.

公开(公告)号：US20230313664A1

公开(公告)日：2023-10-05

申请号：US18331269

申请日：2023-06-08

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Velizar Vesselinov ,  Richard Meehan ,  Qiuhua Liu ,  Wei Chen ,  Minh Trang Chau ,  Yuelin Shen ,  Sylvain Chambon

IPC: E21B44/00 ,  E21B47/024 ,  E21B7/04

CPC classification number: E21B44/00 ,  E21B47/024 ,  E21B7/04

Abstract: A system and method that include receiving sensor data during drilling of a portion of a borehole in a geologic environment. The system and method also include selecting a drilling mode from a plurality of drilling modes based at least on a portion of the sensor data. The system and method additionally include simulating drilling of the borehole using the selected drilling mode and generating a state of the borehole in the geologic environment based on the simulated drilling of the borehole. The system and method further include generating a reward using the state of the borehole and a planned borehole trajectory and using the reward through deep reinforcement learning to maximize future rewards for drilling actions.

公开(公告)号：US20230272705A1

公开(公告)日：2023-08-31

申请号：US18308881

申请日：2023-04-28

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Qiuhua Liu ,  Richard John Meehan ,  Sylvain Chambon ,  Mohammad Khairi Hamzah

IPC: E21B44/00 ,  E21B21/08 ,  G06N7/00 ,  G01V1/50 ,  E21B49/00 ,  G01V11/00 ,  G06F30/20 ,  G06F17/15 ,  G06F17/16 ,  G06F30/27 ,  G06N3/044 ,  G06N3/047 ,  G06N3/08

CPC classification number: E21B44/00 ,  E21B21/08 ,  G06N7/00 ,  G01V1/50 ,  E21B49/003 ,  G01V11/00 ,  G06F30/20 ,  G06F17/15 ,  G06F17/16 ,  G06F30/27 ,  G06N3/044 ,  G06N3/047 ,  G06N3/08 ,  G01V2200/14 ,  G01V2200/16 ,  G06T13/80

Abstract: A system and method that can include 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. The system and method can also include receiving operation data from the equipment responsive to operation in the environment and outputting an actual operation as an actual sequence of operational actions by the deep neural network. The system and method can additionally include performing an operation-level comparison to evaluate the temporal sequence against the actual sequence using a distance function in a latent space of the deep neural network and outputting a score function that quantifies the distance function in the latent space. The system and method can further include controlling an electronic component to execute an electronic operation based on the score function.

公开(公告)号：US11603749B2

公开(公告)日：2023-03-14

申请号：US16192584

申请日：2018-11-15

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Sylvain Chambon ,  Qiuhua Liu

IPC: E21B44/00 ,  E21B21/08 ,  G06N7/00 ,  G01V1/50 ,  E21B49/00 ,  G01V11/00 ,  G06F30/20 ,  G06F17/15 ,  G06F17/16 ,  G06N3/04 ,  G06F30/27 ,  G06N3/08 ,  G06T13/80

Abstract: A method can include receiving multi-channel time series data of drilling operations; training a deep neural network (DNN) using the multi-channel time series data to generate a trained deep neural network as part of a computational simulator where the deep neural network includes at least one recurrent unit; simulating a drilling operation using the computational simulator to generate a simulation result; and rendering the simulation result to a display.

公开(公告)号：US11506021B2

公开(公告)日：2022-11-22

申请号：US16604567

申请日：2018-06-15

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu

IPC: E21B41/00 ,  E21B47/00 ,  G01V1/46 ,  G01V1/48 ,  E21B47/18 ,  E21B49/00

Abstract: A method includes acquiring data associated with a field operation of equipment in a geologic environment; filtering the data using a filter where the filter includes, along a dimension, a single maximum positive value that decreases to a single minimum negative value that increases to approximately zero; and, based on the filtering, issuing a control signal to the equipment in the geologic environment.

公开(公告)号：US20220145745A1

公开(公告)日：2022-05-12

申请号：US17177897

申请日：2021-02-17

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Richard John Meehan ,  Cheolkyun Jeong ,  Velizar Vesselinov ,  Wei Chen ,  Yuelin Shen ,  Minh Trang Chau

IPC: E21B44/00 ,  E21B49/00 ,  E21B47/026 ,  E21B49/08

Abstract: A method for drilling a well includes generating a plurality of proposed drilling actions using a plurality of working agents based on a working environment, simulating drilling responses to the proposed drilling actions using a plurality of validation agents in a validation environment that initially represents the working environment, determining rewards for the proposed drilling actions based on the simulating, using the validation agents, selecting one of the proposed drilling actions, and causing a drilling rig to execute the selected one of the proposed actions.

公开(公告)号：US20210166115A1

公开(公告)日：2021-06-03

申请号：US16636317

申请日：2018-11-15

Applicant: Schlumberger Technology Corporation

Inventor： Yingwei Yu ,  Qiuhua Liu ,  Richard John Meehan ,  Sylvain Chambon ,  Mohammad Khairi Hamzah

IPC: G06N3/08 ,  G06F17/15 ,  G06F17/16

Abstract: A method can include training a deep neural network to generate a trained deep neural network where the trained deep neural network represents functions of a nonlinear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system; generating a base internal state vector, that corresponds to a pre-defined operational procedure, using the trained deep neural network; receiving operation data from the equipment responsive to operation in the environment; generating an internal state vector using the operation data and the trained deep neural network; and comparing at least the internal state vector to at least the base internal state vector.