Field operations system with filter

Patent metadata

Field	Value
Publication number	US-11674375-B2
Application number	US-201816636317-A
Country	US
Kind code	B2
Filing date	Nov 15, 2018
Priority date	Nov 15, 2017
Publication date	Jun 13, 2023
Grant date	Jun 13, 2023

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.

First claim

What is claimed is:

1. A method comprising:
accessing a trained deep neural network wherein the trained deep neural network represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system, wherein the deep neural network comprises a convolution neural network layer that represents a first one of the functions and a long short-term memory layer that represents second one of the functions;
generating a base internal state vector in a latent space, that corresponds to a pre-defined operational procedure, using the trained deep neural network;
receiving operation data from the equipment responsive to controlled operation in the environment by a controller;
generating an internal state vector in the latent space using the operation data and the trained deep neural network;
comparing at least the internal state vector to at least the base internal state vector; and
based on the comparing, calibrating the controller for additional controlled operation in the environment.

2. The method of claim 1 further comprising, based on the comparing, controlling at least one piece of the equipment.

3. The method of claim 1 further comprising rendering a graphical representation of the internal state vector and the base internal state vector to a display.

4. The method of claim 3 wherein the rendering is performed responsive to generating the internal state vector using the operation data.

5. The method of claim 1 wherein the functions comprise transfer functions that associate the internal state vector at a time to a prior internal state vector and an operation vector and wherein the functions comprise a measurement function that associates a measurement vector with the internal state vector.

6. The method of claim 1 wherein the comparing at least the internal state vector to at least the base internal state vector comprises comparing in the latent space.

7. The method of claim 1 wherein the pre-defined operational procedure comprises a series of proscribed actions.

8. The method of claim 1 wherein the comparing at least the internal state vector to at least the base internal state vector comprises utilizing a score function.

9. The method of claim 1 wherein internal states of the internal state vector are represented as points in a state space.

10. The method of claim 9 wherein a distance between two sequential points in the state space represents a temporal process of the dynamic system that transitions the dynamic system from a first one of the points to the second one of the points.

11. The method of claim 10 comprising comparing the temporal process to a process of the pre-defined operational procedure.

12. The method of claim 1 wherein the equipment comprises well construction equipment.

13. The method of claim 1 wherein the environment comprises a formation in the Earth.

14. The method of claim 1 wherein the deep neural network is trained using time series data.

15. The method of claim 1 wherein the deep neural network is trained using multi-channel time series data.

16. A system comprising:
a processor;
memory accessible by the processor;
processor-executable instructions stored in the memory and executable to instruct the system to:
access a trained deep neural network wherein the trained deep neural network represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system, wherein the deep neural network comprises a convolution neural network layer that represents a first one of the functions and a long short-term memory layer that represents second one of the functions;
generate a base internal state vector in a latent space, that corresponds to a pre-defined operational procedure, using the trained deep neural network;
receive operation data from the equipment responsive to controlled operation in the environment by a controller;
generate an internal state vector in the latent space using the operation data and the trained deep neural network;
perform a comparison at least the internal state vector to at least the base internal state vector; and

based on the comparison, calibrate the controller for additional controlled operation in the environment.

17. The system of claim 16 wherein the processor-executable instructions comprise instructions to, based on the comparison, instruct the system to control at least one piece of the equipment.

18. One or more non-transitory computer-readable storage media comprising processor-executable instructions to instruct a computing system to:
access a trained deep neural network wherein the trained deep neural network represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system, wherein the deep neural network comprises a convolution neural network layer that represents a first one of the functions and a long short-term memory layer that represents second one of the functions;
generate a base internal state vector in a latent space, that corresponds to a pre-defined operational procedure, using the trained deep neural network;
receive operation data from the equipment responsive to controlled operation in the environment by a controller;
generate an internal state vector in the latent space using the operation data and the trained deep neural network;
perform a comparison at least the internal state vector to at least the base internal state vector; and
based on the comparison, calibrate the controller for additional controlled operation in the environment.

19. The one or more non-transitory computer-readable storage media of claim 18 wherein the processor-executable instructions comprise instructions to, based on the comparison, instruct the computing system to control at least one piece of the equipment.

Assignees

• Schlumberger Technology Corp

Inventors

• Yu Yingwei
• Liu Qiuhua
• Meehan Richard John
• Chambon Sylvain
• Hamzah Mohammad Khairi

Classifications

• E21B44/00 Primary

  Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions · CPC title

• G01V2200/14

  Quality control · CPC title

• G01V1/50

  Analysing data · CPC title

• G06F30/27

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06N3/08

  Learning methods · CPC title