Rig power system efficiency optimization through image processing

Patent metadata

Field	Value
Publication number	US-11727555-B2
Application number	US-202117185688-A
Country	US
Kind code	B2
Filing date	Feb 25, 2021
Priority date	Feb 25, 2021
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

Abstract

A method includes receiving, by a computer system, a video of a visible state of a component of a generator, the generator powering at least a portion of a rig equipment system at a wellsite. The computer system can determine an operational parameter based on the visible state of the component of the generator imaged in the video, and can transmit the operational parameter to an output device.

First claim

What is claimed is:

1. A method comprising:
receiving, by a computer system configured to implement a machine learning model, a video of a visible state of a component of a generator, the generator powering at least a portion of a rig equipment system at a wellsite;
determining, by the computer system, an operational parameter based on the visible state of the component of the generator imaged in the video, the determining the operational parameter comprises:
receiving, by the machine learning model, training data comprising historical images of the visible state of the component of the generator and historical measured operational parameters;
correlating, by the machine learning model, the historical images with corresponding historical measured operational parameters; and
determining, by the machine learning model, the operational parameter based on a comparison of the video of the visible state with the historical images; and

transmitting, by the computer system, the operational parameter to an output device.

2. The method of claim 1 , wherein the operational parameter is a percentage of a maximum revolutions-per-minute (RPM) of the generator.

3. The method of claim 1 , wherein the component of the generator is an exhaust flapper, and the visible state is a position of the exhaust flapper moving in response to an exhaust stream from the generator.

4. The method of claim 3 , wherein the positon of the exhaust flapper is determined based on a visible cross-sectional area of the exhaust flapper.

5. The method of claim 1 , wherein the generator is included in a generator bank comprising a plurality of generators, each comprising a respective component, the generator bank powering at least the portion of the rig equipment system at the wellsite, wherein the method further comprises:
receiving, by the computer system, a video of a plurality of visible states, the plurality of visible states comprising a visible state of the respective component of each of the plurality of generators;
determining, by the computer system, a respective operational parameter for each of the generators based on the plurality of visible states; and
determining, by the computer, a power availability status of the generator bank based on the respective operational parameter of each of the plurality of generators.

6. The method of claim 5 , further comprising:
determining, by the computer system, power demand parameters of a plurality of components of the portion of the rig equipment system;
transmitting, by the computer system, the power availability status of the generator bank and the power demand parameters to the output device; and
optimizing a power efficiency of the rig equipment system based on the power availability status of the generator bank and the power demand parameters.

7. The method of claim 1 , wherein a camera is disposed at or proximate to the wellsite; and further comprising:
capturing, by a camera, the video; and
transmitting the video to the computer system.

8. The method of claim 7 , wherein the transmitting is via a wireless connection.

9. The method of claim 1 , wherein the video comprises multiple images in sequence of the visible state of the component of the generator.

10. A system for optimizing the efficiency of a rig equipment system at a wellsite, the system comprising:
a camera configured to capture a video of a visible state of a component of a generator, the generator powering at least a portion of the rig equipment system; and
a computer system comprising one or more processors and a non-transitory computer-readable medium storing computer instructions executable by the one or more processors to perform operations, wherein the computer system is configured to implement a machine learning model and wherein the operations comprise:
receiving the video of the visible state of the component of a generator;
determining an operational parameter based on the visible state of the component of the generator imaged in the video; and
transmitting the operational parameter to an output device, wherein the machine learning model is configured to:
receive training data comprising historical images of the visible state of the component of the generator and historical measured operational parameters; and
correlate the historical images with corresponding historical measured operational parameters;

and wherein the determining the operational parameter based on the visible state comprises determining the operational parameter based on a comparison of the video of the visible state with the historical images.

11. The system of claim 10 , wherein the operational parameter is a percentage of a maximum revolutions-per-minute (RPM) of the generator.

12. The system of claim 10 , wherein the component of the generator is an exhaust flapper, and the visible state is a position of the exhaust flapper moving in response to an exhaust stream from the generator.

13. The system of claim 12 , wherein the position of the exhaust flapper is determined based on a visible cross-sectional area of the exhaust flapper.

14. The system of claim 10 , wherein the generator is included in a generator bank comprising a plurality of generators, each comprising a respective component, the generator bank powering at least the portion of the rig equipment system at the wellsite, wherein the operations further comprise:
receiving a video of a plurality of visible states, the plurality of visible states comprising a visible state of the respective component of each of the plurality of generators;
determining a respective operational parameter for each of the generators based on the plurality of visible states; and
determining a power availability status of the generator bank based on the respective operational parameter of each of the plurality of generators.

15. The system of claim 14 , wherein the operations further comprise:
determining power demand parameters of a plurality of components of the portion of the rig equipment system; and
transmitting the power availability status of the generator bank and the power demand parameters to the output device.

16. The system of claim 15 , wherein the output device comprises a display screen with a graphical user interface configured to display the power availability status of the generator bank and the power demand parameters of the plurality of components of the portion of the rig equipment system.

17. The system of claim 10 , wherein the video comprises multiple images in sequence of the visible state of the component of the generator.

18. The system of claim 10 , wherein the camera is configured to wirelessly transmit the video to the computer system.

19. A method comprising:
receiving, by a computer system, a video of a visible state of a component of a generator, the generator powering at least a portion of a rig equipment system at a wellsite, wherein the component of the generator is an exhaust flapper, and the visible state is a position of the exhaust flapper moving in response to an exhaust stream from the generator;
determining, by the computer system, an operational parameter based on the visible state of the component of the generator imaged in the video; and
transmitting, by the computer system, the operational parameter to an output device.

20. A method comprising:
receiving, by a computer system, a video of a plurality of visible states, the plurality of visible states comprising a visible state of a respective component of each of a plurality of generators

Assignees

• Saudi Arabian Oil Co

Inventors

• Affleck Michael
• Mora Arturo Magana
• Gooneratne Chinthaka Pasan
• Contreras Otalvora William

Classifications

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06T7/001 Primary

  using an image reference approach · CPC title

• G06N3/08

  Learning methods · CPC title