Life-time management of downhole tools and components

Patent metadata

Field	Value
Publication number	US-10876926-B2
Application number	US-201715859054-A
Country	US
Kind code	B2
Filing date	Dec 29, 2017
Priority date	Oct 10, 2013
Publication date	Dec 29, 2020
Grant date	Dec 29, 2020

Abstract

Systems, methods and devices for evaluating a condition of a downhole component of a drillstring. Methods include estimating a value of a tool parameter of the component at at least one selected position on the drillstring; and using the estimated value to evaluate the condition of the downhole component. The estimating is done using a trained artificial neural network that receives information from at least one sensor that is positionally offset from the selected position. The method may further include creating a record representing information from estimated values of the tool parameter at the at least one selected position over time. The at least one selected position may include a plurality of positions, such as positions at intervals along the component, including substantially continuously along the component.

First claim

We claim:

1. A method for evaluating a condition of a downhole component of a drillstring, the method comprising:
estimating a plurality of temperature values of the component at a plurality of positions comprising at least a first temperature value at a first selected position on the drillstring and a second temperature value different than the first temperature value at a second selected position on the drillstring different than the first selected position, the estimating comprising:
using at least one temperature sensor to provide temperature information to a trained artificial neural network, and;
using the trained artificial neural network to estimate the plurality of temperature values of the component at the plurality of positions using the temperature information as input; and

using at least one of the estimated plurality of values to evaluate the condition of the downhole component;
wherein each temperature sensor used is positionally offset from each of the plurality of positions.

2. The method of claim 1 further comprising creating a record representing information from estimated temperature values at the first selected position and the second selected position over time.

3. The method of claim 1 wherein the plurality of positions comprises a plurality of positions substantially continuously along the component.

4. The method of claim 1 wherein the at least one temperature sensor is positionally offset by at least half of the axial length of the component from at least one of: i) the first selected position, and ii) the second selected position.

5. The method of claim 1 , wherein the information received from the at least one temperature sensor is at least one other temperature value measured at the at least one sensor.

6. The method of claim 1 further comprising creating a record representing information from estimated vibration parameter values at the first selected position and the second selected position over time.

7. The method of claim 1 wherein the plurality of positions comprises a plurality of positions substantially continuously along the component.

8. The method of claim 1 wherein the at least one vibration sensor is positionally offset by at least half of the axial length of the component from at least one of: i) the first selected position, and ii) the second selected position.

9. The method of claim 1 , wherein the information received from the at least one vibration sensor is at least one other vibration parameter value measured at the at least one sensor.

10. The method of claim 1 wherein using the trained artificial neural network to estimate the plurality of temperature values of the component at the plurality of positions using the temperature information as input further comprises:
accepting the temperature information as input to an input layer;
providing a weighted combination of outputs of the input layer to at least one hidden layer; and
providing an other weighted combination of outputs from one of the at least one hidden layer to an output layer, wherein the output layer provides the plurality of temperature values of the component at the plurality of positions.

11. A method for evaluating a condition of a downhole component of a drillstring, the method comprising:
estimating a plurality of vibration parameter values of the component at a plurality of positions comprising at least a first vibration parameter value at a first selected position on the drillstring and a second vibration parameter value different than the first vibration parameter value at a second selected position on the drillstring different than the first selected position, the estimating comprising:
using at least one vibration sensor to provide vibration information to a trained artificial neural network, and;
using the trained artificial neural network to estimate the plurality of vibration parameter values of the component at the plurality of positions using the vibration information as input; and

using at least one of the estimated plurality of vibration parameter values to evaluate the condition of the downhole component;
wherein each vibration sensor used is positionally offset from each of the plurality of positions.

12. A method for evaluating a condition of a downhole component of a drillstring, the method comprising:
estimating a plurality of values of a first tool parameter of the component at a plurality of positions comprising at least a first value of a first tool parameter at a first selected position on the drillstring and a second value of the first tool parameter different than the first value of a first tool parameter at a second selected position on the drillstring different than the first selected position, the estimating comprising:
using at least one first tool parameter sensor to provide first tool parameter information to a trained artificial neural network, and;
using the trained artificial neural network to estimate the plurality of values of the first tool parameter of the component at the plurality of positions using the first tool parameter information as input; and

using at least one of the estimated plurality of values to evaluate the condition of the downhole component;
wherein each first tool parameter sensor used is positionally offset from each of the plurality of positions, wherein the first tool parameter comprises at least one parameter selected from the group comprising: i) a vibration parameter; ii) a temperature; and iii) a pressure.

13. The method of claim 12 further comprising:
using at least one second tool parameter sensor to provide second tool parameter information to a trained artificial neural network, and;
using the trained artificial neural network to estimate the plurality of values of the first tool parameter of the component at the plurality of positions using the second tool parameter information as input.

14. The method of claim 12 wherein the at least one first tool parameter sensor is positionally offset by at least half of the axial length of the component from at least one of: i) the first selected position, and ii) the second selected position.

15. The method of claim 12 , wherein the first tool parameter comprises a characteristic of a state of a downhole component as it is being used in drilling operations downhole.

16. The method of claim 12 wherein the first tool parameter comprises at least one parameter selected from the group comprising: i) a vibration parameter; and ii) a temperature.

17. The method of claim 12 , wherein the condition is at least one of: i) material fatigue of the component; and ii) estimated remaining useful life of the component.

18. The method of claim 12 , further comprising making a component life management decision about the component using the condition.

19. The method of claim 13 wherein each second tool parameter sensor used is positionally offset from each of the plurality of positions.

20. The method of claim 13 , wherein the first tool parameter is temperature and the second tool parameter is a vibration parameter.

21. A system for evaluating a condition of a downhole component of a drillstring in a borehole using at least one tool parameter sensor on the drillstring, the system comprising:
at least one processor configured to:
estimate a plurality of values of a first tool parameter of the component at a plurality of positions comprising at least a first value of a first tool parameter at a first selected position on the drillstring and a second value of the fi

Assignees

• Baker Hughes A Ge Co Llc
• Baker Hughes Holdings Llc

Inventors

• Dashevskiy Dmitriy
• Macpherson John D

Classifications

• G01M13/00 Primary

  Testing of machine parts · CPC title

• 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

• E21B2200/22

  Fuzzy logic, artificial intelligence, neural networks or the like · CPC title

• E21B41/00 Primary

  Equipment or details not covered by groups E21B15/00 - E21B40/00 · CPC title