Drilling control

Patent metadata

Field	Value
Publication number	US-11828155-B2
Application number	US-202016776373-A
Country	US
Kind code	B2
Filing date	Jan 29, 2020
Priority date	May 21, 2019
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

A method can include receiving sensor data during drilling of a portion of a borehole in a geologic environment; determining a drilling mode from a plurality of drilling modes using a trained neural network and at least a portion of the sensor data; and issuing a control instruction for drilling an additional portion of the borehole using the determined drilling mode.

First claim

What is claimed is:

1. A method comprising:
receiving sensor data by a computing system during drilling of a portion of a borehole in a geologic environment;
using the computing system, determining a drilling mode from a plurality of drilling modes based on a decision of a trained neural network generated by a reinforcement learning framework, wherein the decision is based on at least a portion of the sensor data, wherein the plurality of drilling modes comprises a rotary drilling mode and a sliding drilling mode, and wherein the trained neural network embodies a penalty for the sliding drilling mode in comparison to the rotary drilling mode, a penalty for a rotary drilling mode to sliding drilling mode transition, and a reward for forward drilling; and
using the computing system, responsive to the determined drilling mode being different than a current drilling mode for the drilling of the portion of the borehole, transitioning the current drilling mode to the determined drilling mode for drilling an additional portion of the borehole.

2. The method of claim 1 , wherein the plurality of drilling modes comprises a sliding up drilling mode and a sliding down drilling mode.

3. The method of claim 1 , comprising determining a toolface orientation from a plurality of toolface orientations using the trained neural network and at least a portion of the sensor data.

4. The method of claim 3 , wherein issuing the control instruction comprises issuing an instruction for using the determined toolface orientation.

5. The method of claim 1 , comprising determining a tool survey interval from a plurality of tool survey intervals using the trained neural network and at least a portion of the sensor data.

6. The method of claim 5 , wherein issuing the control instruction comprises issuing an instruction for using the determined tool survey interval.

7. The method of claim 1 , wherein the control instruction for drilling the additional portion of the borehole corresponds to drilling a length of pipe.

8. The method of claim 1 , comprising drilling the additional portion of the borehole.

9. The method of claim 1 , comprising issuing an application programming interface call using at least a portion of the sensor data and receiving the drilling mode in response to the application programming interface call.

10. The method of claim 1 , wherein the determining the drilling mode comprises defining a coordinate system for a portion of a drillstring using at least a portion of the sensor data.

11. The method of claim 10 , wherein the sensor data comprise an inclination of the portion of the drillstring and wherein the coordinate system comprises an axial direction defined using the inclination.

12. The method of claim 10 , wherein the coordinate system is a two-dimensional coordinate system and wherein the plurality of drilling modes comprises a sliding up drilling mode and a sliding down drilling mode.

13. The method of claim 10 , wherein the coordinate system is a three-dimensional coordinate system, and further comprising determining a toolface orientation using the trained neural network and at least a portion of the sensor data.

14. The method of claim 1 , wherein the receiving the sensor data during drilling of the portion of the borehole in the geologic environment comprises performing a survey using sensors of a drillstring that is utilized to perform the drilling wherein the sensors acquire the sensor data.

15. The method of claim 14 , further comprising determining a survey interval using the trained neural network and at least a portion of the sensor data and performing a subsequent survey according to the determined survey interval using the sensors of the drillstring.

16. The method of claim 1 , comprising receiving a planned trajectory for the borehole wherein the determining the drilling mode is based at least in part on the planned trajectory.

17. A system comprising:
a processor;
memory accessible to the processor;
processor-executable instructions stored in the memory and executable by the processor to instruct the system to:
receive sensor data during drilling of a portion of a borehole in a geologic environment;
determine a drilling mode from a plurality of drilling modes based on a decision of a trained neural network generated by a reinforcement learning framework, wherein the decision is based on at least a portion of the sensor data, wherein the plurality of drilling modes comprises a rotary drilling mode and a sliding drilling mode, and wherein the trained neural network embodies a penalty for the sliding drilling mode in comparison to the rotary drilling mode, a penalty for a rotary drilling mode to sliding drilling mode transition, and a reward for forward drilling; and

responsive to the determined drilling mode being different than a current drilling mode for the drilling of the portion of the borehole, transition the current drilling mode to the determined drilling mode for drilling an additional portion of the borehole using the determined drilling mode.

18. One or more computer-readable storage media comprising computer-executable instructions executable to instruct a computing system to:
receive sensor data during drilling of a portion of a borehole in a geologic environment;
determine a drilling mode from a plurality of drilling modes based on a decision of a trained neural network generated by a reinforcement learning framework, wherein the decision is based on at least a portion of the sensor data, wherein the plurality of drilling modes comprises a rotary drilling mode and a sliding drilling mode, and wherein the trained neural network embodies a penalty for the sliding drilling mode in comparison to the rotary drilling mode, a penalty for a rotary drilling mode to sliding drilling mode transition, and a reward for forward drilling; and
responsive to the determined drilling mode being different than a current drilling mode for the drilling of the portion of the borehole, transition the current drilling mode to the determined drilling mode for drilling an additional portion of the borehole using the determined drilling mode.

Assignees

• Schlumberger Technology Corp

Inventors

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

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

• E21B7/04

  Directional drilling · CPC title

• E21B47/024

  of devices in the borehole (determining slope or direction of the borehole E21B47/022) · CPC title

• E21B47/12 Primary

  Means for transmitting measuring-signals or control signals from the well to the surface, or from the surface to the well, e.g. for logging while drilling · CPC title

• E21B2200/22

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