Threaded connection evaluation with machine learning

Patent metadata

Field	Value
Publication number	US-2026087405-A1
Application number	US-202418908014-A
Country	US
Kind code	A1
Filing date	Oct 7, 2024
Priority date	Sep 23, 2024
Publication date	Mar 26, 2026
Grant date	—

Abstract

A method for evaluating threaded connections can include transmitting model parameters from one artificial intelligence to another intelligence, inputting torque and rotation measurements to the second artificial intelligence, and updating the first artificial intelligence using data transmitted from a job location. An apparatus for evaluating threaded connections can include a first artificial intelligence trained to predict threaded connection quality, and a second artificial intelligence configured to receive model parameters from the first artificial intelligence, the second artificial intelligence being configured to predict threaded connection quality while the second artificial intelligence is not in communication with the first artificial intelligence.

First claim

What is claimed is:

1 .A method of evaluating threaded connections for use with a subterranean well, the method comprising:
training a first artificial intelligence on a central server to predict threaded connection quality; transmitting model parameters from the first artificial intelligence to a second artificial intelligence; transporting the second artificial intelligence to a job location remote from the central server; inputting torque and rotation measurements to the second artificial intelligence, the second artificial intelligence thereby predicting a quality of a threaded connection at the job location; transmitting data from the job location to the central server; and updating the first artificial intelligence using the data transmitted from the job location.

2 .The method of claim 1 , further comprising, after the updating, transmitting updated model parameters from the first artificial intelligence to the second artificial intelligence.

3 .The method of claim 1 , further comprising training the second artificial intelligence using the torque and rotation measurements and the predicted quality of the threaded connection.

4 .The method of claim 1 , in which the predicting is performed while the second artificial intelligence is not in communication with the first artificial intelligence.

5 .The method of claim 1 , in which the predicting is performed while the job location is not connected via Internet with the central server.

6 .The method of claim 1 , in which the inputting comprises inputting environmental measurements to the second artificial intelligence.

7 .The method of claim 6 , in which the environmental measurements are selected from the group consisting of temperature, humidity and salt content.

8 .The method of claim 1 , in which the inputting comprises inputting job information to the second artificial intelligence.

9 .The method of claim 8 , in which the job information is selected from the group consisting of thread diameter, thread type, insertion depth, material and lubrication.

10 .The method of claim 1 , in which the inputting comprises inputting historical data to the second artificial intelligence.

11 .An apparatus for evaluating threaded connections for use with a subterranean well, the apparatus comprising:
a first artificial intelligence trained to predict threaded connection quality; a second artificial intelligence configured to receive model parameters from the first artificial intelligence, whereby the second artificial intelligence is capable of predicting threaded connection quality, and in which the second artificial intelligence is configured to predict threaded connection quality while the second artificial intelligence is not in communication with the first artificial intelligence.

12 .The apparatus of claim 11 , further comprising a torque sensor, and a rotation sensor, and in which the second artificial intelligence is configured to predict threaded connection quality in response to input of measurements from the torque and rotation sensors.

13 .The apparatus of claim 11 , in which the second artificial intelligence is configured to predict threaded connection quality in response to input of torque and rotation measurements in real time during a threaded connection make-up process.

14 .The apparatus of claim 11 , in which the second artificial intelligence is configured to predict threaded connection quality further in response to input of environmental measurements.

15 .The apparatus of claim 14 , in which the environmental measurements are selected from the group consisting of temperature, humidity and salt content.

16 .The apparatus of claim 11 , in which the second artificial intelligence is configured to predict threaded connection quality further in response to input of job information to the second artificial intelligence.

17 .The apparatus of claim 16 , in which the job information is selected from the group consisting of thread diameter, thread type, insertion depth, material and lubrication.

18 .The apparatus of claim 11 , in which the second artificial intelligence is configured to predict threaded connection quality while the second artificial intelligence is not connected via Internet with the first artificial intelligence.

19 .The apparatus of claim 11 , in which the first artificial intelligence is configured to receive job data from the second artificial intelligence.

20 .The apparatus of claim 19 , in which the first artificial intelligence is further configured to update the model parameters in response to input of the job data to the first artificial intelligence.

Assignees

• Weatherford Tech Holdings Llc

Inventors

• Ruehmann Rainer
• Sachtleben Benjamin
• Geissler David

Classifications

• E21B19/166

  Arrangements of torque limiters or torque indicators · CPC title

• E21B2200/22

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

• G06N20/00 Primary

  Machine learning · CPC title