Well plug integrity

Patent metadata

Field	Value
Publication number	US-2025369325-A1
Application number	US-202418928664-A
Country	US
Kind code	A1
Filing date	Oct 28, 2024
Priority date	May 30, 2024
Publication date	Dec 4, 2025
Grant date	—

Abstract

Some implementations include a method for predicting a plug leak in a wellbore during hydraulic fracturing operations. The method may include: generating a training data set including feature samples and prediction samples, wherein the feature samples include values derived from past pressure pulses in the well with or without other fracturing treatment data and the prediction samples include values derived from digital acoustic sensing (DAS) sensors located in the wellbore; training, with the training data set, a learning machine to predict the plug leak during the hydraulic fracturing operations based on pressure with or without other treatment data indicating one or more current pressure pulses.

First claim

What is claimed is:

1 . A method for predicting a plug leak in a wellbore during hydraulic fracturing operations, the method comprising:
generating a training data set including feature samples and prediction samples, wherein the feature samples include values derived from past pressure pulses in the well with or without other fracturing treatment data and the prediction samples include values derived from digital acoustic sensing (DAS) sensors located in the wellbore; training, with the training data set, a learning machine to predict the plug leak during the hydraulic fracturing operations based on pressure data indicating one or more current pressure pulses and with or without other treatment data.

2 . The method of claim 1 further comprising:
predicting, by the learning machine after the training, the plug leak in the wellbore based on the pressure data indicating one or more current pressure pulses in the wellbore with or without other treatment data.

3 . The method of claim 2 , wherein the current and past pressure pulses are water hammer pressure pulses arising from the hydraulic fracturing operations.

4 . The method of claim 2 further comprising:
determining, based on the pressure data, resistance in a stage of the wellbore, wherein the predicting the plug leak is based in part on the resistance.

5 . The method of claim 4 further comprising:
determining, based on the pressure data, characterization decay, characterization amplitude, characterization period, and friction factor, wherein the predicting the plug leak is based in part on the characterization decay, characterization amplitude, characterization period, and friction factor.

6 . The method of claim 2 further comprising:
determining a severity of the plug leak is beyond a severity threshold; and
modifying, by a controller in response to the plug leak being beyond the severity threshold, the hydraulic fracturing operations based on an inventory resources for hydraulic fracturing.

7 . The method of claim 1 , wherein one or more of the prediction samples include values deterministically estimated based on the past pressure pulses in the wellbore.

8 . A computer system comprising:
a processor; a learning machine including one or more non-transitory computer-readable mediums including instructions that, when executed by the processor, cause the processor to train learning machine to predict plug leaks in a wellbore during hydraulic fracturing operations, the instructions including
instructions to generate a training data set including feature samples and prediction samples, wherein the feature samples include values derived from past pressure pulses in the well and the prediction samples include values derived from digital acoustic sensing (DAS) sensors located in the wellbore;
instructions to train, with the training data set, a learning machine to predict the plug leaks during the hydraulic fracturing operations based on pressure data indicating one or more current pressure pulses.

9 . The computer system of claim 8 , the instructions further including:
instructions to predict, by the learning machine after the instructions to train are complete, a plug leak in the wellbore based on current pressure data indicating one or more current pressure pulses in the wellbore.

10 . The computer system of claim 9 , wherein the one or more current and past pressure pulses are water hammer pressure pulses arising from the hydraulic fracturing operations.

11 . The computer system of claim 8 , the instructions further including:
instructions to determine, based on the pressure data, resistance in a stage in the wellbore, wherein the prediction of the plug leak is based in part on the resistance.

12 . The computer system of claim 11 , the instructions further including:
instructions to determine, based on the pressure data, characterization decay, characterization amplitude, characterization period, and Darcey factor, wherein the prediction of the plug leak is based in part on the characterization decay, characterization amplitude, characterization period, and Darcey factor.

13 . The computer system of claim 8 , the instructions further including:
instructions to determine a severity of the plug leak is beyond a severity threshold; and instructions to modify, by a controller in response to the plug leak being beyond the severity threshold, the hydraulic fracturing operations based on an inventory resources for hydraulic fracturing.

14 . The computer system of claim 8 , wherein one or more of the prediction samples include values deterministically estimated based on the past pressure pulses in the wellbore.

15 . One or more non-transitory computer-readable mediums including instructions that, when executed by a processor, cause the processor to train learning machine to predict plug leaks in a wellbore during hydraulic fracturing operations, the instructions comprising:
instructions to generate a training data set including feature samples and prediction samples, wherein the feature samples include values derived from past pressure pulses in the well and the prediction samples include values derived from digital acoustic sensing (DAS) sensors located in the wellbore; instructions to train, with the training data set, a learning machine to predict the plug leaks during the hydraulic fracturing operations based on pressure data indicating one or more current pressure pulses.

16 . The one or more non-transitory computer-readable mediums of claim 15 , the instructions further including:
instructions to predict, by the learning machine after the instructions to train are complete, a plug leak in the wellbore based on pressure data indicating one or more current pressure pulses in the wellbore.

17 . The one or more non-transitory computer-readable mediums of claim 16 , wherein the one or more current and past pressure pulses are water hammer pressure pulses arising from the hydraulic fracturing operations.

18 . The one or more non-transitory computer-readable mediums of claim 17 , the instructions further including:
instructions to determine, based on the pressure data, resistance in a stage of the wellbore, wherein the predicting the plug leak is based in part on the resistance.

19 . The one or more non-transitory computer-readable mediums of claim 18 , the instructions further comprising:
instructions to determine, based on the pressure data, characterization decay, characterization amplitude, characterization period, and Darcey factor, wherein the predicting the plug leak is based in part on the characterization decay, characterization amplitude, characterization period, and Darcey factor.

20 . The one or more non-transitory computer-readable mediums of claim 18 , the instructions further comprising:
instructions to determine a severity of the plug leak is beyond a severity threshold; and instructions to modify, by a controller in response to the plug leak being beyond the severity threshold, the hydraulic fracturing operations based on an inventory resources for hydraulic fracturing.

Assignees

• Halliburton Energy Services Inc

Inventors

• Jeremic Aleksandar
• Shetty Dinesh Ananda
• Satti Rajani Prakash

Classifications

• E21B2200/20

  Computer models or simulations, e.g. for reservoirs under production, drill bits · CPC title

• E21B47/117

  Detecting leaks, e.g. from tubing, by pressure testing · CPC title

• E21B43/26 Primary

  by forming crevices or fractures · CPC title

• E21B2200/22

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

• E21B47/107 Primary

  using acoustic means · CPC title