Casing wear prediction using integrated physics-driven and data-driven models

• US 10,487,640 B2
• Filed: 10/17/2014
• Issued: 11/26/2019
• Est. Priority Date: 10/17/2014
• Status: Active Grant

• Current Assignee: Landmark Graphics Corporation (Halliburton Company)
• Original Assignee: Landmark Graphics Corporation (Halliburton Company)
• Inventors: Aniket, Samuel, Robello, Dursun, Serkan
• Primary Examiner(s): Ro, Yong-Suk
• Application Number:
  US15/509,357
• Publication Number:
  US 20170292362A1
• Time in Patent Office: 1,866 Days
• CPC Class Codes: E21B 44/00 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 Class Codes: E21B 47/007 Measuring stresses in a pipe string or casing for locating blocked portions of pipes E21B47/09
• CPC Class Codes: E21B 47/18 through the well fluid , e.g. mud pressure pulse telemetry
• CPC Class Codes: E21B 7/04 Directional drilling
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A casing wear estimation method includes obtaining a set of input parameters associated with extending a partially-cased borehole and applying the set of input parameters to a physics-driven model to obtain an estimated casing wear log. The method also includes employing a data-driven model to produce a predicted casing wear log based at least in part on the estimated casing wear log. The method also includes storing or displaying information based on the predicted casing wear log.

Claims

1. A casing wear estimation method that comprises:

obtaining a set of input parameters associated with extending a partially-cased borehole;

applying the set of input parameters to a physics-driven model to obtain an estimated casing wear log; and

employing a data-driven model to produce a predicted casing wear log based at least in part on said estimated casing wear log; and

storing or displaying information based on the predicted casing wear log.

2. The method of claim 1, further comprising training the data-driven model based on casing wear measurements associated with a previously drilled borehole.

3. The method of claim 1, further comprising training the data-driven model based on casing wear measurements associated with a borehole that is being drilled.

4. The method of claim 1, further comprising training the data-driven model based on at least one wellbore parameter.

5. The method of claim 1, further comprising training the data-driven model based on at least one drilling parameter.

6. The method of claim 1, wherein the data-driven model is regression-based.

7. The method of claim 1, further comprising comparing at least some of the predicted casing wear log to a predetermined threshold, and displaying a warning based on the comparison.

8. The method of claim 1, wherein said employing the data-driven model occurs during a wellbore planning phase, and wherein the method further comprises modifying a drilling plan based at least in part on the predicted casing wear log.

9. The method of claim 8, wherein:

the modified drilling plan includes at least one modified limit on at least one drilling parameter selected from the list consisting of weight on bit, rotation rate, rate of penetration, and torque; and

the modified drilling plan includes at least one modified parameter including modifying the well profile, changing the drilling parameters to reduce contact force, changing the materials properties, and the addition of drill pipe protection equipment.

10. The method of claim 1, wherein said employing the data-driven model occurs during a wellbore drilling phase, and wherein the method further comprises modifying a drilling parameter for a wellbore being drilled based at least in part on the predicted casing wear log, changing the drill string materials, and adding drill string protection equipment.

11. The method of claim 1, wherein the physics-driven model corresponds to at least one of a specific energy model, a linear wear-efficiency model, a non-linear casing wear model, a Hertzian model, an impact wear model, and a wellbore energy model.

12. The method of claim 1, wherein the predicted casing wear log is a function of at least one casing wear value selected from the list consisting of an eroded volume, a groove depth, a wall thickness, a safety margin, and a probability of integrity failure.

13. A casing wear estimation system that comprises:

at least one processor;

a memory in communication with the at least one processing and storing instructions that, when executed, causes the at least one processor to;

obtain a set of input parameters associated with extending a partially-cased borehole;

apply the set of input parameters to a physics-driven model to obtain an estimated casing wear log; and

employ a data-driven model to produce a predicted casing wear log based at least in part on said estimated casing wear log; and

store or display information based on the predicted casing wear log.

14. The system of claim 13, wherein the instructions further cause the at least one processor to train the data-driven model based on casing wear measurements associated with a previously drilled borehole.

15. The system of claim 13, wherein the instructions further cause the at least one processor to train the data-driven model based on casing wear measurements associated with a borehole that is being drilled.

16. The system of claim 13, wherein the instructions further cause the at least one processor to train the data-driven model based on at least one of a wellbore parameter and a drilling parameter.

17. The system of claim 13, wherein the instructions further cause the at least one processor to compare at least some of the predicted casing wear log to a predetermined threshold, and to display a warning based on the comparison.

18. The system of claim 13, wherein the instructions further cause the at least one processor to modify a drilling plan for a future wellbore based at least in part on the predicted casing wear log.

19. The system of claim 13, wherein the instructions further cause the at least one processor to modify a drilling parameter for a wellbore being drilled based at least in part on the predicted casing wear log.

20. A drilling system that comprises:

a processor configured to obtain an estimated casing wear log from a physics-driven model and a measured casing wear log associated with a first borehole segment, to train a data-driven model using the estimated casing wear log and the measured casing wear log, to acquire a subsequent estimated casing wear log from a physics-driven model, and to use the trained data-driven model and the subsequent estimated casing wear log to predict casing wear for a second borehole segment; and

at least one drilling component in communication with the processor, wherein the processor directs an operation of the at least one drilling component based on the predicted casing wear log.