Granted Patent B2

US 12,359,554 · App. 17/201,618 · Granted Jul 15, 2025

Inventors: Damian Pablo San Roman Alerigi (Al-Khobar, SA); Weichang Li (Katy, TX); Sameeh Issa Batarseh (Dhahran, SA)

Assignee: Saudi Arabian Oil Company

E21B47/0025E21B49/00G01N21/47G01N33/24G01N2021/4709G01N2021/4792

Abstract

Claims (64)

1. A method comprising:

irradiating a target surface with a process beam from a laser source during a drilling process;

in response to irradiating with the process beam, receiving, using a lens-coupler assembly, a signal beam that contains light scattered from the target surface as well as light radiating from the target surface;

splitting, using a beam splitter, the signal beam into a first portion on a first arm and a second portion on a second arm, wherein the first portion is further split, by a polarized beam splitter on the first arm, into a first sub-portion of circularly left polarized light and a second sub-portion of circularly right polarized light, and wherein the second portion of the signal beam is unpolarized on the second arm;

performing, on the first arm, a first plurality of intensity and spectrum measurements of the first sub-portion of circularly left polarized light and the second sub-portion of circularly right polarized light, using a device selected from a radiometer sensor and a spectrometer;

performing, on the second arm, a second plurality of intensity and spectrum measurements of the second portion using a device selected from a spectrometer, a charge-coupled device, and a complementary metal-oxide-semiconductor sensor, or any combination thereof; and

determining, using a controller device that is in communication with the laser source, the first arm, and the second arm, a classification of the target surface based on applying, by the controller device, one or more machine learning techniques to at least portions of (i) the first plurality of intensity and spectrum measurements, and (ii) the second plurality of intensity and spectrum measurements.

2. The method of claim 1 , further comprising:

determining a status of the drilling process; and

predicting at least one of: a type of an incoming rock, an outcome of the drilling process, a parameter for performing the first plurality of polarization-dependent intensity and spectrum measurements, or a parameter for performing the second plurality of intensity and spectrum measurements.

3. The method of claim 1 , wherein the one or more machine learning techniques comprise:

identifying a first set of features from the first plurality of intensity and spectrum measurements and a second set of features from the second plurality of intensity and spectrum measurements; and

combining the first set of features and the second set of features in determining the classification of the target surface.

4. The method of claim 3 , further comprising:

establishing a database of the first set of features and the second set of features, wherein the first set of features and the second set of features in combination differentiate two or more types of the target surface.

5. The method of claim 4 , further comprising:

applying the database while applying the one or more machine learning techniques to the at least portions of (i) the first plurality of intensity and spectrum measurements, and (ii) the second plurality of intensity and the spectrum measurements.

6. The method of claim 1 , wherein the one or more machine learning techniques include: a boosting technique, a K-means clustering technique, and a Support Vector Machine (SVM) technique.

7. The method of claim 1 , further comprising:

visualizing the classification of the target surface using a t-distribution stochastic neighbor embedding (tSNE) technique.

8. The method of claim 1 , wherein the first plurality of polarization-dependent intensity and spectrum measurements comprise first intensity measurements on a first branch and second intensity measurements on a second branch,

wherein the first and second intensity measurements are cross-polarized, and

wherein the first and second branches originate from a polarization beam splitter on the polarization arm.

9. The method of claim 1 , further comprising:

capturing, on the non-polarization arm, a plurality of images based on the second portion of the signal beam; and

determining a luminosity based on a histogram of the plurality of images.

10. The method of claim 9 , further comprising:

applying the one or more machine learning techniques to the luminosity in addition to the at least portions of (i) the first plurality of polarization-dependent intensity and spectrum measurements, and (ii) the second plurality of intensity and spectrum measurements; and

based on results from the one or more machine learning techniques, determining at least one of: a classification of the target surface and a status of the drilling process.

11. A high-power laser system comprising:

an optical system that includes:

a laser source that emits a process beam;

a first arm that receives a portion of a signal beam, the first arm comprising a polarizing beam splitter; and

a second arm that receives another portion of the signal beam; and

an analyzer in communication with optical system, wherein the analyzer receives measurement data from the optical system,

wherein the high-power laser system is configured to perform operations of:

irradiating a target surface with a process beam from the laser source during a drilling process;

in response to irradiating with the process beam, receiving, using a lens-coupler assembly, a signal beam that contains light scattered from the target surface as well as light radiating from the target surface;

splitting, using a beam splitter, the signal beam into a first portion on a first arm and a second portion on a second arm, wherein the first portion is further split, by the polarized beam splitter on the first arm, into a first sub-portion of circularly left polarized light and a second sub-portion of circularly right polarized light, and wherein the second portion of the signal beam is unpolarized on the second arm;

performing, on the first arm, a first plurality of intensity and spectrum measurements of the first sub-portion of circularly left polarized light and the second sub-portion of circularly right polarized light, using a device selected from a radiometer sensor and a spectrometer;

performing, on the second arm, a second plurality of intensity and spectrum measurements of the second portion using a device selected from a spectrometer, a charge-coupled device, and a complementary metal-oxide-semiconductor sensor, or any combination thereof; and

determining, using a controller device that is in communication with the laser source, the first arm, and the second arm, a classification of the target surface based on applying, by the controller device, one or more machine learning techniques to at least portions of (i) the first plurality of intensity and spectrum measurements, and (ii) the second plurality of intensity and spectrum measurements.

12. The system of claim 11 , wherein the operations further comprise:

determining a status of the drilling process; and

predicting at least one of: a type of an incoming rock, an outcome of the drilling process, a parameter for performing the first plurality of polarization-dependent intensity and spectrum measurements, or a parameter for performing the second plurality of intensity and spectrum measurements.

13. The high-power laser system of claim 11 , wherein the one or more machine learning techniques comprise:

identifying a first set of features from the first plurality of intensity and spectrum measurements and a second set of features from the second plurality of intensity and spectrum measurements; and

combining the first set of features and the second set of features in determining the classification of the target surface.

14. The high-power laser system of claim 13 , wherein the operations further comprise:

establishing a database of the first set of features and the second set of features, wherein the first set of features and the second set of features in combination differentiate two or more types of the target surface.

15. The high-power laser system of claim 14 , wherein the operations further comprise:

applying the database while applying the one or more machine learning techniques to the at least portions of (i) the first plurality of intensity and spectrum measurements, and (ii) the second plurality of intensity and spectrum measurements.

16. The high-power laser system of claim 11 , wherein the one or more machine learning techniques include: a boosting technique, a K-means clustering technique, and a Support Vector Machine (SVM) technique.

17. The system of claim 11 , wherein the operations further comprise:

visualizing the classification of the target surface using a t-distribution stochastic neighbor embedding (tSNE) technique.

18. The system of claim 11 , wherein the first plurality of polarization-dependent intensity and spectrum measurements comprise first intensity measurements on a first branch and second intensity measurements on a second branch,

wherein the first and second intensity measurements are cross-polarized, and

wherein the first and second branches originate from a polarization beam splitter on the polarization arm.

19. The system of claim 11 , wherein the operations further comprise:

capturing, on the non-polarization arm, a plurality of images based on the second portion of the signal beam; and

determining a luminosity based on a histogram of the plurality of images.

20. The system of claim 19 , wherein the operations further comprise:

applying the one or more machine learning techniques to the luminosity in addition to the first plurality of polarization-dependent intensity and spectrum measurements, and the second plurality of intensity and spectrum measurements; and

based on results from the one or more machine learning techniques, determining at least one of: a classification of the target surface and a status of the drilling process.

Assignments (4)

Continuity (1)

References Cited (43)