Granted Patent B2

US 12,387,307 · App. 17/974,241 · Granted Aug 12, 2025

Inventors: Abdulrahman Mohammed Alqahtani (Al Khobar, SA); Maher Hamed Alerwi (Dhahran, SA); Christian Canto Maya (Dhahran, SA)

Assignee: Saudi Arabian Oil Company

G06T7/0004G01N29/043G01N29/0609G01N29/069G06T7/10G06T7/50

Abstract

Claims (80)

1. A computer-implemented method comprising:

receiving an image collection of an area of a circumferential wall of a vessel, the image collection captured by ultrasonic testing along a thickness and a length of the circumferential wall, the image collection comprising a plurality of images distributed across the area, the plurality of images representing a respective plurality of cracks on the wall within the area;

identifying, from among the plurality of images, a plurality of subsets of images, each subset including at least two images of the plurality of images, cracks represented by images in a subset are adjacent each other;

for the at least two images in each subset of the plurality of subsets:

determining a plurality of distances, each distance determined between an end of an image in each subset and an end of each other image in the subset, and

determining, based on the determined plurality of distances, a crack intensity path for cracks in the subset, the crack intensity path representing a probability of a crack propagating through cracks represented by the at least two images in each subset;

determining, based on the crack intensity path determined for each subset of the plurality of subsets, an operation to be performed on the vessel;

providing the crack intensity as a percentage, wherein the operation to be performed on the vessel comprises:

planning a repair of the vessel in response to determining the crack intensity to be between 25% and 50%; or

scheduling immediate repair of the vessel in response to determining the crack intensity to be between 50% and 75%; or

shutting down the vessel in response to determining the crack intensity to be greater than 75%.

2. The computer-implemented method of claim 1 , wherein determining the crack intensity path comprises:

determining a total length of the cracks in the subset;

multiplying the total length of the cracks by a path angle factor represented by an angle between a line along the thickness of the circumferential wall and a line connecting two cracks that are farthest from each other in the subset; and

dividing a product of the total length and the path angle factor by a crack interaction path representing a total distance between ends of the two cracks that are farthest from each other in the subset.

3. The computer-implemented method of claim 1 , wherein for the at least two images in each subset of the plurality of subsets, determining the plurality of distances comprises:

identifying spatial coordinates of each end in the image collection; and

determining a plurality of differences corresponding to the plurality of distances, each difference being between a spatial coordinate of an end of an image in each subset and a spatial coordinate of an end of each other image in the subset.

4. The computer-implemented method of claim 1 , wherein identifying the plurality of subsets of images comprises identifying ends of each crack represented by each image, wherein identifying the ends of each crack comprises determining a difference in a color of a crack and a color of a portion of the area that excludes a crack.

5. The computer-implemented method of claim 1 , further comprising:

dividing the area into three regions, a first region being a sub-area near an outer surface of the circumferential wall, a third region being a sub-area near an inner surface of the circumferential wall, and a second region being a sub-area between the first region and the third region;

identifying, from among the plurality of images, an image representing a crack in the first region; and

identifying, from among the plurality of images, an image representing a crack in the third region.

6. The computer-implemented method of claim 5 , further comprising:

determining a shortest distance between an end of a crack in the first region and the outer surface of the circumferential wall, wherein the crack intensity path of a subset that includes a crack in the first region is determined based on the shortest distance between the end of the crack in the first region and the outer surface of the circumferential wall; and

determining a shortest distance between an end of a crack in the third region and the inner surface of the circumferential wall, wherein the crack intensity path of a subset that includes a crack in the third region is determined based on the shortest distance between the end of the crack in the third region and the inner surface of the circumferential wall.

7. A non-transitory computer-readable medium storing instructions executable by one or more processors to perform operations comprising:

receiving an image collection of an area of a circumferential wall of a vessel, the image collection captured by ultrasonic testing along a thickness and a length of the circumferential wall, the image collection comprising a plurality of images distributed across the area, the plurality of images representing a respective plurality of cracks on the wall within the area;

identifying, from among the plurality of images, a plurality of subsets of images, each subset including at least two images of the plurality of images, cracks represented by images in a subset are adjacent each other;

for the at least two images in each subset of the plurality of subsets:

determining a plurality of distances, each distance determined between an end of an image in each subset and an end of each other image in the subset, and

determining, based on the determined plurality of distances, a crack intensity path for cracks in the subset, the crack intensity path representing a probability of a crack propagating through cracks represented by the at least two images in each subset;

determining, based on the crack intensity path determined for each subset of the plurality of subsets, an operation to be performed on the vessel; and

providing the crack intensity as a percentage, wherein the operation to be performed on the vessel comprises:

planning a repair of the vessel in response to determining the crack intensity to be between 25% and 50%; or

scheduling immediate repair of the vessel in response to determining the crack intensity to be between 50% and 75%; or

shutting down the vessel in response to determining the crack intensity to be greater than 75%.

8. The non-transitory computer-readable medium of claim 7 , wherein determining the crack intensity path comprises:

determining a total length of the cracks in the subset;

multiplying the total length of the cracks by a path angle factor represented by an angle between a line along the thickness of the circumferential wall and a line connecting two cracks that are farthest from each other in the subset; and

dividing a product of the total length and the path angle factor by a crack interaction path representing a total distance between ends of the two cracks that are farthest from each other in the subset.

9. The non-transitory computer-readable of claim 7 , wherein for the at least two images in each subset of the plurality of subsets, determining the plurality of distances comprises:

identifying spatial coordinates of each end in the image collection; and

determining a plurality of differences corresponding to the plurality of distances, each difference being between a spatial coordinate of an end of an image in each subset and a spatial coordinate of an end of each other image in the subset.

10. The non-transitory computer-readable of claim 7 , wherein identifying the plurality of subsets of images comprises identifying ends of each crack represented by each image, wherein identifying the ends of each crack comprises determining a difference in a color of a crack and a color of a portion of the area that excludes a crack.

11. The non-transitory computer-readable of claim 7 , the operations further comprise:

dividing the area into three regions, a first region being a sub-area near an outer surface of the circumferential wall, a third region being a sub-area near an inner surface of the circumferential wall, and a second region being a sub-area between the first region and the third region;

identifying, from among the plurality of images, an image representing a crack in the first region; and

identifying, from among the plurality of images, an image representing a crack in the third region.

12. The non-transitory computer-readable of claim 11 , the operations further comprise:

determining a shortest distance between an end of a crack in the first region and the outer surface of the circumferential wall, wherein the crack intensity path of a subset that includes a crack in the first region is determined based on the shortest distance between the end of the crack in the first region and the outer surface of the circumferential wall; and

determining a shortest distance between an end of a crack in the third region and the inner surface of the circumferential wall, wherein the crack intensity path of a subset that includes a crack in the third region is determined based on the shortest distance between the end of the crack in the third region and the inner surface of the circumferential wall.

13. A system comprising:

one or more processors; and

a computer-readable medium storing instructions executable by the one or more processors to perform operations comprising:

receiving an image collection of an area of a circumferential wall of a vessel, the image collection captured by ultrasonic testing along a thickness and a length of the circumferential wall, the image collection comprising a plurality of images distributed across the area, the plurality of images representing a respective plurality of cracks on the wall within the area;

identifying, from among the plurality of images, a plurality of subsets of images, each subset including at least two images of the plurality of images, cracks represented by images in a subset are adjacent each other;

for the at least two images in each subset of the plurality of subsets:

determining a plurality of distances, each distance determined between an end of an image in each subset and an end of each other image in the subset, and

determining, based on the determined plurality of distances, a crack intensity path for cracks in the subset, the crack intensity path representing a probability of a crack propagating through cracks represented by the at least two images in each subset;

determining, based on the crack intensity path determined for each subset of the plurality of subsets, an operation to be performed on the vessel; and

providing the crack intensity as a percentage, wherein the operation to be performed on the vessel comprises:

planning a repair of the vessel in response to determining the crack intensity to be between 25% and 50%; or

scheduling immediate repair of the vessel in response to determining the crack intensity to be between 50% and 75%; or

shutting down the vessel in response to determining the crack intensity to be greater than 75%.

14. The system of claim 13 , wherein determining the crack intensity path comprises:

determining a total length of the cracks in the subset;

multiplying the total length of the cracks by a path angle factor represented by an angle between a line along the thickness of the circumferential wall and a line connecting two cracks that are farthest from each other in the subset; and

dividing a product of the total length and the path angle factor by a crack interaction path representing a total distance between ends of the two cracks that are farthest from each other in the subset.

15. The system of claim 13 , wherein for the at least two images in each subset of the plurality of subsets, determining the plurality of distances comprises:

identifying spatial coordinates of each end in the image collection; and

determining a plurality of differences corresponding to the plurality of distances, each difference being between a spatial coordinate of an end of an image in each subset and a spatial coordinate of an end of each other image in the subset.

16. The system of claim 13 , wherein identifying the plurality of subsets of images comprises identifying ends of each crack represented by each image, wherein identifying the ends of each crack comprises determining a difference in a color of a crack and a color of a portion of the area that excludes a crack.

17. The system of claim 13 , the operations further comprise:

dividing the area into three regions, a first region being a sub-area near an outer surface of the circumferential wall, a third region being a sub-area near an inner surface of the circumferential wall, and a second region being a sub-area between the first region and the third region;

identifying, from among the plurality of images, an image representing a crack in the first region; and

identifying, from among the plurality of images, an image representing a crack in the third region.

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

determining a shortest distance between an end of a crack in the first region and the outer surface of the circumferential wall, wherein the crack intensity path of a subset that includes a crack in the first region is determined based on the shortest distance between the end of the crack in the first region and the outer surface of the circumferential wall; and

determining a shortest distance between an end of a crack in the third region and the inner surface of the circumferential wall, wherein the crack intensity path of a subset that includes a crack in the third region is determined based on the shortest distance between the end of the crack in the third region and the inner surface of the circumferential wall.

Assignments (1)

Continuity (1)

References Cited (21)