IP Library › Granted Patent US 12,608,790
Granted Patent B2
US 12,608,790 · App. 18/467,086 · Granted Apr 21, 2026

Analyzing mechanical components

Inventors: Sheldon McCrackin (Yukon, OK); Yandong Wang (Camillus, NY)
Assignee: Baker Hughes Holdings LLC
G06T7/001G06T7/33G06T2207/20212G06T2207/30164
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,608,790
App. No.
18/467,086
Granted
Apr 21, 2026
Kind
B2
Abstract

Data, characterizing a first image and plurality of 3D surface points characterizing a mechanical component before a repair has been performed on the mechanical component and after a repair has been performed on the mechanical component, is received. A second set of data is determined based on combining the received data. The second set of data characterizes an image and dimensions of the mechanical component before and after a repair has been performed on the component. A location of a work area and a size of the work area before and after the repair has been performed on the component is determined based on the second set of data. The second set of data and the determined location and size of the work area before and after the repair has been performed on the component.

Claims (58)

1 . A method comprising:

receiving data characterizing a first image and plurality of 3D surface points characterizing a mechanical component before a repair has been performed on the mechanical component, and a second image and plurality of 3D surface points characterizing the mechanical component after a repair has been performed on the mechanical component, wherein the repair comprises removing material from, or adding material to, the component, wherein the first and second images are acquired using an image sensor, and the 3D surface points characterizing the mechanical component before and after the repair are derived from images acquired using the image sensor;

determining a second set of data based on combining the received data, the second set of data characterizing an image and dimensions of the mechanical component before and after a repair has been performed on the component, wherein determining the second set of data comprises:

determining a 3D transformation to align the mechanical component as characterized by the first plurality of 3D surface points and the mechanical component as characterized by the second plurality of 3D surface points;

determining a first plurality of aligned 3D surface points and a second plurality of aligned 3D surface points using the 3D transformation

identifying features within the first image and the second image;

matching the features between the first image and the second image;

determining a 3D transformation matrix, wherein determining the first plurality of aligned 3D surface points and the second plurality of aligned 3D surface points using the 3D transformation comprises multiplying the 3D transformation matrix with the first or second plurality of 3D surface points; and

spatially transforming the first image to align with the second image, producing a transformed image;

determining a location of a work area and a size of the work area before the repair has been performed on the component and after the repair has been performed on the component, based on the second set of data; and

providing the second set of data and the determined location and size of the work area before the repair has been performed on the component and after the repair has been performed on the component.

2 . The method of claim 1 , further comprising repairing the mechanical component.

3 . The method of claim 1 , wherein the mechanical component includes a turbine blade or a weld.

4 . The method of claim 1 , wherein receiving the data comprises:

acquiring the data from a borescope positioned within a mechanical system.

5 . The method of claim 1 , wherein identifying features within the first image and the second image comprises identifying points indicative of the work area, wherein determining the location and the size comprises:

identifying features indicative of edges of the mechanical component; and

measuring a distance between the features indicative of the work area and the features indicative of the edges of the mechanical component.

6 . The method of claim 5 , wherein measuring a distance comprises measuring a plurality of distances, the method further comprising:

comparing the plurality of measured distances between the mechanical component before the repair and the mechanical component after repair;

determine an amount of material added or removed during the repair based on the comparison; and

provide the determined amount of material added or removed.

7 . The method of claim 1 , wherein providing the second set of data and the determined location and size comprises displaying an image.

8 . A system comprising:

at least one data processor; and

non-transitory memory storing instructions, which, when executed by the at least one data processor causes the at least one data processor to perform operations comprising:

receiving data characterizing a first image and plurality of 3D surface points characterizing a mechanical component before a repair has been performed on the mechanical component, and a second image and plurality of 3D surface points characterizing the mechanical component after a repair has been performed on the mechanical component, wherein the repair comprises removing material from, or adding material to, the component, wherein the first and second images are acquired using an image sensor, and the 3D surface points characterizing the mechanical component before and after the repair are derived from images acquired using the image sensor;

determining a second set of data based on combining the received data, the second set of data characterizing an image and dimensions of the mechanical component before and after a repair has been performed on the component, wherein determining the second set of data comprises:

determining a 3D transformation to align the mechanical component as characterized by the first plurality of 3D surface points and the mechanical component as characterized by the second plurality of 3D surface points;

determining a first plurality of aligned 3D surface points and a second plurality of aligned 3D surface points using the 3D transformation

identifying features within the first image and the second image;

matching the features between the first image and the second image;

determining a 3D transformation matrix, wherein determining the first plurality of aligned 3D surface points and the second plurality of aligned 3D surface points using the 3D transformation comprises multiplying the 3D transformation matrix with the first or second plurality of 3D surface points; and

spatially transforming the first image to align with the second image, producing a transformed image;

determining a location of a work area and a size of the work area before the repair has been performed on the component and after the repair has been performed on the component, based on the second set of data; and

providing the second set of data and the determined location and size of the work area before the repair has been performed on the component and after the repair has been performed on the component.

9 . The system, of claim 8 , wherein the mechanical component comprises a turbine blade.

10 . The system, of claim 8 , wherein the mechanical component comprises a weld.

11 . The system of claim 8 , wherein receiving the data comprises:

acquiring the data from a borescope positioned within a mechanical system.

12 . The system of claim 8 , wherein identifying features within the first image and the second image comprises identifying points indicative of the work area, wherein determining the location and the size comprises:

identifying features indicative of edges of the mechanical component; and

measuring a distance between the features indicative of the work area and the features indicative of the edges of the mechanical component.

13 . The system of claim 8 , wherein providing the second set of data and the determined location and size comprises displaying an image.

14 . A non-transitory computer readable memory storing instructions which, when executed by at least one data processor forming part of at least one computing system, causes the at least one data processor to perform operations comprising:

receiving data characterizing a first image and plurality of 3D surface points characterizing a mechanical component before a repair has been performed on the mechanical component, and a second image and plurality of 3D surface points characterizing the mechanical component after a repair has been performed on the mechanical component, wherein the repair comprises removing material from, or adding material to, the component, wherein the first and second images are acquired using an image sensor, and the 3D surface points characterizing the mechanical component before and after the repair are derived from images acquired using the image sensor;

determining a second set of data based on combining the received data, the second set of data characterizing an image and dimensions of the mechanical component before and after a repair has been performed on the component, wherein determining the second set of data comprises:

determining a 3D transformation to align the mechanical component as characterized by the first plurality of 3D surface points and the mechanical component as characterized by the second plurality of 3D surface points;

determining a first plurality of aligned 3D surface points and a second plurality of aligned 3D surface points using the 3D transformation

identifying features within the first image and the second image;

matching the features between the first image and the second image;

determining a 3D transformation matrix, wherein determining the first plurality of aligned 3D surface points and the second plurality of aligned 3D surface points using the 3D transformation comprises multiplying the 3D transformation matrix with the first or second plurality of 3D surface points; and

spatially transforming the first image to align with the second image, producing a transformed image;

determining a location of a work area and a size of the work area before the repair has been performed on the component and after the repair has been performed on the component, based on the second set of data; and

providing the second set of data and the determined location and size of the work area before the repair has been performed on the component and after the repair has been performed on the component.

15 . The non-transitory computer readable memory of claim 14 , wherein the mechanical component includes a turbine blade or a weld.

16 . The non-transitory computer readable memory of claim 14 , wherein receiving the data comprises:

acquiring the data from a borescope positioned within a mechanical system.

Assignments (2)
CHANGE OF ADDRESS DECLARATION Recorded Jul 30, 2026
From: BAKER HUGHES HOLDINGS LLC
To: BAKER HUGHES HOLDINGS LLC
Reel/Frame 076080/0804 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 31, 2023
From: MCCRACKIN, SHELDON; WANG, YANDONG
To: BAKER HUGHES HOLDINGS LLC
Reel/Frame 065401/0547 →
Continuity (1)
Related Publication 20250095136A1 · Mar 20, 2025
References Cited (9)
US 20180339720A1 · Singh · 2018 [cited by examiner]
US 20220135254A1 · Graham et al. · 2022 [cited by applicant]
US 20220236197A1 · Wang · 2022 [cited by examiner]
US 20230264302A1 · Okuma · 2023 [cited by examiner]
CN 106141435A · 2016 [cited by applicant]
CN 116511727A · 2023 [cited by applicant]
JP 2013145202A · 2013 [cited by examiner]
WO 2023089764A1 · 2023 [cited by applicant]
International Search Report dated Dec. 19, 2024 for International Application No. PCT/US2024/045565, filed Sep. 6, 2024 (3 pgs). [cited by applicant]