Method for inspecting an object

Patent metadata

Field	Value
Publication number	US-12586226-B2
Application number	US-202117373925-A
Country	US
Kind code	B2
Filing date	Jul 13, 2021
Priority date	Jul 13, 2021
Publication date	Mar 24, 2026
Grant date	Mar 24, 2026

Abstract

A method for inspecting an object includes determining a first inspection package that includes a first inspection image of the object and a first designation. The method includes determining data indicative of a second inspection package that includes a second inspection image of the object and a second designation. The method includes determining a first property of the object based on the first inspection image of the object, one or more properties maps of the object, and the first designation. The method includes determining a second property of the object based on the second inspection image of the object, the one or more properties maps of the object, and the second designation. The method includes displaying the first property and the second property or displaying data indicative of a comparison of the first property with the second property.

First claim

We claim:

1 . A method for inspecting an object, the method comprising:
determining a first inspection package that includes a first inspection image of the object and a first designation, wherein the first inspection image includes one or more first inspection image pixel arrays including a location of the one or more first inspection image pixel arrays; determining data indicative of a second inspection package that includes a second inspection image of the object and a second designation, wherein the second inspection image includes one or more second inspection image pixel arrays including a location of the one or more second inspection image pixel arrays, wherein the second inspection image is different than the first inspection image; determining a first orientation of the object relative to an optical sensor for the first inspection image and determining a second orientation of the object relative to the optical sensor for the second inspection image; determining a first property map for the first inspection image based on the first orientation and a second property map for the second inspection image based on the second orientation, wherein, in determining the first property map, only the location of the one or more first inspection image pixel arrays and the orientation of the object in the inspection image are used from the first inspection image, and, wherein, in determining the second property map, only the location of the one or more second inspection image pixel arrays and the orientation of the object in the second inspection image are used from the second inspection image; receiving, recalling, or both, the first property map and the second property map; determining a first property of the object based on the first property map and the first designation, wherein the first property is associated with the first inspection image, wherein the first property is a first distance which is calculated, estimated, or measured from a first adjacent pixel of the first inspection image pixel array to a second adjacent pixel of the first inspection image array, wherein the distance is determined by making a straight line from a middle of a side or a corner of the first adjacent pixel, through the first adjacent pixel, and to a middle of a side of a corner of the second adjacent pixel; determining a second property of the object based on the second property map and the second designation, wherein the second property is associated with the second inspection image, wherein in the second property is a second distance is calculated, estimated, or measured from a first adjacent pixel of the second inspection image pixel array to a second adjacent pixel of the second inspection image array, wherein the distance is determined by making a straight line from a middle of a side or a corner of the second adjacent pixel, through the second adjacent pixel, and to a middle of a side of a corner of the second adjacent pixel; aligning the first property map with the second property map by aligning the location of the one or more first inspection image pixel arrays with the location of the one or more second inspection image pixel arrays; comparing the first property with the second property; displaying the comparison; determining damage to the object between the first distance and the second distance; and determining a maintenance action based on the comparison, including predicting when the damage will exceed an operational limit.

2 . The method of claim 1 , wherein the first inspection image defines a first capture date, wherein the second inspection image defines a second capture date, wherein determining the first property of the object comprises determining the first property of the object proximate to the second capture date.

3 . The method of claim 1 , wherein the first inspection image defines a first capture date, wherein the second inspection image defines a second capture date, and wherein the second capture date is after the first capture date.

4 . The method of claim 3 , wherein the second capture date is at least six months later than the first capture date and up to 15 years later than the first capture date.

5 . The method of claim 3 , wherein determining the first property of the object comprises determining the first property of the object proximate to the second capture date.

6 . The method of claim 1 , wherein the first property is indicative of a feature on the object, wherein the second property is also indicative of the feature on the object, and wherein displaying the comparison comprises displaying a growth of the feature on the object.

7 . The method of claim 6 , wherein the feature is a crack.

8 . The method of claim 1 , wherein the first designation is a first continuous segment of inspection image pixels in an inspection image pixel array, the second designation is a second continuous segment of inspection image pixels in the inspection image pixel array, wherein an inspection image pixel in the first continuous segment of inspection image pixels is also in the second continuous segment of inspection image pixels.

9 . The method of claim 1 , wherein
displaying the comparison further includes, the first property being a first size of a feature on the object, and the second property being a second size of the feature on the object, wherein displaying the comparison includes determining a growth of the feature on the object based on the first size of the feature on the object and the second size of the feature on the object; and comparing the growth of the feature on the object to the operational limit.

10 . The method of claim 9 , comprising displaying an indication if the growth of the feature on the object exceeds the operational limit.

11 . The method of claim 9 , comprising initiating the maintenance action of the object if the growth of the feature on the object exceeds the operational limit.

12 . An inspection system comprising:
a computing system configured to:
determine a first inspection package that includes a first inspection image of an object and a first designation, wherein the first inspection image includes one or more first inspection image pixel arrays including a location of the one or more first inspection image pixel arrays;
determine data indicative of a second inspection package that includes a second inspection image of the object and a second designation, wherein the second inspection image includes one or more inspection second image pixel arrays including a location of the one or more second inspection image pixel arrays wherein the second inspection image is different than the first inspection image;
determine a first orientation of the object relative to an optical sensor for the first inspection image and determining a second orientation of the object relative to the optical sensor for the second inspection image;
determine a first property map for the first inspection image based on the first orientation and a second property map for the second inspection image based on the second orientation, wherein only the location of the one or more first inspection image pixel arrays and the orientation of the object in the inspection image are used from the first inspection image to form the first property map, and, wherein only the location of the one or more second inspection image pixel arrays and the orientation of the object in the second inspection image are used from the second inspection image to form the second property map;
receive, recall, or both, the first property map and the second property map;
determine a first property of the object based on the first property map and the first designation, whe

Assignees

• Gen Electric
• Oliver Crispin Robotics Ltd

Inventors

• Graham Andrew Crispin
• Foxall Julian Matthew
• Miller James Vradenburg
• Dixon Walter V
• Shirsat Vijay

Classifications

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T2200/08

  involving all processing steps from image acquisition to 3D model generation · CPC title

• G06T17/20

  Finite element generation, e.g. wire-frame surface description, {tesselation} · CPC title

• G01B11/2513

  with several lines being projected in more than one direction, e.g. grids, patterns · CPC title

• G06T2207/30164

  Workpiece; Machine component · CPC title