Method and computer program product for automated defect detection during borescoping of an engine

Patent metadata

Field	Value
Publication number	US-12333699-B2
Application number	US-202017638215-A
Country	US
Kind code	B2
Filing date	Aug 26, 2020
Priority date	Aug 29, 2019
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

A method automatically detects defects during borescoping of an engine. A video borescope is inserted into the engine such that, engine blades can be moved successively through the image region of the borescope. A possible defect on an engine blade is identified by image recognition on the basis of a video borescope frame. The movement of the engine blades in the image region is detected by comparing successive frames. The possible defect is tracked by optical image recognition on the basis of the successive frames used for detecting the movement. In a condition where a trace of the possible defect on the video image corresponds to the detected movement in terms of direction and speed over a predefined length, the possible defect is identified as an actual defect.

First claim

The invention claimed is:

1. A method for automated defect detection during borescoping of an engine, in which a video borescope is inserted into the engine in such a way that, during rotation of an engine shaft, engine blades of an engine stage which are secured to the engine shaft are moved successively through the image region of the video borescope, the method comprising:
identifying a possible defect on an engine blade by image recognition on the basis of a frame generated by the video borescope;
detecting the movement of the engine blades in the image region of the video borescope by comparing in each case two successive frames;
tracking the possible defect on the video image along the detected movement by optical image recognition on the basis of the successive frames used for detecting the movement; and
in a condition where a trace of the possible defect on the video image corresponds to the detected movement in terms of direction and speed over a predefined length, identifying the possible defect as an actual defect.

2. The method as claimed in claim 1 ,
wherein the detection of the movement of the engine blades is used to identify the position of the individual engine blades based on a position of an arbitrarily chosen initial engine blade of the engine blades.

3. The method as claimed in claim 1 , wherein the method comprises controlling the rotational movement of the engine axle.

4. The method as claimed in claim 1 , wherein for the detection of the movement of the engine blades, the frames are segmented into individual blade regions.

5. The method as claimed in claim 4 ,
wherein exclusion regions are defined in which the frames are not segmented.

6. The method as claimed in claim 1 , wherein a direction of movement for the engine blades in the image region of the video borescope is predefined.

7. The method as claimed in claim 1 , wherein identifying the possible defect further comprises identifying a notch and/or dent on the engine blade.

8. A non-transitory computer readable storage medium comprising a computer program product comprising program parts which, when loaded in a computer, are designed for carrying out the method as claimed in claim 1 .

9. The method as claimed in claim 4 , wherein the frames are segmented into individual blade regions by a mask region-based convolutional neural network (RCNN) method.

10. The method as claimed in claim 9 , wherein the frames are segmented into individual blade regions by an inception feature extractor.

11. The method as claimed in claim 1 , wherein the two successive frames comprise the frame generated by the video borescope in which the possible defect is identified as one of the two successive frames.

12. The method as claimed in claim 1 , wherein the two successive frames are generated by the video borescope after the frame generated by the video borescope in which the possible defect is identified.

Assignees

• Lufthansa Technik Ag

Inventors

• Hubert Wiebke
• Peters Jan Oke
• Lang Eva
• Platho Matthias
• Appel Alexander

Classifications

• G06T2207/30164

  Workpiece; Machine component · CPC title

• G01N2021/8924

  Dents; Relief flaws · CPC title

• G01N21/892

  characterised by the flaw, defect or object feature examined · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T7/0004 Primary

  Industrial image inspection · CPC title