Method for classifying an etch indication of a component

Patent metadata

Field	Value
Publication number	US-12518371-B2
Application number	US-202217992390-A
Country	US
Kind code	B2
Filing date	Nov 22, 2022
Priority date	Nov 25, 2021
Publication date	Jan 6, 2026
Grant date	Jan 6, 2026

Abstract

A method ( 100 ) for classifying an etch indication ( 11 ) of a component ( 10 ), the method including the steps of: providing a captured image ( 13 ) of the at least one etch indication ( 11 ); detecting at least one criterion ( 15 ) of the etch indication ( 11 ) based on the captured image ( 13 ); comparing the determined criterion ( 15 ) to at least one criteria data set ( 16 ) of etch indications ( 11 ) that is stored in a database; and classifying the etch indication ( 11 ) into at least one predetermined defect class (D) based on the comparison.

First claim

What is claimed is:

1 . A method for operating a turbomachine, the method comprising:
etching a component of the turbomachine to provide an etch indication; classifying the etch indication of the component, the classifying comprising the following steps: a) providing at least one captured image of the etch indication; b) detecting at least one criterion of the etch indication based on the captured image; c) comparing the at least one determined criterion to at least one criteria data set of previous etch indications stored in a database; d) classifying the etch indication into at least one of a plurality of predetermined defect classes based on the comparison, and e) classifying the etch indication into one of a plurality of predetermined criticality classes based on the classified defect class of the at least one etch indication of the component, the plurality of predetermined criticality classes including a first criticality class indicating uncritical defects and a second criticality class indicating critical defects; and operating the turbomachine after the etch indication is classified into the first criticality class; a first defect class of the plurality of predetermined defect classes including false indications; a second defect class of the plurality of predetermined defect classes including defects exhibiting an increase in grain size and a third defect class of the plurality of predetermined defect classes including both defects exhibiting an increase in grain size and an off-specification delta structure; the first criticality class including the first defect class and the second criticality class including both the second and third defect classes.

2 . The method as recited in claim 1 wherein the at least one criterion characterizes a morphology or distribution of a visual structure of the etch indication.

3 . The method as recited in claim 2 wherein the at least one criterion characterizes a contrast of the etch indication, the contrast being displayed in the captured image.

4 . The method as recited in claim 1 further comprising:
d1) outputting the classification into the one of the plurality of defect classes.

5 . The method as recited in claim 1 further comprising:
d2) outputting additional criteria data sets of the at least one defect class into which the etch indication was classified or outputting a manufacturing history.

6 . The method as recited in claim 1 further comprising:
e1) outputting the classification into the one of the plurality of criticality classes.

7 . The method as recited in claim 1 wherein the classification of the etch indication into one of the plurality of criticality classes takes into account a weighting of the defect class.

8 . The method as recited in claim 1 wherein the component is a rotor.

9 . The method as recited in claim 1 wherein the component is a compressor disk or turbine disk for receiving rotor blades.

10 . The method as recited in claim 1 wherein the component is a turbine blisk.

11 . The method as recited in claim 1 wherein a further defect class of the plurality of predetermined defect classes includes a defect type of white spots and a yet further defect class of the plurality of predetermined defect classes includes a defect type of non-metallic inclusions.

12 . A method for operating a turbomachine, the method comprising:
etching a component of the turbomachine to provide an etch indication; classifying the etch indication of the component, the classifying comprising the following steps: a) providing at least one captured image of the etch indication; b) detecting at least one criterion of the etch indication based on the captured image; c) comparing the at least one determined criterion to at least one criteria data set of previous etch indications stored in a database; d) classifying the etch indication into at least one of a plurality of predetermined defect classes based on the comparison, and e) classifying the etch indication into one of a plurality of predetermined criticality classes based on the classified defect class of the at least one etch indication of the component, the plurality of predetermined criticality classes including a first criticality class indicating uncritical defects and a second criticality class indicating critical defects; and operating the turbomachine after the etch indication is classified into the first criticality class; a first defect class of the plurality of predetermined defect classes including false indications; a further defect class of the plurality of predetermined defect classes including a defect type of white spots and a yet further defect class of the plurality of predetermined defect classes includes a defect type of non-metallic inclusions; the first criticality class including the first defect class and the second criticality class including both the further and yet further defect classes.

Assignees

• MTU Aero Engines AG

Inventors

• Bamberg Joachim
• Kolb Markus
• Hueller Marco
• Schoebel Yann

Classifications

• G06T2207/30164

  Workpiece; Machine component · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10056

  Microscopic image · CPC title

• G06T7/0004

  Industrial image inspection · CPC title