US 12,145,748 B2
Method and system for non-destructive inspection of an aeronautical component
Alexis Reynald Paul Huck, Moissy-Cramayel (FR)
Assigned to SAFRAN, Paris (FR)
Appl. No. 17/905,241
Filed by SAFRAN, Paris (FR)
PCT Filed Mar. 9, 2021, PCT No. PCT/EP2021/055924
§ 371(c)(1), (2) Date Aug. 29, 2022,
PCT Pub. No. WO2021/180726, PCT Pub. Date Sep. 16, 2021.
Claims priority of application No. 2002497 (FR), filed on Mar. 13, 2020.
Prior Publication US 2023/0132883 A1, May 4, 2023
Int. Cl. G06T 7/00 (2017.01); B64F 5/60 (2017.01); G06T 3/4038 (2024.01)
CPC B64F 5/60 (2017.01) [G06T 3/4038 (2013.01); G06T 7/0004 (2013.01); G06T 2207/10048 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for non-destructive inspection of an aeronautical component comprising:
a step of obtaining, by means of an active infrared thermography system, a plurality of digital images of a unit zone of the aeronautical component acquired at a plurality of acquisition instants defined over a determined time period, designated acquisition period, each pixel of a digital image acquired at an acquisition instant having an amplitude at this acquisition instant at a point of the aeronautical component; the aeronautical component being fixedly positioned and an acquisition device of the active infrared thermography system is displaced to acquire a plurality of digital images of each unit zone,
a step of estimating, from the acquired digital images of the unit zone, an image of characteristics representative of the unit zone, each pixel of the image of characteristics comprising a vector of characteristics,
a step of partitioning said image of characteristics into a plurality of prediction micro-zones, each prediction micro-zone comprising a plurality of pixels,
a step of comparing the vector of characteristics of each pixel of each prediction micro-zone with a local statistical model estimated beforehand of said prediction micro-zone of said unit zone, designated hereafter local model, by means of a statistical prediction algorithm so as to determine an abnormality index for each pixel of each prediction micro-zone in order to form an abnormality micro-map of each prediction micro-zone of said unit zone, the assembly of the abnormality micro-maps of a unit zone forming an abnormality map of said unit zone,
each local model of a prediction micro-zone having been obtained from the vectors of characteristics of the pixels of at least one annotated image of characteristics representative of a unit zone of at least one learning aeronautical component corresponding to the aeronautical component to inspect, the unit zone of at least one learning aeronautical component corresponding to the unit zone of the aeronautical component to inspect;
the local model of a prediction micro-zone being obtained by means of a learning algorithm from the vectors of characteristics of the pixels of a learning micro-zone of the annotated image of characteristics, the annotated image of characteristics being partitioned into prediction micro-zones in a manner analogous to previously, each prediction micro-zone of the annotated image of characteristics being included in a learning micro-zone of the annotated image of characteristics.