FR3125156B1 - NON-DESTRUCTIVE CONTROL OF A PART - Google Patents

NON-DESTRUCTIVE CONTROL OF A PART Download PDF

Info

Publication number
FR3125156B1
FR3125156B1 FR2107556A FR2107556A FR3125156B1 FR 3125156 B1 FR3125156 B1 FR 3125156B1 FR 2107556 A FR2107556 A FR 2107556A FR 2107556 A FR2107556 A FR 2107556A FR 3125156 B1 FR3125156 B1 FR 3125156B1
Authority
FR
France
Prior art keywords
defect
image
image element
probability value
scores
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
FR2107556A
Other languages
French (fr)
Other versions
FR3125156A1 (en
Inventor
Camille Chapdelaine
Sylvaine Picard
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Safran SA
Original Assignee
Safran SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Safran SA filed Critical Safran SA
Priority to FR2107556A priority Critical patent/FR3125156B1/en
Publication of FR3125156A1 publication Critical patent/FR3125156A1/en
Application granted granted Critical
Publication of FR3125156B1 publication Critical patent/FR3125156B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

L’invention concerne un procédé et un système de contrôle non destructif d’une pièce à partir d’une image (9) de ladite pièce (11), ladite image étant formée par un ensemble d’éléments d’images, caractérisé en ce qu’il comporte: - un module de classification (5) comprenant un ensemble de réseaux de neurones (51), configuré pour classifier un ensemble de scores de défaut pour chaque élément d’image, et - un module de calcul (7) configuré pour : - déterminer pour chaque élément d’image, un indicateur de défaut maximal à partir dudit ensemble de scores de défaut correspondant, - calculer pour chaque élément d’image une valeur de probabilité de défaut en fonction de l’indicateur de défaut maximal, - attribuer un label de défaut à tout élément d’image ayant une valeur de probabilité de défaut qui dépasse un seuil élémentaire prédéterminé, et - rejeter ladite pièce (11) au cas où le nombre d’éléments d’image présentant des labels de défaut dépasse un seuil global prédéterminé. Figure pour l’abrégé : Figure 1.The invention relates to a method and a system for non-destructive testing of a part from an image (9) of said part (11), said image being formed by a set of image elements, characterized in that that it comprises: - a classification module (5) comprising a set of neural networks (51), configured to classify a set of defect scores for each image element, and - a calculation module (7) configured for: - determining for each image element, a maximum defect indicator from said set of corresponding defect scores, - calculating for each image element a defect probability value as a function of the maximum defect indicator, - assign a defect label to any image element having a defect probability value which exceeds a predetermined elementary threshold, and - reject said part (11) in case the number of image elements presenting defect labels exceeds a predetermined global threshold. Figure for abstract: Figure 1.

FR2107556A 2021-07-12 2021-07-12 NON-DESTRUCTIVE CONTROL OF A PART Active FR3125156B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR2107556A FR3125156B1 (en) 2021-07-12 2021-07-12 NON-DESTRUCTIVE CONTROL OF A PART

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR2107556A FR3125156B1 (en) 2021-07-12 2021-07-12 NON-DESTRUCTIVE CONTROL OF A PART
FR2107556 2021-07-12

Publications (2)

Publication Number Publication Date
FR3125156A1 FR3125156A1 (en) 2023-01-13
FR3125156B1 true FR3125156B1 (en) 2023-11-10

Family

ID=77999095

Family Applications (1)

Application Number Title Priority Date Filing Date
FR2107556A Active FR3125156B1 (en) 2021-07-12 2021-07-12 NON-DESTRUCTIVE CONTROL OF A PART

Country Status (1)

Country Link
FR (1) FR3125156B1 (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180322623A1 (en) * 2017-05-08 2018-11-08 Aquifi, Inc. Systems and methods for inspection and defect detection using 3-d scanning
US10672588B1 (en) * 2018-11-15 2020-06-02 Kla-Tencor Corporation Using deep learning based defect detection and classification schemes for pixel level image quantification
US10755401B2 (en) * 2018-12-04 2020-08-25 General Electric Company System and method for work piece inspection
SE1930421A1 (en) * 2019-12-30 2021-07-01 Unibap Ab Method and means for detection of imperfections in products

Also Published As

Publication number Publication date
FR3125156A1 (en) 2023-01-13

Similar Documents

Publication Publication Date Title
US10817956B2 (en) Image-based vehicle damage determining method and apparatus, and electronic device
US10209974B1 (en) Automated model management methods
Valente et al. Correlations enhance the behavioral readout of neural population activity in association cortex
Desiere et al. Using artificial intelligence to classify jobseekers: the accuracy-equity trade-off
Chen et al. Detecting media bias in news articles using gaussian bias distributions
US20190289025A1 (en) Cross-channel detection system with real-time dynamic notification processing
KR102274069B1 (en) Apparatus and method for generating prediction model
US20230222369A1 (en) Facilitating device fingerprinting through assignment of fuzzy device identifiers
Yang et al. The influence of cueing on attentional focus in perceptual decision making
US10628638B1 (en) Techniques to automatically detect fraud devices
Cohen et al. Resolution limit of image analysis algorithms
US20220300364A1 (en) Methods and systems for real-time resolution of errors that are detected by multivariate machine learning models between users using univariate responses
US20150363643A1 (en) Fusion-based object-recognition
US20220230536A1 (en) Method and device for analyzing a sensor data stream and method for guiding a vehicle
FR3125156B1 (en) NON-DESTRUCTIVE CONTROL OF A PART
Zahrawi et al. Improving video surveillance systems in banks using deep learning techniques
Pagliari et al. Regulatory novelty after financial crises: Evidence from international banking and securities standards, 1975–2016
US20230169393A1 (en) Detecting category-specific bias using overfitted machine learning models
US11922377B2 (en) Determining failure modes of devices based on text analysis
Mignone et al. Anomaly detection for public transport and air pollution analysis
US11995477B2 (en) Verification of updated analytical procedures in monitoring systems
US20030095702A1 (en) Systematic design analysis for a vision system
US11663243B2 (en) System and method for object detection
Epure et al. Modeling the dynamics of online news reading interests
US20200265521A1 (en) Multimedia risk summarizer

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20230113

PLFP Fee payment

Year of fee payment: 3