Defects Detection in Rotor Composite Parts using Instance Segmentation - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Defects Detection in Rotor Composite Parts using Instance Segmentation

Nicolas Griselin
  • Fonction : Auteur
  • PersonId : 1385749

Résumé

The manufacturing of rotor composite parts for helicopters involves different steps, including ply preparation, molding, curing, de-molding, machining of parts, quality control and finishing phases (such as painting). During the quality control, each part is systematically inspected using a Radiographic Testing (RT) approach. This is a non-destructive testing (NDT) method, which uses x-rays to examine the internal structure of manufactured components identifying any flaws or defects within the material. In this paper, an instance segmentation approach is used to detect a specific defect in radiography images of composites parts, based on a Mask R-CNN model. Instance segmentation represents a significant advancement in computer vision compared to more conventional approaches (such as classification or object detection). Application to an industrial case is presented here with a precision to predict “defects” about 85%, a recall of 96% and a F1 score of 90%. We also introduce an original labeling technique well suited for industrial purpose.
Fichier principal
Vignette du fichier
ERF2024_Defect_detection_using_Instance_Segmentation_Abstract.pdf (412.9 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Copyright (Tous droits réservés)

Dates et versions

hal-04588729 , version 1 (27-05-2024)
hal-04588729 , version 2 (26-08-2024)

Licence

Copyright (Tous droits réservés)

Identifiants

  • HAL Id : hal-04588729 , version 1

Citer

Nicolas Griselin. Defects Detection in Rotor Composite Parts using Instance Segmentation. 50th European Rotorcraft Forum 2024, Sep 2024, Marseille (13), France. ⟨hal-04588729v1⟩
37 Consultations
19 Téléchargements

Partager

More