Improving the reliability of NDT inspection through information fusion: applications in X-ray and ultrasound modalities

Ahmad Osman (1) , Valerie Kaftandjian (2) , Ulf Hassler (3)

1 Fraunhofer IZFP - Fraunhofer Institute for Nondestructive Testing
2 LVA - Laboratoire Vibrations Acoustique
3 Fraunhofer IIS/EZRT - Fraunhofer-Entwicklungszentrum Röntgentechnik

In this contribution we present a classification method based on the evidence theory. The classification method is compared to the state of the art support vector machine classifier on an industrial radioscopic data and 3D CT data of aluminium castings as well as 3D ultrasonic data of composite materials. The reported experimental results reveal the robustness of the proposed method and its advantages as well as disadvantages.

Mots clés: X-ray; Computed-Tomography; ultrasound; Sampling Phased Array; Aluminium Casting; CFRP; Fusion Theory; defects classification.

Domaines: Sciences de l'ingénieur [physics]

Ahmad Osman, Valerie Kaftandjian, Ulf Hassler. Improving the reliability of NDT inspection through information fusion: applications in X-ray and ultrasound modalities. European Conference on Non Destructive Testing, Oct 2014, Prague, Czech Republic. ⟨hal-01282246⟩