Defect detectability analysis via Probability of defect detection between traditional and deep learning methods in numerical simulations

Authors:
  • UOUpper Austrian University of Applied Sciences (FH OÖ)
    Upper Austrian University of Applied Sciences (FH OÖ)
  • MYMiroslav Yosifov
    Miroslav Yosifov
  • PWPatrick Weinberger
    Patrick Weinberger
  • NGNemak Linz GmbH
    Nemak Linz GmbH
  • MRMichael Reiter
    Michael Reiter
  • BFBernhard Fröhler
    Bernhard Fröhler
  • UAUniversity of Antwerpen
    University of Antwerpen
  • JBJan De Beenhouwer
    Jan De Beenhouwer
  • JKJohann Kastner
    Johann Kastner
  • UPUniversity of Passau
    University of Passau
  • CHChristoph Heinzl
    Christoph Heinzl
Publisher website
Google Scholar
Abstract
X-ray computed tomography (XCT) is one of the most powerful imaging techniques in non-destructive testing (NDT) for detecting, analysing and visualising defects such as pores, fibres, cracks etc. in industrial specimens. Detecting defects in X-ray images, however, is still a challenging problem, as it strongly depends on the quality of the XCT images. Numerical XCT simulation proved to be valuable in order to increase both image quality and detection performance. In this work, we thus analyse the differences between traditional segmentation techniques (i.e., k-means, watershed, Otsu thresholding) and deep learning-based methods (i.e., U-Net, V-Net, modified 3D U-Net) in terms of their defect detection capacity using virtual XCT images. For this purpose, we apply the probability of defect detection (POD) approach on simulated X-ray computed tomography data from aluminium cylinder heads. The XCT simulation tool SimCT was used to generate X-ray radiographs and respective reconstructions from a specimen series which features different well-defined defects with varying sizes, shapes and locations. To generate POD curves and to specify detection limits, the segmentation algorithms are used in predefined regions for defect detection via a hit/miss approach. A comparison and visualisation of six different types of defects is illustrated in 2D and 3D images, together with their POD curves and detection limits.