Explainability of deep learning classifier decisions for optical detection of manufacturing defects in the Automated Fiber Placement process

Sebastian Meister, Mahdieu A.M. Wermes, Jan Stuve, Roger M. Groves

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

1 Citation (Scopus)

Abstract

Automated fibre layup techniques are commonly used composite manufacturing processes in the aviation sector and require a manual visual inspection. Neural Network classification of defects has the potential to automate this visual inspection, however, the machine decision-making processes are hard to verify. Thus, we present an approach for visualising Convolutional Neural Network (CNN) based classifications of manufacturing defects and quantifying its robustness. Our investigations have shown that especially Smoothed Integrated Gradients and DeepSHAP are particularly well suited for the visualisation of CNN classifications. The Smoothed Integrated Gradients technique also reveals advantages in robustness when evaluating degraded input images.

Original languageEnglish
Title of host publicationAutomated Visual Inspection and Machine Vision IV
EditorsJurgen Beyerer, Michael Heizmann
PublisherSPIE
ISBN (Electronic)9781510644083
DOIs
Publication statusPublished - 2021
EventAutomated Visual Inspection and Machine Vision IV 2021 - Virtual, Online, Germany
Duration: 21 Jun 202025 Jun 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11787
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceAutomated Visual Inspection and Machine Vision IV 2021
CountryGermany
CityVirtual, Online
Period21/06/2025/06/20

Keywords

  • CNN
  • Composite Manufacturing
  • Computer Vision
  • Defect classifications
  • Inline Inspection
  • Laser Line Scan Sensor
  • XAI

Fingerprint

Dive into the research topics of 'Explainability of deep learning classifier decisions for optical detection of manufacturing defects in the Automated Fiber Placement process'. Together they form a unique fingerprint.

Cite this