Meister, Sebastian und Wermes, Mahdieu A. M. und Stüve, Jan und Groves, Roger M. (2021) Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing. Composites Part B Engineering. Elsevier. doi: 10.1016/j.compositesb.2021.109160. ISSN 1359-8368.
![]() |
PDF
- Verlagsversion (veröffentlichte Fassung)
2MB |
Kurzfassung
Automated fibre layup techniques are widely used in the aviation sector for the efficient production of composite components. However, the required manual inspection can take up to 50 % of the manufacturing time. The automated classification of fibre layup defects with Neural Networks potentially increases the inspection efficiency. However, the machine decision-making processes of such classifiers are difficult to verify. Hence, we present an approach for analysing the classification procedure of fibre layup defects. Therefore, we comprehensively evaluate 20 Explainable Artificial Intelligence methods from the literature. Accordingly, the techniques Smoothed Integrated Gradients, Guided Gradient Class Activation Mapping and DeepSHAP are applied to a Convolutional Neural Network classifier. These methods analyse the neural activations and robustness of a classifier for an unknown and manipulated input data. Our investigations show that especially Smoothed Integrated Gradients and DeepSHAP are well suited for the visualisation of such classifications. Additionally, maximum-sensitivity and infidelity calculations confirm this behaviour. In future, customers and developers could apply the presented methods for the certification of their inspection systems.
elib-URL des Eintrags: | https://elib.dlr.de/143297/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Zeitschriftenbeitrag | ||||||||||||||||||||
Titel: | Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | 22 Juli 2021 | ||||||||||||||||||||
Erschienen in: | Composites Part B Engineering | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Ja | ||||||||||||||||||||
DOI: | 10.1016/j.compositesb.2021.109160 | ||||||||||||||||||||
Verlag: | Elsevier | ||||||||||||||||||||
ISSN: | 1359-8368 | ||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||
Stichwörter: | Defects Non-destructive testing Process monitoring Automation | ||||||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||
HGF - Programm: | Luftfahrt | ||||||||||||||||||||
HGF - Programmthema: | Komponenten und Systeme | ||||||||||||||||||||
DLR - Schwerpunkt: | Luftfahrt | ||||||||||||||||||||
DLR - Forschungsgebiet: | L CS - Komponenten und Systeme | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | L - Produktionstechnologien | ||||||||||||||||||||
Standort: | Stade | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für Faserverbundleichtbau und Adaptronik > Verbundprozesstechnologien | ||||||||||||||||||||
Hinterlegt von: | Meister, Dr. Sebastian | ||||||||||||||||||||
Hinterlegt am: | 09 Aug 2021 10:48 | ||||||||||||||||||||
Letzte Änderung: | 16 Sep 2021 09:56 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags