Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing

Meister, S.; Wermes, Mahdieu; Stueve, J.; Groves, R.M.

doi:10.1016/j.compositesb.2021.109160

Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing

Title

Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing

Author

Meister, S. (TU Delft Structural Integrity & Composites; Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR))
Wermes, Mahdieu (Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR))
Stueve, J. (TU Delft Aerospace Manufacturing Technologies; Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR))
Groves, R.M. (TU Delft Structural Integrity & Composites)

Date

2021

Abstract

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.

Subject

Automation
Defects
Non-destructive testing
Process monitoring

To reference this document use:

http://resolver.tudelft.nl/uuid:0c43c366-a1ff-48fd-bf61-df8dc88979e3

DOI

https://doi.org/10.1016/j.compositesb.2021.109160

ISSN

1359-8368

Source

Composites Part B: Engineering, 224

Part of collection

Institutional Repository