In the aerospace industry, automated fibre laying processes are often applied for economical composite part fabrication. Unfortunately, the current mandatory visual quality assurance process takes up to 50% of the entire manufacturing time. An automised classification of manufacturing deviations using Neural Networks potentially improves the inspection's effectiveness. Unfortunately, the automated decision-making procedures of machine learning approaches are challenging to trace. Therefore, we introduce an approach for evaluating the classifiers response for this use case. For this purpose, we present a parallel classification approach of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) with suitable intermediate checking stages between both classification processes. The particular novelty of this study is this intermediate comparison to trace the behaviour of the two classifiers along their image processing chains and to project the results back to the input image. With respect to the SVM, we analyse their extracted input features via t-Distributed Stochastic Neighbor Embedding calculations and parallel coordinates plots. Moreover, the classification score of the SVM as well as the feature vector distances within the SVM are investigated. For the CNN, the outputs of its first joined convolutional layer are correlated with the raw input images of different classes using Structural Similarity Index Measure metrics. Additionally, also the CNN's classification rates are analysed. Accordingly, a suitable uncertainty confidence interval for the CNN is determined on the bases of its neural activations. Finally, the relevance of individual pixels for the CNN decision is determined through Smooth Integrated Gradients and linked to the manually extracted image features for the SVM Classifier. The results of this paper are particularly valuable for developers and users of visual inspection systems in safety-critical domains.

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.

The aerospace industry has established the Automated Fiber Placement process as a common technique for manufacturing fibre reinforced components. In this process multiple composite tows are placed simultaneously onto a tool. Currently in such processes manual testing requires often up to 50% of the manufacturing duration. Moreover, the accuracy of quality assurance varies significantly with the inspector in charge. Thus, inspection automation provides an effective way to increase efficiency. However, to achieve a proper inspection performance, the segmentation of layup defects need to be examined. In order to improve such defect detection systems, this paper performs a comprehensive ranking of segmentation techniques. Thus, 29 statistical, spectral and structural algorithms from related work were evaluated based on nine substantial criteria as assessed from literature and process requirements. For reasons of determinism and easy technology transferability without the need of much training data, the development of new Machine Learning algorithms is not part of this paper. Afterwards, seven of the most auspicious algorithms were studied experimentally. Therefore, laser line scan sensor depth maps from fibre placement defects were utilised. Furthermore noisy images were generated and applied for testing algorithm robustness. The test data contained five defect categories with 50 samples per class. It was concluded that Adaptive Thresholding and Cell Wise Standard Deviation Thresholding work best yielding detection accuracies mostly > 97 %. Noteworthy is that influenced input data can affect the detection results. Feasible algorithms with sensible parameter settings were able to perform reliable defect segmentation for layed material.

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.

The Automated Fiber Placement process is established in the aerospace industry for the production of composite components. This technique places several narrow material strips in parallel. Within current industrial Automated Fiber Placement processes the visual inspection takes typically up to 50% of overall production time. Furthermore, inspection quality highly depends on the inspector. Therefore, automation of visual inspection offers a great improvement potential. To ensure reliable defect detection the segmentation of individual defects must be investigated. For this reason, this paper focusses on an assessment of defect segmentation algorithms. Therefore, 29 structural, statistical and spectral algorithms from related work were assessed, theoretically, using the 12 most relevant criteria as assessed from literature and process requirements. Then, seven most auspicious algorithms were analysed in detail. For reasons of determinism, Neural Network approaches are not part of this paper. Manually labelled prepreg defect images from a laser line scan sensor were used for tests. The test samples contain five defect types with 50 samples of each. Additionally, layups without defects were analysed. It was concluded that Adaptive Thresholding works best for global defect segmentation. The Cell Wise Standard Deviation Thresholding performs also quite well, but is very sensitive to grid size. Feasible algorithms perform reliable defect segmentation for layed up material.