期刊
COMPOSITES PART B-ENGINEERING
卷 224, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compositesb.2021.109160
关键词
Defects; Non-destructive testing; Process monitoring; Automation
资金
- Federal Ministry for Economic Affairs and Energy, Germany [20W1911F]
This research proposes an approach for analyzing the classification procedure of fiber layup defects, with smooth integrated gradients and DeepSHAP identified as particularly suitable for visualizing such classifications. Maximum-sensitivity and infidelity calculations confirm the effectiveness of these methods in future applications.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据