Detecting anomalies in image data plays a key role in automated industrial quality control. For this purpose, machine learning methods have proven useful for image processing tasks. However, supervised machine learning methods are highly dependent on the data with which they have been trained. In industrial environments data of defective samples are rare. In addition, the available data are often biased towards specific types, shapes, sizes, and locations of defects. On the contrary, one-class classification (OCC) methods can solely be trained with normal data which are usually easy to obtain in large quantities. In this work we evaluate the applicability of advanced OCC methods for an industrial inspection task. Convolutional Autoencoders and Generative Adversarial Networks are applied and compared with Convolutional Neural Networks. As an industrial use case we investigate the endoscopic inspection of cast iron parts. For the use case a dataset was created. Results show that both GAN and autoencoder-based OCC methods are suitable for detecting defective images in our industrial use case and perform on par with supervised learning methods when few data are available.
Deep Anomaly Detection for Endoscopic Inspection of Cast Iron Parts
Lect.Notes Mechanical Engineering
International Conference on Flexible Automation and Intelligent Manufacturing ; 2022 ; Detroit, MI, USA June 19, 2022 - June 23, 2022
Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus ; Kapitel : 9 ; 91-98
13.10.2022
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Improvements in Detector Design for X-ray Inspection of Cast Parts
SAE Technical Papers | 2009
|Improvements in detector design for x-ray inspection of cast parts
Kraftfahrwesen | 2009
|Slip-Cast Superconductive Parts
NTRS | 1993
|Resonant Inspection Applied to 100% Testing of Nodularity of Cast Ductile Iron
British Library Conference Proceedings | 2008
|Resonant Inspection Applied to 100% Testing of Nodularity of Cast Ductile Iron
SAE Technical Papers | 2008
|