Towards automated aircraft maintenance inspection. A use case of detecting aircraft dents using mask r-cnn
Soufiane Bouarfa (Abu Dhabi Polytechnic, Al Ain)
Anil Doğru (Özyeğin University)
Ridwan Arizar (Singulair Solutions B.V., Rotterdam)
Reyhan Aydoğan (TU Delft - Interactive Intelligence, Özyeğin University)
Joselito Serafico (Abu Dhabi Polytechnic, Al Ain)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Deep learning can be used to automate aircraft maintenance visual inspection. This can help increase the accuracy of damage detection, reduce aircraft downtime, and help prevent inspection accidents. The objective of this paper is to demonstrate the potential of this method in supporting aircraft engineers to automatically detect aircraft dents. The novelty of the work lies in applying a recently developed neural network architecture know by Mask R-CNN, which enables the detection of objects in an image while simultaneously generating a segmentation mask for each instance. Despite the small dataset size used for training, the results are promising and demonstrate the potential of deep learning to automate aircraft maintenance inspection. The model can be trained to identify additional types of damage such as lightning strike entry and exit points, paint damage, cracks and holes, missing markings, and can therefore be a useful decision-support system for aircraft engineers.