Aircraft Fuselage Corrosion Detection Using Artificial Intelligence

Abstract

Corrosion identification and repair is a vital task in aircraft maintenance to ensure continued structural integrity. Regarding fuselage lap joints, typically, visual inspections are followed by non-destructive methodologies, which are time-consuming. The visual inspection of large areas suffers not only from subjectivity but also from the variable probability of corrosion detection, which is aggravated by the multiple layers used in fuselage construction. In this paper, we propose a methodology for automatic image-based corrosion detection of aircraft structures using deep neural networks. For machine learning, we use a dataset that consists of D-Sight Aircraft Inspection System (DAIS) images from different lap joints of Boeing and Airbus aircrafts. We also employ transfer learning to overcome the shortage of aircraft corrosion images. With precision of over 93%, we demonstrate that our approach detects corrosion with a precision comparable to that of trained operators, aiding to reduce the uncertainties related to operator fatigue or inadequate training. Our results indicate that our methodology can support specialists and engineers in corrosion monitoring in the aerospace industry, potentially contributing to the automation of condition-based maintenance protocols.

Analytical Characterisation of Material Corrosion by Biofilms

“…Compared to RGB images, the proposed HSI modality captures reflectance at multiple wavelengths from multiple spatial points on the sample and provides an enormous amount of spectral detail. A key research area that has been developed as a strategy for automatically detecting corrosion on aeroplane structures using images taken by a borescope and also using deep neural networks (DNNs) has been reported by [64]. The authors demonstrate that a robust model could be developed using a dataset that included D-Sight Airplanes Inspection System (DAIS) photos from various lap joints on Boeing and Airbus aircraft.…”

Automated Identification of Hidden Corrosion Based on the D-Sight Technique: A Case Study on a Military Helicopter

“…Recently, numerous steps have been taken toward improving the D-Sight technique to become a quantitative system. Brandoli et al [ 25 ] demonstrated the application of deep neural networks (DNNs) for the detection of hidden corrosion in aircraft fuselage structures. A similar approach was presented by Zuchniak et al [ 26 ], where the authors used machine learning to detect hidden corrosion spots.…”

Monitoring of Hidden Corrosion Growth in Aircraft Structures Based on D-Sight Inspections and Image Processing

“…Several examples of the evaluation of defects in riveted joints using the eddy current technique and X-ray computed tomography can be found in [ 17 , 18 ]. The usage of the latter techniques is defined by their high sensitivity to corrosion as well as their high probability of detection and quantification of corrosion [ 19 ]. A comparative study presented in [ 20 ] shows that in aircraft maintenance practice, many of the mentioned methods are applied simultaneously or in various combinations.…”

“…In the last decade, little attention has been paid to improving the D-Sight technique, while recently several studies have been carried out on the improvement of the detectability of corrosion from D-Sight images with the support of artificial intelligence (AI) methods. In [ 19 ], the authors proposed an automated corrosion detection method in aircraft structures using deep neural networks and demonstrated great precision in corrosion detection using this method. In parallel, the authors of [ 27 , 28 ] demonstrated automatic corrosion detection from D-Sight images using deep learning and multi-teacher knowledge distillation.…”