Using convolutional neural networks to automate aircraft maintenance visual inspection

Name: Using convolutional neural networks to automate aircraft maintenance visual inspection
Author: Doğru, Anıl, Bouarfa, S., Arizar, R., Aydoğan, Reyhan

İsim	Using convolutional neural networks to automate aircraft maintenance visual inspection
Yazar	Doğru, Anıl, Bouarfa, S., Arizar, R., Aydoğan, Reyhan
Basım Tarihi:	2020-12
Basım Yeri	- MDPI
Konu	Aircraft maintenance inspection, Anomaly detection, Defect inspection, Convolutional neural networks, Mask R-CNN, Generative adversarial networks, Image augmentation
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2226-4310
Kayıt Numarası	31456c59-ea24-403f-91e3-e0fc2b008ef9
Lokasyon	Computer Science
Tarih	2020-12
Örnek Metin	Convolutional Neural Networks combined with autonomous drones are increasingly seen as enablers of partially automating the aircraft maintenance visual inspection process. Such an innovative concept can have a significant impact on aircraft operations. Though supporting aircraft maintenance engineers detect and classify a wide range of defects, the time spent on inspection can significantly be reduced. Examples of defects that can be automatically detected include aircraft dents, paint defects, cracks and holes, and lightning strike damage. Additionally, this concept could also increase the accuracy of damage detection and reduce the number of aircraft inspection incidents related to human factors like fatigue and time pressure. In our previous work, we have applied a recent Convolutional Neural Network architecture known by MASK R-CNN to detect aircraft dents. MASK-RCNN was chosen because it enables the detection of multiple objects in an image while simultaneously generating a segmentation mask for each instance. The previously obtained F-1 and F-2 scores were 62.67% and 59.35%, respectively. This paper extends the previous work by applying different techniques to improve and evaluate prediction performance experimentally. The approach uses include (1) Balancing the original dataset by adding images without dents; (2) Increasing data homogeneity by focusing on wing images only; (3) Exploring the potential of three augmentation techniques in improving model performance namely flipping, rotating, and blurring; and (4) using a pre-classifier in combination with MASK R-CNN. The results show that a hybrid approach combining MASK R-CNN and augmentation techniques leads to an improved performance with an F-1 score of (67.50%) and F-2 score of (66.37%).
DOI	10.3390/aerospace7120171
Cilt	7

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Using convolutional neural networks to automate aircraft maintenance visual inspection

Yazar Doğru, Anıl, Bouarfa, S., Arizar, R., Aydoğan, Reyhan

Basım Tarihi 2020-12

Basım Yeri - MDPI

Konu Aircraft maintenance inspection, Anomaly detection, Defect inspection, Convolutional neural networks, Mask R-CNN, Generative adversarial networks, Image augmentation

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2226-4310

Kayıt Numarası 31456c59-ea24-403f-91e3-e0fc2b008ef9

Lokasyon Computer Science

Tarih 2020-12

Örnek Metin Convolutional Neural Networks combined with autonomous drones are increasingly seen as enablers of partially automating the aircraft maintenance visual inspection process. Such an innovative concept can have a significant impact on aircraft operations. Though supporting aircraft maintenance engineers detect and classify a wide range of defects, the time spent on inspection can significantly be reduced. Examples of defects that can be automatically detected include aircraft dents, paint defects, cracks and holes, and lightning strike damage. Additionally, this concept could also increase the accuracy of damage detection and reduce the number of aircraft inspection incidents related to human factors like fatigue and time pressure. In our previous work, we have applied a recent Convolutional Neural Network architecture known by MASK R-CNN to detect aircraft dents. MASK-RCNN was chosen because it enables the detection of multiple objects in an image while simultaneously generating a segmentation mask for each instance. The previously obtained F-1 and F-2 scores were 62.67% and 59.35%, respectively. This paper extends the previous work by applying different techniques to improve and evaluate prediction performance experimentally. The approach uses include (1) Balancing the original dataset by adding images without dents; (2) Increasing data homogeneity by focusing on wing images only; (3) Exploring the potential of three augmentation techniques in improving model performance namely flipping, rotating, and blurring; and (4) using a pre-classifier in combination with MASK R-CNN. The results show that a hybrid approach combining MASK R-CNN and augmentation techniques leads to an improved performance with an F-1 score of (67.50%) and F-2 score of (66.37%).

DOI 10.3390/aerospace7120171

Cilt 7