Neural network system for laser diagnostics of aircraft cabin glazing elements
https://doi.org/10.51955/2312-1327_2024_2_61
Abstract
Assessing the technical condition of glazing elements in the cockpits of operational-tactical aircraft still remains the most important task in ensuring flight safety. To increase the efficiency of operations for non-destructive testing of glazing elements using the speckle structure method of optical radiation, the authors propose to use neural network technologies to automatically identify controlled areas in the cockpit. Artificial intelligence technologies have been used to realise this task. They are based on algorithms of semantic segmentation, classification and detection of monitored areas according to the established markers on the cabin due to the application of convolutional neural network on YOLOv8. The application of machine vision technology have made it possible real-time measurement of the glazing exit from the termination when overpressure has been created inside the cabin. This reduces the time for technical condition assessment by at least 10 times. The use of machine vision technologies have made it possible to measure the value of the glazing outlet from the sealing in real time when creating excessive pressure inside the cabin and thereby reduce the time to assess the technical condition by at least 10 times. The authors have established the reason for the discrepancy between the results of using the speckle-structure method of optical radiation in determining the value of glazing yield from the termination and the "tape" method and developed recommendations to reduce measurement errors.
About the Authors
P. V. Pavlov
Military Training and Research Center of the Air Force "Air Force Academy named after Professor N. E. Zhukovsky and Y. A. Gagarin"
Russian Federation
Russian Federation
Pavel V. Pavlov, Candidate of Technical Sciences, Associate Professor
54A, Starykh Bolshevikov street, Voronezh, 394064
D. I. Tyurnev
Military Training and Research Center of the Air Force "Air Force Academy named after Professor N. E. Zhukovsky and Y. A. Gagarin"
Russian Federation
Russian Federation
Daniil I. Tyurnev
54A, Starykh Bolshevikov street, Voronezh, 394064
N. V. Sukhachev
Military Training and Research Center of the Air Force "Air Force Academy named after Professor N. E. Zhukovsky and Y. A. Gagarin"
Russian Federation
Russian Federation
Nikita V. Sukhachev
54A, Starykh Bolshevikov street, Voronezh, 394064
References
1. Arinichev I. V., Polyanskikh S. V., Arinicheva I. V. (2023). Semantic segmentation of rusts and spots of wheat Computer Optics. 47(1): 118-125. (in Russian)
2. Belikov A. A. (2023). EFFICIENTUDET - a new architecture for semantic image segmentation. Scienceosphere. 4(2): 191-198. (in Russian)
3. Filichkin S. A., Vologdin S. V. (2023). Comparison of the effectiveness of the YOLOv5 and YOLOv8 algorithms for detecting personal protective equipment. Intelligent systems in production. 21(3): 124-131. (in Russian)
4. Gavrilov D. A. (2021). Study of the applicability of the U-Net convolutional neural network to the problem of segmentation of images of aviation equipment. Computer Optics. 45(4): 575–579. (in Russian)
5. Mikhalev O. N., Yanyushkin A. S. (2022). Machine vision and object recognition using neural networks. Robotics and technical cybernetics. 10(2): 113-120. (in Russian)
6. Pavlov P. V., Lagoshny I. S., Vladimirov A. P., Tyurnev D. I., Evsin A. O., Onoshko A. M. Software module for determining the amount of movement of diffuse objects by analyzing the parameters of digital speckle photography. Certificate of registration of the computer program RU 2023617647, 04.12.2023. Application № 2023616464 dated 04.04.2023. (in Russian)
7. Polovinkin A. E., Belozerskikh V. V. (2023). Control system for threshold object recognition using artificial intelligence based on the YOLO neural network. High-performance computing systems and technologies. 7(1): 97-105. (in Russian)
8. Popov A. V., Teslya D. N., Komlev A. B. (2018). System for assessing the strength of structures of aviation and rocket and space technology based on the acoustic emission method. Control. Diagnostics. (8): 34-39. (in Russian)
9. Popov A. V., Voloshina V. Yu., Zhuravsky K. A., Labina M. A. (2022). New methods of acoustic diagnostics of aircraft. Engineer and industrialist today. 3 (57): 48–53. (in Russian)
10. Presnetsov A. M., Tyurin A. P. (2023). Development of a software and hardware complex for monitoring production activities using the YOLOv8 neural network. Intelligent systems in production. (21)2: 140-151. (in Russian)
11. Prokopenko V. V. (2023). Applications of the YOLO neural network model within the framework of the emotion detection task. Naukosfera. 5–2: 305-311. (in Russian)
12. Stepanov A. R., Pavlov P. V., Vladimirov A. P. (2023). Hardware-software complex for speckle-laser diagnostics of aircraft cabin glazing elements. Proceedings of MAI. (129). Available at: https://trudymai.ru/upload/iblock/23a/ee6elfeedmlwwnbvz9rfxl6h92e7dpg3/23_Stepanov_Pavlov_Vladimirov.pdf?lang=ru&issue=129 (accessed 27 November 2023). (in Russian)
13. Terven J. R., Cordova-Esparaza D. M. (2023). A comprehensive review of yolo: from yolov1 to YOLOv8 and beyond. официальный репозиторий YOLOv8. Under review in ACM Computing Surveys (2023). Available at: https://arxiv.org/pdf/2304.00501v1.pdf (accessed 27 November 2023).
14. Vladimirov A. P., Drukarenko N. A., Kamantsev I. S., Pavlov P. V., Evsin A. O. (2021). Speckle diagnostics of glazing elements of aircraft cabins made of organic glass. Aviation industry. (3-4): 97-103. (in Russian)
15. Vladimirov A. P., Kamantsev I. S., Drukarenko N. A., Trishin N. V., Akashen L. A., Druzhinin A. V. (2019). Assessment of fatigue damage in organic glass by optical methods. Optics and spectroscopy. (5): 870-880. (in Russian)
Review
For citations:
Pavlov P.V., Tyurnev D.I., Sukhachev N.V. Neural network system for laser diagnostics of aircraft cabin glazing elements. Crede Experto: transport, society, education, language. 2024;(2):61-76. (In Russ.) https://doi.org/10.51955/2312-1327_2024_2_61
Views:
13
JATS XML
Email this article 