Development of a method for determining the distance between glows and classification of glows during luminescent testing of gas turbine engine blades
- Authors: Alekseev E.A.1, Lomanov A.N.2
-
Affiliations:
- PJSC "UEC-Saturn"
- Rybinsk State Aviation Technical University named after P.A. Solovyov
- Issue: No 1 (2025)
- Pages: 116-125
- Section: Automation and Control of Technological Processes and Productions
- URL: https://journal-vniispk.ru/2072-3172/article/view/361368
- ID: 361368
Cite item
Full Text
Abstract
Machine vision is the basis of control operations during inspection of blade surfaces for defects under UV light. When implementing automated control technology, it is necessary to solve several key problems: obtaining a package of inspection images of a complex profile control object (aircraft blade), determining the real parameters (sizes) of glows for single and group defects, forming expert recommendations (digital trace) for determining the presence of defects on inspected surfaces for the operator or automated systems. A method is presented for determining the distance between glows, eliminating their duplication, and classifying glows during luminescent testing of gas turbine engine blades. The classification is based on a comparison of the obtained indications with reference photomasks. The stages of analysis of classification characteristics and algorithms for their implementation are given.
About the authors
E. A. Alekseev
PJSC "UEC-Saturn"
Author for correspondence.
Email: evgeny.alekseev@uec-saturn.ru
director of digital transformation
A. N. Lomanov
Rybinsk State Aviation Technical University named after P.A. Solovyov
Email: frei@rsatu.ru
cand. Sc. of Engineering, docent, director of the Institute of Information Technologies and Management Systems
References
- Poletaev V. A. Technology for the Production of Gas Turbine Engine Blades / V. A. Poletaev. – Moscow: Mechanical Engineering, 2006. – 256 p.
- Glazkov Yu. A. Capillary Control / under general ed. of V. V. Klyuev. – Moscow: Spektr Publishing House, 2011. – 144 p.
- Quality Control Using Penetrants. Capillary Control / N. P. Kalinichenko, V. K. Kuleshov, A. N. Kalinichenko. – 2nd ed., revised and expanded. – Tomsk: Tomsk Polytechnic University Publishing House, 2007. – 203 p.
- Literature on capillary non-destructive testing [Electronic resource]. – Access mode: https://ndt-testing.ru/ (accessed: 01.08.2021).
- Popko E. A., Vorobyov A. P., Vainshtein I. A. Experience in the use of machine vision in optical non-destructive testing systems // Welding and Diagnostics: Collection of Reports of the International Forum (Ekaterinburg, November 24–25, 2015). – Ekaterinburg: UrFU, 2015. – P. 401–406.
- Ermakov A. A. Methods and Algorithms for Processing and Analyzing Images in Capillary Flaw Detection: Author’s Abstract of PhD Thesis in Technical Sciences. – Vladimir: VlGU, 2009. – 19 p.
- Shipway N. J., Barden T. J., Huthwaite P., Lowe M. J. S. Automated defect detection for fluorescent penetrant inspection using Random Forest // NDT & E International. – 2019. – Vol. 101. – P. 113–123.
- Shipway N. J., Huthwaite P., Lowe M. J. S., Barden T. J. Using ResNets to perform automated defect detection for fluorescent penetrant inspection // NDT & E International. – 2021. – Vol. 119.
- Tout K. Automatic Vision System for Surface Inspection and Monitoring: Application to Wheel Inspection. – Université de Technologie de Troyes – UTT, 2018.
- Bobkov A. B. Selection of segments in an image in the task of orientation based on visual information // Bulletin of MSTU. Instrumentation. – 2002. – No. 3 (48).
- Aust J., Shankland S., Pons D., Mukundan R., Mitrovic A. Automated defect detection and decision support in gas turbine blade inspection // Aerospace. – 2021. – Vol. 8. – Article 30. – https://doi.org/10.3390/aerospace8020030
- Method of image processing using convolutional neural networks. RF Patent No. 2771442. Appl. 11.12.2020, Publ. 05.04.2020, Bul. No. 13.
- Device for non-contact measurement of surface roughness of parts with complex shapes. RF Patent No. 104697. Appl. 16.11.2010, Publ. 20.05.2011.
- Computer vision software and hardware complex for determining and controlling the width of the interturn gap. RF Patent No. 126490. Appl. 03.07.2012, Publ. 27.03.2013, Bul. No. 9.
- Computer vision system for determining inhomogeneities in the depth of image objects. RF Patent No. 2604168. Appl. 27.01.2012, Publ. 10.12.2016, Bul. No. 34.
- Method for detecting surface defects, device for detecting surface defects, production method for steel materials and related technologies. RF Patent No. 2764644. Appl. 08.11.2019, Publ. 19.01.2022, Bul. No. 2.
- Method of non-destructive optical-visual inspection of products using machine vision. RF Patent No. 2777718. Appl. 17.08.2021, Publ. 08.08.2022, Bul. No. 22.
- Li C. et al. YOLOv6: A single-stage object detection framework for industrial applications // arXiv preprint arXiv:2209.02976. – 2022.
- Wang C.-Y., Bochkovskiy A., Liao H.-Y. M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors // arXiv preprint arXiv:2207.02696. – 2022.
- Jocher G., Chaurasia A., Qiu J. YOLO by Ultralytics. – URL: https://github.com/ultralytics/ultralytics
- (accessed: 30.02.2023).
- Sychev I. E., Litvinenko A. M. Automatic defect recognition system based on technical vision // Alternative and Intelligent Energy: Materials of the II Int. Scientific and Practical Conference. – Voronezh: Voronezh State Technical University, 2020. – URL: https://elibrary.ru/item.asp?id=43939127
- Kazakov O. D., Romashov N. E. Detection and recognition of objects in real time using a machine learning model // Challenges of the Digital Economy: Proceedings of the III All-Russian Scientific and Practical Conference with International Participation. – Bryansk: Bryansk State Engineering and Technology University, 2020. – URL: https://elibrary.ru/item.asp?id=44171509
- Yamshchikov S. A. Computer vision in non-destructive testing // New Materials, Equipment and Technologies in Industry: Proceedings of the Int. Scientific and Technical Conference of Young Scientists. – Mogilev: Belarusian-Russian University, 2021. – URL: https://elibrary.ru/item.asp?id=47155489
- Chikmarev D. D., Khabarov A. R., Karelskaya K. A. Computer vision system for flaw detection of objects // Information Resources and Systems in Economics, Science and Education: Proc. XI Int. Scientific and Practical Conf. – Penza: Volga House of Knowledge, 2021. – URL: https://elibrary.ru/item.asp?id=46459923
- Forsyth D. A., Pons D. Computer Vision: A Modern Approach. – Moscow: Williams, 2004. – 928 p.
- Gonzalez R., Woods R. Digital Image Processing. – Moscow: Tekhnosphere, 2005. – 621 p.
- Methods of Computer Image Processing / ed. by V. A. Soifer. – Moscow: Fizmatlit, 2001. – 784 p.
- Priorov A. L., Khryashchev V. V., Topnikov A. I. Processing and Transmission of Multimedia Information: Tutorial. – Yaroslavl: YarSU, 2022.
- Korotaev V. V., Krasnyashchikh A. V. Television Measuring Systems: Textbook. – St. Petersburg: St. Petersburg State University ITMO, 2008. – 108 p.
Supplementary files

