Application of machine vision in laser technologies

DOI: 10.34759/trd-2022-127-25

Аuthors

Molotkov A. A., Tretiyakova O. N.^*

Laboratory of industrial research of the group of companies SPC «Lasers and equipment , Moscow, Russia

*e-mail: tretiyakova_olga@mail.ru

Abstract

The article deals with the problem of applying machine vision methods for practical implementation in the production of modern laser technologies, in particular, selective laser melting technologies. The authors describe the software platform of machine vision created and implemented in production. Examples of the solved problems of machine vision and scientific visualization in the framework of the industrial implementation of new laser technologies are presented.

The results of the executed work allowed creating a specialized machine vision platform with possibilities of functions expansion in future that empowers simplifying solution of a wide range of machine vision tasks for the of laser technologies implementation. The problems of object recognition occurring in the process of laser technologies developing were considered. One of the problems of the object recognition in industry has been solved, namely the problem of finding a sheet in the working field of the machine-tool. The authors developed and implemented an algorithm for the object contours determining from the previously found angles, which was employed to solve the problem of finding and analyzing the quality of holes while perforation, as well as finding geometry of the fused layer in the process of selective laser melting.

The developed software platform for machine vision allows processes recording in isolated environments, the objects boundaries determining in an image, analyzing and processing visual data, forming and presenting a pattern of heat distribution in a three-dimensional object. It empowered combining the calculated data on the product geometry and the data, obtained by video data analyzing from visual observation tools, with the data on the heat distribution, obtained as the result of numerical experiment in accordance with the implemented mathematical model of the selective laser melting process under study. The proposed approach allows automating the production control process and simplifying analysis and identification of critical areas for technologists, as well as the technological parameters selection for the process of selective laser melting.

The created machine vision software platform has been tested and implemented in the software solutions employed in a number of high-tech industrial productions.

Keywords:

machine vision methods, software platform, computer modelling, laser; engineering technologies

References

1. Ezrokhi Yu.A., Kizeev I.S. Trudy MAI, 2022, no. 125. URL: https://trudymai.ru/eng/published.php?ID=168198. DOI: 10.34759/trd-2022-125-25
2. Cherkasova M.V. Trudy MAI, 2022, no. 124. URL: https://trudymai.ru/eng/published.php?ID=167003. DOI: 10.34759/trd-2022-124-08
3. Zaitseva N.I., Pogarskaya T.A. Trudy MAI, 2022, no. 124. URL: https://trudymai.ru/eng/published.php?ID=167106. DOI: 10.34759/trd-2022-124-23
4. Vedyashkina A.V., Rinkyavichus B.S. et al. Nauchnaya vizualizatsiya, 2019, vol. 11, no. 3, pp. 43-53
5. Rometsch P., Jia Q., Yang K., Wu X. Aluminum alloys for selective laser melting — towards improved performance, In book: Additive Manufacturing for the Aerospace Industry, 2019, pp. 301-325. DOI:10.1016/B978-0-12-814062-8.00016-9
6. Mazur M., Leary M. et al. Mechanical properties of Ti6Al4V and AlSi12Mg lattice structures manufactured by Selective Laser Melting (SLM), In book: Laser Additive Manufacturing: Materials, Design, Technologies and Applications, 2016, pp. 119-161. DOI:10.1016/B978-0-08-100433-3.00005-1
7. Mirkoohi E., Seivers D., Garmestani H., Liang S. Heat Source Modeling in Selective Laser Melting, Materials, 2019, vol. 12 (13), pp. 2052. DOI:10.3390/ma12132052
8. Sokolov S.M., Boguslavskii A.A., Fedorov N.G., Vinogradov P.V. Izvestiya YuFU. Tekhnicheskie nauki, 2015, no. 1 (162), pp. 96-109.
9. Kaushik S., Jain A., Chaudhary T., Chauhan N.R. Machine vision based automated inspection approach for clutch friction disc (CFD), Materials Today: Proceedings. 2022, no. 62 (2), pp. 151-157. DOI:10.1016/j.matpr.2022.02.610
10. Stepanov D.N. Programmnye produkty i sistemy, 2014, no. 1, pp. 150-157.
11. Krasnobaev A.A. Obzor algoritmov detektirovaniya prostykh elementov izobrazheniya i analiz vozmozhnosti ikh apparatnoi realizatsii, Preprinty IPM im. M.V. Keldysha, 2005, no. 114, 20 p.
12. Alpatov B.A., Babayan P.V., Balashov O.E., Stepashkin A.I. Metody avtomaticheskogo obnaruzheniya i soprovozhdeniya ob"ektov. Obrabotka izobrazhenii i upravlenie (Methods for automatic detection and tracking of objects. Image processing and management), Moscow, Radiotekhnika, 2008, 176 p.
13. Rakhmatulin I. Neiroseti, glubokoe obuchenie, mashinnoe zrenie v sel’skom khozyaistve. Kratkii obzor dlya 2021 goda. URL: https://www.researchgate.net/publication/350280155_Nejroseti_glubokoe_obucenie_masinnoe_zrenie_v_selskom_hozajstve_Kratkij_obzor_dla_2021_goda17.08.2022 DOI:10.24108/preprints-3112205
14. Ivanov P.V., Boikov A.V. Zapiski Gornogo instituta, 2011, no. 192, pp. 216-218.
15. Bolotova Yu.A., Druki A.A., Spitsyn V.G. Metody i algoritmy intellektual’noi obrabotki tsifrovykh izobrazhenii (Methods and Algorithms for Intelligent Digital Image Processing: Tutorial), — Tomsk: Tomskii politekhnicheskii universitet, 2016, 208 p.
16. Smith S.M., Brady J.M. SUSAN—A New Approach to Low Level Image Processing, International Journal of Computer Vision, 1997, no. 23, pp. 45–78. DOI:10.1023/A:1007963824710
17. Rosten E., Drummond T. Machine Learning for High-Speed Corner Detection, Computer Vision — ECCV 2006, Lecture Notes in Computer Science, pp. 430–443. DOI:10.1007/11744023_34
18. Molotkov A.A., Tret’yakova O.N. Nauchnaya vizualizatsiya, 2019, vol. 11, no. 4, pp. 1-12. DOI: 10.26583/sv.11.4.01
19. Lebedkin I.F., Molotkov A.A., Tret’yakova O.N. Trudy MAI, 2018, no. 101. URL: https://trudymai.ru/eng/published.php?ID=97045
20. Molotkov A.A., Tret’yakova O.N. 29-ya Mezhdunarodnaya konferentsiya po komp’yuternoi grafike i mashinnomu zreniyu — GraphiCon 2019: sbornik trudov, Bryansk, Bryanskii gosudarstvennyi tekhnicheskii universitet, 2019, pp. 78-81.

Download