A.Yu. Viryasova1, A.I. Vlasov2, D.I. Klimov3, T.T. Mamedov4, A.P. Myagkov5

1,3–5 JSC "Russian Space Systems" (Moscow, Russia)

2 Bauman Moscow State Technical University (Moscow, Russia)

1 virnastya@yandex.ru, 2 vlasovai@bmstu.ru, 3 klimov.di@spacecorp.ru,

4 mamedov.tt@spacecorp.ru, 5 contact@spacecorp.ru

Problem setting. Currently, the task of predicting failures of functional elements of industrial products is relevant in terms of the possibility of additional analysis and prevention of an emergency or emergency. With the development of neural network technology, the possibilities for this are greatly increased. It is proposed to predict the causes of failures of functional elements of rocket and space technology products using algorithms applicable for the operation of machine vision systems.

Target. The purpose of this work is to analyze possible methods of using neural networks in the space industry to reduce the occurrence of failures of functional elements.

Results. In the course of the work, two main directions of neural networks were considered: machine vision and time series prediction. The article provides examples of possible applications of artificial intelligence for the problem of predicting failures in the space industry. The following directions are considered: an algorithm for determining thermally hazardous zones by the non-contact method using HSV-conversion, a comprehensive analysis of data from the vibration measurement subsystem and the SKUT-40 system with the ability to predict failures and determine the source of increased mechanical impacts, as well as the possibility of video recording with subsequent issuance of one-time commands in automatic mode.

Practical significance. The results of the analysis can have practical value for developers working in the space industry. Information on the possibility of improving the indicators of space systems by introducing promising directions of neural networks, namely computer vision and time series prediction, is given.

Viryasova A.Yu., Vlasov A.I., Klimov D.I., Mamedov T.T., Myagkov A.P. Methods for predicting failures of functional elements of rocket and space technology products using visual decomposition and machine learning. Neurocomputers. 2024. V. 26. № 1. Р. 54-66. DOI: https://doi.org/10.18127/j19998554-202401-06 (In Russian)

1. Zhukov A.A., Steshenko V.B., Kapustyan A.V. Problems of development and application of nano- and microsystem technology in promising RCT products. Problems of development of promising micro- and nanoelectronic systems (MES). 2012. № 1. P. 612–617. (In Russian)
2. Krasnov M.I., Steshenko V.B. Electronic component base for space purposes. Rocket and space instrumentation and information systems. 2021. V. 8. № 2. P. 88–101. (In Russian)
3. Kurnosenko A.E., Vlasov A.I. Application of multilevel decomposition to create a digital twin of the assembly production of electronic equipment. Information and mathematical technologies in science and management. 2022. № 3(27). P. 126–134. (In Russian)
4. Vlasov A.I. The concept of visual analysis of complex systems in the context of synchronous design technologies. Sensors and systems. 2016. № 8-9(206). P. 19–25. (In Russian)
5. Vlasov A., Naumenko A. Analysis of Visual Modeling Tools Development for Complex Production Systems. Lecture Notes in Information Systems and Organisation. 2022. V. 54. P.335-346. DOI 10.1007/978-3-030-94617-3_24.
6. Vlasov A.I., Shakhnov V.A. Visual Methodology for the Multi-factor Assessment of Industrial Digital Transformation Components. Lecture Notes in Information Systems and Organisation. 2021. V. 44. P. 57–65. DOI 10.1007/978-3-030-73261-5_6.
7. Vlasov A.I., Rasyuk A.A., Khokhlunova O.D. FPGA System Design Using Visual Languages. Problems of development of promising micro- and nanoelectronic systems (MES). 2022. № 3. P. 18–23. DOI 10.31114/2078-7707-2022-3-18-23. (In Russian)
8. Vlasov A.I., Marikova E.A. Analysis of Visual Modeling Methods for Complex Systems. Dynamics of complex systems – XXI century. 2020. V. 14. № 3. P. 5–22. DOI 10.18127/j19997493-2003-01. (In Russian)
9. Gaifulina D.A., Kotenko I.V. Analysis of Deep Learning Models for Network Anomaly Detection in Internet of Things. Information and control systems. 2021. № 1(110). P. 28–37. DOI 10.31799/1684-8853-2021-1-28-37. (In Russian)
10. Vizilter Yu.V., Gorbatsevich V.S., Zheltov S.Yu. Structure-Functional Analysis and Synthesis of Deep Convolutional Neural Networks. Computer optics. 2019. V. 43. № 5. P. 886–900. DOI 10.18287/2412-6179-2019-43-5-886-900. (In Russian)
11. Nesterov A.V. Computer methods and tools for deep processing, analysis and synthesis of publicly available documents. Novosibirsk: GPSTB of the Siberian Branch of the USSR Academy of Sciences. 1991. 214 p. (In Russian)
12. Fedorenko Yu.S., Gapanyuk Yu.E. Analysis of the Deep Neural Networks Characteristics in the Context of Digits Recognition Task. Neurocomputers: development, application. 2017. № 2. P. 24–30. (In Russian)
13. Vlasov A.I., Artemiev B.V., Selivanov K.V., Mironov K.S., Isroilov J.O. Predictive Control Algorithm for a Variable Load Hybrid Power System on the Basis of Power Output Forecast. International Journal of Energy Economics and Policy. 2022. V. 12. № 3. P. 1–7. DOI 10.32479/ijeep.12912.
14. Adamov A.P., Adamova A.A., Tsivinskaya T.A. Sensors for Control Systems of Tightness of the Case of the Aircraft. Reliability and quality of complex systems. 2018. № 4(24). P. 134–141. DOI 10.21685/2307-4205-2018-4-15. (In Russian)
15. Sergeeva N.A., Tsivinskaya T.A., Shakhnov V.A. Control and Measuring Mems Devices with Use of Small-Sized Sensitive Elements from Single-Crystal Silicon for Space Branch. Sensors and systems. 2016. № 3(201). P. 32–39. (In Russian)
16. Mileshin S.A., Tsivinskaya T.A., Sergeeva N.A. Microelectromechanical Sensors and Microstructures in Aerospace Applications. KnE Engineering. 2018. P. 336–343. DOI 10.18502/keg.v3i6.3012.
17. Loskutov A.I., Rylkov A.I., Ryakhova E.A., Borodyuk A.A. Proactive Model of the Onboard Avionics Autonomous Spacecraft Diagnosis with the Prediction of the Faults Occurrence and Localization Based on Neural Networks. Flight. All-Russian Scientific and Technical Journal. 2020. № 10. P. 8–19. (In Russian)
18. Loskutov A.I., Stolyarov A.V., Ryakhova E.A. Method for Control of Technical State of Onboard Radioelectronic Equipment of Spacecrafts Based on Interaction of Elements of Distributed Technical Diagnosis System. Control. Diagnostics. 2021. V. 24. № 1(271). P. 44–50. DOI 10.14489/td.2021.01.pp.044-050. (In Russian)
19. Polyakov A.A., Fetisov M.V. Classification of Data Preprocessing Algorithms for Machine Learning. Technologies of engineering and information systems. 2021. № 4. P. 70–79. (In Russian)
20. Polyakov A.A., Fetisov M.V. Classification of Methods for Determining Recognition Accuracy in Machine Learning Tasks. Technologies of engineering and information systems. 2022. № 1. P. 3–11. (In Russian)
21. Ivanova G.S., Fokina Yu.O. Analysis of the Use of Machine Learning Algorithms in Fraud Monitoring Systems. Technologies of engineering and information systems. 2022. № 2. P. 121–132. (In Russian)
22. Gaev A.V., Rogotovsky A.D., Lanzberg A.V. Classification of Physical Objects with the Help of Convolutional Neural Networks on the Example of the Gas Recognition Task. Technologies of engineering and information systems. 2019. № 1. P. 95–104. (In Russian)
23. Ivanova G.S., Dobryanskaya E.M. Designing a Hybrid Recommender System Based on Data Compression Algorithms. Technologies of engineering and information systems. 2022. № 2. P. 98–105. (In Russian)
24. Ivanova G.S., Golovkov A.A., Tyurin S.A. Object Detection and Classification in Images of Urban Infrastructure. Technologies of engineering and information systems. 2017. № 2. P. 15–25. (In Russian)
25. Ivanova G.S., Golovkov A.A., Tyurin V.A. Object Detection and Classification in Infrared Images. Technologies of engineering and information systems. 2017. № 2. P. 81–90. (In Russian)
26. Popov A.Yu., Evdokimov A.A. Classification of Critical Situations of an Aircraft Based on Automatic Data Analysis. Technologies of engineering and information systems. 2018. № 3. P. 40–53. (In Russian)
27. Vlasov A.I., Grigoriev P.V., Krivoshein A.I., Shakhnov V.A., Filin S.S., Migalin V.S. Smart management of technologies: predictive maintenance of industrial equipment using wireless sensor networks. Entrepreneurship and Sustainability Issues. 2018. V. 6. № 2. P. 489–502. DOI 10.9770/jesi.2018.6.2(2).
28. Vlasov A.I., Echeistov V.V., Krivoshein A.I., Shakhnov V.A., Filin S.S., Migalin V.S. An information system of predictive maintenance analytical support of industrial equipment. Journal of Applied Engineering Science. 2018. V. 16. № 4. P. 515–522. DOI 10.5937/jaes16-18405.
29. Vlasov A.I., Yudin A.V., Shakhnov V.A., Usov K.A., Salmina M.A. Design methods of teaching the development of internet of things components with considering predictive maintenance on the basis of mechatronic devices. International Journal of Applied Engineering Research. 2017. V. 12. № 20. P. 9390–9396.
30. Vlasov A.I., Grigoriev P.V., Krivoshein A.I. Model of Predictive Equipment Maintenance with Application of Wireless Touch Networks. Reliability and quality of complex systems. 2018. № 2(22). P. 26–35. DOI 10.21685/2307-4205-2018-2-4. (In Russian)
31. Yuldashev M.N., Vlasov A.I., Novikov A.N. Energy-efficient algorithm for classification of states of wireless sensor network using machine learning methods. Journal of Physics: Conference Series. 2018. P. 032153. DOI 10.1088/1742-6596/1015/3/032153.
32. Amaeva L.A. Comparative analysis of data mining methods. Innovative science. 2017. № 2-1. P. 27–29. (In Russian)
33. Al-Rammahi A.A.H., Gromov Yu.Yu., Koshelev E.V., Minin Yu.V. Review and Analysis of Big Data Clustering Algorithms. Devices and Systems. Management, control, diagnostics. 2021. № 9. P. 30–38. DOI 10.25791/pribor.9.2021.1292. (In Russian)
34. Pestunov I.A., Sinyavsky Yu.N. Clustering Algorithms in Satellite Images Segmentation Tasks. Bulletin of the Kemerovo State University. 2012. № 4-2(52). P. 110–125. (In Russian)
35. About Epsilon Launch Vehicle. [Electronic resource] – Access mode: https://global.jaxa.jp/projects/rockets/epsilon/, date of reference 25.12.2022.
36. Klimov D.I. Video Telemetric Control of Industrial Products. Rocket and space instrumentation and information systems. 2018. V. 5. № 2. P. 89–98. DOI 10.30894/issn2409-0239.2018.5.2.89.98. (In Russian)
37. Klimov D.I. Measurement of the Physical Quantities Characterizing Factors of Impact on Industrial Products by a Remote Contactless Method. Radio engineering. 2018. № 2. P. 80–84. (In Russian)
38. Ganiev R. The Angara rocket risks falling apart due to engine vibration. [Electronic resource] – Access mode: https://hi-news.ru/eto-interesno/raketa-angara-riskuet-razvalitsya-iz-za-vibracii-dvigatelya.html, date of reference 25.12.2022. (In Russian)
39. Lieberman M.Yu. On modeling the processes of formation of launch loads that have a dynamic effect on the spacecraft. Questions of electromechanics. Proceedings of VNIIEM. 2013. V. 136. № 5. P. 19–30. (In Russian)
40. Joblove G.H., Greenberg D. Color spaces for computer graphics. Proceedings of the 5th annual conference on Computer graphics and interactive techniques. 1978. P. 20–25. DOI 10.1145/800248.807362.
41. Klimov D.I., Mamedov T.T. Video Monitoring System for Tracking the Processes Accompanying the Movement of Rocket and Space Technology Products. AIP Conference Proceedings. 2021. V. 2318. P. 150032. DOI 10.1063/5.0036482.
42. Dolgov E.N. Artificial intelligence for aircraft control. Young scientist. 2021. № 16(358). P. 81–86. (In Russian)
43. Prudius A.A., Karpunin A.A., Vlasov A.I. Analysis of machine learning methods to improve efficiency of BIG DATA processing in industry 4.0. Journal of Physics: Conference Series. 2019. P. 032065. DOI 10.1088/1742-6596/1333/3/032065.
44. Michalski R.S., Carbonell J.G., Mitchell T.M. Machine Learning: An Artificial Intelligence Approach. Berlin: Springer. 1983. DOI 10.1007/978-3-662-12405-5.
45. Wang L., Cheng L., Zhao G. Machine Learning for Human Motion Analysis: Theory and Practice. IGI Global. 2009. 318 p.
46. Lekun Ya. How the machine learns. Revolution in the field of neural networks and deep learning. Moscow: Alpina PRO. 2021. 335 p. ISBN 978-5-907394-92-6. (In Russian)
47. Gridnev V.N., Sergeeva M.D., Chebova A.I. Linear Models for Detection of Faults in the Electronic Cells with Using Thermal Imaging Method. Control. Diagnostics. 2014. № 8. P. 57–66. DOI 10.14489/td.2014.08.pp.057-066. (In Russian)
48. Amirkhanov A.V., Aristov R.S., Vlasov A.I., Gladkikh A.A., Zakharchenko A., Makarchuk V.V. The use of modern models of artificial neural networks for the analysis of defects in the manufacture of submicron VLSI. Nanoindustry. 2017. № S(74). P. 395–406. (In Russian)
49. Aristov R.S., Vlasov A.I., Veryasova A.Yu., Gladkikh A.A., Makarchuk V.V. Investigating Diff Erent Convolution Neural Network Models Used for Imaging Defects Classification of VLSI Patterns. Nanoindustry. 2018. № S(82). P. 392–398. (In Russian)
50. Averyanikhin A.E., Vlasov A.I., Evdokimova E.V. Hierarchical pyramidal subsampling in deep convolutional networks for visual pattern recognition. Neurocomputers. 2021. V. 23. № 1. P. 17–31. DOI 10.18127/j19998554-202101-03. (in Russian)
51. Buyanov A.A., Vlasov A.I., Gridnev V.N. The neuronet hardware and software integrated system for defectoscopy of printed circuits based on microsections. The 3D international scientific conference "Computer methods and inverse problems in NDT and diagnostics". 2002. P. 71.
52. Viryasova A.Yu., Vlasov A.I., Gladkikh A.A. Neural Network Methods for Integral Structure Non-Destructive Testing. Neurocomputers: development, application 2019. № 2. P. 54–67. DOI 10.18127/j19998554-201902-06. (in Russian)
53. Buyanov A.I., Vlasov A.I., Zagoskin A.V. Application of Neural Network Methods at Defectoscopy of Printed-Circuit Boards.  Neurocomputers: development, application. 2002. № 3. P. 42–70. (in Russian)
54. Panfilova S.P., Vlasov A.I., Gridnev V.N., Chervinsky A.S. Contactless thermal control of electronic equipment products. Manufacture of electronics. 2007. № 3. P. 25–30. (in Russian)
55. Panfilova S.P., Vlasov A.I., Gridnev V.N., Chervinsky A.S. Thermography of Electronic Devices. Technology and design in electronic equipment. 2007. № 6. P. 42–49. (in Russian)
56. Vlasov A.I. The current state and trends in the development of the theory and practice of active quenching of wave fields. Devices and control systems. 1997. № 12. P. 59–70. (in Russian)
57. Vlasov A.I., Volodin E.A., Sementsov S.G., Shakhnov V.A. Electronic Systems of Active Management of Wave Fields: History and Tendencies of Development. Foreign radioelectronics. The successes of modern radio electronics. 2002. № 4. P. 3–23. (in Russian)
58. Vlasov A.I. Neural Network Realization of Microprocessor Systems Active Noise and Vibration Control. Neurocomputers: development, application. 2000. № 1. P. 40–44. (in Russian)
59. Vlasov A.I. Principles of active suppression of the action of vibration fields on electronic equipment. Devices and control systems. 1996. № 11. P. 30–32. (In Russian)