Model for monitoring the technical condition of onboard equipment of space vehicles based on the values of telemetered parameters of transient processes

The issues of identifying the onboard equipment of spacecraft and formalizing the process of monitoring its technical condition are considered. The ambiguity of the assessment of the technical condition of the onboard equipment based on the parameters characterizing the transient processes is revealed. An approach to estimating the parameters of transient processes using a neural network is proposed. A mathematical problem has been set – to develop a model for monitoring the technical condition of onboard equipment of spacecraft with minimization of erroneous decisions about the type of technical condition in the control process. A conceptual model for monitoring the technical condition of the onboard equipment, extended by a neural network transformation of the telemetered parameters of transient processes, is proposed. The application of the model in a distributed control system for spacecraft onboard equipment makes it possible to eliminate indirect control by calculated parameter values in order to achieve maximum control reliability. The effectiveness of the proposed approach is shown on the example of a spacecraft motion control system. The values of signs of technical condition are estimated according to the values of the telemetered parameters of the angular velocities received from the sensors. The obtained results showed the advantages of using multilayer neural networks for the formation of additional features of dynamic systems and the possibility of achieving high accuracy of estimation of these features with their help, thereby ensuring the maximum completeness of the technical condition control.

1. Mikoni S. V., Sokolov B. V., Yusupov R. M. Qualimetry of models and polymodel complexes: monograph, Moscow, RAN Publ., 2018, 314 p. (In Russ.)

2. Li Z., Tian L., Jiang Q., Yan X. Industrial & Engineering Chemistry Research, 2020, vol. 59, pp. 18061–18069. https://doi.org/10.1021/acs.iecr.0c03082

3. Guan L., Qiao F., Zhai X., Wang D. IEEE Transactions on Instrumentation and Measurement, 2022, vol. 71, 3522111. https://doi.org/10.1109/TIM.2022.3200695

4. Diao N., Zhang Y., Sun X., Song C., Wang W., Zhang H. IEEE Transactions on Power Electronics, 2023, vol. 38, no. 2, pp. 2539–2551. https://doi.org/10.1109/TPEL.2022.3216870

5. Burrola G. L., Leal M. Á. L., Mijares J. S. 2022 XXIV Robotics Mexican Congress (COMRob), Mineral de la Reforma/ State of Hidalgo, Mexico, 2022, pp. 48–53. http://dx.doi.org/10.1109/COMRob57154.2022.9962315

6. Loskutov A. I., Klykov V. A., Ryakhova E. A., Stolyarov A. V., Shestopalova O. L. Measurement. Monitoring. Management. Control, 2021, vol. 1(35), pp. 5–16. (In Russ.) https://doi.org/10.21685/2307-5538-2021-1-1

7. Loskutov A. I., Klykov V. A. Kontrol’. Diagnostika, 2016, no. 4, pp. 57–63. (In Russ.) https://elibrary.ru/vszfaf

8. Yakimov V. L., Maltsev G. N. Informatics and Automation, 2022, vol. 21, no. 1, pp. 126–160. (In Russ.) https://doi.org/10.15622/ia.2022.21.5

9. Walsh S., Murphy D., Doyle M., et. al. Aerospace, 2021, vol. 8(9), 254. https://doi.org/10.3390/aerospace8090254

10. Monteiro J. P., Rocha R. M., Silva A., Afonso R., Ramos N. Aerospace, 2019, vol. 6(12), 131. https://doi.org/10.3390/aerospace6120131

11. Suhadis N. M. Proc. International Conference of Aerospace and Mechanical Engineering 2019. In: Lecture Notes in Mechanical Engineering. Springer, Singapore. 2020, pp. 563– 573. https://doi.org/10.1007/978-981-15-4756-0_50