Determination of the force impact of an ion thruster plume on an orbital object via deep learning

Heading: 
Space Energy, Power and Propulsion
1Redka, MO, 2Khoroshylov, SV
1Institute of Technical Mechanics of the National Academy of Science of Ukraine and the State Space Agency of Ukraine, Dnipropetrovsk, Ukraine
2Institute of Technical Mechanics of the National Academy of Sciences of Ukraine and the State Space Agency of Ukraine, Dnipro, Ukraine
Space Sci. & Technol. 2022, 28 ;(5):15-26
https://doi.org/10.15407/knit2022.05.015
Publication Language: English
Abstract: 
The subject of research is the process of creating a neural network model (NNM) for determining the force impact of an ion thruster (IT) plume on an orbital object during non-contact space debris removal. The work aims to develop NNMs and study the influence of various factors on the accuracy of determining the force transmitted by the ion plume of the thruster to a space debris object (SDO). The tasks to resolve are to choose the structures of the NNMs, form a data set and use this data to train and validate the NNMs, and to explore the influence of the model structure and optimizer parameters on the accuracy of force determination. The methods used are plasma physics, computer simulation, deep learning, and optimization using an improved version of stochastic gradient descent. As a result of research, three NNMs have been developed, which differ in the number of hidden layers and neurons in hidden layers. For training and validation of the NNMs, a data set was generated for an SDO approximated by a cylinder using an autosimilar description of the ion plasma propagation.
       The data set was obtained for various relative positions and orientations of the object in the process of its removal from an orbit. Using this data set, the NNM parameters were optimized with the supervised learning method. The optimizer and its parameters are selected, providing a small error at the stage of validating learning outcomes. It was found that the accuracy of determining the force depends on the relative position and orientation of the SDO, as well as the architecture of the NNM, and the features of this influence were identified. The approach applied allows us to obtain the possibility of using methods of deep learning to determine the force impact of the IT plume on the SDO. The proposed models provide the accuracy of the force impact determination, which is sufficient for solving the considered class of problems. At the same time, NNM makes it possible to obtain results much faster in comparison with the methods used previously. This fact makes the NNMs promising to use both on-board and in mathematical modeling of missions to remove space debris.
Keywords: :ion thruster, deep learning, neural network model, space debris object, transmitted force
Full text (PDF)
References: 

1. Liou, J.-C, Anilkumar, A. K., Virgili, B., Hanada, T., Krag, H., & Lewis, H. et al. (2013). Stability of the future leo environment - an IAADC comparison study. Proc. of the 6th European Conference on Space Debris, Darmstadt, 2013 vol.723.

Retrieved from: https://conference.sdo.esoc.esa.int/proceedings/sdc6/paper/199.

2. Phipps C. R., Reilly J. P. (1997). ORION: Clear-ing Near-Earth Space Debris in Two Years Using a 30-kW Repetitively-Pulsed Laser. XI International Sympo-sium on Gas Flow and Chemical Lasers and High-Power Laser Conference, (4 April 1997). pp. 728-731.
https://doi.org/10.1117/12.270174

3. Takeichi N. (2006). Practical Operation Strategy for Deorbit of an Electrodynamic Tethered System. J. of Spacecraft and Rockets. vol. 43. no 6. pp. 1283-1288.
https://doi.org/10.2514/1.19635

doi:10.2514/1.19635.
https://doi.org/10.2514/1.19635

4. Dron', M., Golubek, A., Dubovik, L., Dreus, A., Heti, K. (2019). Analysis of ballistic aspects in the com-bined method for removing space objects from the near Earth orbits. Eastern-European Journal of Enterprise Technologies, 2 (5 (98)), 49-54.
https://doi.org/10.15587/1729-4061.2019.161778

5. Golubek A., Dron' M., Dubovik L., Dreus A., Kulyk O., Khorolskiy P. (2020). Development of the combined method to de-orbit space objects using an electric rocket propulsion system. Eastern-European Journal of Enterprise Technologies, 4 (5 (106)), 78-87.
https://doi.org/10.15587/1729-4061.2020.210378

6. Bombardelli, C., & Peláez, J. (2011). Ion Beam Shepherd for Contactless Space Debris Removal. JGCD, vol. 34, no. 3, pp. 916 - 920.
https://doi.org/10.2514/1.51832

doi:10.2514//1.51832

7. Phipps, C. R., & Reilly, J. P. (1997). ORION: Clearing Near-Earth Space Debris in Two Years Using a 30-kW Repetitively-Pulsed Laser. SPIE Proc. of the International Society for Optical Engineering, Edin-burgh, UK, pp. 728 - 731.
https://doi.org/10.1117/12.270174

8. Takeichi, N. (2006). Practical Operation Strate-gy for Deorbit of an Electrodynamic Tethered System. J. of Spacecraft and Rockets, vol. 43, no. 6, pp. 1283 - 1288. doi:10.2514//1.19635.
https://doi.org/10.2514/1.19635

9. Alpatov, A. P., Zakrzhevskii, A. E., Fokov, A. A., & Khoroshylov, S. V. (2015). Determination of optimal position of ion-beam shepherd in relation to space junk object. Technical Mechanics, no.2, pp. 37-48.

10. Khoroshylov, S. V. (2018). Control system of a spacecraft for contactless removal of space junk. Nauka ta innovacii, vol. 14, no. 4, pp. 5-18.
https://doi.org/10.15407/scin14.04.005

11. Khoroshylov, S. V. (2012). Relative control of an ion beam shepherd satellite in eccentric orbits. Acta Astronautica, no. 76, pp. 89-98.
https://doi.org/10.1016/j.actaastro.2020.06.027

12. Cichocki, F., Merino, M., & Ahedo, E. (2015). Collisionless Plasma thruster plume expansion model. Plasma Sources Science and Technology, vol. 24, no.3, pp. 83 - 95.
https://doi.org/10.1088/0963-0252/24/3/035006

13. Bombardelli, C., Urrutxua, H., Merino, M., Ahedo, E., & Pelaez, J. (2012). Relative dynamics and control of an ion beam shepherd satellite. Spaceflight mechanics, vol. 143, pp. 2145 -2158.

14. Alpatov, A. P., Cichocki, F., Fokov, A. A., Khoroshylov, S. V., Merino, M., & Zakrzhevskii, A. E. (2015). Algorithm for Determination of Force Transmit-ted by Plume of Ion Thruster to Orbital Object Using Photo Camera. 66th International Astronautical Con-gress, Jerusalem, Israel, pp. 1-9.

15. Fokov, A. A., & Khoroshilov, S. V. (2016). Val-idation of simplified method for calculation of trans-mitted force from plume of electric thruster to orbital object. Aviatsionno-kosmicheskaya tekhnika i tekhnologiya, no. 2, pp. 55-66.

16. Mitchell, T. (1997). Machine Learning. New York, NY: McGraw-Hill.

17. Pierson H., & Gashler M. (2017). Deep learning in robotics: a review of recent research. Adv. Robotics, vol. 31, no. 16, pp. 821-835.
https://doi.org/10.1080/01691864.2017.1365009

18. Khoroshylov, S. V., & Redka, M. O. (2021). Deep learning for space guidance, navigation, and con-trol. Space Science and Technology, vol. 27, no. 6 (133), pp. 38-52.
https://doi.org/10.15407/knit2021.06.038

19. Cybenko, G. (1989). Approximation by super-positions of a sigmoidal function. Mathematics of Con-trol, Signals, and Systems, vol. 2, no. 4, pp. 303-314.
https://doi.org/10.1007/BF02551274

doi:10.1007//BF02551274.

20. Hornik, K. (1991). Approximation capabilities of multilayer feedforward networks. Neural Networks, vol. 4, no. 2, pp. 251-257.
https://doi.org/10.1016/0893-6080(91)90009-T