Document Type : Research Article

Authors

1 M.Sc . Department of Aerospace Engineering, Khajeh Nasir Toosi University of Technology, Tehran.Iran.

2 Assistant Professo. Department of Aerospace Engineering, Khajeh Nasir Toosi University of Technology, Tehran, Iran.

3 M.Sc. Department of Aerospace Engineering, Khajeh Nasir Toosi University of Technology, Tehran, Iran.

Abstract

In this paper, an orbit control algorithm is implemented for low earth orbit (LEO) satellites, using artificial neural networks (ANN), model-based predictive control (MPC), and linear quadratic regulator (LQR). As a self-tuning regulator structure, an ANN is used to learn the model of the satellite with external disturbances, after extracting a linear online model, based on ANN. Both LQR and MPC controllers are used to keep the satellite in its orbit. 

Keywords

Main Subjects

[1]  Melton, R.G., “Fundamentals of Astrodynamics and Applications”, J. Guid. Control. Dyn., Vol. 21, No. 4, pp. 672–672, 1998.
[2]  Tavakoli M.M. and Assadian, N., “Model Predictive Orbit Control of a Low Earth Orbit Satellite Using Gauss’s Variational Equations”, Proc. Inst. Mech. Eng. Part G J. Aerosp. Eng., Vol. 228, No. 13, pp. 2385–2398, 2014.
[3]  Giri, D.K., “Attitude Control of Satellites Actuated by Hybrid Actuators”, The 2019 International Conference on Mechatronics, Robotics and Systems Engineering (MoRSE), Bali, Indonesia, 2019.
[4]  Darvishpoor, S., Roshanian, J., and Tayefi, M., “A Novel Concept of Vtol BI-Rotor Uav Based on Moving Mass Control”, Aerosp. Sci. Technol., Vol. 107, pp. 106238, 2020.
[5]  Ahmed P.S. and Guang-Qian, X., “Autonomous Orbit Control With Position and Velocity Feedback, Using Modern Control Theory”, US-0319161, 1997.
[6]  Tavakkoli, M.M., “Model Predictive Orbit Control of a LEO Satellite Using Gauss’s Variational Equations”, Ms.c. Thesis, Sharif University of Technology, Tehran, Iran, 1997 (In Persian).
 [7] Weiss, A., Kalabić, U.V., and Di Cairano, S., “Station Keeping and Momentum Management of Low-Thrust Satellites Using MPC”, Aerosp. Sci. Technol., Vol. 76, pp. 229–241, 2018.
[8]  Lim, Y. Jung, Y., and Bang, H., “Robust Model Predictive Control for Satellite Formation Keeping With Eccentricity/Inclination Vector Separation”, Adv. Sp. Res., Vol. 61, No. 10, pp. 2661–2672, 2018.
[9]  Prieto, D.  and Ahmad, Z., “A Drag Free Control, Based on Model Predictive Technics”, Proc. Am. Control Conf., Vol. 3, pp. 1527–1532, 2005.
[10]   Caverly, R.J., Di Cairano, S., and Weiss, A., “Electric Satellite Station Keeping, Attitude Control, and Momentum Management by MPC”, IEEE Trans. Control Syst. Technol., Early Access Article, 2020.
[11]   Hu, Q., Xie, J., and Wang, C., “Dynamic Path Planning and Trajectory Tracking Using MPC for Satellite with Collision Avoidance”, ISA Trans., Vol. 84, pp. 128–141, 2019.
[12]   Yu, J., Yingchun, Z., and Jing, J., “Nonlinear MPC for Attitude System of Miniature Satellite Using Multiple MEMS Actuators”, The 10th World Congress on Intelligent Control and Automation, Beijing, China, 2012.
[13]   Mitchell, T.M., Machine learning, McGraw Hill, New York, 1997.
[14]   Darvishpoor, S., Roshanian, J., Raissi, A., and Hassanalian, M., “Configurations, Flight Mechanisms, and Applications of Unmanned Aerial Systems: A Review”, Prog. Aerosp. Sci., Vol. 121, p. 100694, 2020.
[15]   Darvishpoor, S. and J. Roshanian, “A Survey on Unmanned Aerial Vehicles : Scheme Approach”, The 18th International Conference of Iranian Aerospace Society, 2020.
[16]   Darvishpoor, S. and Roshanian, J., “Design and Implementation of an Entirely Machine Learning Based Controller for an Unmanned Quadrotor”, The 17th International Conference Iranian Aerospace Societ, Tehran, Iran, 2018.
[17]   Darvishpoor, S. and Roshanian, J., “Design and Implementation of a Comprehensive Controller Based Entirely on Machine Learning for an Unmanned Four-seater”, The 17th International Conference Iranian Aerospace Societ, Tehran, Iran, 2018.
 [18]  Åkesson, B.M. and Toivonen, H.T., “A Neural Network Model Predictive Controller”, J. Process Control, Vol. 16, No. 9, pp. 937–946, 2006.
[19]   Piche, S., Keeler, J.,  Martin, G., Boe, G., Johnson, D., and Gerules, M., “Neural Network Based Model Predictive Control”, NIPS Conference, Denver, Colorado, USA, , 1999.
[20]   Ranković, V. Radulović, J. Grujović, N., and Divac, D., “Neural Network Model Predictive Control of Nonlinear Systems Using Genetic Algorithms”, Int. J. Comput. Commun. Control, Vol. 7, No. 3, pp. 540–549, 2012.
[21]   Henriksen, L.C. and Poulsen, N.K., “An Online Re-Linearization Scheme Suited For Model Predictive and Linear Quadratic Control”, Technical University of Denmark, Lyngby, Denmark, IMM-Technical Report-2010-13, 2010.
[22]   Winqvist, R. Venkitaraman, A., and Wahlberg, B., “On Training and Evaluation of Neural Network Approaches for Model Predictive Control”, arXiv:2005.04112, 2020.
[23]   Pon Kumar, S.S., Tulsyan, A., Gopaluni, B., and Loewen, P., “A Deep Learning Architecture for Predictive Control”, IFAC-PapersOnLine, Vol. 51, No. 18, pp. 512–517, 2018.
[24]   Ławryńczuk, M., “Neural Networks in Model Predictive Control”, Stud. Comput. Intell., Vol. 252, pp. 31–63, 2009.
[25]   Curtis., H.D. Orbital Mechanics for Engineering Students, Elsevier Butterworth-Heinemann, Oxford, 2014.
[26]   Camacho, E.F.  and (Carlos) Bordons, C., Model Predictive Control, Springer, New York, 2007.