Information and communication and chemical technologies

Vol. 1 No. 30 (2026) / 2026-03-30 / Number of views: 192

ADAPTIVE NONLINEAR CONTROL OF SPACECRAFT ATTITUDE USING NEURAL NETWORKS

Authors

L.N. Gumilyov Eurasian National University
https://orcid.org/0000-0003-2109-4512
L.N. Gumilyov Eurasian National University
https://orcid.org/0009-0004-9847-9669
Astana IT University
https://orcid.org/0000-0002-1328-8109
Abai Kazakh National Pedagogical University
https://orcid.org/0000-0001-9064-3330
Astana IT University
https://orcid.org/0000-0002-0289-0874
L.N. Gumilyov Eurasian National University
https://orcid.org/0000-0002-2526-6492

Keywords

adaptive control system, nonlinear dynamics, spacecraft, stabilization, neural networks, control systems

Link to DOI:

https://doi.org/10.58805/kazutb.v.1.30-1318

How to quote

Bisenbi , M.A., et al. “ ADAPTIVE NONLINEAR CONTROL OF SPACECRAFT ATTITUDE USING NEURAL NETWORKS”. Vestnik KazUTB, vol. 1, no. 30, Mar. 2026, doi:10.58805/kazutb.v.1.30-1318.

Abstract

Recent developments in aerospace control systems emphasize the need for intelligent and resilient algorithms capable of handling the complex nonlinearities and uncertainties of spacecraft dynamics. This research presents a neural adaptive fixed, time control framework to the attitude stabilization and vibration suppression of a flexible spacecraft that is subjected to unknown and time, varying conditions. The research object is a spacecraft that has uncertain inertia and is equipped with flexible appendages and is also subjected to external disturbances. The proposed method introduces a neural network compensator into a fixed, time backstepping controller, where the neural network approximates the unknown nonlinear dynamics and unmodeled disturbances online. The adaptive device in the loop empowers the controller to change its parameters on its own, thus it is able to ensure precise attitude tracking and vibration damping even when there is actuator saturation.

Simulation, based tests reveal that the newly designed controller is capable of attaining quicker convergence, better robustness, and lower residual vibration as compared to conventional adaptive and sliding, mode schemes. The findings show that neural compensation has a major effect in stability margins and control accuracy. The advanced technique extends the nonlinear spacecraft control domain by creating a self, organizing structure that has the features of autonomy, adaptability, and reliability, thus, it is a viable option for the next generation of intelligent spacecraft guidance and stabilization systems