Fully Adaptive-Gain-Based Intelligent Failure-Tolerant Control for Spacecraft Attitude Stabilization Under Actuator...

Area of Science:

• Aerospace Engineering
• Control Systems Theory
• Artificial Intelligence

Background:

• Spacecraft attitude stabilization is critical for mission success.
• Actuator saturation and failures pose significant challenges to control systems.
• Existing methods may struggle with uncertainties and real-time adaptation.

Purpose of the Study:

• To develop novel neural network-based control schemes for spacecraft attitude stabilization.
• To address actuator saturation and failures using anti-saturation adaptive strategies.
• To enhance robustness against modeling uncertainties, external disturbances, and actuator faults.

Main Methods:

• Design of two controllers incorporating anti-saturation functions.
• Implementation of radial basis function neural networks (RBFNNs) with fixed-time terminal sliding mode (FTTSM).
• Development of a fully adaptive-gain controller for improved robustness and adaptivity.

Main Results:

• Both proposed controllers effectively handle actuator saturation and failures.
• The adaptive controllers demonstrate robustness against uncertainties and disturbances.
• Scalar adaptive parameters ensure light computational load and avoid controller redesign.

Conclusions:

• The proposed neural network-based control schemes are feasible for spacecraft attitude stabilization.
• The anti-saturation adaptive strategies enhance system reliability and performance.
• The methods offer efficient and adaptable solutions for complex spacecraft control problems.