Fault-Tolerant Sun-Pointing Attitude Control Based on Physics-Guided Neural Networks

To ensure system reliability and maintain power supply in fault conditions, this article proposes a fault-tolerant sun-pointing controller based on physics-guided neural networks for handling sensor faults. The proposed controller gains the fault tolerance ability by learning from the behavior of the nominal controller, which integrates a physics-based model with a deep learning model to exploit implicit physical insights during the learning process. The proposed controller enhances the intrinsic interpolative nature of the pure deep learning model, thereby improving fault tolerance for unknown faults. Furthermore, a novel loss function that incorporates the physics-based model is proposed. The loss function assigns different loss terms to the fault-free and the fault datasets, facilitating accurate utilization of loss terms. Unlike traditional active fault-tolerant control schemes, the proposed method requires no explicit fault detection and diagnosis module. The effectiveness of the proposed controller is validated through hardware-in-the-loop simulations. The results indicate that the proposed controller outperforms the pure deep learning controller, as evidenced by a shorter sun-pointing convergence time and more precise angular velocity.