An adaptive finite time composite fault tolerant control strategy based on an optimized neural network for Attitude control systems (ACSs) of satellites is proposed considering the state time-varying delays, concurrent actuator and sensor faults, system uncertainties, modelable external disturbance and operating noise. An uncertain time-varying state space model for ACSs of satellites is established, and sensor faults are equivalent to actuator-like faults. A disturbance observer is designed for estimating the modelable external disturbance, and an improved dwarf mongoose optimization (DMO) algorithm based on the Levy flight distribution is utilized to optimize the basis function of hyperbasis function neural networks to better estimate the augmented actuator faults that include the actuator fault and the actuator-like fault. Furthermore, an adaptive finite time composite fault-tolerant controller is proposed, which includes the delay-dependent feedback control law, disturbance estimation based-disturbance compensation law and the adaptive fault compensation law based on the augmented fault estimation using the improved DMO-hyper basis function neural network. The finite time boundness of the close-loop dynamics to the uncertainties, operating noise, and augmented actuator faults and the robustness of the measurement to the uncertainties, operating noise and augmented actuator faults are analyzed, and the observer and controller design is formulated as the linear matrix inequalities. Simulation examples for ACSs in different working conditions are considered to exhibit the proposed method's effectiveness.

中文翻译：

---

卫星姿态控制系统的神经自适应有限时间复合容错控制

考虑到状态时变延迟、并发执行器和传感器故障、系统不确定性、可建模的外部干扰和运行噪声，提出了一种基于优化神经网络的卫星姿态控制系统（ACS）自适应有限时间复合容错控制策略。建立了卫星ACS的不确定时变状态空间模型，将传感器故障等效为执行器类故障。设计了扰动观测器来估计可建模的外部扰动，并利用基于 Levy 飞行分布的改进型矮猫鼬优化 (DMO) 算法来优化超基函数神经网络的基函数，以更好地估计增强执行器故障，包括执行器故障和类执行器故障。此外，提出了一种自适应有限时间复合容错控制器，包括依赖于延迟的反馈控制律、基于扰动估计的扰动补偿律以及基于使用改进的DMO-超基的增强故障估计的自适应故障补偿律。函数神经网络。分析了闭环动力学对不确定性、运行噪声和增强执行器故障的有限时间有界性以及测量对不确定性、运行噪声和增强执行器故障的鲁棒性，并将观测器和控制器设计公式化为线性矩阵不等式。ACS在不同工作条件下的仿真例子被认为展示了所提出方法的有效性。