欠驱动航天器编队重构的切换神经网络控制

针对圆轨道欠驱动航天器编队重构问题，将传统的自适应神经网络控制器和自适应滑模控制器相结合，设计了一种切换神经网络控制器，用以跟踪由伪谱法求解得到的航天器编队重构的最优开环控制轨迹。自适应神经网络控制器在活跃区域内工作，利用径向基神经网络(RBFNNs)近似动力学系统中的不确定项，自适应滑模控制器在活跃区域外工作，利用自适应律来估计近似误差上界，并采用李雅普诺夫方法证明了闭环系统稳定性。数值仿真结果表明切换神经网络控制器可在欠驱动条件下实现编队重构，与线性滑模控制器相比，实现了控制器快速、高精度、强鲁棒等控制性能。

Switching Neural Network Control for Underactuated Spacecraft Formation Reconfiguration

For the formation reconfiguration of underactuated spacecraft in a circular orbit，a switching neural network controller is designed based on the combination of the traditional adaptive neural network controller and the adaptive sliding mode controller to track the optimal open loop control trajectory of spacecraft formation reconstruction solved by the pseudospectral method. The adaptive neural network controller works in the active region and the dynamics uncertainties are approximated by the radial basis function neural networks (RBFNNs). The adaptive sliding mode controller works outside the active region and the upper bound of the approximate error is estimated by the adaptive law. The stability of the closed loop control system is proved via the Lyapunov based approach. The numerical simulation results have demonstrated the rapid，high precision，and robust performance of the proposed controller compared with the linear sliding mode controller.