In this paper, a Broad Learning System (BLS) based adaptive full state constrained controller is investigated for a class of Space Unmanned Systems (SUSs) subjected to the actuator faults and input nonlinearities. In order to guarantee the time-varying state constraints and reduce the control complexity simultaneously, two nonlinear error transformations are utilized in this work. By estimating the lower boundary of the nonlinear actuator effectiveness, the instable dynamic caused by the actuator faults and input nonlinearities can be overcome. With the aid of the universal approximation ability of the BLS, the unknown nonlinear terms existing in the SUS attitude dynamic model can be handled. Furthermore, benefiting from the nodes dynamic adjusting mechanism of BLS, the control response speed and accuracy can be improved. The simulation results are presented to demonstrate the effectiveness and advantages of the proposed BLS-based adaptive full state constrained control method.

在本文中，针对一类受到执行器故障和输入非线性影响的空间无人系统（SUS），研究了基于广泛学习系统（BLS）的自适应全状态约束控制器。为了保证时变状态约束并同时降低控制复杂度，本文采用了两种非线性误差变换。通过估计非线性执行器有效性的下限，可以克服由执行器故障和输入非线性引起的动态不稳定。借助BLS的通用逼近能力，可以处理SUS姿态动力学模型中存在的未知非线性项。此外，受益于BLS的节点动态调整机制，可以提高控制响应速度和准确性。