School of Information and Control Engineering, Liaoning Petrochemical University, Fushun 113001, China.
School of Information and Control Engineering, Liaoning Petrochemical University, Fushun 113001, China.
ISA Trans. 2023 Jun;137:144-159. doi: 10.1016/j.isatra.2023.01.011. Epub 2023 Jan 14.
This paper designs an interval type-2 fuzzy neural network sliding mode robust controller (IT2FNNSMRC) to improve the stability of the vibrational angle of the orbital plane in magnetic rigid spacecraft attitude control. The control system consists of an interval type-2 fuzzy neural network (IT2FNN) controller, a PD controller, and a robust controller in parallel connection. The IT2FNN controller, as a nonlinear regulator, compensates the nonlinearity of the controlled object; the PD controller, as a feedback controller, ensures the global asymptotic stability of the control system; the robust controller inhibits input load disturbance. The IT2FNN controller hereof has a self-organizing function which enables it to automatically determine the network structure and parameters online. At the stage of IT2FNN structure learning, the standard on rule growth is set according to the incentive intensities of IT2FNN rule premises. A new rule is generated when the incentive intensities of rules are all smaller than a certain threshold; next, a significance index is set for each rule. When the significance index of some rule decays to a certain threshold, the corresponding rule shall be deleted to achieve the goals of optimizing IT2FNN structure and reducing system complexity. At the stage of parameter learning, adaptive adjustment of IT2FNN parameters is made via the sliding mode control theory learning algorithm, and the stabilities of the algorithm and control system are proven using Lyapunov function. Finally, the proposed control scheme is used in the control of a magnetic rigid spacecraft, as compared to three other designed control methods. Simulation results show that IT2FNNSMRC has superior control precision and stability. And the IT2FNN which adopts the proposed learning algorithm can address uncertainty satisfactorily, with higher computational implementability.
本文设计了一种区间型 2 阶模糊神经网络滑模鲁棒控制器（IT2FNNSMRC），以提高磁悬浮刚体航天器轨道平面振动角的稳定性。该控制系统由区间型 2 阶模糊神经网络（IT2FNN）控制器、PD 控制器和鲁棒控制器并行组成。IT2FNN 控制器作为非线性调节器，补偿被控对象的非线性；PD 控制器作为反馈控制器，确保控制系统的全局渐近稳定性；鲁棒控制器抑制输入负载干扰。这里的 IT2FNN 控制器具有自组织功能，能够在线自动确定网络结构和参数。在 IT2FNN 结构学习阶段，根据 IT2FNN 规则前提的激励强度设置规则增长的标准。当规则的激励强度都小于一定阈值时，生成新规则；接下来，为每个规则设置一个显著指数。当某些规则的显著指数衰减到一定阈值时，相应的规则将被删除，以达到优化 IT2FNN 结构和降低系统复杂性的目标。在参数学习阶段，通过滑模控制理论学习算法对 IT2FNN 参数进行自适应调整，并使用 Lyapunov 函数证明算法和控制系统的稳定性。最后，将提出的控制方案用于磁悬浮刚体航天器的控制，并与其他三种设计的控制方法进行比较。仿真结果表明，IT2FNNSMRC 具有更高的控制精度和稳定性。并且采用所提出学习算法的 IT2FNN 可以很好地解决不确定性问题，具有更高的计算可实现性。
