论文部分内容阅读
针对导弹六自由度非线性模型,根据时标分离原理将导弹系统分为快慢不同的四个回路。针对快、慢回路,提出了一种基于神经网络的自适应滑模控制器设计方案。首先分别在快、慢回路中采用反馈线性化实现解耦控制,然后设计基于神经网络的自适应滑模控制器来保证系统鲁棒性及性能,其中神经网络用来逼近系统的不确定性。理论分析及计算机仿真都表明,按照该方法设计的控制器不仅具有较强的鲁棒性,而且保证了闭环系统的渐近稳定性。
According to the six-degree-of-freedom missile nonlinear model, the missile system is divided into four loops with different velocities according to the time-scale separation principle. For fast and slow loops, an adaptive sliding mode controller design based on neural network is proposed. Firstly, the feedback linearization is used to realize the decoupling control in fast and slow loops respectively. Then an adaptive sliding mode controller based on neural network is designed to ensure the robustness and performance of the system. The neural network is used to approximate the system uncertainty. Theoretical analysis and computer simulation show that the controller designed by this method not only has strong robustness, but also ensures the asymptotic stability of the closed-loop system.