论文部分内容阅读
利用自回归小脑模型神经网络(recurrent cerebella model neural network,RCMAC)良好的非线性逼近能力和自学习能力,结合反馈线性化和反演控制方法,提出了一种自适应非线性控制策略,用于高速再入飞行器控制系统的设计。该方案将RCMAC干扰观测器(recurrent cerebella disturbance observer,RCDO)用于估计系统模型的不确定项,同时采用反演控制方式设计伪线性控制项,并利用符号函数逼近误差的上界,根据Lyapunov稳定性理论设计了权值更新规则,保证闭环系统信号有界。高速再入飞行器的六自由度仿真结果验证了方法的有效性和鲁棒性。
By using the good non-linear approximation ability and self-learning ability of recurrent cerebella model neural network (RCMAC), an adaptive nonlinear control strategy is proposed for feedback linearization and inversion control Design of High Speed Reentry Vehicle Control System. In the scheme, the recurrent cerebella disturbance observer (RCDO) is used to estimate the uncertainties of the system model. At the same time, the pseudo-linear control term is designed by the inversion control method. The upper bound of the error is approximated by the symbolic function. According to the Lyapunov stability The theory of sex is designed to update the weights to ensure that the closed-loop system signals are bounded. Six degrees of freedom simulation of the high-speed reentry vehicle validates the effectiveness and robustness of the proposed method.