论文部分内容阅读
提出基于模糊神经网络欠驱动水下自主机器人(AUV)的L_2增益鲁棒跟踪控制方法,该方法通过在线学习逼近动力学模型的不确定项.控制器克服了由于缺少横向推力对跟踪误差的影响,在考虑未知海流干扰情况下,实现了系统对模糊神经网络逼近误差的L_2增益小于γ.利用Lyapunov稳定性理论证明了闭环控制系统误差信号一致最终有界.最后,通过精确模型参数和参数扰动仿真实验验证了该控制方法具有很好的跟踪效果和较强的鲁棒性.
An L 2 gain robust tracking control method based on the fuzzy neural network under-actuated Underwater Autonomous Robot (AUV) is proposed, which approximates the uncertainties of the dynamic model by online learning. The controller overcomes the influence of the lack of lateral thrust on the tracking error , The L 2 gain of the approximation error of the fuzzy neural network is less than γ under the assumption of unknown current disturbance.The Lyapunov stability theory is used to prove that the error signal of the closed-loop control system is uniform and ultimately bounded.Finally, through the exact model parameters and parameter perturbations Simulation results show that the proposed control method has good tracking performance and strong robustness.