考虑未知死区非线性的自适应模糊神经UUV航迹跟踪控制

Robust adaptive self-organizing neuro-fuzzy tracking control of UUV with unknown dead-zone nonlinearity

针对无人水下航行器(unmanned underwater vehicles, UUV)在航迹跟踪控制中存在未知死区非线性和工作环境不确定性的问题,提出一种鲁棒自适应自组织模糊神经控制策略,采用滑模趋近律控制框架和自组织模糊神经网络逼近器在线估计系统未知状态和进行参数的自适应,并采用有限增益鲁棒控制器补偿重构误差。根据李雅普诺夫稳定性理论分析证明所有参数和跟踪状态均有界,并且当时间趋向于无穷大时,跟踪误差及其导数都趋向于零且闭环系统的信号有界。通过与已有控制策略对比仿真表明,该控制策略具有先进性和有效性,对无人水下航行器设计具有指导意义。

A robust adaptive self-organizing neuro-fuzzy control scheme for trajectory tracking of unmanned underwater vehicle with uncertainties and unknown dead-zone nonlinearity was proposed. The scheme adopted a novel sliding mode reaching law control framework and a self-organizing neuro-fuzzy network approximator to estimate the unknown dynamic and self-adaptive the parameter. The robust controller was employed to provide the finite L2-gain property to cope with reconstruction errors. Lyapunov stability theory analysis showed that tracking errors and their derivatives were stable and all signals in the closed-loop system were bounded. Comparative simulation results demonstrated the effectiveness and superiority of the proposed scheme, which could be a reference for the design of unmanned underwater vehicle.