增益自适应滑模控制器在微型飞行器飞行姿态控制中的应用

Gain adaptive sliding mode controller for flight attitude control of MAV

针对微型飞行器的姿态角摄动引起的系统不确定性及外界干扰等问题,提出了基于区间二型模糊神经网络辨识的增益自适应模糊控制器。首先,给出了微型飞行器姿态动力学模型。然后,采用区间二型模糊神经网络对滑模控制器中由于姿态角摄动引起的系统不确定性进行在线辨识,通过增益自适应滑模控制器中的校正控制项对辨识误差及负载干扰进行补偿。最后,通过设计李亚普诺夫函数,得到闭环系统一致稳定条件下的区间二型模糊神经网络参数在线调整的自适应律及滑模增益自适应律。仿真对比表明,与传统的增益自适应滑模控制器和基于一型模糊神经网络辨识的滑模控制器及相比,本文提出的控制器不仅对系统的不确定性因素及外界干扰具有较强的鲁棒性,而且稳定误差小,跟踪精度高。

A gain adaptive sliding mode controller based on interval type-II fuzzy neural network identification was proposed to handle the system uncertainty and the external disturbances come from the attitude angle disturbance of a Micro Aircraft Vehicle（MAV）.Firstly,the attitude dynamical model of MAV was established.Then,the interval type-II fuzzy neural network was used to approximate the nonlinearity function and uncertainty functions in the attitude angle dynamic model of the MAV.The correct items from the gain adaptive sliding mode controller were taken to compensate identification errors and load disturbances.Finally,Lyapunov stability theorem was designed and the adaptive law and the sliding mode gain adaptive law for adjusting on line interval type-II fuzzy neural network parameters were obtained under the condition of asymptotic stability of the closed-loop system.The numerical simulation and comparison were performed and the results show that the proposed control system has not only stronger robustness to system uncertainty and external disturbances but also more excellent steady characteristics and tracking accuracy as compared with the conventional adaptive sliding model controller and the type-I fuzzy neural network based sliding mode controller.