基于模型预测的倾转旋翼自主着舰控制

无人机在自主着舰过程中会面临复杂的海况和舰艇的未知运动,对舰艇的未来运动预估和对外界环境的抗扰,对无人机末端安全自主着舰有着重要的意义。因此,针对倾转四旋翼无人机在复杂海况下的全自主着舰过程,设计了一种基于模型预测的改进自抗扰控制器。利用前馈(BackPropagation,BP)神经网络实现对舰艇未来运动的预测,针对局部BP神经网络易陷于局部最优解并且基本不具备泛化能力的问题,将全局误差引入到BP神经网络中,并且为加快模型的训练速度,将基于全局误差可变的学习速率算法引入到全局误差BP 神经网络。利用自抗扰控制器(Active Disturbance Rejection Control,ADRC)实现对外界环境抗干扰控制,通过扩张状态观测器(Extended Sate Observer,ESO)实现对外界未知环境的观测和补偿,并且将滑膜控制方法引入到非线性状态误差反馈器(Nonlinear State Error Feedback,NLSEF)中,加快系统的收敛速度。通过在不同舰艇运动模型下的一系列数字化仿真,验证了文中所提控制方法的有效性与合理性,仿真结果表明了文中所提控制方法可实现无人机在复杂海况下的全自主着舰。

Autonomous Landing Control for Tilt Rotor Basedon Model Prediction

Unmanned Aerial Vehicle (UAV) will face complex sea conditions and unknown motion in the process of autonomous landing, which is of great significance to the prediction of future motionof warship and the rejection of disturbance to the external environment for the safe landing of UAV terminal. Therefore, an improved Active DisturbanceRejectionControl(ADRC)based on modelprediction is designed for the fully autonomous landing process of quad tilt rotor UAV under complex sea conditions. The Back Propagation (BP) neural network is used to predict the future motion of warship. In order to solve the problem that the local BP neural network is easy to fall into the local optimal solution and basically does not have the generalization ability,the global error is introduced into the BP neural network, and in order to speed up the training speed of the model,the learning rate algorithm based on the global error variable is introduced into the global error BP neural network.The ADRC is used to realize the anti-interference control of the external environment, and The Ex-tended Sate Observer (ESO) is used to observe and compensate the unknown environment. The slide model control method is introduced into the Nonlinear State Error Feedback(NLSEF) to speed up the convergence speed of the system. Through a series of digital simulations under different warship motion models, the effectiveness and rationality of the control method proposed in this paper are veri-fied and verified. The simulation results show that the control method proposed in this paper can real-ize the fully autonomous landing of UAV under complex sea conditions.