【摘要】 为实现欠驱动自治水下机器人(AUV)的精确地形跟踪控制,设计了一种自适应神经网络控制器.采用径向基神经网络估计时变水动力阻尼引起的AUV模型不确定部分和外界海流干扰,设计自适应学习律来实现神经网络权值的最优估计.基于李雅普诺夫稳定性理论分析了跟踪控制系统的稳定性,设计的控制器可以使闭环误差系统渐近稳定且系统状态有界.仿真实验中选择实际测量得到的期望随机真实地形进行跟踪实验,并且要求AUV相对地形保持一个恒定的高度偏差.结果表明,该控制方法可以有效地降低模型非线性和不确定性引起的扰动,具有较高的跟踪精度,满足实际工程需求.更多还原

【Abstract】 In order to realize the bottom following control for underactuated autonomous underwater vehicle(AUV) accurately,an adaptive neural network controller is designed.In order to deal with the parameter variations and uncertainties due to time-varying hydrodynamic dampings,the radial basis function(RBF) neural network(NN) is adopted to estimate unknown terms where an adaptive law is chosen to guarantee optimal estimation of the weight of NN.The stability of the tracking control system is analyzed based on the Lyapunov stability theorem,and the closed error system is asymptotical stable and the system states are bounded by the designed controller.Bottom profile with real measured data is used to evaluate the performance of the bottom following controller.Simulation results demonstrate that the proposed controller is effective to eliminate the disturbances caused by vehicle’s nonlinear and uncertainty,and has higher tracking accuracy for engineering application.更多还原