摘要
针对传统滑模控制在自主水下航行器(AUV)的控制过程中存在抖振以及执行机构饱和对其控制性能的不利影响,提出一种基于神经网络的滑模控制方法。采用径向基函数神经网络(RBFNN)和自适应观测器对运动模型中的不确定项和未知外界干扰进行在线估计,削弱滑模抖振;采用RBFNN对控制输入受限前后的差值进行逼近,克服执行机构饱和引起的控制振荡。仿真结果表明,该控制方法相较于传统滑模控制具有更好的适应性和控制精度。
Considering the traditional sliding mode controller's chattering during the control of Autonomous Underwater Vehicle(AUV) and the adverse effects of actuator saturation on control performance,a sliding mode control method based on neural network has been proposed.The Radial Basis Function Neural Network(RBFNN) and adaptive observer are used to estimate the uncertain terms and unknown external disturbances in the motion model online to reduce sliding mode chattering.At the same time,the RBFNN is used to approximate the difference between the control inputs before and after being restricted to overcome the control oscillation caused by actuator saturation.The numerical simulation shows that this control method has better adaptability and control accuracy compared with traditional sliding mode control.
作者
欧阳晨
李璟璟
Ouyang Chen;Li Jingjing(Shandong Institute of Space Electronic Technology,Yantai,China;Yantai Research Institute,Harbin Engineering University,Yantai,China)
出处
《科学技术创新》
2024年第7期96-99,共4页
Scientific and Technological Innovation