考虑输入饱和的无人艇神经网络命令滤波反步控制
Neural Network-Based Command Filtered Backstepping Control for USV with Input Saturation
刘炳文 1于金鹏 1刘加朋 1王保防 1齐瑞1
作者信息
- 1. 青岛大学自动化学院,山东青岛 266071;山东省工业控制重点实验室,山东青岛 266071
- 折叠
摘要
针对具有输入饱和和未知非线性的无人水面艇(USV)系统的轨迹跟踪控制问题,提出一种基于命令滤波反步的自适应轨迹跟踪控制策略.利用径向基函数神经网络(RBFNN)逼近系统中的未知动态,减少了需要设计的自适应律数量,降低了系统的复杂度,并基于反步法设计了系统的控制律;通过引入命令滤波器及其补偿机制,解决了计算复杂的问题,消除了滤波误差的影响,提高了系统的控制精度;最后仿真验证了所提方法的有效性.
Abstract
A command filtered backstepping control method is proposed for the trajectory tracking problem of unmanned surface vehicle(USV)system with input saturation and unknown nonlinearity.The radial basis function neural network(RBFNN)is used for the approximation of the unknown dynamics,which can reduce the amount of adaptive laws and the complexity of the system.The control law is designed by the backstepping method.The command filter with error compensation mechanism is introduced into the system and the effect of filtering error is eliminated so that the control accuracy is improved.Finally,the effectiveness of the method is shown by the simulation experiment.
关键词
无人水面艇/命令滤波控制/神经网络/轨迹跟踪Key words
unmanned surface vehicle(USV)/command filter control/neural network/trajectory tracking引用本文复制引用
基金项目
教育部"长江学者奖励计划"特聘教授经费项目(T2022265)
国家重点研发计划(2017YFB1303503)
国家自然科学基金(61973179)
青岛市重点研发专项(21-1-2-6-nsh)
出版年
2024