摘要
针对USV运动航向控制问题,利用基于Lyapunov稳定性理论的滑模控制方法设计USV航向控制律.考虑到USV运动系统具有不确定性,利用具有万能逼近性能的模糊系统对USV运动模型中不确定项及外界干扰项进行模糊逼近.为了进一步提高模糊系统的逼近性能,采用具有学习能力快的RBF神经网络对模糊系统进行在线学习,优化模糊规则.仿真结果表明基于RBF网络优化的模糊控制该算法能够实现USV航向连续稳定跟踪.
For the problem of the heading control of USV(Unmanned Surface Vehicle)motion,the adaptive control law is designed by using the sliding mode control method based on Lyapunov stability theory.Considering the uncertainty of the USV motion system,the fuzzy system with universal approximation performance is used to fuzzily approximate the uncertainties and external disturbances in the USV motion model.In order to further improve the approximation performance of the fuzzy system,the radial basis function(RBF)neural network with fast learning ability is used to learn the fuzzy system online and optimize the fuzzy rules.The simulation results show that the proposed fuzzy control algorithm optimized by RBF neural network can achieve continuous and stable tracking of USV heading.
作者
王仁强
缪克银
孙建明
WANG Ren-qiang;MIAO Ke-yin;SUN Jian-ming(College of Navigation,Jiangsu Maritime Institute,Nanjing Jiangsu 211170,China)
出处
《广州航海学院学报》
2019年第4期16-19,共4页
Journal of Guangzhou Maritime University
基金
江苏省高校自然科学研究计划项目(19KJA150005
18KJB580003
19KJD580001)
关键词
USV
运动控制
滑模控制
自适应控制
模糊控制
RBF神经网络
Unmanned Surface Vehicle
motion control
sliding model control
adaptive control
fuzzy control
RBF neural network