大连海事大学学报 >
2016 , Vol. 42 >Issue 1: 1 - 6
DOI: https://doi.org/10.16411/j.cnki.issn10067736.2016.01.001
基于模糊神经网络的无人水下航行器航迹跟踪控制
收稿日期: 2015-12-16
修回日期: 2016-01-14
网络出版日期: 2016-01-15
基金资助
国家自然科学基金资助项目(51479018, 51379002); 中央高校基本科研业务费专项资金资助项目(3132014322).
Trajectory tracking for unmanned underwater vehicle based on fuzzy neural network
Received date: 2015-12-16
Revised date: 2016-01-14
Online published: 2016-01-15
针对外界扰动的无人水下航行器航迹跟踪控制问题，通过定义一个动态滑模面，结合Lyapunov稳定性理论，设计航迹跟踪滑模控制器.考虑到系统中存在的未建模动态，在保证不引入模型参数的前提下，采用模糊神经网络在线逼近理想滑模控制律,并根据Lyapunov稳定性理论及投影算法得出模糊神经网络的参数自适应律.理论分析证明闭环控制系统的一致渐近稳定性、所有变量的有界性及跟踪误差及其导数渐近趋向于零.仿真实验验证了所提控制策略的有效性.
关键词： 无人水下航行器(UUV); 航迹跟踪; 滑模控制(SMC); 模糊神经网络(FNN)
刘彦呈 , 付俞鑫 , 文元全 , 刘厶源 , 王 宁 . 基于模糊神经网络的无人水下航行器航迹跟踪控制[J]. 大连海事大学学报, 2016 , 42(1) : 1 -6 . DOI: 10.16411/j.cnki.issn10067736.2016.01.001
To cope with the external disturbances for tracking unmanned underwater vehicles (UUV), a trajectory tracking sliding mode controller (SMC) was designed combining with Lyapunov stability theorem by defining a sliding surface. Considering the unconstructed dynamics existing in the UUV system, a fuzzy neural network (FNN) was employed to online approximate the ideal sliding mode control law without introducing any model parameters. Moreover, the adaptation laws for parameters of FNN were derived by the Lyapunov stability theorem and projection algorithm. Theoretical analysis proves that the asymptotical stability of overall closedloop control system, the boundedness of all signals and the tracking error and its first derivative converge to zero. Simulation tests verify the effectiveness of the proposed scheme.
[1]陈佳,邢继峰.基于模糊自适应PID的潜艇深度控制[J].舰船科学技术,2011,33(2):56-60.
CHEN Jia,XING Ji-feng.Depth control of submarine based on fuzzy adaptive PID[J].Ship Science and Technology, 2011,33(2):56-60.(in Chinese)
[2]ERKAN K,ERDAL K.Adaptive neuro-fuzzy control of a spherical rolling robot using sliding mode control theory based online learning algorithm[J].IEEE Transactions on Cybernetics,2013,43(1):170-179.
[3]陈子印,王宏健,边信黔.基于反馈增益的AUV稳定神经网络反步变深控制[J].控制与决策,2013,28(3): 407-412.
CHEN Zi-yin,WANG Hong-jian,BIAN Xin-qian.Stable neural network backstepping for diving control of AUV based on feedback gain[J].Control and Decision,2013, 28(3):407-412.(in Chinese)
[4]汪伟,边信黔,王大海.AUV深度的模糊神经网络滑模控制[J].机器人,2003,25(3):209-212.
WANG Wei,BIAN Xin-qian,WANG Da-hai.Fuzzy neural network sliding-mode control of auto depth for AUV[J]. Robot,2003,25(3):209-212.(in Chinese)
[5]WAI Rong-jong,MUTHUSAMY R.Design of fuzzy-neural-network-inherited backstepping control for robot manipulator including actuator dynamics[J].IEEE Transactions on Fuzzy Systems,2014,22(4):709-722.
[6]林雷,任华彬,王洪瑞.基于模糊神经网络的机器人滑模自适应控制[J].控制工程,2007,14(5):532-539.
LIN Lei,REN Hua-bin,WANG Hong-rui.Sliding mode adaptive control for robots based on fuzzy neural net-works[J].Control Engineering of Chi-na,2007,14(5):532-539.(in Chinese)
[7]俞建成,张艾群,王晓辉,等.基于模糊神经网络水下机器人直接自适应控制[J].自动化学报,2007,33(8): 840-846.
YU Jian-Cheng,ZHANG Ai-Qun,WANG Xiao-Hui,et al. Direct adaptive control of underwater vehicles based on fuzzy neural networks[J].Acta Automatica Sinica,2007, 33(8):840-846.(in Chinese)
[8]FOSSEN T I.Marine control systems[M].Trondheim, Norway:Marine Cybernetics,2002:50-91.
[9]SLOTINE J J E,LI Wei-ping.Applied nonlinear con-trol[M].Englewood Cliffs,NJ:Prentice-Hall,1991:122-126.
/
| 〈 |
|
〉 |