基于正交神经网络的动力定位自适应控制器设计  

Dynamic positioning adaptive controller design based on orthogonal neural network

作　　者：徐海祥[1,2] 卢林枫 余文曌 韩鑫 朱梦飞 XU Haixiang *;LU Linfeng;YU Wenzhao;HAN Xin;ZHU Mengfei(Key Laboratory of High Performance Ship Technology of Ministry of Education,Wuhan University of Technology,Wuhan 430063,China;School of Transportation,Wuhan University of Technology,Wuhan 430063,China)

机构地区：[1]武汉理工大学高性能舰船技术教育部重点实验室,湖北武汉430063 [2]武汉理工大学交通学院,湖北武汉430063

出　　处：《大连理工大学学报》2019年第2期172-178,共7页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(51879210;51479158);中央高校基本科研业务费专项资金资助项目(172102003)

摘　　要：动力定位船舶在海上进行定点定位作业时不可避免地会受到风、浪、流海洋环境力的干扰,这种持续的环境力扰动会导致船舶在实际定位时产生静态误差,不能准确地到达目标定位点.在利用反步法进行控制器设计时,大多数文献引入自适应积分项用于抵抗外界环境扰动,通过在控制器中加入船舶当前位置与目标位置的偏差积分项估计出外界未知环境扰动,从而达到自适应控制效果.在此基础上,改进了自适应积分项为正交基神经网络项进行控制器设计,以补偿静态误差,实现准确定位.最后通过水池模型试验对比验证了所设计控制器的可行性.Dynamic positioning ship will inevitably be disturbed by marine environmental forces such as wind,waves and current which cause static errors in the actual positioning of the ship.When using the backstepping method to design the controller,most of the documents introduce adaptive integral to resist the environmental load interference.By adding the deviation integral of the current position of the ship and the target position in the controller,the unknown environment disturbance is estimated,thus the adaptive control effect is achieved.On this basis,the adaptive integral term is improved for the orthogonal basis neural network to design the controller and the purpose of eliminating static deviation and realizing the accurate positioning is achieved.Finally,the feasibility of the designed controller is verified through the comparison of model experiments.

关 键 词：动力定位 定点定位 自适应控制 模型试验 

分 类 号：U674[交通运输工程—船舶及航道工程]