一种基于扩展状态观测器的智能船舶Nomoto模型参数辨识方法  

Extended state observer-based parameter identification of Nomoto model for autonomous vessels

作　　者：朱曼 文元桥[1,2,3] 孙吴强 雷涛[2] ZHU Man;WEN Yuanqiao;SUN Wuqiang;LEI Tao(State Key Laboratory of Maritime Technology and Safety,Wuhan 430063,China;Intelligent Transportation Systems Research Center,Wuhan University of Technology,Wuhan 430063,China;National Engineering Research Center for Water Transport Safety,Wuhan 430063,China;Sunwin Intelligent Co.,Ltd.,Hefei,230000,China)

机构地区：[1]水路交通控制全国重点实验室,湖北武汉430063 [2]武汉理工大学智能交通系统研究中心,湖北武汉430063 [3]国家水运安全工程技术研究中心,湖北武汉430063 [4]合肥赛为智能有限公司人工智能研究院,安徽合肥230000

出　　处：《中国舰船研究》2023年第3期75-85,共11页Chinese Journal of Ship Research

基　　金：国家自然科学基金资助项目(52001237);武汉理工大学三亚科教创新园开放基金资助项目(2020KF0037)。

摘　　要：[目的]为了支持制导、导航、控制等船舶智能化技术的测试验证平台的搭建,利用系统辨识技术得到高精度的智能船舶野本(Nomoto)运动模型参数。[方法]充分结合扩展状态观测器(ESO)以及鲁棒加权最小二乘支持向量回归(RW-LSSVR)算法的优势,提出一种高效低成本的混合参数辨识方法。为解决模型参数辨识中无法直接有效获取某些状态量的问题,构建了基于ESO的状态估计方法。基于估计方法与直接测量的船舶运动状态量,采用具有较强抗异常值干扰的RW-LSSVR对智能船舶二阶线性Nomoto运动模型参数进行辨识。以已知模型的两艘船舶为测验对象,对所提参数估计与辨识方法进行综合测验。[结果]在利用较少传感器的情况下,通过ESO可较精确地估计出非直接测量的船舶运动状态量,并且利用RW-LSSVR辨识得到的参数值十分接近标准值。[结论]利用所提方法获得的估计状态可用于参数辨识,并且辨识模型具有较好的泛化性。[Objectives]In order to create a simulation test platform to effectively test the key technologies of intelligent ships such as guidance,navigation and control technology,this study uses system identification technology to identify the parameters of the Nomoto motion model of an intelligent ship with high precision.[Methods]A hybrid parameter identification method is proposed by fully combining the advant-ages of the extended state observer(ESO)and the robust weighted least square support vector regression al-gorithm(RW-LSSVR),our previously well-evaluated identification method.The ESO-based state estimator is applied to calculate immeasurable states using measurable states and the second-order linear Nomoto model.To evaluate the proposed approach,models of two vessels with predefined parameter values are employed for simulation tests.[Results]The proposed approach not only estimates immeasurable states with high accur-acy,but also ensures good performance in steering model parameter identification,with values very close to the nominal values.[Conclusions]The proposed ESO-based identification method shows good generalizab-ility and can effectively provide satisfactory estimates of immeasurable states,making it highly applicable to parameter identification.

关 键 词：智能船舶 Nomoto模型 状态估计 RW-LSSVR算法 混合参数辨识方法 

分 类 号：U666.1[交通运输工程—船舶及航道工程]