基于SVR的船舶简化分离型模型水动力系数辨识研究  

Hydrodynamic coefficients identification of ship simplified modular model based on support vector regression

作　　者：宋利飞 王毓清 彭伟 李培勇[1,2] 刘禹杉 张永峰 SONG Lifei;WANG Yuqing;PENG Wei;LI Peiyong;LIu Yushan;ZHANG Yongfeng(Key Laboratory of High Performance Ship Technology(Wuhan University of Technology),Ministry of Education,Wuhan 430063,China;School of Naval Architecture,Ocean and Energy Power Engineering,Wuhan University of Technology,Wuhan 430063,China;Guangzhou Shipyard International Co.Ltd.,Guangzhou 511462,China;The 92942 Unit of PLA,Beijing 100055,China;Wuhan University of Technology,Wuhan 430070,China)

机构地区：[1]高性能舰船技术教育部重点实验室(武汉理工大学),湖北武汉430063 [2]武汉理工大学船海与能源动力工程学院,湖北武汉430063 [3]广船国际有限公司,广东广州511462 [4]中国人民解放军92942部队,北京100055 [5]武汉理工大学,湖北武汉430070

出　　处：《中国舰船研究》2025年第1期65-75,共11页Chinese Journal of Ship Research

基　　金：国家自然科学基金资助项目(51809203)。

摘　　要：[目的]为解决船舶分离型(MMG)模型水动力系数辨识存在的共线性和参数漂移问题,提出一种基于支持向量回归(SVR)的三自由度简化分离型模型建模方法。[方法]首先,在样本数据的基础上提出一种数据预处理策略,以提升样本的有效性;然后,通过Lasso回归算法筛选对模型影响较显著的水动力系数,以减小多重共线性的程度;接着,针对分离型模型推导水动力系数辨识的回归模型,通过SVR进行水动力系数辨识;最后,采用差分法和数据中心化重构回归模型,以削弱参数漂移对水动力辨识误差的影响。[结果]试验结果显示,水动力系数预报值与数值模拟结果吻合较好,均方根误差(RMSE)和相关系数(CC)的计算结果均在良好范围内。[结论]通过SVR算法可以成功辨识出分离型模型的水动力导数,辨识得到的水动力系数精度较高,并且所建立的模型具有较好的预报能力和鲁棒性。[Objectives]To address the issue of multicollinearity and parameter drift in the identification of hydrodynamic coefficients in ship separated-type models,this paper proposes a method for modeling simplified three-degree-of-freedom modular models based on support vector regression(SVR).[Methods]Initially,a processing strategy is introduced to enhance the effectiveness of the sample data.Further,Lasso regression is introduced to select the most influential hydrodynamic coefficients and alleviate multicollinearity.Subsequently,a regression model for the identification of hydrodynamic derivatives is derived for the MMG model.A data centralization and differencing method is then employed to reconstruct the regression model,mitigating the impact of parameter drift on hydrodynamic derivative identification errors.[Results]Simulation experiments demonstrate good agreement between the hydrodynamic coefficient forecast values and numerical simulation results.The calculated values of root mean square error(RMSE)and correlation coefficient(CC)fall within a favorable range.[Conclusions]The SVR algorithm successfully identifies the hydrodynamic derivatives of the modular model,the identified hydrodynamic coefficients exhibit high accuracy,and the established model demonstrates good predictive capability and robustness.

关 键 词：船舶 操纵性 水动力学 数学模型 参数辨识 支持向量回归 白箱建模 

分 类 号：U661.33[交通运输工程—船舶及航道工程]