基于点云特征提取的波浪增阻预报及对比研究  

Added wave resistance prediction and comparative study based on point cloud feature extraction

作　　者：吴铭峰 朱仁传[1] 徐德康 WU Mingfeng;ZHU Renchuan;XU Dekang(School of Ocean and Civil Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]上海交通大学船舶海洋与建筑工程学院,上海200240

出　　处：《中国舰船研究》2025年第2期227-234,共8页Chinese Journal of Ship Research

基　　金：上海交通大学"深蓝计划"资助项目(SL2020ZD104)。

摘　　要：[目的]为在设计阶段快速预报船舶波浪增阻,提出一种基于点云特征提取的神经网络模型——波浪增阻点云预报模型。[方法]以S60船为例,与传统的基于主要设计参数的模型预报进行对比;参照船模试验结果,分析点云预报模型在准确性和稳定性等方面的优势,探讨利用静水阻力预训练优化模型的方法。[结果]结果显示,基于点云特征提取的波浪增阻预报模型在全部5艘S60母型船上的预报结果的决定系数R^(2)=0.74~0.90,而基于主要设计参数的模型会在部分船型中失效。[结论]所做研究可为船舶波浪增阻预报提供新的思路和方法,有利于在设计阶段充分考虑波浪增阻的影响从而有利于设计和优化船型。[Objective]In order to rapidly forecast added wave resistance in the ship design stage,this paper proposes a neural network based on point cloud feature extraction.[Methods]Taking the Series 60 as an example,the corresponding added wave resistance prediction model is set up and compared with the traditional model based on the principal design parameters.By referring to S60 ship tests,the characteristics of the point cloud prediction model in terms of accuracy and stability are discussed,as well as the method of pretraining and optimizing the model using ship calm-water resistance data.[Results]The prediction results indicate that the proposed model can perform well in all five S60 ships,with the coefficient of determination R^(2) ranging from 0.74 to 0.90,while the traditional model based on the design parameters fails to make the correct prediction in some case.[Conclusion]This study provides new insights and a new approach to predicting added resistance in ship design,and may help to optimize ship forms by fully considering the impact of added wave resistance in the design phase.

关 键 词：波浪增阻 船舶设计 点云特征提取 预训练 

分 类 号：U661.3[交通运输工程—船舶及航道工程]