期刊文献+

船舶操纵性能及其代理模型构建(英文) 被引量:1

Ship Manoeuvring Performance and Construction of its Metamodels
下载PDF
导出
摘要 为了提高船舶操纵性能计算效率,文章结合基于NAPA计算仿真结果和支持向量回归方法预报海洋平台支援船的操纵性能,在收集足够相关船型信息前提下,采用能够合理探索设计空间和抽样的拉丁超立方方法获取了30条样本船型数据。通过NAPA仿射变化、位移转换及根据船型设计变量进行局部调整从而生成系列船型以表达船体几何形状。针对每个船型,分别计算了5项操纵性衡准指标:进距、战术直径、横距、10°舵角第一超越角和20°舵角第一超越角。为提高船舶操纵性能的计算效率,文中利用作者早先新提出的一种单参数Lagrangian支持向量回归算法来训练并构建代理模型以预报船舶操纵性能,该算法整合了Laplace损失函数,仅采用单参数控制计算误差并于置信区间中增加了b^2/2项。以海洋平台支援船为例,采用SPL-SVR算法预报船舶操纵性能,并与基于NAPA计算仿真结果、人工神经网络、经典支持向量回归算法进行对比。不需要昂贵的仿真代码计算,文中采用SPL-SVR算法建立的船舶操纵性能响应面模型比较适合船型初步设计的工程实际应用,并具有较好的效率和适用性。 To improve the efficiency of ship manoeuvring calculation technique, NAPA-based cal- culations and Support Vector Regression (SVR) were combined to predict the manoeuvring perfor- mance of the Offshore Support Vessels (OSV), and enough ship information about the offshore sup- port vessel were gathered; a series of 30 similar hull bodies was adopted by the Latin Hypercube Design which were employed to explore the design space and to sample data for covering the design space. The ship hull series were generated from the affine and displacement transformation and some adjustments in NAPA according to the ship design variables, thus creating the calculation model for the hull geometry expression. For each of the ship models, 5 different manoeuvrability criteria were calculated, which were the advance, tactical diameter, transfer, 10°/10° first overshoot angle and 20° /20° first overshoot angle. To improve the efficiency of manoeuvring calculation, the Single-parame- ter Lagrangian Support Vector Regression (SPL-SVR) was adopted and trained to establish the meta- models and predict the manoeuvring performance and this new algorithm was first proposed by the author and combined with Laplace loss function, which has only one parameter to control the errors 2 and adds b/2 to the item of confidence interval at the same time, For the OSV case, the manoeuvra- bility criteria were predicted with the SPL-SVR and compared with the NAPA-based calculation results with manoeuvring manager, the Artificial Neural Network results and classical SVR results. The results agreed well with each other. Instead of requiring the evaluation of expensive simulation codes, the metamodels of ship manoeuvring performance were suitable for the practical application in ship preliminary design stage and all the numerical results show the effectiveness and practicability of the new approximation algorithms.
出处 《船舶力学》 EI CSCD 北大核心 2015年第12期1463-1474,共12页 Journal of Ship Mechanics
基金 Supported by the National Natural Science Foundation of China(Grant No.51509114) the Natural Science Foundation of Jiangsu Province of China(Grant No.BK2012696)
关键词 代理模型 支持向量机 船舶操纵性 metamodel Support Vector Machine ship manoeuvring
  • 相关文献

参考文献2

二级参考文献11

  • 1Diez M, He W, Campana E F, Stem F. Deterministic and multivariate stochastic uncertainty quantification for the Delft catamaran with variable Froude number and/or geometry using URANS and potential flow solvers [J]. submitted to Computers & Fluids, 26 February 2012b.
  • 2Kleijnen J P C. Statistical tools for simulation practitioners[M]. Marcel Dekker Inc, 1987.
  • 3Iin R, Chen W, Simpson T W. Comparative studies of metamodelling techniques under multiple modeling criteria[J]. Structural Multidisciplinary Optimization, 2000, 23: 1-13.
  • 4Simpson T W, Peplinski J D, Koch P N, Allen J K. Metamodels for computer-based engineering design: Survey and rec- ommendations[J]. Engineering with Computers, 2001, 17: 129-150.
  • 5Vapnik V. The nature of statistical learning theory[M]. Springer, 1995.
  • 6Steinwart I, Christmann A. Support vector machines[M]. Springer, 2008.
  • 7Suykens J A K. Nonlinear modelling and support vector machines[C]. IEEE Instrumentation and Measurement Technology Conference, 2001.
  • 8Suykens J A K, Gestel T V, Brabanter J D, Moor B D, Vandewalle J. Least square support vector machines[M]. World Scientific Pub Co Inc, 2003.
  • 9Wang W, Xu Z, Lu W, Zhang X. Determination of the spread parameter in the Gaussian kernel for classification and re- gression[J]. Neurocomputing,2003, 55: 643-663.
  • 10Mousaviraad S M, He W, Diez M, Stem F. Framework for convergence and validation of stochastic UQ and relationship to deterministic V&Vwith example for a unit problem[J]. International Journal for Uncertainty Quantification, 2012, in press.

共引文献2

同被引文献4

引证文献1

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部