小水线面双体船受海浪冲击时结构应力的准确预测对保证航行安全具有重要意义。采用有限元软件进行应力的数值仿真需要花费巨大的时间成本，构建近似模型成为解决这一问题的有效途径。由于样本点有限，当选择不适当的近似模型时难以保证近似模型精度，组合近似模型（EMs）技术能避免选择单一近似模型的不足和缺陷。本文采用组合近似建模技术预测小水线面双体船在受海浪冲击时的最大结构应力，并与单一近似模型预测精度进行比较，结果表明，组合近似模型的精度更高，能够有效预测最大结构应力，具有较大的工程实用价值。
Predicting the structural stress of small waterplane area twin hull (SWATH) is of great significance to ensure the safety of navigation when the ship is impacted by the waves. The numerical calculation of stress by finite element software can be very time-consuming. Building the metamodel becomes an effective way to solve this problem. Because of the limitation of sample size, a improper metamodel may cause low metamodel accuracy. Ensemble of metamodels (EMs) can avoid the disadvantage of single metamodel. EMs is applied to predict the the structural stress of SWATH and compared with single-fidelity metamodel for metamodel accuracy. The results indicate that the EMs can ensure the metamodel accuracy.
2017,39(7): 15-18 收稿日期：2016-09-27
DOI：10.3404/j.issn.1672-7649.2017.07.003
分类号：U663
基金项目：国家自然科学基金资助项目（51505163）
作者简介：舒乐时(1992-),男,硕士研究生,研究方向为复杂系统工程多学科优化设计
参考文献：
[1] ZHOU Q, SHAO X, JIANG P, et al. An adaptive global variable fidelity metamodeling strategy using a support vector regression based scaling function[J]. Simulation Modelling Practice and Theory, 2015, 59: 18–35.
[2] CROMBECQ K, GORISSEN D, DESCHRIJVER D, et al. A novel hybrid sequential design strategy for global surrogate modeling of computer experiments[J]. Siam Journal on Scientific Computing, 2011, 33(4): 1948–1974.
[3] 宋磊, 王建, 杨卓懿. Kriging模型在潜器型线优化设计中的应用研究[J]. 船舶力学, 2013(1): 8–13.SONG Lei, WANG Jian, YANG Zhuo-yi. Research on shape optimization design of submersible based on Kriging model[J]. Journal of Ship Mechanics, 2013(1): 8–13.
[4] 常海超, 冯佰威, 刘祖源, 等. 近似技术在船型阻力性能优化中的应用研究[J]. 中国造船, 2012, 53(1): 88–98.CHANG Hai-chao, FENG Bai-wei, LIU Zu-yuan, et al. Research on application of approximate model in hull form optimization[J]. Shipbuilding of China, 2012, 53(1): 88–98.
[5] 苟鹏, 崔维成. 基于Kriging模型的深潜器多球交接耐压壳结构优化[J]. 船舶力学, 2009(1): 100–106.GOU Peng, CUI Wei-cheng. Structural optimization of multiple intersecting spherical pressure hulls based on Kriging model[J]. Journal of Ship China, 2009(1): 100–106.
[6] ZHOU Q, SHAO X, JIANG P, et al. Differing mapping using ensemble of metamodels for global variable-fidelity metamodeling[J]. CMES: Computer Modeling in Engineering and Sciences, 2015, 106(5): 323–355.
[7] LEWIS R M, NASH S G. Model problems for the multigrid optimization of systems governed by differential equations[J]. SIAM Journal on Scientific Computing, 2005, 26(6): 1811–1837.
[8] 许辉, 周奇. 多学科优化中的近似模型及其在艇体结构优化中的应用[J]. 舰船科学技术, 2014, 36(12): 6–10.XU Hui, ZHOU Qi. Approximation methods of multidis-ciplinary design optimization and their application in shell hull of submarine[J]. Ship Science and Technology, 2014, 36(12): 6-10.
[9] POWELL M J D. Radial basis functions for multivariable interpolation: a review[C]//Algorithms for Approximation. Clarendon Press, 1987: 143–167.
[10] ZHOU Q, RONG Y, SHAO X, et al. Optimization of laser brazing onto galvanized steel based on ensemble of metamodels[J]. Journal of Intelligent Manufacturing, 2016: 1-15.
[11] ZERPA L E, N V QUEIPO, S PINTOS, et al. An optimization methodology of alkaline–surfactant–polymer flooding processes using field scale numerical simulation and multiple surrogates[J]. Journal of Petroleum Science and Engineering, 2005, 47(3): 197–208.
[12] GOEL T, R T HAFTKA, W SHYY, et al. Ensemble of surrogates[J]. Structural and Multidisciplinary Optimization, 2007, 33(3): 199–216.
[13] ACAR E, M RAIS-ROHANI. Ensemble of metamodels with optimized weight factors[J]. Structural and Multidisciplinary Optimization, 2009, 37(3): 279–294.
[14] XIONG F, XIONG Y, CHEN W, et al. Optimizing Latin hypercube design for sequential sampling of computer experiments[J]. Engineering Optimization, 2009, 41(8): 793–810.
[15] JIANG P, SHU L, ZHOU Q, et al. A novel sequential exploration-exploitation sampling strategy for global metamodeling[J]. IFAC-PapersOnLine, 2015, 48(28): 532–537.
