一种基于数独分组的拉丁超立方试验设计方法

doi:10.16182/j.issn1004731x.joss.20-FZ0472

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (11): 2185-2191.doi: 10.16182/j.issn1004731x.joss.20-FZ0472

一种基于数独分组的拉丁超立方试验设计方法

张甜甜¹, 李妮¹, 龚光红¹, 卢元杰²

1.自动化科学与电气工程学院,北京航空航天大学,北京 100191;
2.中国航空研究院,北京 100029

收稿日期:2020-07-10 修回日期:2020-08-05 出版日期:2020-11-18 发布日期:2020-11-17
作者简介:张甜甜(1996-),女,山东菏泽,硕士生,研究方向为同时定位与建图、深度学习;李妮(1980-),女,湖南衡阳,博士,教授,研究方向为虚拟样机、混合现实技术;龚光红(1968-),女,土家族,四川石柱,博士,教授,研究方向为系统仿真与虚拟现实。

A Fast Latin Hyper Cube Experiment Design Method Based on Soduku Grouping

Zhang Tiantian¹, Li Ni¹, Gong Guanghong¹, Lu Yuanjie²

1. School of Automation Science,Beihang University (BUAA),Beijing 100191,China;
2. Chinese Aeronautical Establishment,Beijing 100129,China

Received:2020-07-10 Revised:2020-08-05 Online:2020-11-18 Published:2020-11-17

摘要/Abstract

摘要： 为解决拉丁超立方设计在复杂因子的实验设计空间中存在优化时间长和因子水平组合爆炸的问题。提出一种基于数独分组的拉丁超立方设计方法。该方法对因子通过数独分组降维,在降维后的各个子空间中平移种子设计。将基于数独分组的拉丁超立方设计与另外两种常用的拉丁超立方设计方法在中高维度试验空间中进行对比,结果表明,基于数独分组的拉丁超立方设计有较优的空间填充性和最短的运行时间。

关键词: 试验设计, 拉丁超立方设计, 数独分组, 扩展平移传播

Abstract: In order to solve the long optimization time and parameter level combination explosion in the complex experiment design space of Latin Hypercube design, which is one of the most popular method in experiment design, a fast Soduku grouping-based method is proposed. The optimal seed design is expanded and transformed in the grouped spaces. Experiments are conducted to compare the Soduku grouping-based Latin Hypercube design method with other two commonly used Latin Hypercube design methods in the middle and high dimension experiment space. The results show that Soduku grouping method is more efficient in computation and has better space-filling performance.

Key words: experiment design, latin hypercube design, soduku grouping, extended translational propagating

中图分类号:

TP391.9

张甜甜, 李妮, 龚光红, 卢元杰. 一种基于数独分组的拉丁超立方试验设计方法[J]. 系统仿真学报, 2020, 32(11): 2185-2191.

Zhang Tiantian, Li Ni, Gong Guanghong, Lu Yuanjie. A Fast Latin Hyper Cube Experiment Design Method Based on Soduku Grouping[J]. Journal of System Simulation, 2020, 32(11): 2185-2191.

参考文献

[1] 别晓峰,董艳,王剑飞.作战仿真实验设计的基本问题探讨[J].军事运筹与系统工程,2008,22(4):51-56.
Bie Xiaofeng,Dong Yan,Wang Jianfei.Discussion on the Basic Problems of Combat Simulation Experiment Design[J].Military Operation Research and System Engineering,2008,22(4):51-56.
[2] McKay M D,Beckman R J,Conover W J.A Comparison of Three Methods for Selecting Values of Input Variables from a Computer code[J].Technometrics(S1537-2723),1979,42(1):239-245.
[3] Iman R L,Conover W J.Small Sample Sensitivity Analysis Techniques for Computer Models,with an Application to Risk Assessment[J].Communications in Statistics Part A:Theory and Methods(S0361-0926),1980,9(17):1749-1842.
[4] Xing D D,Zhu M Y.Simulation Screening Experiments Using Lasso-optimal Supersaturated Design and Analysis:a Maritime Operations Application[C].The 2013 Winter Simulation Conference.Washington D.C,IEEE Press,2013:497-508.
[5] Jin R,Chen W,Sudjianto A.An Eifficient Algorithm for Constructing Optimal Design of Computer Experiments[J].Journal of Statiscal Planning and Inference(S0378-3758),2005,134(1):268-287.
[6] Bates S J,Sienz J,Toropov V V.Formulation of the Optimal Latin Hypercube Design of Experiments Using a Permutation Genetic Algorithm[C].Forty-Fifth AIAA/ ASME/ASCE/AHS/ASC Structures,Structural Dynamics and Materials Conference.Palm Springs,CA,2004:19-22.
[7] liefvendahl M,Stocki R.A Study on Algorithms for Optimization of Latin Hypercubes[J].Journal of Statiscal Planning and Inference(S0378-3758),2006,136(9):3231-3247.
[8] Grosso A,Jamali A,Locatelli M.Finding Maximin Latin Hypercube Designs by Iterated Local Search Heuristics[J].European Journal of Operational Research(S0377-2217),2009,197(2):541-547.
[9] Felipe A C Viana,Gerhard Venter,Vladimir Balabanov.An Algorithm for Fast Optimal Latin Hypercube Design of Experiments[J].International Journal for Numerical Methods in Engineering(S1097-0207),2009,82(2):135-156.
[10] Zhai Gang,Ma Yaofei,Song Xiao,et al.A Novel Experiment Design Method[C].2015,Asia Simulation Conference.Singapore Springer,2015:28-39.
[11] Morris M D,Mitchell T J.Exploratory Designs for Computational Experiments[J].Journal of Statiscal Planning and Inference(S0378-3758),1995,43(3):381-402.
[12] Maaten L V D,Hinton G.Visualizing Data Using t-SNE[J].Journal of Machine Learning Research(S1532-4435),2008,9(1):2579-2605.
[13] Maaten L V D.Accelerating t-SNE using Tree-Based Algorithms[J].Journal of Machine Learning Research(S1532-4435),2014,15(1):3221-3245.

一种基于数独分组的拉丁超立方试验设计方法

A Fast Latin Hyper Cube Experiment Design Method Based on Soduku Grouping

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	张登辉, 晁涛, 王松艳, 马萍. 基于改进拉丁超立方的制导控制系统性能评估[J]. 系统仿真学报, 2017, 29(10): 2345-2352.
[2]	于雅楠. 改善旋翼飞行体气动力参数的正交试验优化设计[J]. 系统仿真学报, 2016, 28(3): 668-675.
[3]	叶雪荣, 陈岑, 王一行, 翟国富. 基于EDA的开关电源健康状态评估方法研究[J]. 系统仿真学报, 2015, 27(1): 185-191.