本文将拉丁超立方抽样法与条件期望和对偶变数方差减缩技术组合用于分析船体总纵极限强度可靠性。
This paper proposes Latin hypercube sampling combined with variance reduction techniques of conditional expectation and antithetic variates to assess ultimate strength reliability of ship hull girder.
在一系列不同的极限状态函数条件下，对随机抽样法和拉丁超立方抽样法以及是否使用方差减缩技术进行了比较研究。
Comparative study on random sampling and Latin hypercube sampling with and without variance reduction techniques is carried out to a number of different limit state functions.
为了减少随机抽样的次数并保证蒙特卡罗法的数值模拟精度，对比引入了重要抽样法和拉丁超立方体抽样方法；
To reduce sampling number and assure simulation precision, Importance Sampling method and Latin Hypercube Sampling method are coupled with Neumann expansion SFEM respectively.
为了减少随机抽样的次数并保证蒙特卡罗法的数值模拟精度，对比引入了重要抽样法和拉丁超立方体抽样方法；
To reduce sampling number and assure simulation precision, Importance Sampling method and Latin Hypercube Sampling method are coupled with Neumann expansion SFEM respectively.
应用推荐