An importance sampling method for reliability analysis based on optimal Latin Hypercube sampling

摘要：

　　The correlation consistency with target random variables and homogeneous distribution in the domain of definition are taken into account at the same time when a Latin Hypercube sampling plan is made,which is turned into an multi-objective optimization of the sampling plan and solved with an enhanced stochastic evolutionary(ESE)algorithm.The obtained optimal Latin Hypercube sampling plan is applied in the following importance sampling.Several numerical examples are presented and the reliability analysis results show that better accuracy and efficiency than the traditional Latin Hypercube importance sampling method is achieved.

关键词： Importance sampling Latin Hypercube sampling enhanced stochastic evolutionary optimal LHS plan

作者: Wei Zhao Peng Liu Haiming Zou

作者单位: Key Laboratory of Disaster Forecast and Control in Engineering,Ministry of Education of China,Jinan University,Guangzhou 510632,China

会议类型: 国际会议

会议名称: The 7th World Conference on Structural Control and Monitoring(7WCSCM)(第七届结构控制与监测世界大会)

会议地点: 青岛

会议语种:英文

页码: 2861-2871

在线出版日期: 2018-07-22（万方平台首次上网日期，不代表论文的发表时间）