基于聚类椭球模型的不确定性传播分析  

Uncertain propagation based on the Cluster-Ellipsoid model

作　　者：刘浩 杨开云 张德权 LIU Hao;YANG Kai-yun;ZHANG De-quan(GD Midea Heating ＆ Ventilating Euqipment Co.,Foshan 538311,China;School of Mechanical and Vehicle Engineering,Hunan University,Changsha 410082,China)

机构地区：[1]广东美的暖通设备有限公司,佛山538311 [2]湖南大学机械与运载工程学院,长沙410082

出　　处：《计算力学学报》2018年第4期431-436,共6页Chinese Journal of Computational Mechanics

基　　金：国家自然科学基金(71271078);湖南大学汽车车身先进设计制造国家重点实验室自主研究课题(51475003)资助项目

摘　　要：针对随机结构提出了基于聚类椭球模型的非概率不确定性传播方法。首先,将聚类椭球模型分解成多个子椭球模型;然后,在各个子椭球模型中求解结构响应的子边界;接着,在所有子椭球模型内的子边界中寻优,获得响应的边界。考虑到计算精度和效率等问题,引入传统非概率不确定性传播策略和基于功能度量法的传播策略,分别对响应的子边界进行计算;最后,通过数值算例验证了本文方法的有效性。A non-probabilistic uncertainty propagation scheme was proposed for stochastic structures based on a Cluster-Ellipsoid model.Firstly,the Cluster-Ellipsoid model was decomposed into a series of sub-ellipsoid models.After that,the sub-boundaries of structural response can be determined in the several sub-ellipsoid models.And then,the boundaries of the structural response are obtained from all the boundaries of sub-ellipsoid models.Considering the computational accuracy and efficiency in uncertainty propagation,the traditional non-probabilistic uncertainty propagation and the performance-measure-approach-based schemes are introduced to calculate the sub-boundaries of the response in this study.Finally,three numerical examples demonstrate the effectiveness of the proposed method.

关 键 词：不确定性传播 聚类椭球模型 功能度量法 蒙特卡洛模拟法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] O213.2[自动化与计算机技术—计算机科学与技术]