论文速递 | ​概率矩计算的二次点估计法

文摘   2025-01-01 19:00   上海  
Quadratic point estimate method for probabilistic moments computation

概率矩计算的二次点估计法

引用格式 | Cited by
Ko MH, Papakonstantinou KG, 2024. Quadratic point estimate method for probabilistic moments computation. Probabilistic Engineering Mechanics, 79: 103705.
DOI: 10.1016/j.probengmech.2024.103705
摘要 | Abstract
本文详细介绍了原创发展的二次点估计方法 (quadratic point estimate method, QPEM),旨在采用 2n^2 + 1 个样本 (或 σ) 点高效精确地计算概率分布的前四阶输出矩,其中 n 为输入随机变量数。所提二次点估计方法特别为低维和中高维问题的现有采样和求积方法提供了有效精确且实用的替代方案。给出了详细的理论推导,证明所提方法在对称输入分布下可达到五阶以上精度。从简单多项式函数到随机场非线性有限元分析的各种数值算例验证了理论发现,并进一步展示了二次点估计方法从低维到高维问题的精度、效率和适用性。
关键词: 不确定性传播, 点估计法, σ 点, 概率矩积分, 确定性抽样, 数值积分
This paper presents in detail the originally developed Quadratic Point Estimate Method (QPEM), aimed at efficiently and accurately computing the first four output moments of probabilistic distributions, using 2n^2 + 1 sample (or sigma) points, with n, the number of input random variables. The proposed QPEM particularly offers an effective, superior, and practical alternative to existing sampling and quadrature methods for low- and moderately-high-dimensional problems. Detailed theoretical derivations are provided proving that the proposed method can achieve a fifth or higher-order accuracy for symmetric input distributions. Various numerical examples, from simple polynomial functions to nonlinear finite element analyses with random field representations, support the theoretical findings and further showcase the validity, efficiency, and applicability of the QPEM, from low- to high-dimensional problems.
Keywords: Uncertainty propagation; Point estimate method; Sigma points; Probabilistic moment integrals; Deterministic sampling; Numerical integration.
图 1: 2n + 1 点估计方法示意图

Fig. 1. Schematic representation of illustrative 2n + 1 PEM

图 2: 二次点估计方法示意图

Fig. 2. Schematic representation of the QPEM

图 3: 二次点估计方法的稳定性因子

Fig. 3. Stability factor of the QPEM

图 4: 非连续函数示例的相对误差

Fig. 4. Relative errors for the illustrative, discontinuous function example

图 5: 不同维度多项式函数的矩估计

Fig. 5. Moments estimation for polynomial functions with varying dimensions

图 6: 屋顶结构示意图

Fig. 6. Schematic drawing of the roof structure

图 7: 屋顶桁架结构算例的相对误差

Fig. 7. Relative errors for the roof truss structure example

图 8: 含轴向刚度随机场的弹性杆

Fig. 8. Elastic bar with random field axial rigidity

图 9: 弹性杆算例的相对误差

Fig. 9. Relative errors for the elastic bar example

图 10:弹性模量随机场的四分之一圆孔板

Fig. 10. Quarter-plate with a circular hole and random field elastic modulus

图 11: 开孔板算例的相对误差

Fig. 11. Relative errors for the plate with a hole example

图 12: 含弹性模量随机场的材料非线性简支梁

Fig. 12. Simply supported beam with material nonlinearity and random field elastic modulus

图 13: 简支梁算例的相对误差

Fig. 13. Relative errors for the simply supported beam example

作者信息 | Authors

Min-Hyeok Ko

美国宾夕法尼亚州立大学 (Pennsylvania State University) 土木与环境工程系

Konstantinos G. Papakonstantinou, 通讯作者 (Corresp.)

美国宾夕法尼亚州立大学 (Pennsylvania State University) 土木与环境工程系

Email: kpapakon@psu.edu



律梦泽 M.Z. Lyu | 编辑 (Ed)

P.D. Spanos | 审校 (Rev)

陈建兵 J.B. Chen | 审校 (Rev)

彭勇波 Y.B. Peng | 审校 (Rev)

Probab Eng Mech
国际学术期刊 Probabilistic Engineering Mechanics 创立于 1985 年,SCI 收录,JCR Q1,现任主编是美国工程院院士、中国科学院外籍院士、莱斯大学 Pol D. Spanos 教授。
 最新文章