|
|
论文:2012,Vol:30,Issue(1):88-93 |
|
|
引用本文： |
|
|
郝文锐, 吕震宙, 田龙飞. 基于相关变量分解的重要性测度分析新方法[J]. 西北工业大学 |
|
|
Hao Wenrui, Lu Zhenzhou, Tian Longfei. A Novel and Rational Method Based on Decomposition of Correlated Variables for Analyzing Importance Measure[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于相关变量分解的重要性测度分析新方法 |
|
| 郝文锐, 吕震宙, 田龙飞 |
|
| 西北工业大学 航空学院,陕西 西安 710072 |
| 摘要: |
| 为了清晰地掌握相关输入变量情况下响应量方差的来源,有必要将重要性测度分离为相关部分和独立部分。通过将相关变量构造为独立变量的线性组合,相关输入变量对功能响应的方差贡献可被分离为相关部分和非相关部分,提出线性响应量情况下基于相关变量分解的重要性测度分析方法。所提方法不仅能将某一相关变量对响应的方差贡献分解为独立部分和相关部分,还可将其相关贡献分离为其与每一相关变量间的相关贡献分量。在此基础上针对非线性响应量的情况建立了基于迭代一阶泰勒展开的重要性求解方法,该方法可在响应的一阶泰勒展开式的方差与原响应方差基本一致的情况下对相关变量进行重要性测度求解。采用所提方法,对文中数值算例和工程应用算例中各相关输入变量的相关部分和独立部分的重要性测度指标进行了求解,证明了文中提出的基于相关变量分解的重要性测度方法是合理、可行的。 |
| 关键词:
灵敏度分析
重要性测度
相关变量分解
泰勒展开
多项式
|
|
| A Novel and Rational Method Based on Decomposition of Correlated Variables for Analyzing Importance Measure |
|
| Hao Wenrui, Lu Zhenzhou, Tian Longfei |
|
| College of Aeronautics,Northwestern Polytechnical University,Xi'an 710072,China |
| Abstract: |
| Sections 1 and 2 of the full paper explain the method mentioned in the title,which we believe is noveland rational.Their core consists of."For exploring the origin of the variance of the output response in the case thatcorrelated input variables are involved,it is necessary to divide the variance based importance measure (VBIM) in-to the correlated part and the uncorrelated one.Correlated variables are constructed by the linear combination of in-dependent factors to divide the contributions by correlated input variables into correlated ones and uncorrelatedones,by which the novel method based on the decomposition of correlated variables for analyzing importance meas-ure is proposed.The novel method not only can divide the contribution by an individual input variable into uncorre-lated one and correlated one,but also can separate the latter into components of the individual input variable corre-lated with each of other input variables.For nonlinear responses,an iterative first-order Taylor expansion basedmethod is established,which aims at analyzing the importance measure of correlated variables when the variance ofresponse is consistent with its first-order Taylor expansion." The proposed novel method is employed to obtain re-spectively the VBIMs of two examples.The calculated results,presented in Tables 1 and 3,and their analysis dem-onstrate preliminarily that the novel method based on the decomposition of correlated variables for analyzing impor-tance measure is indeed rational. |
| Key words:
decomposition
iterative methods
polynomials
probability
regression analysis
reliability
sensitivity analysis
correlated variables
importance measure
Taylor expansion
|
|
| 收稿日期: 2011-04-21
修回日期:
|
| DOI: |
| 基金项目: 国家自然科学基金(51175425)；航空科学基金(2011ZA53015)；博士学科点专项科研基金(20116102110003)；航天支撑基金(2011XW010001)资助 |
| 通讯作者:
Email： |
| 作者简介: 郝文锐(1987-),西北工业大学硕士研究生,主要从事飞行器可靠性工程的研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Aven T，Nokland T E. On the Use of Uncertainty Importance Measures in Reliability and Risk Analysis. Reliability Engineeringand System Safety, 2010, 95(2): 127～133
[2] Doksum K，Samarov A，Nonparametric Estimation of Global Functionals and a Measure of the Explanatory Power of Covariates inRegression. Ann Statist 1995; 23 (5):1443～1473
[3] Satelli A. The Role of Sensitivity Analysis in the Corroboration of Models and Its Link to Model Structural and Parametric Uncer-tainty. Reliability Engineering and System Safety, 1997;57(1):1～4
[4] Sobol I M. Global Sensitivity Indices for Nonlinear Mathematical Models and Their Monte Carlo Estimates. Mat Comput Simula-tion, 2001, 55(1):221～80
[5] Iman R L，Hora S C. A Robust Measure of Uncertainty Importance for Use in Fault Tree System Analysis. Risk Anal, 1990, 10(3):401～406
[6] Satelli A，Sensitivity Analysis for Importance Assessment. Risk Anal, 2002, 22(3): 579～590
[7] Borgonovo E. A New Uncertainty Importance Measure. Reliability Engineering and System Safety, 2007, 92(6): 771～784
[8] Cui L J，Lu Z Z，Zhao X P. Moment-Independent Importance Measure of Basic Random Variable and Its Probability Density E-volution Solution. Science China Technological Sciences, 2010, 53(4): 1138～1145
[9] Xu Chonggang，George Zdzislaw Gertner. Uncertainty and Sensitivity Analysis for Models with Correlated Parameters. ReliabilityEngineering and System Safety, 2008, 93(6): 1563～1573
[10] 郝文税, 吕震宙, 田龙飞. 基于方差的相关输入变量重要性测度新方法. 航空学报, 2011, 32(9):1637～1643Hao Wenrui，Lu Zhenzhou，Tian Longfei. A Novel Method for Analyzing Variance Based Importance Measure of Correlated Vari-ables. Acta Aeronautica et Astronautica Sinica, 2011, 32(9): 1637～1643 (in Chinese) |
|
|
|
相关文献: |
|
|
1．阮文斌, 吕震宙, 李露祎.状态模糊情况下矩独立重要性测度及其态相关参数解法[J]. 西北工业大学, 2012,30(5): 675-680 |
|
|
|
|
|
|
