Entropy-Based Importance Measure for Uncertain Model Inputs
作者： Tang Zhangchun , Lu Zhenzhou , Jiang Biao , Pan Wang , Zhang Feng
DOI: 10.2514/1.J051669
关键词:
摘要: In the information theory, entropy is a measure of uncertainty associated with random variable. To identify important variables system subjected to many variables, novel entropy-based importance for proposed in this paper. The method evaluates effect variable on output responses by calculating change value. This technique focuses influence input and can be easily extended case taking correlations among into consideration. Besides, within any partial region interest also evaluated global sensitivity indicator. mathematical properties are investigated proven detail. Three simple numerical examples employed demonstrate applicability new measure, then probabilistic risk assessment model us...
harvard.edu
sci-hub.se 参考文章(37)
Athanasios Papoulis, Probability, random variables and stochastic processes ,(1965)
E. Borgonovo, W. Castaings, S. Tarantola, Model emulation and moment-independent sensitivity analysis: An application to environmental modelling Environmental Modelling and Software. ,vol. 34, pp. 105- 115 ,(2012) , 10.1016/J.ENVSOFT.2011.06.006
W. Castaings, E. Borgonovo, M.D. Morris, S. Tarantola, Sampling strategies in density-based sensitivity analysis Environmental Modelling and Software. ,vol. 38, pp. 13- 26 ,(2012) , 10.1016/J.ENVSOFT.2012.04.017
J.P.C. Kleijnen, J.C. Helton, Statistical Analyses of Scatterplots to Identify Important Factors in Large-Scale Simulations, 1: Review and Comparison of Techniques Reliability Engineering & System Safety. ,vol. 65, pp. 147- 185 ,(1999) , 10.1016/S0951-8320(98)00091-X
E. Borgonovo, A new uncertainty importance measure Reliability Engineering & System Safety. ,vol. 92, pp. 771- 784 ,(2007) , 10.1016/J.RESS.2006.04.015
CE Shennon, Warren Weaver, A mathematical theory of communication Bell System Technical Journal. ,vol. 27, pp. 379- 423 ,(1948) , 10.1002/J.1538-7305.1948.TB01338.X
Hongzhe Dai, Wei Wang, Application of low-discrepancy sampling method in structural reliability analysis Structural Safety. ,vol. 31, pp. 55- 64 ,(2009) , 10.1016/J.STRUSAFE.2008.03.001
Harry Millwater, Gulshan Singh, Miguel Cortina, Development of a localized probabilistic sensitivity method to determine random variable regional importance Reliability Engineering & System Safety. ,vol. 107, pp. 3- 15 ,(2012) , 10.1016/J.RESS.2011.04.003
Ronald L. Iman, A Matrix-Based Approach to Uncertainty and Sensitivity Analysis for Fault Trees1 Risk Analysis. ,vol. 7, pp. 21- 33 ,(1987) , 10.1111/J.1539-6924.1987.TB00966.X
Gregory C. Critchfield, Keith E. Willard, Donald P. Connelly, Probabilistic sensitivity analysis methods for general decision models Computers and Biomedical Research. ,vol. 19, pp. 254- 265 ,(1986) , 10.1016/0010-4809(86)90020-0