研究生: |
李美麗 Merry - Natalia Maranata |
---|---|
論文名稱: |
Benchmark studies on several reliability methods based on tail estimation Benchmark studies on several reliability methods based on tail estimation |
指導教授: |
卿建業
Jianye Ching |
口試委員: |
楊亦東
I-Tung Yang 劉家男 Chia-Nan Liu |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 營建工程系 Department of Civil and Construction Engineering |
論文出版年: | 2008 |
畢業學年度: | 96 |
語文別: | 英文 |
論文頁數: | 130 |
外文關鍵詞: | tail distribution, quantile-function |
相關次數: | 點閱:162 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
Failure probabilities of engineering structures are small, usually less than 0.01. Therefore, accurately estimating the tail of the distribution of the performance function is essential. This study compares several nonparametric reliability methods based on tail-fitting concept, including quantile-function (QF) methods, generalized Pareto distribution (GPD) methods and moment-matching (MM) methods.
The comparisons are made on several typical geotechnical design examples. The comparisons show that the performance of quantile-function methods is satisfactory, especially the QF method with minimum cross entropy since it effectively assumes the tail distribution to be exponential, which is roughly a correct assumption for many examples. The GPD method also provides reasonably stable results if the sampling threshold is carefully chosen. For most methods, the performance depends on the choice of threshold, which is found to perform the best when chosen to be around 80% of the failure threshold. The moment methods turn out to perform poorly due to its unrealistic assumptions.
References
Abramowitz, M. and Stegun, I.A. (1972). Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables, 9th printing. Dover, New York.
Ching, J.Y., Porter, A.K., and Beck, L.J. (2003). Uncertainty Propagation and Feature Selection for Loss Estimation in Performance-based Earthquake Engineering. Research report of Earthquake Engineering Research Laboratory, EERL 2003-03. Pasadena, California.
Ching, J.Y. (2008). Equivalence Between Reliability and Factor Safety. Journal of Probabilistic Engineering Mechanics, doi:10.1016/j.probengmech.2008.04.004.
Ching, J.Y. and Hsieh, Y.Y. (2007). Local Estimation of Failure Probability and Its Confidence Interval with Maximum Entropy Principle. Journal of Probabilistic Engineering Mechanics, 22, 39-49.
Castillo, E. (1988). Extreme Value Theory in Engineering. Academic Press, Inc
Cornell, C.A., (1969). A Probabilty-Based Structural Code. Journal of The American Concrete Institute, 66, 974-985
Djeng, J., Pandey MD. (2007). Estimation of minimum cross-entropy quantile function using fractional probability weighted moments. Journal of Probabilistic Engineering Mechanics, doi:10.1016/j.probengmech.2007.12.016.
Davison, A. C. and Smith, R. L. (1990). Models of Exceedances Over High Thresholds. Journal of the Royal Statistical Society, 52(Ser. B), 393–442.
Greenwood JA, Landwehr JM, Matalas NC. (1979). Probability weighted moments: definition and relation to parameters of several distributions expressible in inverse form. Journal of Water Resources Research, 15(5), 1049–1054.
Hosking, J.R.M. (1986). The theory of probability weighted moments. NY: IBM Research Report, RC 12210, Yorktown Heights.
Hosking, J. R. M. (1990). L-moments: analysis and estimation of distributions using linear combinations of order statistics. Journal of the Royal Statistical Society, 52(Series B), , 105-124.
Hosking, J. R. M., and Wallis, J. R. (1997). Regional frequency analysis: an approach based on L-moments”. Cambridge, U.K.: Cambridge University Press.
Jaynes, E.T. (1957). Information theory and statistical mechanics. Physic Review, 106, 620–630.
Kapur, J.N. and Kesavan, H.K. (1992). Entropy optimization principles with applications. San Diego, USA: Academic Press Inc..
Landwehr, J.M., Matalas, N.C. and Wallis, J.R. (1979). Probability weighted moments compared with some traditional techniques in estimating Gumbel parameters and quantiles. Journal of Water Resources Research, 15(5), 1055–1064.
Ono, T., and Idota, H. (1986). Development of high order moment standardization method into structural design and its efficiency. Journal of Structural and Construction Engineering, AIJ, 36, 5, 40-7.
Madsen, H.O., and Egeland, T. (1989). Structural Reliability – Models and Application. International Statistical Review, 57(3), 185-203.
Pandey, M.D. (2000). Direct Estimation of Quantile Functions Using the Maximum Entropy Principle. Journal of Structural Safety, 22(1), 61-79.
Pandey, M.D. (2001). Minimum Cross-Entropy Method for Extreme Value Estimation using Peaks-Over-Threshold Data. Journal of Structural Safety, 23(4), 345-363.
Pickands, J. (1975). Statistical inference using order statistics. Annals of Statistics, 3, 119–131.
Rosenblueth, E. (1975), Point estimates for probability moments, Proceeding National Academia of Science, 72(10), 3812-3814.
Shore, J.E. and Johnson, R.W. (1980). Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy. IEEE Trans. on Information Theory, 26(1), 26–37.
Tichy, M. (1994). First Order Third Moment reliability method. Journal of Structural Safety, 16, 189-200.
Zhao, Y. and Ono, T. (2001). Moment Method for Structural Reliability, Journal of Structural Safety, 23, 47-75.
Zhao, Y., Lu, Z., and Ono, T. (2006). A Simple Third-Moment Method for Structural Reliability . Journal of Asian Architecture and Building Engineering, 5(1), 129-136.
Xu, L. and Cheng, G..D. (2003). Discussion on: Moment Methods for Structural Reliability. Journal of Structural Safety, 25 (2), 193-199.