Calculation of Posterior Probabilities for Bayesian Model Class Assessment and Averaging from Posterior Samples Based on Dynamic System Data

被引:131
作者
Cheung, Sai Hung [1 ]
Beck, James L. [1 ]
机构
[1] CALTECH, Div Engn & Appl Sci, Pasadena, CA 91125 USA
关键词
MARGINAL LIKELIHOOD; STRUCTURAL MODELS; UPDATING MODELS; CLASS SELECTION; IDENTIFICATION; UNCERTAINTIES; BRIDGE;
D O I
10.1111/j.1467-8667.2009.00642.x
中图分类号
TP39 [计算机的应用];
学科分类号
080201 [机械制造及其自动化];
摘要
In recent years, Bayesian model updating techniques based on dynamic data have been applied in system identification and structural health monitoring. Because of modeling uncertainty, a set of competing candidate model classes may be available to represent a system and it is then desirable to assess the plausibility of each model class based on system data. Bayesian model class assessment may then be used, which is based on the posterior probability of the different candidates for representing the system. If more than one model class has significant posterior probability, then Bayesian model class averaging provides a coherent mechanism to incorporate all of these model classes in making probabilistic predictions for the system response. This Bayesian model assessment and averaging requires calculation of the evidence for each model class based on the system data, which requires the evaluation of a multi-dimensional integral involving the product of the likelihood and prior defined by the model class. In this article, a general method for calculating the evidence is proposed based on using posterior samples from any Markov Chain Monte Carlo algorithm. The effectiveness of the proposed method is illustrated by Bayesian model updating and assessment using simulated earthquake data from a ten-story nonclassically damped building responding linearly and a four-story building responding inelastically.
引用
收藏
页码:304 / 321
页数:18
相关论文
共 57 条
[41]
Mackay D.J.C., 1993, ASHARE Transactions, V100, P1053
[42]
Meng XL, 1996, STAT SINICA, V6, P831
[43]
EQUATION OF STATE CALCULATIONS BY FAST COMPUTING MACHINES [J].
METROPOLIS, N ;
ROSENBLUTH, AW ;
ROSENBLUTH, MN ;
TELLER, AH ;
TELLER, E .
JOURNAL OF CHEMICAL PHYSICS, 1953, 21 (06) :1087-1092
[44]
Bayesian updating and model class selection for hysteretic structural models using stochastic simulation [J].
Muto, Matthew ;
Beck, James L. .
JOURNAL OF VIBRATION AND CONTROL, 2008, 14 (1-2) :7-34
[45]
Annealed importance sampling [J].
Neal, RM .
STATISTICS AND COMPUTING, 2001, 11 (02) :125-139
[46]
NEAL RM, 2005, 0511 U TOR
[47]
NEWTON MA, 1994, J R STAT SOC B, V56, P3
[48]
Modal flexibility analysis of cable-stayed Ting Kau bridge for damage identification [J].
Ni, Y. Q. ;
Zhou, H. F. ;
Chan, K. C. ;
Ko, J. M. .
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2008, 23 (03) :223-236
[49]
Bayesian Learning Using Automatic Relevance Determination Prior with an Application to Earthquake Early Warning [J].
Oh, Chang Kook ;
Beck, James L. ;
Yamada, Masumi .
JOURNAL OF ENGINEERING MECHANICS, 2008, 134 (12) :1013-1020
[50]
Updating robust reliability using structural test data [J].
Papadimitriou, C ;
Beck, JL ;
Katafygiotis, LS .
PROBABILISTIC ENGINEERING MECHANICS, 2001, 16 (02) :103-113