A Bayesian approach for integrating multilevel priors and data for aerospace system reliability assessment  

作　　者：Jian GUO Zhaojun LI Thomas KEYSER 

机构地区：[1]Department of Industrial Engineering and Engineering Management, Western New England University

出　　处：《Chinese Journal of Aeronautics》2018年第1期41-53,共13页中国航空学报（英文版）

摘　　要：This paper investigates Bayesian methods for aerospace system reliability analysis using various sources of test data and expert knowledge at both subsystem and system levels. Four sce- narios based on available information for the priors and test data of a system and/or subsystems are studied using specific Bayesian inference techniques. This paper proposes the Bayesian melding method for integrating subsystem-level priors with system-level priors for both system- and subsystem-level reliability analysis. System and subsystem reliability outcomes are compared under different scenarios. Computational challenges for posterior inferences using the sophisticated Bayesian melding method are addressed using Markov Chain Monte Carlo （MCMC） and adaptive Sam- piing Importance Re-sampling （SIR） methods. A case study with simulation results illustrates the applications of the proposed methods and provides insights for aerospace system reliability analysis using available multilevel information.This paper investigates Bayesian methods for aerospace system reliability analysis using various sources of test data and expert knowledge at both subsystem and system levels. Four sce- narios based on available information for the priors and test data of a system and/or subsystems are studied using specific Bayesian inference techniques. This paper proposes the Bayesian melding method for integrating subsystem-level priors with system-level priors for both system- and subsystem-level reliability analysis. System and subsystem reliability outcomes are compared under different scenarios. Computational challenges for posterior inferences using the sophisticated Bayesian melding method are addressed using Markov Chain Monte Carlo （MCMC） and adaptive Sam- piing Importance Re-sampling （SIR） methods. A case study with simulation results illustrates the applications of the proposed methods and provides insights for aerospace system reliability analysis using available multilevel information.

关 键 词：Bayesian inference Bayesian melding Multilevel information Markov Chain Monte Carlo （MCMC） Sampling Importance Resampling （SIR） System reliability 

分 类 号：V37[航空宇航科学与技术—航空宇航推进理论与工程] V57