| 研制阶段系统可靠性增长的Bayesian评估与预测 |
| |
| 引用本文： | 明志茂,张云安,陶俊勇,陈循.研制阶段系统可靠性增长的Bayesian评估与预测[J].机械工程学报,2010,46(4). |
| |
| 作者姓名： | 明志茂 张云安 陶俊勇 陈循 |
| |
| 作者单位： | 1. 国防科技大学机电工程与自动化学院,长沙,410073
2. 国防科技大学机电工程与自动化学院,长沙,410073;马里兰大学可靠性与风险性研究中心,马里兰州,20742,美国 |
| |
| 基金项目： | 国家部委预研(51319030302);;国家部委预研基金(9140A19030506KG0166)资助项目 |
| |
| 摘 要： | 基于新Dirichlet先验分布,建立一种适合小子样复杂系统异总体可靠性增长分析的Bayesian模型。充分利用先验信息和阶段试验信息,结合产品研制的试验数据,利用最优化方法研究新的Dirichlet先验分布容易定量和衡量先验参数确定的方法,解决了超参数物理意义不明确难以确定问题。通过变量替换的Gibbs抽样简化了后验推断,合理估算出当前阶段和后续试验阶段产品可靠性的Bayesian点估计和置信下限;结合试验数据,利用该模型实现了未来阶段可靠性的预测,扩展了模型应用范围。实例表明该模型参数含义清晰明确,简单易行,利于工程应用。
|
| 关 键 词： | 可靠性增长模型 Bayesian 新Dirichlet分布 马尔科夫蒙特卡罗模拟 Gibbs抽样 |
Bayesian Reliability Assessment and Prediction During Product Development |
| |
| MING Zhimao,ZHANG Yunan,TAO Junyong,CHEN Xun.Bayesian Reliability Assessment and Prediction During Product Development[J].Chinese Journal of Mechanical Engineering,2010,46(4). |
| |
| Authors: | MING Zhimao ZHANG Yunan TAO Junyong CHEN Xun |
| |
| Affiliation: | 1.College of Mechatronics Engineering and Automation/a>;National University of Defense Technology/a>;Changsha 410073/a>;2.Center for Risk and Reliability/a>;University of Maryland/a>;MD 20742/a>;USA |
| |
| Abstract: | A Bayesian reliability growth model of diverse populations based on the new Dirichlet prior distribution is studied.Aiming at some history and expert information during the development of a weapon,a Bayesian reliability growth model is presented based on the new Dirichlet distribution.Bayesian point assessment and confidence lower limit on product reliability at current stage are inputted by comprehensively making use of prior information and field test information at every stage.The method for determining ... |
| |
| Keywords: | Bayesian Reliability growth model Bayesian analysis New Dirichlet distribution Markov chain Monte Carlo(MCMC) simulation Gibbs sampling |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
