返回
Sequential Bayesian inference for Weibull distribution parameters with initial hyperparameter optimization for system reliability estimation
DOI:10.1016/j.ress.2022.108516.png)
摘要
En 中文
In this study, we investigated the sequential Bayesian inference of the Weibull distribution parameters of the components of a system the remaining useful life of which can be estimated using lifetime estimation or survival function of certain types of components. Failure observations are collected sequentially and analyzed as censored data. Here, we propose a sequential Bayesian inference with optimized prior distribution (SBOPD) to provide an effective way to estimate the parameters of the Weibull distribution of the components. In this framework, the Bayesian inference of the parameters of the Weibull distribution is updated by a certain number of new failure observations. Two measures are used to estimate more accurately and effectively in the preliminary stages of the system life cycle; the posterior distribution of the previous update is used as the prior information of the new update, and the initial prior distribution is optimized using prior knowledge of the parameters. With optimized hyperparameters for the initial prior distribution, parameter estimation with SBOPD provided a better estimate at the preliminary stages of the system life than conventional methods.
Keyword:
System reliability
Component reliability
Weibull distribution
Bayesian inference
Weibull parameter estimation
Prior distribution
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
R
IF:
11
论文数:
9.0K
被引数:
4.2W
机构
引用论文
Remaining useful life estimation - A review on the statistical data driven approaches剩余使用寿命估算 -- 统计数据驱动方法综述
Hybrid remaining useful life prediction method. A case study on railway D-cables混合剩余使用寿命预测方法铁路D型电缆案例研究

