.png){kind=icon}
返回
A Markov chains prognostics framework for complex degradation processes
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ress.2019.106621.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a prognostics methodology to deal with complex degradation processes for which condition monitoring data constitute the only available source of physical information. The proposed methodology is general, but here it is illustrated and tested using a case study about fatigue crack propagation in metallic structures. The prognostics method relies on a stochastic damage model based on Markov chains, which is embedded within a sequential state estimation framework for remaining useful life prediction and time-dependent reliability estimation. As key contribution, the resulting prediction and updating equations are shown to be obtained as closed-form expressions, whereby analytical equations for the remaining useful life and time-dependent reliability are obtained as by-product. Original contributions to the model parameter inference and the minimum required amount of data for prognostics are also provided.
Keyword:
Damage prognostics
Markov chains
Sequential prediction
Time-dependent reliability
Remaining useful life
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
.png){kind=icon}
Bivariate Analysis of Incomplete Degradation Observations Based on Inverse Gaussian Processes and Copulas基于逆高斯过程和Copulas的不完全退化观测的二元分析
PREAI
分享收藏
查看更多内容