...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Reliability, IEEE Transactions on >Fusion Approach for Prognostics Framework of Heritage Structure
【24h】

Fusion Approach for Prognostics Framework of Heritage Structure

机译：遗产结构预测框架的融合方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The Cutty Sark is undergoing major conservation to slow down the deterioration of the original Victorian fabric of the ship. While the conservation work being carried out is “state of the art,” there is no evidence at present of the effectiveness of the conservation work over the next fifty years. A prognostics framework is being developed to monitor the “health” of the ship''s iron structures to help ensure a 50 year life once conservation is completed, with only minor deterioration taking place over time. This paper presents the prognostics framework being developed, which encompasses four approaches: 1-Canary and Parrot devices, 2-Physics-of-Failure (PoF) models, 3-Precursor Monitoring and Data Trend Analysis, and 4-Bayesian Networks. “Canary” and “Parrot” devices have been designed to mimic the actual mechanisms that would lead to failure of the iron structures, with canary devices failing faster to act as an indicator of forthcoming failures, while parrot devices fail at the same rate as the structure under consideration. A PoF model based on a decrease of the corrosion rate over time is used to predict the remaining life of an iron structure. Mahalanobis Distance (MD) is used as a precursor monitoring technique to obtain a single comparison metric from multiple sensor data to represent anomalies detected in the system. Bayesian Network models are then used as a fusion technique, integrating remaining life predictions from PoF models with information of possible anomalies from MD analysis to provide a new prediction of remaining life. This paper describes why, and how the four approaches are used for diagnostic and prognostics purposes, and how they are integrated into the prognostics framework.
机译：Cutty Sark正在接受大规模养护，以减缓船上原始维多利亚时期织物的老化。尽管正在进行的保护工作是“最新技术”，但目前尚无证据表明在未来五十年中保护工作的有效性。正在开发一种预测框架，以监测船上铁结构的“健康状况”，以确保确保养护完成后有50年的使用寿命，并且随着时间的推移只会出现很小的恶化。本文介绍了正在开发的预后框架，其中包括四种方法：1-金丝雀和鹦鹉设备，2-故障物理（PoF）模型，3-前体监控和数据趋势分析以及4-贝叶斯网络。 “金丝雀”和“鹦鹉”设备的设计旨在模仿会导致铁结构故障的实际机制，金丝雀设备无法更快地充当即将发生的故障的指标，而鹦鹉设备的失败率与正在考虑的结构。基于腐蚀速率随时间降低的PoF模型用于预测铁结构的剩余寿命。马氏距离（MD）用作前体监测技术，可从多个传感器数据中获得单个比较指标，以表示系统中检测到的异常。然后将贝叶斯网络模型用作融合技术，将PoF模型的剩余寿命预测与MD分析中可能出现的异常信息进行整合，以提供剩余寿命的新预测。本文介绍了为什么以及如何将这四种方法用于诊断和预后目的，以及如何将它们集成到预后框架中。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号