• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Reliability Engineering & System Safety >Managing infrastructure asset: Bayesian networks for inspection and maintenance decisions reasoning and planning
【24h】

Managing infrastructure asset: Bayesian networks for inspection and maintenance decisions reasoning and planning

机译：管理基础设施资产：贝叶斯网络进行检查和维护决策推理和规划

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

Models of maintenance problems must handle complex assumptions, allowing, for example, the condition of some assets to be rated directly using multiple states while in others the condition rating is inferred from that of the components from which they are assembled. The overall condition inferred, which informs the maintenance decisions, requires evidential reasoning under uncertainty. This paper uses Bayesian networks to address these challenges with real case studies. We apply the binary factorisation technique to allow inference of multi-state condition prediction, and further extend it to predict the condition of an asset with multiple components. These models are used to recommend inspection decisions such as which assets to inspect and when to inspect them. Models are also developed to evaluate the effectiveness of repair interventions and to use this to suggest repair actions. We show how to model multiple interventions within the asset life cycle considering both repair effectiveness and further deterioration. This modelling allows us to plan maintenance activities for an asset over its whole life cycle.
机译：维护问题的模型必须处理复杂的假设，允许例如使用多个状态的一些资产的条件，而在其他状态下，条件评级被从组装组件的组件的那些推断出条件等级。推断维护决策的整体情况需要在不确定性下证明是证据推理。本文使用贝叶斯网络解决了这些挑战，实际案例研究。我们应用二进制分子化技术以允许推动多状态条件预测，并进一步扩展它以预测具有多个组件的资产的状况。这些模型用于建议检查决策，例如检查哪些资产以及何时检查它们。还开发了模型来评估修理干预的有效性并使用这提出修复行动。我们展示了如何考虑修复效果和进一步恶化的资产生命周期内的多种干预措施。此建模允许我们在其整个生命周期中规划资产的维护活动。

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