• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Reliability Engineering & System Safety >Statistical learning techniques for the estimation of lifeline network performance and retrofit selection
【24h】

Statistical learning techniques for the estimation of lifeline network performance and retrofit selection

机译：统计学习技术估算生命线网络性能和改造选择

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 reliability of water supply networks subjected to catastrophic events is a crucial concern to communities, but our ability to assess these systems is limited by their size and complexity. This paper proposes a statistical learning technique, Random Forests, to efficiently estimate network performance in place of direct physical simulation. This technique uses a set of explanatory metrics that describe the impact of seismic damage to network behavior. The approach is applied to a case study network, the Auxiliary Water Supply System of San Francisco. The resulting statistical model is shown to replicate network performance estimates from flow-based hydraulic simulation, and exhibits good performance in identifying components to retrofit to improve the reliability of the system. The favorable performance and computational advantages of this approach make it an attractive tool for infrastructure reliability and risk mitigation analyses.
机译：经受灾难性事件的供水网络的可靠性是对社区的至关重要，但我们评估这些系统的能力受其大小和复杂性的限制。本文提出了一种统计学习技术，随机森林，以有效地估算网络性能代替直接物理仿真。该技术使用一组解释性指标，描述地震损坏对网络行为的影响。该方法适用于旧金山辅助供水系统的案例研究网络。结果显示所得到的统计模型从基于流动的液压模拟复制网络性能估计，并且在识别用于改进系统的可靠性的情况下表现出良好的性能。这种方法的有利性能和计算优势使其成为基础设施可靠性和风险缓解分析的有吸引力的工具。

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