• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Reliability and optimization of structural systems >Bayesian network with Gaussian variables for post-earthquake emergency management
【24h】

Bayesian network with Gaussian variables for post-earthquake emergency management

机译：具有高斯变量的贝叶斯网络用于地震后的应急管理

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

We propose a probabilistic methodology to assess the reliability of a network of bridges in the aftermath of an earthquake, allowing real-time updating when data collected by visual inspection or instrumented monitoring are available. The approach makes use of a Bayesian network with conditional Gaussian distributions to model the correlations in demands and capacities of the bridges. The main benefit of the approach relative to using a Bayesian network with discrete variables is that it can handle a large number of variables (in the order of a few thousand), performing exact inference. In this work, we propose a formulation to model the prior assumptions on seismic excitation and on capacity and damage state by linear relationships and conditional Gaussian distributions. We present the effectiveness of the methodology on a large bridge network, showing how the reliability of links and of the connectivity between selected locations is progressively updated as information on ground acceleration at recording sites and on observed displacement and condition state of selected bridges becomes available.
机译：我们提出了一种概率方法来评估地震后桥梁网络的可靠性，以便在通过目视检查或仪器监测收集到的数据可用时进行实时更新。该方法利用具有条件高斯分布的贝叶斯网络来建模桥梁需求和容量之间的相关性。该方法相对于使用具有离散变量的贝叶斯网络的主要好处是，它可以处理大量变量（几千个），执行精确的推断。在这项工作中，我们提出了一种公式，用于通过线性关系和条件高斯分布来建模关于地震激励以及容量和破坏状态的先验假设。我们介绍了该方法在大型桥梁网络上的有效性，显示了随着记录站点的地面加速度信息以及选定桥梁的观测位移和状态状态的信息的可用，如何逐步更新链接的可靠性以及选定位置之间的连通性。

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