Intelligent resilience analysis for infrastructure considering uncertain real-time data

对大型复杂基础设施系统进行全面而高效的数值模拟和分析对现代社会变得越来越重要。这些模型是基础设施弹性框架的核心，供利益相关者就基础设施运营、风险预防、维护、维修、恢复和规划做出具有成本效益的决策。现实分析的主要挑战包括连接所有系统级别的众多模型和性能度量，分析关键结构可用或由结构健康监测（SHM）生成的大量数据集，以及考虑所有可用数据中固有的不确定性。同时，详细建模的关键组件之间的系统相互作用的考虑是至关重要的。本提案在结构组件、区域子系统和全球基础设施系统层面解决了这些挑战。在组件层面，将开发基于自动机器学习的智能代理建模程序，将SPP 2388参考桥的大量可用数据浓缩为概率、时间和状态连续的代理模型。该模型将根据SHM收集的实时数据进行更新。由冲突、模糊或不正确（实时）数据引起的不确定性将被量化并通过系统模型传播。在区域子系统层面，关键基础设施组件被链接并集成到一个新开发的系统可靠性模型中，该模型能够进行全面而有效的数值分析。通过将相似的组件聚类为组件类型，进一步降低了该子系统模型的复杂性。从子系统可靠性建模得到的信息被集成到开发的生命周期弹性决策框架（LCRF）中，包括恢复模型和成本函数。这将使决策者能够在考虑组件寿命和资金限制的情况下，在维护、大修和维修计划以及设计过程中做出具有成本效益的生命周期决策。以Bad Oeynhausen附近的参考公路桥（A2）“weserstrombr<e:1> cke”为例，对所开发的组件级方法进行了演示。在系统层面上，考虑了北莱茵-威斯特伐利亚州的基础设施系统，其中将县划分为区域子系统，并假设进一步关键结构部件的物理特性以进行演示。

Comprehensive yet efficient numerical modeling and analysis of large and complex infrastructure systems is becoming increasingly important for modern societies. Such models are at the heart of an infrastructure resilience framework for stakeholders to make cost-effective decisions about infrastructure operations, risk prevention, maintenance, repair, recovery, and planning. Key challenges for a realistic analysis include interconnecting numerous models and performance measures at all system levels, analyzing the massive data sets available for critical structures or generated from Structural Health Monitoring (SHM), and accounting for the inherent uncertainty in all available data. At the same time, the consideration of systemic interactions between key components modeled in detail is crucial.The present proposal addresses these challenges at the structural component, regional subsystem, and global infrastructure system levels. At the component level, an intelligent surrogate modeling procedure based on automated machine learning will be developed to condense the vast amount of data available for the SPP 2388 reference bridge into a probabilistic, time- & state-continuous surrogate model. This model will be updated based on real-time data collected by SHM. Uncertainties arising from conflicting, vague, or incorrect (real-time) data will be quantified and propagated through the systemic model. At the regional subsystem level, critical infrastructure components are linked and integrated into a newly developed system reliability model that enables comprehensive yet efficient numerical analysis. The complexity of this subsystem model is further reduced by clustering similar components into component types. Information resulting from subsystem reliability modeling is integrated into the developed Life Cycle Resilience decision-making Framework (LCRF), including recovery models and cost functions. This will enable decision-makers to make cost-efficient life cycle decisions in the maintenance, overhaul and repair planning as well as design process, taking into account component lifetimes and monetary constraints. The developed approaches on component level are demonstrated for the reference highway bridge (A2) "Weserstrombrücke" near Bad Oeynhausen. On the system level, the North Rhine-Westphalian infrastructure system is considered, whereby the counties are divided into regional subsystems and physical properties of further critical structural components are assumed for demonstration purposes.