NSF Convergence Accelerator Track D: Intelligent Surveillance Platform for Damage Detection and Localization of Civil Infrastructure

NSF融合加速器支持以使用为灵感，以团队为基础，多学科的努力，以应对国家重要性的挑战，并将在不久的将来为社会提供有价值的成果。这个融合加速器第一阶段项目的更广泛的影响和潜在的社会效益是通过促进对建筑结构的广泛监测和状态评估来减少老化，恶化和极端事件对民用基础设施的社会和经济影响。可靠的结构健康监测工具对于优先考虑国家老化基础设施的维护和维修决策是必要的。精确的，现场校准的损伤检测工具的发展是必要的，以减少理论与实践的差距。反过来，该项目将通过减少老龄化、恶化和极端事件对民用基础设施的社会和经济影响，促进社区的福祉。该项目旨在创造性地将机器学习（ML）和模式识别学科的进步与基于物理的推理相结合，开发一种新颖、准确、现场校准和验证的计算平台，用于民用基础设施的现场监测。这个分两个阶段的项目的主要成果是一个智能计算平台，包括用于土木工程结构的基于视频的损伤检测和监测的数据和算法。第一阶段将侧重于选择基准结构、收集数据和开发平台原型，并将在第二阶段进行现场校准。到第二阶段结束时，项目团队打算进一步开发和现场校准将ML模型与视频分析模块集成的计算平台，该平台将在选定的基准结构上实施，并编写了用户手册和教育材料，该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准。

The NSF Convergence Accelerator supports use-inspired, team-based, multidisciplinary efforts that address challenges of national importance and will produce deliverables of value to society in the near future. The broader impact and potential societal benefit of this Convergence Accelerator Phase I project is to reduce the societal and economic impact of aging, deterioration, and extreme events on civil infrastructure by facilitating widespread monitoring and condition assessment of constructed structures. Reliable structural health monitoring tools are necessary for prioritizing maintenance and repair decisions regarding the nation’s aging infrastructure. Development of accurate, field-calibrated damage detection tools is needed to reduce the theory-to-practice gap. In turn, this project will promote the wellbeing of the community by reducing the societal and economic impact of aging, deterioration, and extreme events on civil infrastructure. The envisioned work requires diverse perspectives from multiple disciplines, and partnerships crossing organizational, institutional, and disciplinary boundaries.This project aims to creatively integrate advances in Machine Learning (ML) and pattern recognition disciplines with physics-based reasoning to develop a novel, accurate, field-calibrated, and verified computational platform for in-situ monitoring of civil infrastructure. The main deliverable of this two-phased project is an intelligent computational platform consisting of data and algorithms for video-based damage detection and monitoring of civil engineering structures. Phase I will focus on the selection of thebenchmark structures, collection of data, and the development of a prototype of the platform, which will be field calibrated in Phase II. By the end of Phase II, the project team intend to have further developed and field-calibrated the computational platform integrating the ML model with a video analytics module, which will be implemented on selected benchmark structures, and have prepared user manuals and educational materials for end-users.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.