Revolutionizing Canada's Aging Civil Infrastructure Assessment and Renewal: An Integrated, Multi-Scale, Remote Sensing, Data-Driven Approach

彻底改变加拿大老化的民用基础设施评估和更新：综合、多尺度、遥感、数据驱动的方法

• 批准号: RGPIN-2021-03597
• 负责人: Nehdi, Moncef
• 金额: $ 3.79万
• 依托单位: McMaster University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=749092
• 关键词: Revolutionizing; Canada; Aging; Civil; Infrastructure

Canada's civil infrastructure is the nation's most vital physical asset and is central to the quality of life of all Canadians. However, the most recent 2019 Report Card shows that our infrastructure is at risk, requiring considerable investments, while we still rely on outdated methods for infrastructure condition assessment and renewal. This is despite that Canada has been spending more on infrastructure renewal than on building new one; a trend expected to intensify in post-COVID-19 to mitigate a looming recession and ensure that lifeline systems can sustain crisis situations. Without creating a robust strategy to modernize Canada's infrastructure assessment and renewal, Canada's enormous investments in this area will be at risk, and competitors will control a related annual global market of US$ 10 trillion. This research program aims at reforming the condition assessment, damage diagnosis, design of repair strategies, and service life prognosis for aging concrete structures. It will surpass current subjective and operator sensitive visual inspection methods, to establish a rational, data-driven framework that integrates materials science and forensic engineering for robust condition assessment. Powerful machine learning algorithms using drone and robotic acquired big data will be deployed to deliver precise structural condition appraisal and prioritize aging structures for urgency of repair. Multi-scale and multi-source data will be integrated to identify the cause of structural damage. The machine learning framework will also be trained to identify effective repair strategies towards sustainable, resilient and economic infrastructure renewal in Canada. Big discovery often occurs at the crossroads of disciplines. Thus, this research will fuse synergistic knowledge areas and multi-scale data to invent strategies for infrastructure renewal. Remote sensing data will be acquired on aging concrete structures that are critical to national security or vulnerable to climate change effects. Machine learning algorithms will be trained as a robust intelligent framework for automated condition assessment to precisely identify and classify damage in these structures, allocate a global damage index, and prioritize structures for repair. This novel research program bridges critical knowledge gaps at the interface of materials science, forensic engineering and artificial intelligence to empower the inspector with robust portable decision-making tools for infrastructure appraisal and renewal. This transformative research will have pervasive impact via training Canada's future leaders on pioneering technology for infrastructure assessment and renewal, revolutionizing the condition assessment of aging structures, delivering faster and more precise results at lower cost, and allowing smarter resource allocation. The research will also empower the Canadian private sector to become a global leader with cutting-edge technology and robust gears in its toolkit.

加拿大的民用基础设施是国家最重要的物质资产，对所有加拿大人的生活质量至关重要。然而，最新的2019年报告卡显示，我们的基础设施面临风险，需要大量投资，而我们仍然依赖过时的基础设施状况评估和更新方法。尽管加拿大在基础设施更新上的支出一直高于新建基础设施；这一趋势预计将在2019冠状病毒病后加剧，以缓解迫在眉睫的经济衰退，并确保生命线系统能够维持危机局势。如果没有一个强有力的战略来实现加拿大基础设施的现代化评估和更新，加拿大在这一领域的巨大投资将面临风险，竞争对手将控制每年10万亿美元的相关全球市场。本研究旨在改革老化混凝土结构的状态评估、损伤诊断、修复策略设计和使用寿命预测。它将超越目前的主观和操作者敏感的视觉检测方法，建立一个合理的、数据驱动的框架，将材料科学和法医工程相结合，用于稳健的状态评估。利用无人机和机器人获取的大数据，将部署强大的机器学习算法，以提供精确的结构状况评估，并优先考虑老化结构的紧急维修。综合多尺度、多源数据，识别结构损伤原因。机器学习框架还将进行培训，以确定有效的修复策略，以实现加拿大可持续、有弹性和经济基础设施的更新。重大发现往往出现在学科交叉的地方。因此，本研究将融合协同知识领域和多尺度数据来制定基础设施更新策略。将获取对国家安全至关重要或易受气候变化影响的老化混凝土结构的遥感数据。机器学习算法将被训练成一个强大的智能框架，用于自动状态评估，以精确识别和分类这些结构中的损伤，分配全局损伤指数，并优先考虑需要修复的结构。这一新颖的研究项目弥合了材料科学、法医工程和人工智能之间的关键知识鸿沟，为检查员提供了强大的便携式决策工具，用于基础设施评估和更新。这项变革性的研究将通过培训加拿大未来的领导者在基础设施评估和更新方面的前沿技术，彻底改变老化结构的状态评估，以更低的成本提供更快，更精确的结果，并允许更智能的资源分配，从而产生广泛的影响。这项研究还将使加拿大私营部门成为拥有尖端技术和强大工具的全球领导者。