Developing an instrumentation architecture and a self-learning algorithm for creating digital twins of municipal bridges

开发用于创建市政桥梁数字孪生的仪器架构和自学习算法

• 批准号: 576165-2022
• 负责人: Ruparathna, VithanapalpitaVKRJ
• 金额: $ 1.82万
• 依托单位: University of Windsor
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 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=748994
• 关键词: Developing; instrumentation; architecture; self; learning

A digital twin is a virtual model that is an exact representation (or twin) of a physical system. Digital twin technology supports proactive infrastructure management by assisting in monitoring and maintaining, optimizing performance, and understanding failure cause. Digital twin technology increases the service life, safety, resiliency, and level of service of civil infrastructure while decreasing operational costs. Bridge infrastructure is a crucial component of civil infrastructure systems. However, the digital twin technology has not yet been used for bridge infrastructure management in Canada. The objective of this research is to develop the system architecture for creating a digital twin of a bridge infrastructure to aid dynamic infrastructure management decision-making. This research aims to develop an instrumentation architecture for real-time monitoring and acquisition of the physical infrastructure data. Moreover, a self-learning algorithm will be developed to predict bridge deterioration. This research proposes a state-of-the-art solution for current bridge infrastructure management challenges. The outcomes of this research will support United Nations Sustainable Development Goals, sustainable cities and communities (Goal # 11), and industry innovation and infrastructure (Goal # 9).

数字孪生是一种虚拟模型，它是物理系统的精确表示（或孪生）。数字孪生技术通过协助监控和维护、优化性能以及了解故障原因，支持主动式基础设施管理。数字孪生技术可以延长民用基础设施的使用寿命、安全性、弹性和服务水平，同时降低运营成本。桥梁基础设施是民用基础设施系统的重要组成部分。然而，数字孪生技术尚未在加拿大用于桥梁基础设施管理。本研究的目标是开发系统架构，用于创建桥梁基础设施的数字孪生模型，以帮助动态基础设施管理决策。本研究的目的是开发一种仪器架构的实时监测和采集的物理基础设施的数据。此外，还将开发一种自学习算法来预测桥梁的劣化。这项研究提出了一个国家的最先进的解决方案，目前的桥梁基础设施管理的挑战。这项研究的成果将支持联合国可持续发展目标、可持续城市和社区（目标11）以及行业创新和基础设施（目标9）。