Cloud-based digital twinning for structural health monitoring using deep learning

Digital Twin technology has recently gathered pace in the engineering communities as it allows for the convergence of the real structure and its digital counterpart throughout their entire life-cycle. With the rapid development of supporting technologies, including machine learning, 5G/6G, cloud computing, and Internet of Things, Digital Twin has been moving progressively from concept to practice. In this paper, a Digital Twin framework based on cloud computing and deep learning for structural health monitoring is proposed to efficiently perform real-time monitoring and proactive maintenance. The framework consists of structural components, device measurements, and digital models formed by combining different sub-models including mathematical, finite element, and machine learning ones. The data interaction among physical structure, digital model, and human interventions are enhanced by using cloud computing infrastructure and a user-friendly web application. The feasibility of the proposed framework is demonstrated via case studies of damage detection of model bridge and real bridge structures using deep learning algorithms, with high accuracy of 92%.

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.