MS05 AI and Digital Clones: The Future of Structural Monitoring and Decision-making
Distinguished Prof. J. Geoffrey Chase: email@example.com
Distinguished Professor J. Geoffrey Chase: Department of Mechanical Engineering & Centre for Bio-Engineering, University of Canterbury, New Zealand. firstname.lastname@example.org.
Professor Chao Xu: School of Astronautics, Northwestern Polytechnical University, China. chao_xu @nwpu.edu.cn.
Dr Cong Zhou: Department of Mechanical Engineering & Centre for Bio-Engineering, University of Canterbury, New Zealand. email@example.com.
Abstract of the special session：
As the rise of digital clones powered by AI machine learning technology, automated creation of digital clones or “virtual patients” offers significant potential to achieve better insights on dynamic systems behavior. For structural systems, the ability to assess not just structural damage, but to predict subsequent behaviours offers the potential to drive better decisions and optimise outcomes confidence based on longer-term monitoring. The same logic applies in biomedical and other systems. The primary goal of integrating digital clones, machine learning and Internet of Things is to extend structural and other monitoring from a damage-monitoring role into a more comprehensive quantified tool for assessing ongoing structural safety, reliability, and future repair/retrofit needs.
This approach stretches nonlinear dynamic modelling, safety assessment, risk treatment and financial analysis into a smart service leveraging trends for increasing instrumentation and data resources of structures. Such digital clones and smart services have been emerging amongst companies and industry giants to optimise product lifecycle use with the potential to provide billions of dollars in smart service revenues. This session thus aims to bring together a range of inter-disciplinary research focusing on, but not necessarily limited to, digital clones for structures, application of machine-learning algorithms for SHM, system identification, SHM instrumentations, automated modelling, nonlinear modelling, financial risk analysis, risk prediction and treatment.
Overall, this session provides an opportunity to share and discuss new advances using digital clones and machining learning technology in the broad field of SHM applications, such as civil engineering, astronautics engineering, aerospace engineering and biomedical engineering.
ICOSSAR 2021 Secretariat
Tongji University, 1239 Siping Road, Shanghai 200092, China Email: firstname.lastname@example.org
© 2021 ICOSSAR 2021 Powered by Weicheng