Research projects at RISE Lab focus on smart and resilient infrastructure systems through sensing, structural health monitoring, computer vision, AI/ML, digital twins, prognosis, and decision support.
The projects listed here represent ongoing sponsored, internal, exploratory, and collaborative research activities.
Sponsored Research Projects#
High-Fidelity Digital Twins via Scientific Discovery Using Physics-Informed Machine Learning and Uncertainty Quantification for Structural Health Monitoring and Performance Assessment
This project develops high-fidelity digital twin frameworks for structural health monitoring and performance assessment of civil infrastructure systems. The research integrates physics-informed machine learning, scientific discovery, nonlinear dynamics, and uncertainty quantification to improve the reliability of model updating, damage interpretation, and predictive assessment.
The project is motivated by the need to monitor structures and seismic protection systems that may exhibit nonlinear behaviour due to base isolation, energy dissipation devices, cracks, yielding, fatigue, or degradation during service life. The broader aim is to support safer, more intelligent, and more resilient infrastructure systems through data-informed and physically meaningful digital twins.
Seed-Funded and Collaborative Research Projects#
System Identification of Nonlinear Dynamic Systems Using Interpretable Machine Learning Methods for Applications in Structural Health Monitoring
This project focuses on interpretable machine learning methods for system identification of nonlinear dynamic systems in structural health monitoring. The research aims to understand structural behaviour from measured vibration response and support reliable detection, interpretation, and assessment of damage in civil infrastructure systems.
The broader objective is to develop data-driven yet physically meaningful models that can help identify nonlinear behaviour, improve structural monitoring, and support the development of digital representations of damaged or evolving structures.
Computer-Vision and Physics-Informed Machine Learning Based Bridge Structural Health Monitoring
This project develops computer-vision and machine-learning methods for bridge structural health monitoring and condition assessment. The research explores how visual measurements can support full-field monitoring of bridge response and complement traditional sensing approaches.
The project also investigates physics-informed learning approaches to improve the reliability, robustness, and physical consistency of bridge condition assessment models, with validation through laboratory-scale experiments.
Student and Collaborative Opportunities#
Students and collaborators interested in these areas are encouraged to explore the Research page and the Join the Group page.
Specific project topics are discussed individually based on research needs, student background, time commitment, and available opportunities.