Efficient machine learning-based modeling for regional reliability analysis of infrastructure systems
Advisor: Hadi Meidani
Location: illinois.zoom.us/j/7651344825?pwd=WHQwcmxQYWVOS3RQQnVtV3NZUUhkdz09
Abstract:
This dissertation explores the reliability and resilience of infrastructure systems, focusing on transportation networks, water distribution networks, power distribution networks, and communication systems. As infrastructure systems become increasingly interconnected and susceptible to disruptions from natural hazards and human-induced events, there is a growing need for efficient, scalable, and adaptive modeling techniques. This work leverages deep learning methodologies, particularly Physics Informed Neural Network (PINN) and Graph Neural Networks (GNNs), to enhance infrastructure system analysis, addressing challenges related to system identification, reliability assessment, traffic assignment, dynamic flow forecasting, and infrastructure asset management. By integrating physics-informed constraints, heterogeneous graph representations, and data-driven optimization strategies, this dissertation provides novel solutions that improve computational efficiency, predictive accuracy, and decision-making in complex infrastructure networks.
The research contributions span multiple domains, beginning with PIDynNet, a physics-informed neural network designed for nonlinear structural system identification. The dissertation then presents a rapid seismic reliability assessment framework for highway bridge networks, demonstrating the capability of GNN-based models to predict connectivity loss under probabilistic seismic scenarios. Additionally, a heterogeneous GNN model is introduced for user equilibrium traffic assignment, incorporating virtual links to improve demand propagation and flow estimation. Further advancing traffic flow modeling, the Heterogeneous Spatio-Temporal Graph Sequence Network (HSTGSN) is proposed to forecast dynamic traffic conditions, even in sensor-limited environments. A multi-class traffic assignment framework leveraging multi-view GNNs is also developed to differentiate between vehicle types, providing a more granular understanding of traffic flow dynamics. Finally, a GA-GNN optimization framework is introduced to enhance transportation equity in seismic retrofit planning, balancing network resilience with social equity considerations.
The dissertation concludes by summarizing key findings and outlining future research directions. Expanding GNN applications to multi-hazard risk assessment can improve infrastructure resilience across various disaster scenarios. Enhancing the generalization capability of GNN models will further improve adaptability to diverse infrastructure topologies and hazard conditions. Additionally, integrating real-time sensor data into GNN-driven frameworks will enable dynamic infrastructure monitoring, proactive risk assessment, and real-time decision-making. By addressing these challenges, future research can extend the impact of deep learning methodologies in infrastructure resilience, fostering the development of smarter, more adaptive, and disaster-resilient infrastructure systems.