Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article

Degree

Doctor of Philosophy

Program

Civil and Environmental Engineering

Supervisor

El Naggar, M. Hesham

Abstract

This thesis investigates the seismic performance of bridge systems using a combination of numerical simulations and machine learning techniques to assess structural responses and predict damage, considering soil-structure interaction. A finite element model (FEM) is developed in OpenSees to simulate the seismic behavior of a pile-soil-bridge system and is validated against shake table test data. The bridge model, consisting of four piers supported by pile groups, is subjected to two earthquake records, El Centro and Tianjin, at varying intensity levels. The results showed good agreement with the experimental data, with the El Centro earthquake inducing higher acceleration and moment responses, while the Tianjin earthquake caused greater displacement responses, underscoring the impact of earthquake characteristics on bridge behavior. A fragility study is then conducted for a three-span bridge supported by helical piles in cohesive soil. Latin Hypercube Sampling (LHS) is employed for addressing material uncertainty and Incremental Dynamic Analysis (IDA) is used to derive the fragility curves. A total of 6,600 nonlinear time history analyses are conducted on 15 bridge samples subjected to 22 ground motion records. The key factors influencing damage at piers and helical piles are identified. Consequently, regression analysis revealed that longer spans increased drift, while damping ratio and pile spacing significantly affected settlement. Helical piles are found to be more vulnerable to ductility demands than to settlement, marking them as a critical component in the system. Machine learning algorithms are then applied to classify damage states based on the dataset obtained from numerical analyses. Among the twelve models evaluated, CatBoost and LightGBM provided the best classification performance, while traditional models like Linear Discriminant Analysis and Naive Bayes struggled with class imbalance. The findings highlight the effectiveness of machine learning in seismic damage prediction, despite the challenges posed by imbalanced datasets.

Summary for Lay Audience

This study investigates how bridges perform during earthquakes, with a focus on how their foundations interact with the soil. Using computer simulations, a bridge subjected to two real earthquakes is simulated to examining how different seismic forces affect the structure. This allows for a deeper understanding of how varying earthquake characteristics influence the structure's response during and after seismic events, offering critical insights into how bridges withstand seismic loading.

The second part of the thesis develops "fragility curves" which are tools used to estimate the likelihood of different levels of damage a bridge could experience during an earthquake. The study investigate a bridge supported by helical piles in cohesive soil, by conducting 6,600 simulations to assess potential damage for bridges with different geometries and varying soil conditions subjected to different earthquake scenarios. Key factors like material strength and pile spacing are found to influence the damage, providing insights into how design choices affect the seismic performance of bridges.

The final part of the thesis utilizes common machine learning algorithms to predict damage levels based on data from these simulations. Since some damage states are underrepresented, techniques like oversampling and undersampling are applied to address class imbalance. Oversampling involves adding more instances of less common damage categories, while undersampling reduces the number of instances in more common categories. The performance of these methods varied, with some algorithms better suited to handling the class imbalance than others. The results underscore the potential of machine learning in earthquake damage assessment, while also highlighting the challenges posed by imbalanced data in such applications.

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

COinS