Stripe-Based Fragility Analysis of Concrete Bridge Classes Using Machine Learning Techniques
This work addresses the need for more accurate and efficient seismic risk assessment for bridge infrastructure, particularly for engineers and planners, though it is incremental as it builds on existing stripe-based approaches with machine learning enhancements.
The paper tackles the problem of generating fragility curves for concrete bridges under seismic loads by introducing a machine learning framework that reduces computational effort and avoids unrealistic assumptions like lognormality in demand models. The result is a methodology that efficiently updates fragility curves for new parameters and identifies key uncertain variables, demonstrated through case studies of multi-span concrete bridges in California.
A framework for the generation of bridge-specific fragility utilizing the capabilities of machine learning and stripe-based approach is presented in this paper. The proposed methodology using random forests helps to generate or update fragility curves for a new set of input parameters with less computational effort and expensive re-simulation. The methodology does not place any assumptions on the demand model of various components and helps to identify the relative importance of each uncertain variable in their seismic demand model. The methodology is demonstrated through the case studies of multi-span concrete bridges in California. Geometric, material and structural uncertainties are accounted for in the generation of bridge models and fragility curves. It is also noted that the traditional lognormality assumption on the demand model leads to unrealistic fragility estimates. Fragility results obtained the proposed methodology curves can be deployed in risk assessment platform such as HAZUS for regional loss estimation.