Integrating Machine Learning Techniques into Post-Earthquake Residual Capacity Assessment of Reinforced Concrete Structures

Assessing the seismic residual capacity of damaged structures and infrastructures after a major earthquake is critical to support decision-making on re-occupancy, repair, or demolition. This task typically requires collecting information on the observed earthquake-related damage to structural components and performing additional safety and economic loss evaluations for the damaged structure. While an expert engineering judgment remains crucial to assess damage severity, modern machine-learning techniques such as Convolutional Neural Networks (CNNs) can represent a valuable supporting tool to automate and standardize this process. In this context, this paper presents and discusses a framework for post-earthquake seismic residual capacity assessment of damaged buildings, integrated with and enhanced by a CNN-based damage detection tool. The framework employs nonlinear static analyses performed through a simplified analytical/mechanical procedure and capacity reduction factors for damaged structural components. The level of earthquake-related damage is automatically evaluated from images using a CNN based on a Visual Geometry Group Network 16 (VGG16) architecture, trained on 5,000 images sourced from existing databases and re-labelled by experts. The proposed framework is implemented for a case-study reinforced concrete structure for illustrative purposes. The seismic performance before and after the damaging earthquake is evaluated in terms of a capacity-to-demand safety index, considering also the possible uncertainties in the CNN-based damage classification. The results highlight the potential of the CNN-based framework to support emergency planning and decision-making, particularly for large building portfolios.