In this study, the seismic vulnerability of the Ferdowsi School building in Tabriz is investigated. The research began with comprehensive fieldwork, during which exploratory surveys and in-depth technical inspections of all structural components were performed. Experimental testing of prismatic masonry specimens was carried out to evaluate their mechanical characteristics, and the resulting properties were then incorporated as input parameters into the numerical model. The seismic vulnerability assessment was then carried out using nonlinear static (pushover) analysis, applying a lateral load pattern proportional to the first vibration mode of the structure. For numerical simulation, the building was modeled in the ABAQUS finite element software using the macro-modeling technique. The results of the nonlinear static analysis indicated that the building does not possess sufficient load-bearing capacity at the target displacement. Damage was primarily concentrated in the form of cracking in the masonry walls as well as in the dome-shaped sections of the roof, requiring the implementation of a seismic retrofitting scheme to enhance the structure’s seismic performance. To rehabilitate the structure, horizontal and vertical reinforced concrete beams were introduced as confining elements for the masonry walls and subsequently applied in the strengthening project. Furthermore, due to the presence of a domed roof at the first-floor level, it was strengthened using FRP composite materials to enhance tensile capacity and ductility. At the second-floor level, where the roof structure is made of timber elements, a steel cable system was employed to improve its strength and diaphragm action. As for the third-floor timber truss roof, the connections were upgraded and reinforced to provide reliable force transmission and to maintain the overall integrity of the structural system. Following the implementation of the retrofitting measures, the structural model was re-analyzed using nonlinear static analysis. The results demonstrated that the proposed strengthening scheme successfully increased the structural capacity up to the target displacement level and satisfied the intended performance requirements. In the final section of the paper, the implementation details of the retrofitting interventions, as well as the practical experiences gained during the implementation process, are presented and discussed.

Double-layer barrel vault roofs with double-layer vertical walls are widely used in important public buildings because of their high structural efficiency, favorable stiffness-to-weight ratio, and architectural versatility. Although incremental dynamic analysis (IDA) is a widely accepted approach for seismic assessment, it requires numerous nonlinear time-history analyses (NTHAs), resulting in high computational cost. This study presents an artificial neural network (ANN)-based surrogate modeling framework to accurately predict the seismic response of these structural systems, reducing the need for repeated NTHAs, enabling rapid estimation of structural dynamic responses, and facilitating direct development of seismic fragility curves. The proposed framework substantially decreases computational effort while maintaining an effective balance between accuracy and efficiency. A comprehensive seismic damage database is first generated using finite element (FE) models developed in OpenSees. Fragility curves are then obtained using both the conventional IDA procedure and the proposed ANN-based surrogate approach. Results show that the ANN surrogate accurately predicts the responses of structures subjected to scaled ground motions and effectively captures their nonlinear seismic behavior. Furthermore, the resulting fragility curves closely match those from the conventional IDA method, demonstrating the accuracy, reliability, and efficiency of the proposed framework for rapid seismic assessment of double-layer barrel vault structures with double-layer walls.