The efficient and accurate prediction of structural responses in reinforced concrete components under blast loading plays a critical role in emergency repair decision, structural strengthening, and protective design. Existing rapid methods for calculating structural response, such as analytical models and lightweight data-driven approaches, are computationally efficient. However, they are limited in accurately resolving three-dimensional structural response fields. A Graph Neural Network (GNN)-based model for the rapid prediction of damage in reinforced concrete (RC) columns was proposed in this paper. By leveraging the neighborhood node aggregation mechanism of GNNs, the model efficiently transmits mechanical correlation information within the structure. This allows the model to establish an end-to-end mapping between blast load inputs and the 3D structural response of the component, enabling rapid prediction of the column’s damage state. Furthermore, a multi-scenario feature coupling training strategy is introduced to significantly enhance the model’s generalization capability. This strategy enables the GNN model to effectively adapt to variations in key design and loading parameters, including reinforcement ratios, explosive charge weights, and blast locations. The results demonstrate that the proposed model achieves a prediction time of merely 55 milliseconds per instance, representing a computational speed improvement of four orders of magnitude over conventional methods; meanwhile, the prediction error remains below 3.33%. Furthermore, it delivers high-precision damage predictions across various blast scenarios. The proposed study successfully highlights the significant potential of GNN-based approaches in predicting blast-induced damage and offers an innovative, data-driven solution for rapid structural assessment and protective design in the field of blast engineering.

To accurately predict the explosion power fields in buildings, solving the failure of traditional empirical formulas often failing to account for complex environmental factor due to their inability to account for complex environmental factors, and that of numerical simulations inefficient for large-scale urban scenarios and do not meet the needs of rapid damage assessment. Addressing this challenge, an innovative prediction model for explosion power fields based on graph neural networks (GNN) was constructed using an end-to-end strategy. This model enabled rapid and precise forecasting of three-dimensional physical fields, including peak overpressure, peak impulse, and shock-wave arrival times on building surfaces. Compared with numerical simulations, the proposed GNN model demonstrated excellent predictive performance: it achieved a mean square error of 0.97% for predicting surface overpressure parameters of single buildings with varying geometries, and an average prediction error of 3.17% for complex geometric buildings and building communities. When applied to real-world urban settings, the model maintains an average prediction error of 1.29%, completing individual physical field predictions in under 0.6 seconds—three to four orders of magnitude faster than numerical simulations. Furthermore, the model's high-precision predictions allow for the reconstruction of overpressure time history curves at any building surface location and the accurate assessment of structural damage. The proposed GNN model offers a novel approach for rapidly and accurately predicting explosion power fields in urban buildings during blast events. This advancement significantly enhances the capabilities for explosion damage assessment and anti-explosion design in ultra-large-scale complex engineering scenarios, providing substantial engineering value.