This study presents a method for the automated design of reinforced concrete (RC) beam cross-sections using an artificial neural network (ANN) trained with cost-optimized data generated by the crow search algorithm (CSA). To effectively employ the CSA, recognized for its benefits in addressing engineering problems among metaheuristic algorithms, the design variables of the RC beam cross-section were mediated. The goal is to improve the design efficiency and prediction accuracy by using data with clear trends derived through metaheuristic optimization. The ANN model is trained with input variables, including the design bending moment and the beam height, and outputs design variables, such as the beam width, number of reinforcement bars, and bar diameters. The model trained with the CSA-optimized data is compared with one trained using randomly generated data. The results show that the CSA-trained model achieves a higher prediction accuracy across all the output variables, with a particularly strong linear relationship for beam width. Additionally, a design scenario demonstrates that the CSA-based model can propose a cross-section with an approximately 17.3% cost reduction compared to the random model. The design based on the CSA methodology demonstrates greater efficiency, as it employs a smaller value for the beam width and requires less reinforcement while still satisfying the flexural requirements. Conversely, the design utilizing the random dataset proves inefficient in terms of both the value for the beam width and the reinforcement layout. A SHAP analysis further confirms that the CSA-based model learns more meaningful structural relationships. The findings emphasize the critical role of high-quality training data in ANN-based structural design and suggest the potential for extending the framework to multi-objective design tasks.
We propose PushoverGNN, a graph neural network surrogate for the seismic assessment of reinforced concrete frames. The model jointly predicts global capacity curves and member-level plastic rotations using a shared encoder. The capacity curve is parameterized to unify bilinear and trilinear forms, with a softplus-chain that algebraically enforces structural consistency. Trained on 3,000 simulations and evaluated on 354 directional test samples, PushoverGNN achieves a mean R2 of 0.665 for capacity parameters and 83.1% accuracy for ASCE 41-17 performance grading. Under ASCE 7-22 hazard levels, the surrogate reproduces the performance point and hinge states of fiber-element analysis at approximately 129× lower wall-clock cost for the end-to-end seismic performance assessment of a representative low-rise frame. By replacing the nonlinear static procedure with a single graph forward pass, the model enables rapid large-scale seismic evaluation and design optimization while maintaining physical admissibility.