Computational predictions for estimating the maximum deflection of reinforced concrete panels subjected to the blast load

We investigate the resistance of reinforced concrete panels (RCPs) due to explosive loading using nonlinear finite element analysis and surrogate models. Therefore, gene expression programming model (GEP), multiple linear regression (MLR), multiple Ln equation regression (MLnER), and their combination are used to predict the maximum deflection of RCPs. The maximum positive and negative errors, mean of absolute percentage error (MAPE), and statistical parameters such as the coefficient of determination, root mean square error (RMSE). Normalized square error (NMSE), and fractional bias are utilized to evaluate and compare the performance of the models. We also present a novel statistical table to demonstrate the distribution of percentage errors indicating that MLnER is the best model for predicting the maximum deflection of RCPs under blast loading. We also carry out a detailed parameter study. The independent variables include the weight of charge, standoff distance, panel thickness, panel dimensions, reinforcement ratio, the compressive strength of concrete and yield strength of the reinforcement. We find that the key parameters are the panel thickness and compressive strength with respect to the explosive strength of RCPs, and the explosive weight and distance from the explosive have the most impact on the RCP failure.