Chained machine learning model for predicting load capacity and ductility of steel fiber–reinforced concrete beams

Abstract

One of the main issues associated with steel fiber–reinforced concrete (SFRC) beams is the ability to anticipate their flexural response. With a comprehensive grid search, several stacked models (i.e., chained, parallel) consisting of various machine learning (ML) algorithms and artificial neural networks (ANNs) were developed to predict the flexural response of SFRC beams. The flexural performance of SFRC beams under bending was assessed based on 193 experimental specimens from real-life beam models. The ML techniques were applied to predict SFRC beam responses to bending load as functions of the steel fiber properties, concrete elastic modulus, beam dimensions, and reinforcement details. The accuracy of the models was evaluated using the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) of actual versus predicted values. The findings revealed that the proposed technique exhibited notably superior performance, delivering faster and more accurate predictions compared to both the ANNs and parallel models. Shapley diagrams were used to analyze variable contributions quantitatively. Shapley values show that the chained model prediction of ductility index is highly affected by two other targets (peak load and peak deflection) that show the chained algorithm utilizing the prediction of previous steps for enhancing the prediction of the target feature. The proposed model can be viewed as a function of significant input variables that permit the quick assessment of the likely performance of SFRC beams in bending.