Improved shear strength prediction model for SFRC beams without stirrups

Abstract

PurposeThe application of steel fiber reinforced concrete (SFRC) beams is limited in practice, partially due to the lack of accurate shear strength prediction models. This study aims to develop a reliable shear strength prediction model for SFRC beams.Design/methodology/approachIn this study, an artificial neural network was employed to predict the shear strength of SFRC beams, utilizing a comprehensive database of 562 experimental studies. Multiple neural networks were established with varying hyperparameters, and their performance was evaluated using statistical parameters.FindingsThe neural network with 11 neurons showed superior results than other networks. The performance evaluation, efficiency and accuracy of the selected neural network were examined using margin of deviation, k-fold cross-validation, Shapley analysis, sensitivity analysis and parametric analysis. The proposed artificial neural network model accurately predicts the shear strength and outperforms other existing equations.Originality/valueThis research contributes to overcoming the limitations of existing prediction models for shear strength of SFRC beams without stirrups by developing a highly accurate model based on ANN. Utilizing a comprehensive database and rigorous evaluation techniques enhances the reliability and applicability of the proposed model in practical engineering applications.