Modeling shear strength of medium- to ultra-high-strength steel fiber-reinforced concrete beams using artificial neural network

Abstract

This paper presents an approach for the prediction of the shear strength of steel fiber-reinforced concrete (SFRC) beams using artificial neural network (ANN) model developed based on existing experimental results. Experimental database containing 173 SFRC beams without stirrups (having concrete compressive strength ranging from 20.6 to 175 MPa, classified as medium-strength, high-strength and ultra-high-strength concrete beams) and steel fiber of various shapes (hooked, crimped and straight/plain) is used to develop an ANN model. The influence of various factors affecting the shear strength of SFRC beams is also analyzed based on experimental data. The developed ANN model is validated and tested with additional data from 36 experimental beams. The shear strengths predicted based on ANN model are found to be in good agreement with the experimental values. The results show that ANN model has strong potential as a feasible design tool for predicting the shear strength of SFRC beams without transverse reinforcement/stirrups within the range of input parameters considered in this study. The developed ANN model is also found to be more accurate in predicting the shear strength compared with existing empirical equations especially for high- to ultra-high-strength SFRC beams.