PREDICTION OF MECHANICAL PROPERTIES OF STEEL FIBRE-REINFORCED CONCRETE UNDER ELEVATED TEMPERATURE USING ARTIFICIAL NEURAL NETWORK TECHNIQUES (ANN)

Premkumar GSenthil Selvan S^*

• Department of Civil Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, India

Steel Fibre-Reinforced Concrete (SFRC) undergoes significant changes in its mechanical properties when exposed to high temperatures. While several studies have explored machine learning techniques to predict SFRC compressive strength under elevated temperatures, there remains a noticeable gap in addressing other essential mechanical properties. Previous research has primarily concentrated on compressive and flexural strength, largely overlooking split tensile and bond strength. This study aims to bridge this gap by introducing an Artificial Neural Network (ANN) model designed to forecast compressive strength, flexural strength, split tensile strength, and bond strength. Through the analysis of 967 experimental datasets covering various concrete mixes, the model underwent thorough training and rigorous testing. The findings demonstrate that the proposed model adeptly predicts compressive, split tensile, flexural, and bond strength, achieving R 2 values ranging from 0.85 to 0.88. In summary, the model provides accurate predictions with minimal error across the key mechanical properties of SFRC.