PREDICTING THE COMPRESSIVE STRENGTH OF SELF COMPACTING CONCRETE USING ARTIFICIAL NEURAL NETWORK

Artificial neural network have recently been widely used to simulate the human activities in many areas of civil engineering applications. In the present paper, an artificial neural network study is carried out to predict the compressive strength of self-compacting concrete. This paper aims to show a possible applicability of artificial neural network to predict the compressive strength of self-compacting concrete. An artificial neural network model is built, trained and tested using the available experimental results for 104 different mixture proportions gathered from the technical literature. The data used in the artificial neural network model are arranged in a format of six input parameters that cover the content of cement, fly ash, water, superplasticizer, coarse aggregate and fine aggregate and, an output parameter which is compressive strength of self-compacting concrete. The statistical values for compressive strength predicted by artificial neural network are also compared to those obtained using regression models. The training and testing results in the artificial neural network model show that artificial neural network can be an alternative approach for the predicting the compressive strength of self-compacting concrete using concrete ingredients as input parameters.