Prediction Of Compressive Strength And Slump Of Concrete Using Artificial Neural Network Modeling

The paper discusses the concept of artificial neural network (ANN) to predict the behavior of a concrete primarily determined by the mix proportion of the concrete mix. The prediction models for the slump and the 28 days compressive strength of concrete are developed using the multilayer perceptron neural network. The ANN model proposed is based on 9 input parameters such as average paste thickness, water–cement ratio, fly ash– binder ratio, grain volume fraction of fine aggregates and the amount of cement, fly ash, fine aggregates, coarse aggregates and super-plasticizers. The proposed concrete mix proportion design is expected to reduce the number of trials, saves cost of material as well as labor and also saves time as it provides higher accuracy. The concrete designed is expected to have lower cement and water contents and hence is economical.