Experimental Investigation on Strength Characteristics of Self-Compacting Self- Curing Concrete and Prediction by Artificial Neural Network (ANN)

Abstract

Self-compacting concrete (SCC) is considered as a concrete which can be placed and compacted under its self-weight with little or no vibration effort, and which is at the same time cohesive enough to be handled without segregation or bleeding of fresh concrete. Intelligence system is a field of computer science that designs and studies efficient computational methods for solving problems. This research study presents the comparative performance of the models developed to Predict 28 days strength using artificial neural networks approach. The data used in the models was obtained experimentally with various fine aggregate replacement of a Quarry Dust (0, 10, 20, 30, 40%) Self-Curing agent constant and addition of mineral admixture Fly Ash. Mix proportions of Self Compacting and Self Curing for M40 grade concrete were arrived. For each concrete mix 150×150×150 mm cubes, 150×300 mm cylinders were cast and left for Self-Curing for at ambient temperature at 28 days and results are compared with Self Compacting Concrete (SCC). The Slump Flow, J-Ring, U-Box, L-Box and V-Funnel test are carried out on the fresh properties and in harden concrete Compressive Strength, Split Tensile Strength were determined. The flow properties on SCC with cement, Fly Ash as additional for Cementitious material and various proportions of Quarry Dust has been performed and found that the values were within the limits prescribed by EFNARC. The experimental data obtained are used to train the feed forward artificial neural network type. Finally, the trained ANN (artificial neural network) is used for predicting Self Compacting and Self Curing concrete strength properties. The experimental result is compared with ANN result, which suits with minor negligible errors.