PREDICTION OF COMPRESSION STRENGTH OF CONCRETE BY USING ARTIFICIAL NEURAL NETWORK

Abstract

Concrete cubes strength determination tests are usually performed at three days to one year after pouring the concrete. The waiting period required to perform such test may delay the construction progress, decision making and neglecting such test would limit the quality control checks in large construction projects. Therefore, it becomes necessary that the rapid and reliable prediction of concrete strength is essential for pre-design or quality control of construction. It is possible to facilitate the modification of the mix proportion if the concrete does not meet the required design stage, which may save time and construction costs. The early prediction of concrete strength is essential for estimating the desirable time for concrete form removal, project scheduling, quality control and estimating delay if any. Artificial Neural Network (ANN) is used to predict the compressive strength of concrete. Standard back propagation is used to train the networks. Networks are trained and tested at various learning rate and momentum factor and after many trials these were kept constant for this study. However, according to the standard test procedure, the results of a compressive strength test on cement can be known only after 7 or 28 days. To overcome this difficulty, artificial neural network for predicting the 28 days’ compressive strength of cement is introduced. The results of artificial neural network are then compared with the available experimental results. The comparison shows the validity of the method. This report investigates the use of artificial neural network in evaluating the compressive strength of concrete. It is observed that artificial neural networks can predict compressive strength of concrete with 91 to 98 % accuracy.