Prediction of compressive and flexural strengths of a modified zeolite additive mortar using artificial neural network

Abstract

Artificial neural network (ANN) has been used to predict the compressive and flexural strength of a mortar made with a modified zeolite additive (MZA). The ANN had three layers, which included the input, hidden and output layer. The input layer had six parameters: cement quantity, silica sand quantity, modified zeolite additive (MZA) quantity, water quantity, curing period, and load weights. The output layer consisted of either the compressive or the flexural strength. While developing the ANN model, 30 samples were used for training and testing. Two assessments were carried out, first to determine the effective number of neurons in the hidden layer in predicting the compressive strength. The second assessment evaluated the accuracy with which the neural network would predict the compressive or flexural strength under different load weights. In general, the ANN learnt from the training data and was able to give excellent results. For the compressive strength, the testing data was estimated with a correlation coefficient (R2) of 0.9967, 0.9938, 0.9924 and 0.6676 for four load weights, while the flexural strength was predicted with R2 of 0.9984 and 0.9990 for two load weights. The ANN can be used to augment or in lieu of experimental work to determine both the compressive and the flexural strength of mortar.