Prediction of Expansion due to Sulfate of Ground Bottom Ash Mortar by an Artificial Neural Network

Abstract

This paper presents the application of the artificial neural network model (ANN) to predict the expansion of ground bottom ash mortar due to sodium sulfate. Portland cement type I was replaced by ground bottom ash at ratios of 0, 10, 20, 30, 40, 50 and 60 percent by weight of binder. The expansion of mortar which immersed in 5% sodium sulfate at various ages was measured. To show the efficiency of the proposed model, the prediction results of the ANN model are compared with the multiple linear regression (MLR) and the multiple second order polynomial regression (MSPR) models through statistical values. From the prediction results, it was found that the ANN model has a very high expansion prediction accuracy and more effective than the MLR and MSPR. The ANN model has a statistical value of absolute variance higher than 0.99. Therefore, it is concluded that the ANN model has a strong prediction capability of expansion due to sulfate of ground bottom ash mortar.

Keywords

• prediction
• expansion of mortar
• ground bottom ash
• sulfate
• artificial neural network