Prediction of Mortar Compressive Strengths for Different Cement Grades in the Vicinity of Sodium Chloride Using ANN

Abstract

The compressive strength values of cement mortar usually affect by sodium chloride quantities, chemical admixtures and cement grades so that an artificial neural network model was performed to predict the compressive strength of mortar value for different cement grades and sodium chloride (NaCl) percent. A three layer feed forward artificial neural network (ANN) model having four input neurons such as cement grades, various water to cement ratio, sodium chloride solution content, one output neuron and five hidden neurons was developed to predict of mortar each compressive strength.To this aim, twelve different mixes under three sodium chloride solution of 0%, 5% and 10% submerged after 60 days has been adopted to measure compressive strength.Artificial neural network (ANN) analysis indicated that by using ANN as non-linear statistical data modeling tool, a strong correlation between the sodium chloride percent of cement mortar and compressive strength can be established. Moreover modeling tools has great influence on the different cement grade such as 42.5 and 32.5 MPa.