PREDICTION OF COMPRESSIVE & FLEXURAL STRENGTHS OF MICRO AL2O3BLENDED WITH CONCRETE USING ANN

Artificial Neural Networks (ANN) are used to predict the strength properties of Micro Al2O3 blended in concrete. ANN has 3 layers which included output, input and hidden layers. The input layer consists of quantity of cement, fine aggregate, coarse aggregate, water content, percentage of Micro Al2O3, curing period. The output layer consists of compressive strength, flexural strength of Micro Al2O3 blended with concrete. Two assessments were carried out, determination of effective number of neurons in hidden layer for predicting the network structure is carried out in first assessment. In second assessment, evaluation of accuracy of prediction network is done under different load conditions.