Predicting Compressive and Tensile Strength of Concrete Containing Recycled Aggregates using Modified Ann
Abstract
Artificial Neural Network (ANN) are used for the prediction of Mechanical properties of Recycled aggregates in Concrete. In General ANN has 3 layers which included Input, output and hidden layers, In this the input layer consists of Quantity of Cement, Fine aggregate, Coarse aggregate, Water content, Super Plasticizer, Percentage of Recycled aggregate and Curing period. The output layer consists of Compressive and Tensile strength of concrete blended with recycled aggregates. While developing the ANN model 33 samples are used as training and testing data sets. While training ANN model two Assessment were carried out, in this determination of effective number of neurons in hidden layer for predicting the network structure is carried out in first assessment and In second assessment, Evaluation of accuracy of prediction network is done under different load conditions. In general ANN learns from training and gives extremely good Accurate results. ANN model is used to escalate the experimental data to predict the compressive and tensile strength properties of Concrete partially added with recycled aggregates. High accurate Outcomes are observed with comparing the Experimental results to the results obtained after training of Neural Networks.