In recent decades, artificial neural networks are known as intelligent methods for modeling of beh..
全部>>
In recent decades, artificial neural networks are known as intelligent methods for modeling of behavior of physical phenomena. In this paper, implementation of an artificial neural network has been developed for prediction of compressive strength of concrete. A MISO (Multi Input Single Output) adaptive system has been introduced which can model the proposed phenomenon. The data has been collected by experimenting on concrete samples and then the neural network has been trained using these data. From among 432 specimens, 300 data sample has been used for train, 66 data sample for validation and 66 data sample for the final test of the network. The 3-day strength parameter of concrete in the introduced structure also has been used as an important index for predicting the 28-day strength of the concrete. The simulations in this paper are based on real data obtained from concrete samples which indicate the validity of the proposed tool.
还原>>
