Prediction of Compressive Strength of Concrete by Data-Driven Models

چکیده مقاله

The aim of this study is prediction of 28-day compressive strength of concrete by data-driven models. Hence, by considering concrete constituents as input variables, two data-driven models namely Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models are constructed for the purpose of predicting the 28-days compressive strength of different concrete mix designs. Comparing the two models illustrates that MLR model is not a suitable model of predicting the compressive strength; however, ANN can be used to efficiently predict the compressive strength of concrete.