Application of Artificial Intelligence to Predict Compressive Strength of Concrete from Mix Design Parameters: A Structural Engineering Application

摘要

There are no fixed formulations for mixing concrete constituents to obtain the compressive strength. Concrete mixing is predominantly a qualitative knowledge-based approach subjected to variations. Reliance on such an approach compromises the precision and accuracy of concrete properties, and hence necessitates the development of a reliable mixing formulation. Statistical modeling techniques like Multiple Linear Regression Analysis (MLRA) have been used in the past. However, these methods have failed to accurately predict the compressive strength. This is due to the highly nonlinear relationship between the concrete proportions and its properties. In this paper a Neural Network model for predicting the compressive strength of concrete for different mix-design parameters is developed. A neural network model based on five hidden layers was trained using the results of a series of previously conducted experiments. Each experiment consisted of five parameters and a corresponding compressive strength obtained from 28-days cylinders tests. It was observed that the neural network model performed with satisfactory results in predicting the 28-day compressive strength of concrete.