Importance Of Compressive Strength Of Concrete

716 Words2 Pages

2.1 Introduction In a traditional way, a concrete mix is designed based on the code requirements and recommendations which uses the empirical values obtained from previous experiences. Compressive strength of concrete is determined by conducting standard uniaxial compression test on standard cylindrical sample specimens of ages 7 & 28 days, following the standard procedure and test values are reported in accordance with ASTM and ACI standards . If the strength value obtained from the test is less than the required strength after 28 days from date of placing of concrete, the entire process of concrete mix design has to be repeated until the required strength value is achieved, which is time consuming and costly. Numerous test samples with different mix ingredient proportions have to be created to achieve the required strength and is an iterative process. So, every mix designer wants a tool or methodology to predict the compressive strength of concrete required at the time of design, before placing the concrete. As we know that, the relationship between Compressive Strength and its mix ingredients is complex and highly non linear. The data scientists, researchers and engineers are trying to develop several approaches using regression function for the accurate prediction of compressive strength of concrete. Recently, data mining tools are becoming more popular and reliable methods to predict the compressive strength of concrete than others. The section below reviews and discusses some of the popular, relevant and effective data mining tools developed so far, to predict the 28 days compressive strength of concrete. 2.2 Multiple Regression Model The first popular regression equation used in the prediction of compressive streng... ... middle of paper ... ...per plasticizer, fine aggregates and coarse aggregates. The method of least squares is used to estimate the regression coefficients in the above model. A lot of researchers have used multiple regression models to improve the prediction accuracy of concrete strength. It is still a popular model because the model that once fitted can predict the required value more quickly than other modeling techniques and can be easily implemented in computer applications. By performing correlation analysis, it also provides insight knowledge about the key factors influencing the 28 days compressive strength of concrete. Although it gives better performance where there are few independent variables, it performs poor modeling when the number of independent variables is more and the relationship between independent variables and dependent variable becomes complex and highly nonlinear.

Open Document