Prediction of Static Modulus and Compressive Strength of Concrete from Dynamic Modulus Associated with Wave Velocity and Resonance Frequency Using Machine Learning Techniques

摘要

The static elastic modulus ( ) and compressive strength ( ) are critical properties of concrete. When determining and , concrete cores are collected and subjected to destructive tests. However, destructive tests require certain test permissions and large sample sizes. Hence, it is preferable to predict using the dynamic elastic modulus ( ), through nondestructive evaluations. A resonance frequency test performed according to ASTM C215-14 and a pressure wave (P-wave) measurement conducted according to ASTM C597M-16 are typically used to determine . Recently, developments in transducers have enabled the measurement of a shear wave (S-wave) velocities in concrete. Although various equations have been proposed for estimating and from , their results deviate from experimental values. Thus, it is necessary to obtain a reliable value for accurately predicting and . In this study, values were experimentally obtained from P-wave and S-wave velocities in the longitudinal and transverse modes; and values were predicted using these values through four machine learning (ML) methods: support vector machine, artificial neural networks, ensembles, and linear regression. Using ML, the prediction accuracy of and was improved by 2.5–5% and 7–9%, respectively, compared with the accuracy obtained using classical or normal-regression equations. By combining ML methods, the accuracy of the predicted and was improved by 0.5% and 1.5%, respectively, compared with the optimal single variable results.