Application of Neural Networks for Estimation of Concrete Strength

Abstract

The uniaxial compressive strength of concrete is the most widely used criterion in producing concrete. Although testing of the uniaxial compressive strength of concrete specimens is done routinely, it is performed on the 28th day after concrete placement. At this point, it is too late to make improvements if the test result does not satisfy the required strength. Therefore, the strength estimation before the placement of concrete is highly desirable. This study presents the first effort in applying neural network-based system identification techniques to predict the compressive strength of concrete based on concrete mix proportions. Back-propagation neural networks were developed, trained, and tested using actual data sets of concrete mix proportions provided by two ready-mixed concrete companies. The compressive strengths estimated by the neural networks were verified by laboratory testing results. This study demonstrated that the neural network techniques are effective in estimating the compressive strength of concrete based on the mix proportions. Application of these techniques will contribute significantly to the concrete quality assurance.