Application of Probabilistic Neural Networks for Prediction of Concrete Strength

Abstract

The compressive strength of concrete is a commonly used criterion in producing concrete. However, the tests on the compressive strength are complicated and time consuming. More importantly, it is too late to make improvements even if the test result does not satisfy the required strength, since the test is usually performed on the 28th day after the placement of concrete at the construction site. Therefore, accurate and realistic strength estimation before the placement of concrete is very important. This study presents the probabilistic technique for predicting the compressive strength of concrete on the basis of concrete mix proportions. The estimation of the strength is performed using the probabilistic neural network which is an effective tool for the pattern classification problem and provides a probabilistic viewpoint as well as a deterministic classification result. Application of probabilistic neural networks in the compressive strength estimation of concrete is performed using the mix proportion data and test results of two concrete companies. It has been found that the present methods are very efficient and reasonable in predicting the compressive strength of concrete probabilistically.