Estimating Distribution of Concrete Strength Using Quantile Regression Neural Networks

Abstract

This paper is aimed at demonstrating the possibilities of adaptingQuantile Regression Neural Network (QRNN) to estimate the distribution ofcompressive strength of high performance concrete (HPC). The databasecontaining 1030 compressive strength data were used to evaluate QRNN. Each dataincludes the amounts of cement, blast furnace slag, fly ash, water,superplasticizer, coarse aggregate, fine aggregate (in kilograms per cubicmeter), the age, and the compressive strength. This study led to the followingconclusions: (1) The Quantile Regression Neural Networks can buildaccurate quantile models and estimate the distribution of compressive strengthof HPC. (2) The various distributions of prediction of compressive strength of HPCshow that the variance of the error is inconstant across observations, whichimply that the prediction is heteroscedastic. (3) The logarithmic normaldistribution may be more appropriate than normal distribution to fit thedistribution of compressive strength of HPC. Since engineers should not assumethat the variance of the error of prediction of compressive strength isconstant, the ability of estimating the distribution of compressive strength ofHPC is an important advantage of QRNN.