Model for mix design of brick aggregate concrete based on neural network modelling

Abstract

This article proposes an optimized quantitative model for proportioning concrete mixtures based on cement content, water-cement ratio and percentage of recycled aggregate replacement according to preffered recycled brick aggregate concrete (RBAC) compressive strength. A database compiled from 147 experimental tests of RBAC compressive strength was processed by neural network modelling to achieve a reliable prediction, which was investigated by three-fold validation. The performance of the representative neural network model was verified by parametric analysis with a brief review of the influence of each RBAC component. The focus of the main results is enhancement of the neural network modelling results and consequently new interpretation and conceptualisation for theoretical advancement and practical applied research on RBAC concrete content.