Prediction of concrete strength using multilayer perceptron neural network-based utilizing sustainable waste materials

Abstract

This research reports a laboratory study on the optimal levels of vitrified Polish waste (VPW) and ground granulated blast furnace slag (GGBS) as partial substitutes for cement to examine the strength properties of concrete. Ordinary Portland cement was partially substituted with 5%, 10%, 15%, and 20% mixtures of vitrified polish waste and ground granulated blast-furnace slag (GGBFS). The water-to-cementitious materials ratio was consistently set at 0.38 for all mixtures. The concrete’s strength qualities were assessed using compressive testing, strength testing, splitting tensile strength testing, and flexural strength testing. The compression strength test was executed at 7 and 28 days of curing, while the split tensile strength and flexural strength tests were conducted on M30, M35, and M40 grade concrete. The mix proportions for M30, M35, and M40 are 1:1.615:3.427, 1:1.50:3.25, and 1:1.40:3.15, respectively. The test findings demonstrated that the compressive strength, split tensile strength, and flexural strength of concrete mixtures incorporating GGBFS and VPW enhance with the increasing proportions of GGBS and VPW. A multilayer perceptron (MLP) neural network was used to evaluate concrete strength, and the predicted results were very similar to the actual measurements. The findings demonstrate that an optimal level of 15% GGBFS and VPW relative to the total binder content yields no further enhancement in compressive strength, split tensile strength, or flexural strength with additional GGBFS and VPW.