Application of Ann for Prediction of Chloride Penetration Resistance and Concrete Compressive Strength

Abstract

The purpose of this paper is to present Artificial Neural Network (ANN) models to predict compressive strength and chloride penetration levels of self-consolidating concrete (SCC) mixes. The ANN models used to predict chloride penetration resistance were developed using input variables including the ratio of water to binder (w/b), and the contents of coarse aggregate, fine aggregate, fly ash, and silica fume. For prediction of concrete compressive strength, the fundamental ANN parameters considered include w/b ratio, the amount of High Range Water Reducing (HRWR) admixture, and the contents of coarse aggregates, fine aggregates, silica fume, and fly ash. Compressive strength data from published literature was used to train the developed ANN and successful models were validated using compressive strength data tested by the investigators. The trained ANN was able to predict compressive strength and chloride iron penetration levels successfully.