LAUSR

Engineered Geopolymer Composites has proved to be an excellent eco-friendly strain hardening composite materials, as well as, it exhibits high tensile strain capacity. An intelligent computing tool based predictive model to anticipate the compressive strength of ductile geopolymer composites would help various researchers to analyse the material type and its contents; the dosage of fibers; producing tailor-made materials; less time consumption; cost-saving etc., which could suit for various infrastructural applications. This paper attempts to develop a suitable ANN based machine learning model in predicting the compressive strength of strain hardening geopolymer composites with greater accuracy. A simple ANN network with a various number of hidden neurons have been trained, tested and validated. The results revealed that with seventeen inputs and one output parameters respectively for mix design & compressive strength and thirteen hidden neurons in its layer have provided the notable prediction with R2 as 96% with the RMSE of 2.64. It is concluded that a simple ANN model would have the perspective of estimating the compressive strength properties of engineered geopolymer composite to an accuracy level of more than 90%. The sensitivity analysis of ANN model with 13-hidden neurons, also confirms the accuracy of prediction of compressive strength.