High performance concrete (HPC) is developed gradually over the last 15 years with respect to production of concrete with higher and higher strength. The objective of the present study is to investigate the effect of mineral admixtures and by-products towards the performance of HPC. HPC with mineral admixture of silica fume at the replacement levels of 0%, 5%, 10%, 15% & 20% were studied at the age of 28 days and industrial by-products of bottom ash and steel slag aggregate at the replacement level of 10%, 20%, 30%, 40% & 50% were studied at the age of 28 days. Finally strength has enhanced with the mix of silica fume can replaced by cement with 5% and bottom ash and steel slag can replaced by fine and coarse aggregate with 10% can be achieved higher strength when compared with other percentage of mixes. The combination mixes can be classified as binary and ternary mixes. Binary mixes involved combinations of silica fume and bottom ash (SF+BA), silica fume and steel slag aggregate (SF+SSA), bottom ash and steel slag aggregate (BA+SSA) and Ternary mixes involved combination of three materials such as silica fume, bottom ash and steel slag aggregate (SF+BA+SSA) in High performance concrete. The use of industrial by-products in concrete is gaining popularity due to various advantages. An Artificial Neural Network technique for the prediction of compressive strength of concrete was performed for the concrete data obtained from laboratory experimental work done in this study. The variables used in the prediction models were the mix proportioning elements. The multiple nonlinear regression models yielded excellent correlation coefficients for the prediction of compressive strength at different curing ages as well as the other variations which includes use of silica fume as a partial replacement of cement, bottom ash and steel slag aggregate as a partial replacement of fine aggregate and coarse aggregate for the production of high performance concrete. Non destructive techniques are the one that can be used to predict the strength without damaging the structure. In the present study, the compressive strength of high performance concrete has been predicted using Artificial Neural Network (ANN). The predicted strength was compared with the experimentally obtained actual compressive strength of concrete and equations were developed for different models. Finally statistical analysis of RBH, UPV, and compressive strength relationship represents a good correlation between actual compressive strength and predicted compressive strength.
