Predicting Compressive Strength of Self- Compacting Concrete Using Bagasse Ash and Rice Husk Ash

Self-compacting concrete (SCC) is one of the types of concrete which will compact by its own weight. Now a days, due to the increase in cost of cement and sand it is very much important to think for other materials as a replacement of concrete materials. This paper presents the comparative performance of the models developed to predict 28 to 180 days compressive strengths using neural network techniques for the data taken from experimentally for SCC mixes containing rice husk ash and baggase ash as partial replacement of cement and quarry dust in fine aggregates with two different topologies. The data used in the models are arranged in the format of nine input parameters and are cement, fine aggregate, coarse aggregate, water content, rice husk ash, baggase ash, quarry dust, water cement ratio and superplasticizer dosage and an output parameter is 28 to 180 days compressive strength of two different topologies 9-8-7 and 9-9-7. The significance of different input parameters is also given for predicting the strengths at various ages using neural network. The performance of the model can be judged by the normalized root-mean-square error, coefficient of correlation and average absolute relative error. The results of the present investigation indicate that artificial neural network have strong potential feasible tool for predicting compressive strength of concrete.