Abstract
Sustainable and renewable energy has gained global prominence because of the alarming depletion of natural resources and rise in greenhouse gas (GHG) emissions. With the increasing utilisation of supplementary cementitious materials (SCMs) in concrete, it has become necessary to accurately predict the properties of concrete. In the construction field, the development of artificial intelligence-based prediction models has received remarkable attention. As a result, developing a model to predict the properties of SCC with regards to sustainability concerns is essential to save time, cost and energy. However, models for the prediction of fresh properties of concrete is scarce. To carry out this assessment in an automated manner, this research work proposes a novel jellyfish optimiser-based modified sigmoid-activated artificial neural network (JO-mSigmoid-ANN) model for the prediction through the regression analysis of the flow and mechanical properties of the 60 and 80 MPa SCC, in which 0.5% and 0.75% of hybrid steel fibres (hooked steel and micro steel) were added. The ANN results were compared with the experimental results obtained in this research as well as the results available in the existing literature. The proposed model effectively predicts the flow and mechanical properties of SCC blended with hybrid steel fibres in comparison with the experimental data set with R2 values of 0.9679 and 0.9931. Similarly, the R2 value obtained for four existing data sets are 0.9868, 0.9164, 0.9338 and 0.74619, respectively.