New insight into the prediction of strength properties of cementitious mortar containing nano- and micro-silica based on porosity using hybrid artificial intelligence techniques

摘要

Nowadays, the accurate prediction of strength properties of cementitious materialscontaining nano- and micro-silica (NS–MS) remains an open question because ofthe highly nonlinear function of its constituents on the porosity. In the presentstudy, a combined framework is developed by integrating ant colony optimization(ACO), particle swarm optimization (PSO), and biogeography-based optimization(BBO) with the artificial neural network (ANN) to predict compressive and flexuralstrengths of cement mortar in two different forms of ignoring (ANN_Ⅱ) andconsidering (ANN_Ⅲ) the porosity as an input parameter. This procedure is accomplishedconsidering the porosity effect on the strengths and implementing anexperimental program containing 32 mixes (960 specimens) with different NS–MScontents at various ages. Macro- and micro-structural analyses showed that NS–MS caused more decreased pore structure, and thus this situation increasesstrength properties compared to their separate use. Also, MBBO-MOANNIIIresults indicated an improvement in convergence speed and model accuracy comparedto other models. This improvement is because of considering the porosity.