Applying ANN – PSO algorithm to maximize the compressive strength and split tensile strength of blended self curing concrete on the impact of supplementary cementitious materials

This study was intended to get the optimized Compressive strength and split tensile strength of Blended Self CuringConcrete(BSCC) on the impact of Supplementary Cementitious Materials (SCM’s). The experiments were conducted by varying the quantity of Cement, Flyash, Ground Granulated Blast Furnace Slag (GGBFS), Silica Fume and Slump with fixed quantity of Fine aggregate, Coarse aggregate, S.P and Water. Totally 13 different mix proportions were prepared and tested for Compressive Strength (CS) and Split Tensile Strength (STS). Both strengths were calculated for 7, 14 and 28 days. To optimize the compressive strength and split tensile strength, a feed forward Artificial Neural Network (ANN) model was developed, and Particle Swarm Optimization (PSO) algorithm was used by optimizing the weighing factors of the network in the neural power software. Finally, with a root mean square error of 0.008223, 0.006559, and 0.009743 for CS and 0.008905, 0.006999, and 0.008745 for STS, the model was obtained for 7, 14, and 28 days. The percentage contribution of input parameters is also discussed separately for compressive strength and split tensile strength of 7, 14 and 28 days of curing. Finally, the optimized compressive strength and split tensile strength were found to be 42.3552 N/mm 2 and 4.3113 N/mm 2 respectively for 28 days. .