Dynamic Adaptive Weight Sparrow Search Algorithm for High-Strength Self-Consolidating Concrete Mix Design

Concrete is the most used human-made material that has been utilized in the construction industry. Mix design optimization is difficult due to properties of concrete based on chemical and physical properties of the components as well as their relative proportions. Since number of parameters are comprised in a concrete mix design, identifying an optimal mixing design has always been a challenge for concrete engineers. Hence, this research proposes the Dynamic Adaptive Weighting Sparrow Search Algorithm (DAWSSA) approach for the High Strength Self-Consolidating Concrete mixt design (HSCC). This proposed methodology utilizes the data normalization and data partitioning techniques to normalize the data for enhancing the performance. Then, Best-Worst Method (BWM) approach is accomplished for pairwise comparisons of the quality criteria. The effectiveness of the proposed DAWSSA is estimated by utilizing various error metrices like R-Square (R2), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) of values about 0.86, 1.57 and 2.29 respectively when compared to the previous works such as Multi-objective Salp Swarm Algorithm (MOSSA) and SSA-Extreme Gradient Boosting (SSA-XGB).