Advancing Concrete Mix Proportion through Hybrid Intelligence: A Multi-Objective Optimization Approach.

Abstract

Concrete mixture design has been a key focus in concrete research. This study presents a new method for concrete mixture design by combining artificial neural networks (ANN), genetic algorithms (GA), and Scipy libraries for hybrid intelligent modeling. This method enables the prediction of concrete mechanical properties and the optimization of mix proportions with single or multi-objective goals. The GA is used to optimize the structure and weight parameters of ANN to improve prediction accuracy and generalization ability (R2 > 0.95, RMSE and MAE < 10). Then, the Scipy library combined with GA-ANN is used for the multi-objective optimization of concrete mix proportions to balance the compressive strength and costs of concrete. Moreover, an AI-based concrete mix proportion design system is developed, utilizing a user-friendly GUI to meet specific strength requirements and adapt to practical needs. This system enhances optimization design capabilities and sets the stage for future advancements. Overall, this study focuses on optimizing concrete mixture design using hybrid intelligent modeling and multi-objective optimization, which contributes to providing a novel and practical solution for improving the efficiency and accuracy of concrete mixture design in the construction industry.