ENHANCING CONCRETE MANUFACTURING: LEVERAGING A HYBRID SWARM-INTELLIGENT GRAVITATIONAL SEARCH OPTIMIZED RANDOM FOREST MODEL INCORPORATING WASTE GLASS FOR IMPROVED STRENGTH ASSESSMENT

Abstract

Concrete is a fundamental construction material, widely used due to its durability and versatility. However, enhancing its mechanical properties, such as strength, while simultaneously addressing sustainability concerns remains a significant challenge. This study presents a novel approach to optimize concrete mix designs by incorporating waste glass particles, using a Hybrid Swarm-Intelligent Gravitational Search Optimized Random Forest (SIGSORF) model. The primary objective is to improve the strength assessment of concrete while reducing environmental impact through waste glass utilization. The first step in the study is to examine the physical and chemical characteristics of waste glass to see if it may somewhat substitute traditional pebbles in the manufacturing of mortar. Then clean the data and preprocess for use in training and validating the SIGSORF model. The SIGSORF model is designed to intelligently select proportions of waste glass and other concrete components to maximize compressive strength and flexural strength while minimizing environmental impact. The experimental results are then compared with predictions made by the SIGSORF model, demonstrating its effectiveness in optimizing concrete mix designs for improved strength. Ultimately, this study promotes the utilization of waste materials in construction, fostering a more environmentally responsible and economically viable concrete production approach.

Keywords

• concrete manufacturing
• swarm-intelligent gravitational search optimized random forest (sigsorf)
• waste glass
• environmental impact
• sustainability