Optimization of Polymer Concrete Composed of Waste Materials using Hybrid CNN-GA Models for Sustainable Construction

The research focuses on enhancing the environmental sustainability of the construction industry by exploring the use of polymer concrete made from recycled waste materials, such as plastics, glass, and fly ash. This study aims to optimize the mix composition for polymer concrete by employing a hybrid AI model combining Convolutional Neural Networks (CNN) with Genetic Algorithms (GA). These technologies are used to find the optimal material ratios and curing conditions that improve the mechanical properties of the concrete while minimizing environmental impact. This approach seeks to reduce the carbon footprint and energy consumption typically associated with conventional cement-based concrete production by utilizing recycled materials. The study also includes a Life Cycle Sustainability Assessment (LCSA), evaluating the long-term environmental, economic, and social impacts of polymer concrete compared to traditional cement concrete. The results highlight significant reductions in CO2 emissions and cost savings, alongside improvements in the material’s durability. Ultimately, this research demonstrates the potential for polymer concrete to contribute to sustainable development within the construction industry.