Strength and durability predictions of ternary blended nano-engineered high-performance concrete: Application of hybrid machine learning techniques with bio-inspired optimization

Higher-strength, longer-lived, and environmentally friendly high-performance concrete (HPC) necessitates advanced formulation of materials and predictive modeling techniques. The traditional designs of high-performance concrete often fail to optimize the mix parameters suitably, mainly from the point of sustainability view, and lack the capacity to model complex nonlinear relationships among material properties and performance metrics. The current paper introduces the integrated framework of nano-engineered materials that comprises nano-silica, graphene oxide (GO), and carbon nanotubes (CNTs) along with advanced artificial intelligence (AI) methods in the predictive modeling and optimization of high-performance concrete (HPC). The Machine Learning (ML) models consisting of Random Forest (RF), Gradient Boosting Machines (GBM), and Deep Neural Networks (DNNs) were implemented to predict compressive and tensile strengths , elastic modulus , and durability metrics such as chloride penetration and sulfate resistance sets. Dimensionality reduction techniques , such as Principal Component Analysis (PCA) and Partial Least Squares (PLS), improved model interpretability and performance sets. Optimization of mix designs was carried out using bio-inspired algorithms, namely Genetic Algorithms (GA) and Particle Swarm Optimization (PSO), to balance mechanical performance, material efficiency, and environmental sustainability. The results suggest strength improvement up to 15% and durability up to 30% while reducing cement content and associated carbon emissions. This is the framework, which exploits artificial intelligence techniques in predictive modeling and optimization to achieve scalable and sustainable next-generation high-performance concrete designs. It is at the intersection of theoretical potential and practical application that the work is advancing the role of artificial intelligence in construction material science toward contributing to sustainable infrastructure development process.