AI Method Predicted Chloride Resistance in Concrete
Researchers developed a new model to improve the sustainability of recycled aggregate concrete mixtures.
Updated on Sept. 30, 2026 in Artificial Intelligence
Live Poll
Do you trust artificial intelligence to improve the safety and sustainability of public infrastructure?
Scientists have leveraged artificial neural networks to accurately predict chloride resistance in recycled aggregate concrete. The study aims to minimize reliance on virgin construction materials by optimizing sustainable mixture designs.
Why it matters
By identifying precise material combinations that resist chloride diffusion, the model enables the engineering of durable, eco-friendly concrete. This approach reduces environmental impacts associated with standard concrete production.
The artificial neural network achieved an R2 value of 0.9935, with 98% of predictions falling within 6% of measured results. The optimized mixture utilized a 0.35 water-to-binder ratio and 425 kg/m3 binder content.
The players
Scientific Reports
This is a peer-reviewed, open-access journal that publishes original research from across all areas of the natural sciences and engineering.
The details
Researchers utilized artificial neural networks and response surface methodology to analyze non-linear relationships between concrete components like slag and crumb rubber. The team discovered that higher slag content and longer curing periods consistently enhanced the material's resistance to chloride.
Timeline
The findings were published in the journal Scientific Reports on September 30, 2026.
The Tech Race
This study advances the development of sustainable construction materials by providing a precise computational framework for optimizing recycled concrete performance. It signals a move toward replacing traditional trial-and-error design methods with AI-driven predictive modeling in civil engineering.
This research provides engineers with a more efficient toolset to create durable, sustainable building materials for future infrastructure projects. Improved chloride resistance translates to longer-lasting concrete structures and potentially lower maintenance costs for public works.
The takeaway
Using AI to optimize concrete mixtures allows for the effective integration of recycled waste products without sacrificing structural integrity. This digital approach to material science helps bridge the gap between sustainability goals and real-world construction durability.
Further reading
For more on how machine learning is reshaping engineering, explore our Artificial Intelligence section.
More information
View the complete details of the research in the Scientific Reports journal study.
Source note: This article includes information reported by AZoBuild.
Live Poll
Do you trust artificial intelligence to improve the safety and sustainability of public infrastructure?
