Work

Research Progress on Machine Learning Prediction of Compressive Strength of Nano-Modified Concrete

Year: 2025

Type: article

Abstract: Nano-modified concrete has attracted wide attention due to its improved mechanical properties. Among them, compressive strength is the most critical indicator. However, testing nano-concrete is costly and complex because it requires control over many factors, such as nanoparticle content and dispersion. Machine learning offers a data-driven way to predict compressive strength more efficiently. It reduces trial-and-error efforts and supports mix design optimization. Currently, machine learning is more adept at handling complicated datasets than experimental and traditional statistical models. In this article, the development of machine learning research in predicting the strength of concrete enhanced by nanoparticles is reviewed. First, we systematically outline a three-phase ML framework encompassing data curation, model development, and validation protocols; next, popular algorithms and their uses in predicting the strength of nano-modified concrete are evaluated, such as Artificial Neural Networks, K-Nearest Neighbor, Random Forest, etc. Ultimately, the article offers a forward-looking perspective on how future machine learning advancements can foster and accelerate the development of nano-modified concrete.

Source: Applied Sciences

DOI: 10.3390/app15094733

Authors: Ruyan Fan, Ankang Tian, Yikun Li, Yue Gu, Zhenhua Wei

Institutions: Hohai University, Southern University of Science and Technology

Language: English

Topic: Innovative concrete reinforcement materials

Subfield: Civil and Structural Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,896