Open Access

ARTICLE

A Machine-Learning Approach for the Prediction of Fly-Ash Concrete Strength

by Shanqing Shao¹, Aimin Gong¹, Ran Wang¹, Xiaoshuang Chen¹, Jing Xu², Fulai Wang^1,*, Feipeng Liu^2,3,*

1 College of Water Conservancy, Yunnan Agricultural University, Kunming, 650201, China
2 Institute of International Rivers and Eco-Security, Yunnan University, Kunming, 650500, China
3 Southwest Survey and Planning Institute of National Forestry and Grassland Administration, Kunming, 650031, China

* Corresponding Authors: Fulai Wang. Email: ; Feipeng Liu. Email:

(This article belongs to the Special Issue: Advances in Solid Waste Processing and Recycling Technologies for Civil Engineering Materials)

Fluid Dynamics & Materials Processing 2023, 19(12), 3007-3019. https://doi.org/10.32604/fdmp.2023.029545

Received 25 February 2023; Accepted 18 April 2023; Issue published 27 October 2023

Abstract

The composite exciter and the CaO to Na₂SO₄ dosing ratios are known to have a strong impact on the mechanical strength of fly-ash concrete. In the present study a hybrid approach relying on experiments and a machine-learning technique has been used to tackle this problem. The tests have shown that the optimal admixture of CaO and Na₂SO₄ alone is 8%. The best 3D mechanical strength of fly-ash concrete is achieved at 8% of the compound activator; If the 28-day mechanical strength is considered, then, the best performances are obtained at 4% of the compound activator. Moreover, the 3D mechanical strength of fly-ash concrete is better when the dosing ratio of CaO to Na₂SO₄ in the compound activator is 1:1; the maximum strength of fly-ash concrete at 28-day can be achieved for a 1:1 ratio of CaO to Na₂SO₄ by considering a 4% compound activator. In this case, the compressive and flexural strengths are 260 MPa and 53.6 MPa, respectively; the mechanical strength of fly-ash concrete at 28-day can be improved by a 4:1 ratio of CaO to Na₂SO₄ by considering 8% and 12% compound excitants. It is shown that the predictions based on the aforementioned machine-learning approach are accurate and reliable.

---

Keywords

---