Prediction of concrete compressive strength based on machine learning

Yuanke Zhao; Yong Ge

doi:10.1117/12.3046761

27 September 2024 Prediction of concrete compressive strength based on machine learning

Yuanke Zhao, Yong Ge

Proceedings Volume 13261, Tenth International Conference on Mechanical Engineering, Materials, and Automation Technology (MMEAT 2024); 132611G (2024) https://doi.org/10.1117/12.3046761
Event: 10th International Conference on Mechanical Engineering, Materials, and Automation Technology (MMEAT 2024), 2024, Wuhan, China

Abstract

This study employs four machine learning methods, encompassing linear, nonlinear, and integrated models, to forecast the 28-day compressive strength of concrete. The input variables consist of seven concrete constituents: cement, water, fly ash, mineral powder, coarse aggregate, fine aggregate, and water reducer. A dataset comprising 3752 experimental observations on concrete strength is utilized for training and validating the predictive models. By assessing four performance metrics, it is determined that the nonlinear model generally outperforms the linear model, with the integrated learning random forest model exhibiting the highest efficacy. The Dung beetle optimizer is applied to enhance the random forest model, resulting in the development of a robust machine learning prediction model capable of providing more precise estimations of the 28-day compressive strength of concrete.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yuanke Zhao and Yong Ge "Prediction of concrete compressive strength based on machine learning", Proc. SPIE 13261, Tenth International Conference on Mechanical Engineering, Materials, and Automation Technology (MMEAT 2024), 132611G (27 September 2024); https://doi.org/10.1117/12.3046761

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available