Utilizing Machine Learning Approaches for Assessing the Unconfined Compressive Strength of a Crushed Stone-Cement-Pozzolan Mixture
Year: 2024
Type: conference-paper
Abstract: This research examines the use of artificial pozzolans, industrial waste products, as a sustainable alternative to traditional cement in soil improvement works aiming to reduce environmen-tal damage caused by industrial production. Various regression and machine learning techniques, including Support Vector Re-gression, Random Forest, Extreme Gradient Boosting, Ridge, LASSO, and Elastic Net Regression, are applied to predict uncon-fined compressive strength (UCS) with various compositions of cementitious crushed stone soil samples with cylindrical shapes. Cylindrical cementitious crushed stone soil samples have different contents including different amounts of water, bind-er, and pozzo-lan additives like fly ash, silica fume, and granulated blast furnace slag, type of pozzolan, curing time, and number of layers of cylin-drical samples and blow for each compacted layer. Among the algorithms utilized, XGBoost performs better in estimating UCS with an RMSE of 1.5920, an MSE of 2.5346, and an MAE of 1.2858. The study underscores the environmental benefits of com-bining experimental approaches with advanced Artificial Intelli-gence methods, offering a sustainable solution that recycles waste materials while enhancing performance.
Authors: URAY, Esra, OFLAZ, Zarina
Language: English
Subfield: Civil and Structural Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7134995338