Title:
Optimization of Sulfate Balance in LC3 by Machine Learning
Author(s):
Washburn
Publication:
Web Session
Volume:
Issue:
Appears on pages(s):
Keywords:
DOI:
Date:
11/3/2024
Abstract:
This study assesses the influence and quantifies the relative significance of compositional predictors on the sulfate balance and cumulative heat evolved by 24 h for LC3 through a stepwise regression model based on calorimetry and X-ray diffraction data. Sulfate balance was defined as the time difference between the sulfate depletion point and the time of maximum of alite peak obtained from a time derivative of data obtained through isothermal calorimetry. A methodology based on Kernel smoothing was used to precisely identify these events and allowed the optimization of sulfate to regulate ettringite formation and C3A dissolution. The results suggest that the metakaolin fraction influences the sulfate balance of LC3 both directly and through its interactions with other constituent materials.