Machine learning in concrete science:applications,challenges,and best practices

Concrete,as the most widely used construction material,is inextricably connected with human development.Despite conceptual and methodological progress in concrete science,concrete formulation for target properties remains a challenging task due to the ever-increasing complexity of cementitious systems.With the ability to tackle complex tasks autonomously,machine learning(ML)has demonstrated its transformative potential in concrete research.Given the rapid adoption of ML for concrete mixture design,there is a need to understand methodological limitations and formulate best practices in this emerging computational field.Here,we review the areas in which ML has positively impacted concrete science,followed by a comprehensive discussion of the implementation,application,and interpretation of ML algorithms.We conclude by outlining future directions for the concrete community to fully exploit the capabilities of ML models.

Adsorption properties of polycarboxylate ether-based superplasticizer on cement particles and their resultant dispersion

The cement dispersion performance of a polycarboxylate(PCE)-based superplasticizer is highly related to their adsorption behaviors as a function of time.This study evaluated effects of PCEs on rheological properties of cementitious materials.First,characteristics of PCEs were characterized via permeation chromatography(GPC)and Fourier-transform infrared spectrometry(FT-IR).The adsorption behavior of single and blended PCEs on cementitious composites was identified using total organic carbon analyzer(TOC).Based on the measurement of PCE adsorption,the changes of rheological properties of cementitious materials as well as the number of dispersed cement particles were characterized using a rheometer and laser spectroscopy,respectively.The experimental results support the systematic mechanism of PCE adsorption,cement dispersion,and the decrease in viscosity of cementitious materials.