Molecular Engineering of Superplasticizers for Metakaolin-Portland Cement Blends with Hierarchical Machine Learning

Abstract

Blending metakaolin (MK), a calcined clay, into portland cement (PC) improves resulting concrete material properties, ranging from strength to durability, as well as reducing embodied CO2 and energy. However, superplasticizers developed for PC can be inefficient or ineffective for improving the dispersion of PC-MK blends. Here, a novel machine algorithm is applied to tailor a superplasticizer to address poor flowability characteristic of 15/85 blends of MK-PC. A hierarchical machine learning (HML) system is trained on a library of seven superplasticizers using a middle layer, which represents underlying physical interactions that determine system responses, based on polymer contributions to physicochemical forces in both the pore solution and particle surface. Following reparameterization of the response surface by polymer composition, the trained algorithm predicted that a novel styrene sulfonate-methacrylic acid-poly(ethylene glycol) methacrylate copolymer would maximize slump of the MK-PC paste. Synthesis of the algorithm prediction resulted in a water-soluble polymer with an extremely high intrinsic viscosity that nevertheless increased the slump flow of the MK-PC paste but did not plasticize pure PC paste. The results from this study demonstrate the importance of HML as a design tool for the molecular engineering of complex material systems.