Dataset Information

Machine learning enables prompt prediction of hydration kinetics of multicomponent cementitious systems.

ABSTRACT: Carbonaceous (e.g., limestone) and aluminosilicate (e.g., calcined clay) mineral additives are routinely used to partially replace ordinary portland cement in concrete to alleviate its energy impact and carbon footprint. These mineral additives-depending on their physicochemical characteristics-alter the hydration behavior of cement; which, in turn, affects the evolution of microstructure of concrete, as well as the development of its properties (e.g., compressive strength). Numerical, reaction-kinetics models-e.g., phase boundary nucleation-and-growth models; which are based partly on theoretically-derived kinetic mechanisms, and partly on assumptions-are unable to produce a priori prediction of hydration kinetics of cement; especially in multicomponent systems, wherein chemical interactions among cement, water, and mineral additives occur concurrently. This paper introduces a machine learning-based methodology to enable prompt and high-fidelity prediction of time-dependent hydration kinetics of cement, both in plain and multicomponent (e.g., binary; and ternary) systems, using the system's physicochemical characteristics as inputs. Based on a database comprising hydration kinetics profiles of 235 unique systems-encompassing 7 synthetic cements and three mineral additives with disparate physicochemical attributes-a random forests (RF) model was rigorously trained to establish the underlying composition-reactivity correlations. This training was subsequently leveraged by the RF model: to predict time-dependent hydration kinetics of cement in new, multicomponent systems; and to formulate optimal mixture designs that satisfy user-imposed kinetics criteria.

SUBMITTER: Lapeyre J

PROVIDER: S-EPMC7886887 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning enables prompt prediction of hydration kinetics of multicomponent cementitious systems.

Lapeyre Jonathan J Han Taihao T Wiles Brooke B Ma Hongyan H Huang Jie J Sant Gaurav G Kumar Aditya A

Scientific reports 20210216 1

Carbonaceous (e.g., limestone) and aluminosilicate (e.g., calcined clay) mineral additives are routinely used to partially replace ordinary portland cement in concrete to alleviate its energy impact and carbon footprint. These mineral additives-depending on their physicochemical characteristics-alter the hydration behavior of cement; which, in turn, affects the evolution of microstructure of concrete, as well as the development of its properties (e.g., compressive strength). Numerical, reaction- ...[more]

PMID: 33594212

Similar Datasets

Project description:The addition of expansive agents could overcome the main disadvantages of raw concrete including high brittleness and low tensile strength. Few studies have investigated the early hydration kinetics of expansive cementitious binders, though the findings from the early hydration kinetics are helpful for understanding their technical performances. In this study, mixtures of 3CaO•3Al2O3•CaSO4 and CaSO4 (i.e., ZY-type™ expansive agent) with different proportions of mineral admixtures (e.g., fly ash and slag) were added into cement pastes to investigate the early hydration kinetics mechanism of expansive cementitious binders. Early hydration heat evolution rate and cumulative hydration heat were measured by isothermal calorimeter. Kinetic parameters were estimated based on the Krstulovic-Dabic model and Knudsen equations. Mechanical performances of expansive cementitious binders were tested in order to evaluate if they met the basic requirements of shrinkage-compensating materials in technical use. The early hydration heat released from cementitious binders containing ZY-type™ expansive agent was much greater than that released by pure cement, supporting the idea that addition of the expansive agent would improve the reaction of cement. The early hydration kinetic rates were decreased due to the reactions of the mineral admixture (e.g., fly ash or slag) and the ZY-type™ expansive agent in the cement system. The hydration reaction of cementitious binders containing ZY-type™ expansive agent obeyed the Krstulovic-Dabic model well. Three processes are involved in the hydration reaction of cementitious binders containing ZY-type™ expansive agent. These are nucleation and crystal growth (NG), interactions at phase boundaries (I), and diffusion (D). The 14-day expansion rates of cementitious binders containing ZY-type™ expansive agent are in the range of 2.0 × 10-4 to 3.5 × 10-4, which could meet the basic requirements of anti-cracking performances in technical use according to Chinese industry standard JGJ/T 178-2009. This study could provide an insight into understanding the effects of expansive agents on the hydration and mechanical performances of cementitious binders.

Dataset Information

Machine learning enables prompt prediction of hydration kinetics of multicomponent cementitious systems.

Publications

Machine learning enables prompt prediction of hydration kinetics of multicomponent cementitious systems.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets