skip to main content

Title: Machine learning enables prompt prediction of hydration kinetics of multicomponent cementitious systems

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; more » and to formulate optimal mixture designs that satisfy user-imposed kinetics criteria.

« less
; ; ; ; ; ;
Award ID(s):
1932690 1661609
Publication Date:
Journal Name:
Scientific Reports
Nature Publishing Group
Sponsoring Org:
National Science Foundation
More Like this
  1. The dissolution kinetics of Portland cement is a critical factor in controlling the hydration reaction and improving the performance of concrete. Tricalcium silicate (C3S), the primary phase in Portland cement, is known to have complex dissolution mechanisms that involve multiple reactions and changes to particle surfaces. As a result, current analytical models are unable to accurately predict the dissolution kinetics of C3S in various solvents when it is undersaturated with respect to the solvent. This paper employs the deep forest (DF) model to predict the dissolution rate of C3S in the undersaturated solvent. The DF model takes into account several variables, including the measurement method (i.e., reactor connected to inductive coupled plasma spectrometer and flow chamber with vertical scanning interferometry), temperature, and physicochemical properties of solvents. Next, the DF model evaluates the influence of each variable on the dissolution rate of C3S, and this information is used to develop a closed-form analytical model that can predict the dissolution rate of C3S. The coefficients and constant of the analytical model are optimized in two scenarios: generic and alkaline solvents. The results show that both the DF and analytical models are able to produce reliable predictions of the dissolution rate of C3Smore »when it is undersaturated and far from equilibrium.« less
  2. Abstract

    Advances in visual perceptual tasks have been mainly driven by the amount, and types, of annotations of large-scale datasets. Researchers have focused on fully-supervised settings to train models using offline epoch-based schemes. Despite the evident advancements, limitations and cost of manually annotated datasets have hindered further development for event perceptual tasks, such as detection and localization of objects and events in videos. The problem is more apparent in zoological applications due to the scarcity of annotations and length of videos-most videos are at most ten minutes long. Inspired by cognitive theories, we present a self-supervised perceptual prediction framework to tackle the problem of temporal event segmentation by building a stable representation of event-related objects. The approach is simple but effective. We rely on LSTM predictions of high-level features computed by a standard deep learning backbone. For spatial segmentation, the stable representation of the object is used by an attention mechanism to filter the input features before the prediction step. The self-learned attention maps effectively localize the object as a side effect of perceptual prediction. We demonstrate our approach on long videos from continuous wildlife video monitoring, spanning multiple days at 25 FPS. We aim to facilitate automated ethogramming bymore »detecting and localizing events without the need for labels. Our approach is trained in an online manner on streaming input and requires only a single pass through the video, with no separate training set. Given the lack of long and realistic (includes real-world challenges) datasets, we introduce a new wildlife video dataset–nest monitoring of the Kagu (a flightless bird from New Caledonia)–to benchmark our approach. Our dataset features a video from 10 days (over 23 million frames) of continuous monitoring of the Kagu in its natural habitat. We annotate every frame with bounding boxes and event labels. Additionally, each frame is annotated with time-of-day and illumination conditions. We will make the dataset, which is the first of its kind, and the code available to the research community. We find that the approach significantly outperforms other self-supervised, traditional (e.g., Optical Flow, Background Subtraction) and NN-based (e.g., PA-DPC, DINO, iBOT), baselines and performs on par with supervised boundary detection approaches (i.e., PC). At a recall rate of 80%, our best performing model detects one false positive activity every 50 min of training. On average, we at least double the performance of self-supervised approaches for spatial segmentation. Additionally, we show that our approach is robust to various environmental conditions (e.g., moving shadows). We also benchmark the framework on other datasets (i.e., Kinetics-GEBD, TAPOS) from different domains to demonstrate its generalizability. The data and code are available on our project page:

    « less
  3. Abstract

    Portland cement emits bright near-infrared photoluminescence that can be excited by light wavelengths ranging from at least 500–1000 nm. The emission has a peak wavelength near 1140 nm and a width of approximately 30 nm. Its source is suggested to be small particles of silicon associated with calcium silicate phases. The luminescence peak wavelength appears independent of the cement hydration state, aggregates, and mechanical strain but increases weakly with increasing temperature. It varies slightly with the type of cement, suggesting a new non-contact method for identifying cement formulations. After a thin opaque coating is applied to a cement or concrete surface, subsequent formation of microcracks exposes the substrate’s near-infrared emission, revealing the fracture locations, pattern, and progression. This damage would escape detection in normal imaging inspections. Near-infrared luminescence imaging may therefore provide a new tool for non-destructive testing of cement-based structures.

  4. The thermoelectric module (TEM) is a device that integrates multiple thermoelectric (TE) elements to realize the mutual conversion of heat and power. Due to the advantages of no moving parts and flexible expansion, the application of conventional Bi2Te3-based TEM in buildings has attracted the attention of researchers. On the other hand, the TE behavior of hardened cement composites was found by combining conductive additives with cement. Therefore, a new study on cement-based TEM for building energy harvesting and emperature control is proposed. To simulate the performance of cement-based TEM, a three-dimensional heat transfer model considering temperature-dependent TEM characteristics was established. The validity of the model is verified by comparing the results with commercial simulation software and experiments. Different from the existing analytical models and commercial software, the customized model has greater scalability, optimization, and control flexibility. Through parametric studies, the model can guide the design of TEM and the development of TE cement.
  5. Renewably-sourced, recyclable materials that can replace or extend the service life of existing technologies are essential to accomplish humanity's quest for sustainable living. In this contribution, remeltable composites were prepared in a highly atom-economical reaction between plant-derived terpenoid alcohols (10 wt% citronellol, geraniol, or farnesol) and elemental sulfur (90 wt%). Investigation into the microstructures led to elucidation of a mechanism for terpenoid polyene cyclization initiated by sulfur-centered radicals. The formation of these cyclic structures contributes significantly to understanding the mechanical properties of the materials and the extent to which linear versus crosslinked network materials are formed. The terpenoid–sulfur composites can be thermally processed at low temperatures of 120 °C without loss of mechanical properties, and the farnesol–sulfur composite so processed exhibits compressive strength 70% higher than required of concrete for residential building. The terpenoid–sulfur composites also resist degradation by oxidizing acid under conditions that disintegrate many commercial composites and cements. In addition to being stronger and more chemically resistant than some commercial products, the terpenoid–sulfur composites can be used to improve the acid resistance of mineral-based Portland cement as well. These terpenoid–sulfur composites thus hold promise as elements of sustainable construction on their own or as additives to extend themore »operational life of existing technologies, while the cyclization behaviour could be an important contributor in other polymerizations of terpenoids.« less