Limestone calcined clay cement (LC3) is a sustainable alternative to ordinary Portland cement, capable of reducing the binder’s carbon footprint by 40% while satisfying all key performance metrics. The inherent compositional heterogeneity in select components of LC3, combined with their convoluted chemical interactions, poses challenges to conventional analytical models when predicting mechanical properties. Although some studies have employed machine learning (ML) to predict the mechanical properties of LC3, many have overlooked the pivotal role of feature selection. Proper feature selection not only refines and simplifies the structure of ML models but also enhances these models’ prediction performance and interpretability. This research harnesses the power of the random forest (RF) model to predict the compressive strength of LC3. Three feature reduction methods—Pearson correlation, SHapley Additive exPlanations, and variable importance—are employed to analyze the influence of LC3 components and mixture design on compressive strength. Practical guidelines for utilizing these methods on cementitious materials are elucidated. Through the rigorous screening of insignificant variables from the database, the RF model conserves computational resources while also producing high-fidelity predictions. Additionally, a feature enhancement method is utilized, consolidating numerous input variables into a singular feature while feeding the RF model with richer information, resulting in a substantial improvement in prediction accuracy. Overall, this study provides a novel pathway to apply ML to LC3, emphasizing the need to tailor ML models to cement chemistry rather than employing them generically.
- NSF-PAR ID:
- 10387899
- Date Published:
- Journal Name:
- Algorithms
- Volume:
- 16
- Issue:
- 1
- ISSN:
- 1999-4893
- Page Range / eLocation ID:
- 7
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
more » « less
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.
-
Calcium aluminate cement (CAC) has been explored as a sustainable alternative to Portland cement, the most widely used type of cement. However, the hydration reaction and mechanical properties of CAC can be influenced by various factors such as water content, Li2CO3 content, and age. Due to the complex interactions between the precursors in CAC, traditional analytical models have struggled to predict CAC binders’ compressive strength and porosity accurately. To overcome this limitation, this study utilizes machine learning (ML) to predict the properties of CAC. The study begins by using thermodynamic simulations to determine the phase assemblages of CAC at different ages. The XGBoost model is then used to predict the compressive strength, porosity, and hydration products of CAC based on the mixture design and age. The XGBoost model is also used to evaluate the influence of input parameters on the compressive strength and porosity of CAC. Based on the results of this analysis, a closed-form analytical model is developed to predict the compressive strength and porosity of CAC accurately. Overall, the study demonstrates that ML can be effectively used to predict the properties of CAC binders, providing a valuable tool for researchers and practitioners in the field of cement science.more » « less
-
more » « less
Abstract Alkali‐activated mortar (AAM) is an emerging eco‐friendly construction material, which can complement ordinary Portland cement (OPC) mortars. Prediction of properties of AAMs—albeit much needed to complement experiments—is difficult, owing to substantive batch‐to‐batch variations in physicochemical properties of their precursors (i.e., aluminosilicate and activator solution). In this study, a machine learning (ML) model is employed; and it is shown that the model—once trained and optimized—can reliably predict compressive strength of AAMs solely from their initial physicochemical attributes. Prediction performance of the model improves when multiple compositional descriptors of the aluminosilicate are combined into a singular, composite chemostructural descriptor (i.e.,
network ratio andnumber of constraints ); thus, reducing the degrees of freedom. Through interpretation of the ML model's outcomes—specifically the variable importance for the AAMs’ compressive strength—a simple, easy‐to‐use, closed‐form analytical model is developed. Results demonstrate that the analytical model yields predictions of compressive strength of AAMs without scarifying much accuracy compared to the ML model. Overall, this study's outcomes demonstrate a roadmap—incorporates composite chemostructural descriptors in ML models—that can be employed to design AAMs to achieve targeted compressive strength. -
more » « less
ABSTRACT The utilization of predictive mechanisms to resolve asphaltene precipitation during oil production is a cleaner and less expensive means than the mechanical/chemical remediation techniques currently employed. Existing models lack predictive success due to opposing views on temperature-asphaltene precipitation interactions. In this study, the effect of varying temperatures (40, 50, 60, 70 80 and 90 °C) and brine concentrations (0 – 5 wt.%) on the long-time kinetics of asphaltene precipitations was evaluated. A series of experiments were conducted using the filtration technique and the confocal microscopy to study asphaltene precipitation on a model oil system consisting of asphaltenes, a precipitant, and a solvent. Furthermore, the Avrami modeling technique was employed to predict the morphology, and growth rate of the precipitating asphaltenes. The experimental results suggested that temperature significantly affects asphaltene precipitation including imparting its precipitation mechanism with a cross-behavioral pattern. Asphaltene precipitation in the system displayed an initial fast kinetics upon increasing temperature. The fast kinetics observed in the early times is due to the increasing dipole-dipole interactions between asphaltene sub-micron particles stimulated by increased temperature. However, the pattern changes into slower precipitations as the time progresses upon continuous heating of the reservoir fluid. The reason is the increased solubility of the asphaltenes imparted into the model oil system upon further increments in temperature. The presence of brine in the model-oil system also enhanced the rate and precipitation of asphaltenes. The experimental data were further analyzed with the Avrami crystallization fitting model to predict the formation, growth, morphology, and growth geometry of the precipitating asphaltenes. The Avrami model successfully predicted the asphaltene morphologies, growth rates and the crystal growth geometries. The growth geometries (rods, discs, or spheres) of the asphaltenes in the model oil systems upon temperature increments, ranged from 1.4 – 3.5. These values are indicative that temperature impacts the growth process of asphaltenes in the model system causing variations from a rod-like sporadic process (1.0 ≤ n ≤ 1.9) to a spherical sporadic growth process (3.0 ≤ n ≤ 3.9). This work precisely emphasizes the impact of temperature on asphaltene precipitations under long kinetic time, thus, providing a clear pathway for developing successful kinetic and thermodynamic models capable of predicting asphaltene precipitation reliably. The accurate prediction of asphaltene precipitation will eliminate the need for the use of harmful remediation solvents like benzene/toluene/ethylbenzene/xylene (BTEX). This study is therefore a critical step in the right direction to achieving accurate predictive model evaluations of asphaltene precipitations.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/a16010007
