Predicting nepheline precipitation in waste glasses using ternary submixture model and machine learning

Date

2021-11-01

Author

Lu, Xiaonan
Sargın, Irmak
Vienna, John D.

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

232
views

0
downloads

Nepheline precipitation in nuclear waste glasses during vitrification can be detrimental due to the negative effect on chemical durability often associated with its formation. Developing models to accurately predict nepheline precipitation from compositions is important for increasing waste loading since existing models can be overly conservative. In this study, an expanded dataset of 955 glasses, including 352 high-level waste glasses, was compiled from literature data. Previously developed submixture models were refitted using the new dataset, where a misclassification rate of 7.8% was achieved. In addition, nine machine learning (ML) algorithms (k-nearest neighbor, Gaussian process regression, artificial neural network, support vector machine, decision tree, etc.) were applied to evaluate their ability to predict nepheline precipitation from glass compositions. Model accuracy, precision, recall/sensitivity, and F1 scores were systemically compared between different ML algorithms and modeling protocols. Model prediction with an accuracy of similar to 0.9 (misclassification rate of similar to 10%) was observed for different algorithms under certain protocols. This study evaluated various ML models to predict nepheline precipitation in waste glasses, highlighting the importance of data preparation and modeling protocol, and their effect on model stability and reproducibility. The results provide insights into applying ML to predict glass properties and suggest areas for future research on modeling nepheline precipitation.

Subject Keywords

crystals, crystallization, glass, modeling, model, nuclear waste, COMPRESSIVE STRENGTH, CONCRETE, DISSOLUTION

URI

https://hdl.handle.net/11511/96125

Journal

JOURNAL OF THE AMERICAN CERAMIC SOCIETY

DOI

https://doi.org/10.1111/jace.17983

Collections

Department of Metallurgical and Materials Engineering, Article

Suggestions

OpenMETU
Core

Comparison Of Formulae For Shear Strength Of Unsaturated Soils Zehtab, Kaveh Hassan; Toker, Nabi Kartal; Ahmadiadli, Mohammad (2012-06-30) During last 60 years many research studies have been conducted on calculation of shear strength of unsaturated soils and effects of matric suction on it. Several formulae are developed for predicting shear strength of unsaturated soils, based on strength tests on unsaturated soils. A variety of experimental techniques and laboratory equipment are used for unsaturated shear strength characterization. This study discusses the accuracy of shear strength prediction for unsaturated soils with three different for...
Influence of fly ash composition on non-gray particle radiation in combusting systems Ates, CİHAN; Selçuk, Nevin; Külah, Görkem (2018-08-01) In this study, chemical composition dependency of both radiative properties of ash particles and radiative heat exchange are investigated for conditions typically encountered in industrial coal-fired furnaces. For that purpose, chemical composition dependent / independent complex index of refraction models are utilized to evaluate (i) spectral particle absorption efficiencies, scattering efficiencies and asymmetry factors, (ii) particle cloud properties representing pulverized coal fired furnaces (PC-Fired)...
LIFE CYCLE ASSESSMENT OF ACTIVATED CARBON ADSORPTION AND OZONATION TO REMOVE MICROPOLLUTANTS FROM TEXTILE WASTEWATER Akdeniz, Ayşe Sena; Yetiş, Ülkü; Department of Environmental Engineering (2022-8-29) To avoid potential adverse effects by micropollutants in secondary textile wastewater, it is necessary to apply an advanced treatment process, among which activated carbon adsorption and ozone oxidation are the most attractive alternatives. There is still a lack of studies evaluating the environmental impacts of these processes for the tertiary treatment of textile wastewater. Using the life cycle assessment (LCA) methodology, this study assesses and compares the environmental impacts of ozone oxidation and...
Assessment of porosity-permeability variation on the response of sandy soils via hypoplasticity model Bayraktaroğlu, Hilmi.; Huvaj Sarıhan, Nejan; Department of Civil Engineering (2019) Hydro-mechanical characteristic of the saturated sands is highly influenced by their porosity and permeability. During loading, unloading and reloading compaction of sands, loosening and re-compaction take place, which leads to changes in pore volume and permeability. In order to accurately simulate these real-life conditions, new variables and phenomena should be investigated using sophisticated numerical tools and equipment. In this study, the behavior of water saturated sands subjected to cyclic and dyna...
Measurement of particulate volume fraction in a coflow diffusion flame using transient thermocouple technique Rolando, A; D'Alessio, A; D'Anna, A; Allouis, Christophe Gerard; Beretta, F; Minutolo, P (2004-05-01) Transient-thermocouple-based measurements have been used to detect soot and nanoparticles in a coflowing diffusion flame of ethylene. Total particulate volume fractions are measured as a function of the radial coordinate at different axial locations and are compared with the results obtained by UV-visible absorption measurements. The good agreement between the two independent measurements demonstrates that transient-thermocouple measurement is a powerful technique to measure total particulate volume fractio...

Citation Formats

X. Lu, I. Sargın, and J. D. Vienna, “Predicting nepheline precipitation in waste glasses using ternary submixture model and machine learning,” JOURNAL OF THE AMERICAN CERAMIC SOCIETY, vol. 104, no. 11, pp. 5636–5647, 2021, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/96125.