Artificial intelligence density model for oxide glasses
Source abstract
Abstract
Abstract A comprehensive study to perform glass density prediction employing artificial intelligence using a dataset of 6630 oxide glass samples. The prediction is done based on Ionic packing ratio as the independent variable and experimental densities from the dataset as the dependent variable. Random forest regression and artificial neural networks were observed as the best models training the density datasets. The random forest regression had the least average R2 score for large datasets. Artificial neural networks employing sigmoid and ReLU activation functions dominate in predicting the glass density as compared to tanh and identity activation functions. Based on this study we can theoretically predict the density of any oxide glass to an extent of maximum accuracy for a known glass composition.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Glass properties and applications · Pigment Synthesis and Properties · Luminescence Properties of Advanced Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Varshneya · 2013
2. Feltz · 2001
3. Physical and optical properties of Co2+, Ni2+ doped 20ZnO+ xLi2O+(30− x) K2O+ 50B2O3 (5≤ x≤ 25) glasses: observation of mixed alkali effect10.1016/j.materresbull.2012.04.075 ↗
4. X-ray photoelectron spectroscopy (XPS) and radiation shielding parameters investigations for zinc molybdenum borotellurite glasses containing different network modifiers10.1007/s10853-017-0974-0 ↗
5. Structural, optical features and gamma ray shielding properties of Bi2O3-TeO2-B2O3-GeO2 glass system10.1016/j.ceramint.2020.04.021 ↗
6. El-Mallawany · Simul. Radiation Shielding Prop. Glasses Contain PbO · 2018 · 151 · 239
7. Electronic polarizability, dielectric, and gamma-ray shielding properties of some tellurite-based glasses10.1007/s00339-019-2976-z ↗
8. Experimental investigations on elastic and radiation shielding parameters of WO3-B2O3-TeO2 glasses10.1016/j.jnoncrysol.2020.120207 ↗
9. The heavy metal oxide glasses within the WO3-MoO3-TeO2 system to investigate the shielding properties of radiation applications10.1016/j.pnucene.2017.10.008 ↗
10. Al-Hadeethi · 2019 · vol. 45 · 24858
11. Photoluminescence and semiconducting behavior of Fe, Co, Ni and Cu implanted in heavy metal oxide glasses10.1016/j.jmrt.2015.11.003 ↗
12. Physical, thermal, structural and optical properties of Dy3+ doped lithium alumino-borate glasses for bright W-LED10.1016/j.jlumin.2016.11.027 ↗
13. Microstructure dependence of ion transport in glass-nanocomposites10.1007/s10832-019-00197-0 ↗
14. The density of the soda-lime-magnesia glasses and some observations on the calculation of density
15. The molecular refractions and molecular volumes of glasses
16. Morey · 1954
17. The density of silicate glasses as a function of composition10.1364/JOSA.30.000420 ↗
18. Systematic analysis of optical glasses concerning their refractive indices and densities
19. Physikalisch-chemische Untersuchungen über den Feinbau von Gläsern. V. Gläser der binären Systeme von P2O5 mit CdO, Na2O und Li2O10.1002/zaac.19492600402 ↗
20. Global model for calculating room-temperature glass density from the composition10.1111/j.1551-2916.2007.01751.x ↗
21. Comparison of two equations for calculation of densities of glasses from their compositions10.1111/j.1151-2916.1954.tb13979.x ↗
22. Scholze · 1991
23. Physicochemical model for predicting molten glass density10.1016/j.jnoncrysol.2008.07.013 ↗
24. Empirical equation for calculating the density of oxide glasses10.1111/j.1551-2916.2009.03363.x ↗
25. Mixed alkali effect in physical and optical properties of Li2O-Na2O-WO3-B2O3 glasses10.1016/j.jnoncrysol.2012.06.004 ↗
26. Physical, optical, and spectroscopic studies on MgO-BaO- B2O3 glasses
27. Density and mechanical properties of calcium aluminate cement
28. Characterization of B2O3 and/or WO3 containing tellurite glasses10.1016/j.jnoncrysol.2011.11.012 ↗
29. Effect of Y2O3 and La2O3 on structure and dielectric properties of aluminoborosilicate glasses10.1016/j.jnoncrysol.2018.05.020 ↗
30. Preparation and characterization of TeO2-WO3-Li2O glasses10.1016/j.jnoncrysol.2013.07.020 ↗
31. Structural investigations on 20MO-xBi2O3-(80-x)B2O3 (M=Ca, Sr and Ba; x=15 and 55) glasses10.1016/j.jnoncrysol.2011.08.002 ↗
32. Comparative analysis of artificial intelligence techniques for material selection applied to manufacturing in Industry 4.010.1016/j.promfg.2019.07.027 ↗
33. Predicting glass transition temperatures using neural networks10.1016/j.actamat.2018.08.022 ↗
34. Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments10.1126/sciadv.aaq1566 ↗
35. A machine learning approach for engineering bulk metallic glass alloys10.1016/j.actamat.2018.08.002 ↗
36. Structural investigation and simulation of acoustic properties of some tellurite glasses using artificial intelligence technique10.1016/j.jallcom.2010.12.064 ↗
37. Ultrasonic and artificial intelligence approach: elastic behavior on the influences of ZnO in tellurite glass systems10.1016/j.jallcom.2020.155350 ↗
38. Machine learning on density and elastic property of oxide glasses driven by large dataset10.1016/j.jnoncrysol.2019.119768 ↗
39. Explainable machine learning algorithms for predicting glass transition temperatures10.1016/j.actamat.2020.01.047 ↗
40. Data-driven predictive models for chemical durability of oxide glass under different chemical conditions10.1038/s41529-020-0118-x ↗
41. Artificial neural network modelling: an introduction
42. Density, viscosity and surface tension of 50ro–50P2O5 (R: Mg, Ca, Sr, Ba, and Zn) glass melts
43. Physical and optical properties of zinc arsenic tellurite glasses10.1016/j.rinp.2012.10.002 ↗
44. Elliott, Mathieu Bauchy, Revisiting the Makishima-Mackenzie model for predicting the Young's modulus of oxide glasses10.1016/j.actamat.2020.05.047 ↗
45. Revised values of effective ionic radii10.1107/S0567740870003576 ↗