Machine Learning for Glass Modeling

Adama Tandia, Mehmet C. Onbasli, John C. Mauro

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

With abundant composition-dependent glass properties data of good quality, machine learning-based models can enable the development of glass compositions with desired properties such as liquidus temperature, viscosity, and Young's modulus using much fewer experiments than would otherwise be needed in a purely experimental exploratory research. In particular, research companies with long track records of exploratory research are in the unique position to capitalize on data-driven models by compiling their earlier internal experiments for research and product development. In this chapter, we demonstrate how Corning has used this unique advantage to develop models based on neural networks and genetic algorithms to predict compositions that will yield a desired liquidus temperature as well as viscosity, Young's modulus, compressive stress, and depth of layer.

Original languageEnglish (US)
Title of host publicationSpringer Handbooks
PublisherSpringer
Pages1157-1192
Number of pages36
DOIs
StatePublished - Jan 1 2019

Publication series

NameSpringer Handbooks
ISSN (Print)2522-8692
ISSN (Electronic)2522-8706

Fingerprint

Learning systems
Glass
Elastic moduli
Chemical analysis
Viscosity
Compressive stress
Product development
Genetic algorithms
Experiments
Neural networks
Temperature
Industry

All Science Journal Classification (ASJC) codes

  • General

Cite this

Tandia, A., Onbasli, M. C., & Mauro, J. C. (2019). Machine Learning for Glass Modeling. In Springer Handbooks (pp. 1157-1192). (Springer Handbooks). Springer. https://doi.org/10.1007/978-3-319-93728-1_33
Tandia, Adama ; Onbasli, Mehmet C. ; Mauro, John C. / Machine Learning for Glass Modeling. Springer Handbooks. Springer, 2019. pp. 1157-1192 (Springer Handbooks).
@inbook{bf0ea493dbee494494bb16d970c11349,
title = "Machine Learning for Glass Modeling",
abstract = "With abundant composition-dependent glass properties data of good quality, machine learning-based models can enable the development of glass compositions with desired properties such as liquidus temperature, viscosity, and Young's modulus using much fewer experiments than would otherwise be needed in a purely experimental exploratory research. In particular, research companies with long track records of exploratory research are in the unique position to capitalize on data-driven models by compiling their earlier internal experiments for research and product development. In this chapter, we demonstrate how Corning has used this unique advantage to develop models based on neural networks and genetic algorithms to predict compositions that will yield a desired liquidus temperature as well as viscosity, Young's modulus, compressive stress, and depth of layer.",
author = "Adama Tandia and Onbasli, {Mehmet C.} and Mauro, {John C.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-319-93728-1_33",
language = "English (US)",
series = "Springer Handbooks",
publisher = "Springer",
pages = "1157--1192",
booktitle = "Springer Handbooks",

}

Tandia, A, Onbasli, MC & Mauro, JC 2019, Machine Learning for Glass Modeling. in Springer Handbooks. Springer Handbooks, Springer, pp. 1157-1192. https://doi.org/10.1007/978-3-319-93728-1_33

Machine Learning for Glass Modeling. / Tandia, Adama; Onbasli, Mehmet C.; Mauro, John C.

Springer Handbooks. Springer, 2019. p. 1157-1192 (Springer Handbooks).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Machine Learning for Glass Modeling

AU - Tandia, Adama

AU - Onbasli, Mehmet C.

AU - Mauro, John C.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - With abundant composition-dependent glass properties data of good quality, machine learning-based models can enable the development of glass compositions with desired properties such as liquidus temperature, viscosity, and Young's modulus using much fewer experiments than would otherwise be needed in a purely experimental exploratory research. In particular, research companies with long track records of exploratory research are in the unique position to capitalize on data-driven models by compiling their earlier internal experiments for research and product development. In this chapter, we demonstrate how Corning has used this unique advantage to develop models based on neural networks and genetic algorithms to predict compositions that will yield a desired liquidus temperature as well as viscosity, Young's modulus, compressive stress, and depth of layer.

AB - With abundant composition-dependent glass properties data of good quality, machine learning-based models can enable the development of glass compositions with desired properties such as liquidus temperature, viscosity, and Young's modulus using much fewer experiments than would otherwise be needed in a purely experimental exploratory research. In particular, research companies with long track records of exploratory research are in the unique position to capitalize on data-driven models by compiling their earlier internal experiments for research and product development. In this chapter, we demonstrate how Corning has used this unique advantage to develop models based on neural networks and genetic algorithms to predict compositions that will yield a desired liquidus temperature as well as viscosity, Young's modulus, compressive stress, and depth of layer.

UR - http://www.scopus.com/inward/record.url?scp=85075934771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075934771&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-93728-1_33

DO - 10.1007/978-3-319-93728-1_33

M3 - Chapter

AN - SCOPUS:85075934771

T3 - Springer Handbooks

SP - 1157

EP - 1192

BT - Springer Handbooks

PB - Springer

ER -

Tandia A, Onbasli MC, Mauro JC. Machine Learning for Glass Modeling. In Springer Handbooks. Springer. 2019. p. 1157-1192. (Springer Handbooks). https://doi.org/10.1007/978-3-319-93728-1_33