Sintered SiO2 Modulus of Rupture Optimization by Means of Artificial Neural Networks

Miroslav Kvíčala; Michaela Štamborská

doi:10.4028/www.scientific.net/AMR.1119.807

Paper Titles

Thermal Conductivity and Specific Heat Capacity of Different Compositions of Yttria Stabilized Zirconia-Nickel Mixtures
p.783

Experimental Verification of Effect of Adhesive Layer Thickness Used for Strain Gauge Mounting
p.789

Research on Damage Mechanism of Aluminum Foam Sandwich Plate Subjected to Blast Loading
p.794

The Mechanical Properties and the Influence of Parameters for Metallic Closed-Cell Foam Subjected to High-Strain Rates
p.799

Sintered SiO₂ Modulus of Rupture Optimization by Means of Artificial Neural Networks
p.807

The Main Factors that Influence the Mechanical Properties of Honeycomb Board
p.812

Mechanical Properties of High-Strength Steel Obtained Using DIC for Specimens with a Hole
p.816

Recycled Plastic Quality Indicator Development Using Material Testing Results and Radar Chart
p.821

Finite Element Modeling of Effect of Adhesive Layer and Carrier Thickness Used for Strain Gauge Mounting
p.828

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 1119Sintered SiO2 Modulus of Rupture Optimization by...

Sintered SiO₂ Modulus of Rupture Optimization by Means of Artificial Neural Networks

Abstract:

This article discusses the use of artificial neural networks for solving industrial non-trivial problem, which is undoubtedly modulus of rupture optimization in case of sintered ceramics based on amorphous SiO₂. Melting crucibles made from high purity silica are commonly used for production of high purity silicon ingots that are used in photovoltaic industry. Optimal modulus of rupture is very important variable that is related to the reliability and crucible usage value.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 1119)

Pages:

807-811

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1119.807

Citation:

Cite this paper

Online since:

July 2015

Authors:

Miroslav Kvíčala*, Michaela Štamborská

Keywords:

Modulus of Rupture, Neural Networks, Optimization, Silica, Sintering

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] B. Gallien, T. Duffar and J.P. Garandet: Journal of Crystal Growth Vol. 390 (2014), p.125 – 128.

Google Scholar

[2] B. Gallien, Th. Duffar, S. Lay and F. Robaut: Journal of Crystal Growth Vol. 318 (2011), p.208 – 211.

DOI: 10.1016/j.jcrysgro.2010.10.100

Google Scholar

[3] J. Gajewski and T. Sadowski: Computational Materials Science Vol. 82 (2014), p.114 – 117.

Google Scholar

[4] L. R., Sha and Y. Yang: Advanced Materials Research Vol. 834 – 836 (2014), p.1877 – 1880.

Google Scholar

[5] V. Mařík, O. Štěpánková and J. Lažanský et al: Artificial intelligence 4, (In Czech) Academia Publishing, Praha, (2003).

Google Scholar

[6] J. Šíma and R. Neruda: Theoretical questions of neural networks, (In Czech) Matfyzpress, Praha, (1996).

Google Scholar

[7] C. E Loo and J. Heikkinen: ISIJ International Vol. 52 (2012), p.2158 – 2167.

Google Scholar

[8] A. E. Kushchevskii: Powder Metallurgy and Metal Ceramics Vol. 51 (2012), p.35 – 41.

Google Scholar

[9] R. Meca, M. Kvíčala, Z. Jančíkova and O. Zimný: Hutnické listy Vol. 56 (2014), p.29 – 32.

Google Scholar