Application of Support Vector Machine to Predicting Mechanical Properties of TC4

Zhe Zhe Hou; Yan Liang Du; Wei Gang Zhao; Meng Zhao; Shuang Chao Peng

doi:10.4028/www.scientific.net/AMR.189-193.1854

Paper Titles

Study on the Distribution Law of the Crashed Coal Fragmentation
p.1834

Numerical Analysis on Impact Load of Elasto-Plastic Spherical Impact
p.1840

Anslysis of the 5-m Heavy Plate Mill Stand Based on MSC.Marc Finite Element Method
p.1844

Temperature Simulation in High-Speed Grinding by Using Deform-3D
p.1849

Application of Support Vector Machine to Predicting Mechanical Properties of TC4
p.1854

The Research on Friction Impacting on Drawing High-Strength Steel
p.1858

Laser Anneal-Induced Effects on the NBTI Degradation of Advanced-Process 45nm High-K PMOS
p.1862

Research on Performance Characteristic of Novel Fomichev Plug Used in Julong-Type Piercer
p.1867

Study on the Burning Characteristics of Poor-Quality Anthracite in Supercritical W-Shaped Flame Boiler
p.1872

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 189-193Application of Support Vector Machine to...

Application of Support Vector Machine to Predicting Mechanical Properties of TC4

Abstract:

On the basis of numerous experimental results the effect of heat treatment on mechanical properties of TC4 alloy is studied. A computer model expressing the relationships between heat treatment and mechanical properties has been established with supported vector machine method. The input parameters were determined by the heating temperature and heating time which are important factors of the mechanical performance, and the output parameters are tensile and yield strength and elongation. The model is established by libsvm with RBF kernel function, e-SVR and proper parameters. Experimental results show that prediction accuracy made by using support vector machine reached over 95%, and the model has good learning precision and generalization and it can be used for predicting the mechanical properties of TC4 alloy.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 189-193)

Pages:

1854-1857

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.189-193.1854

Citation:

Cite this paper

Online since:

February 2011

Authors:

Zhe Zhe Hou, Yan Liang Du, Wei Gang Zhao, Meng Zhao, Shuang Chao Peng

Keywords:

Elongation, Libsvm, Prediction, Support Vector Machine (SVM), Tensile Strength, Yield Strength

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Ying-Wei Kang et al. Dynamic temperature modeling of an SOFC using least squares support vector machines[J]. Journal of Power Sources 179 (2008) , p.683–692.

DOI: 10.1016/j.jpowsour.2008.01.022

Google Scholar

[2] Y. -W. Kang et al. Dynamic temperature modeling of an SOFC using least squares support vector machines[J]. Journal of Power Sources 179 (2008), p.683–692.

DOI: 10.1016/j.jpowsour.2008.01.022

Google Scholar

[3] Zhehe Yao et al. On-line chatter detection and identification based on wavelet and support vector machine[J] Journal of Materials Processing Technology 210 (2010) , p.713–719.

DOI: 10.1016/j.jmatprotec.2009.11.007

Google Scholar

[4] V.N. Vapnik, The Nature of Statistical Learning Theory[M], Springer, New York (1995).

Google Scholar

[5] C. -C. Chang, C. -J. Lin, LIBSVM: a library for support vector machines[J]( 2001), Software available at http: /www. csie. ntu. edu. tw/cjlin/libsvm.

Google Scholar

[6] Z. -D. Zhong et al. Modeling a PEMFC by a support vector machine[J]. Journal of Power Sources 2006 (160) , p.293–298.

Google Scholar