Prediction of Porosity of Porous NiTi Alloy from Processing Parameters Based on SVR

Qi Sheng Yan

doi:10.4028/www.scientific.net/AMR.393-395.231

Paper Titles

On the Design and Development of a Novel Real-Time Transaction Price Estimation System
p.213

Optimization on Heat Treatment Process of 45CrMnSi Steel by Orthogonal Test
p.217

Photochromism and Optical Recording of a Novel Photochromic Hybrid Diarylethene Bearing an Isoxazole Unit
p.222

Poisoning Effect of Combined Addition of Fe and Mn on Carbon Inoculation of Mg-3%Al Alloy
p.226

Prediction of Porosity of Porous NiTi Alloy from Processing Parameters Based on SVR
p.231

Preparation and Characterization of Heparin-Immobilized Poly(Ether Urethanes)
p.236

Preparation and Characterization of Hollow Silica Nanospheres
p.240

Preparation and Luminescent Properties of Nancrystalline Zro₂:Eu³⁺ by Emulsion Method
p.244

Preparation and Microstructure of TiB₂/Al Composites
p.249

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 393-395Prediction of Porosity of Porous NiTi Alloy from...

Prediction of Porosity of Porous NiTi Alloy from Processing Parameters Based on SVR

Abstract:

The regression principle of support vector machines (SVM) based on the statistic learning theory is introduced and mathematical model combined with grid search and Leave-one-out cross validation (LOOCV) which is used to predict the porosity of porous NiTi alloy from processing parameters is established by support vector regression technology. In this model, temperature, particle size and green density are as input parameters and porosity of reacted products is as output paramater. The results show that the relative maximum predicting error is 0.1% under the condition of using a small quantity of samples to build the mathematical model, and the predicting precision of SVR model is obviously better than that of BP neural network model. It is suggested that SVR is an effective and powerful tool for predicting porosity of porous NiTi alloy.

You might also be interested in these eBooks

Biotechnology, Chemical and Materials Engineering

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 393-395)

Pages:

231-235

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.393-395.231

Citation:

Cite this paper

Online since:

November 2011

Authors:

Qi Sheng Yan

Keywords:

BP Neural Network (BPNN), NiTi SMA, Porosity, Predicting Model, Process Parameter, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] V.I. Itin, V.E. Gyunter, S.A. Shabalovskaya, etal. Mechanical properties and shape memory of porous NiTi. Mater Charact, 32, (1994), p.179.

DOI: 10.1016/1044-5803(94)90087-6

Google Scholar

[2] B.Y. Li, L.J. Rong, Y.Y. Li, etal. Fabrication of celular NiTi intermetallic compounds. J Mater Res, 15(2000), p.10.

Google Scholar

[3] Y. Yue J.C. Zhu, Y. Liu, etal. Prediction of processing-properties of TA15 Titanium alloy based on BP neural network. Rare metal materials and engineering, 38(2009), p.1811.

Google Scholar

[4] Q. Li, J.Y. Yu, X.D. Sun, etal. Research on relationship between process parameters and porosity of porous NiTi alloy using artificial neural network. Materials science&technology, 15(2007), p.316.

Google Scholar

[5] V.N. Vapnik. The Nature of Satistical Learning Theory. New York Springer Verlag(1995).

Google Scholar

[6] S.R. Gunn. Support Vector Machines for Classification and Regression. Technical Report, Image Speech and Intelligent Systems Research Group, university of Southampton(1997).

Google Scholar