Prediction of Properties of Cu-15Ni-8Sn Alloys Based on Least Square Support Vector Machines

Shan Feng Fang; Ming Pu Wang

doi:10.4028/www.scientific.net/AMR.813.479

Paper Titles

Surface Quality Prediction of Atmospheric Pressure Plasma Arc Cleaning Based on Least Square Support Vector Machine
p.460

Study on Surface Pre-Treatment of FeCrAl Metallic Substrate for Hydrogen Production Catalysts
p.465

The Influence of Modification Conditions on Activation of Coal Fly Ash
p.471

Vibration-Assisted Electrochemical Polishing for Extremely Smooth Surface Generation
p.475

Prediction of Properties of Cu-15Ni-8Sn Alloys Based on Least Square Support Vector Machines
p.479

Decomposition of Ilmenite by Ammonium Hydroxide
p.484

Research Advances on Application Status and Non-Thermal Efficiency of Microwave Pyrolysis
p.489

Precipitation Phase and Impurities Distribution of Metallurgical Grade Silicon by Vacuum Refining Followed Slag Treatment
p.492

Boron Removal from Metallurgical-Grade Silicon by Slag Refining with Yttria-Silica System
p.497

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 813Prediction of Properties of Cu-15Ni-8Sn Alloys...

Prediction of Properties of Cu-15Ni-8Sn Alloys Based on Least Square Support Vector Machines

Abstract:

A new model based on least square support vector machines (LSSVM) and capable of forecasting mechanical and electrical properties of Cu-15Ni-8Sn alloys has been proposed. Data mining and artificial intelligence techniques of copper alloys are used to examine the forecasting capability of the model. In order to improve predictive accuracy and generalization ability of LSSVM model, leave-one-out-cross-validation (LOOCV) technique is adopted to determine the optimal hyper-parameters of LSSVM automatically. The forecasting performance of the LSSVM model and the artificial neural network (ANN) has been compared with the experimental values. The result shows that the LSSVM model provides slightly better capability of generalized prediction compared to ANN. The present calculated results are consistent with the experimental values, which suggest that the proposed LSSVM model is feasible and efficient and is therefore considerd to be a promising alternative method to forecast the variation of the hardness and electrical conductivity with aging temperature and aging time.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 813)

Pages:

479-483

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.813.479

Citation:

Cite this paper

Online since:

September 2013

Authors:

Shan Feng Fang, Ming Pu Wang

Keywords:

Copper Alloy, Data Mining (DM), Least Squares Support Vector Machines (Ls-SVM), Leave-One-Out-Cross-Validation, Mechanical Property

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] L.H. Schwartz and S. Mahajam, J.T. Plewes: Acta Metall. Vol. 22 (1974), p.601.

Google Scholar

[2] Y.H. Wang: Phase transformations of Cu-15Ni-8Sn-XSi and Cu-9Ni-2. 5Sn-1. 5A1-0. 5Si alloys and their effects on the alloy's properties( PhD Thesis) (Central South University, Changsha 2004).

Google Scholar

[3] Y.H. Wang, M.P. Wang, B. Hong, Z. Li and G.Y. Xu: Heat Treatment of Metals Vol. 28 (2003), p.41.

Google Scholar

[4] S.L. Zheng, J.M. Wu and Y.W. Zeng: Trans Nonferrous Met. Soc. China Vol. 9 (1999), p.707.

Google Scholar

[5] S. Spooner and B.G. Lefevre: Metall. Trans. Vol. 11 (1980), p.1085.

Google Scholar

[6] S.S. Kim, J.C. Rhu, Y.C. Jung, S.Z. Han and C.J. Kim: Scripta Mater. Vol. 40 (1999), p.1.

Google Scholar

[7] J.A.K. Suykens, G.T. Van, B.J. De and J. Vandewalle: Least-Squares Support Vector Machines (World Scientific, Singapore 2002).

DOI: 10.1142/5089

Google Scholar