Polymer Ratio Optimization Based on Support Vector Machine and Genetic Algorithm

Abstract:

For getting rid trial-and-error method of polymer blending modification depends on experience, nonlinear relation of polymer ratio and its properties is obtained by Support Vector Machine and Genetic Algorithm. While the application of genetic algorithms to optimize the SVM model. Decision function in the relational model of SVM as the objective function, and optimized the value of polymer properties and its ratio by genetic algorithms. Experiments show that the method has some values.

• Periodical: Applied Mechanics and Materials (Volumes 444-445)
• Pages: 1026-1032
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.444-445.1026
• Online since: October 2013
• Authors: Zhi Shan, Hen Luo, Shu Hao Qin
• Keywords: Genetic Algorithm (GA), Nonlinear Relation, Optimizing Material Propertie, Polymer Properties, Polymer Ratio, Support Vector Machine (SVM)

References

[1] F ENG Wu-feng, WANG Chun-qing, ZHANG Lei. Calculation during material design, a new tendency in material design[J]. Materials Science and Technology, 2000, 8(4): 57-62.

[2] LI Qiang, YU Jing-yuan , SUN Xu-dong, LIU Zhi-gang. relationship between process parameters and porosity NiTi alloy using artificial neural network [J]. Materials Science and Technology 2007. 15(3): 316-318.

[3] WANG Mei, WANG Zhuo, WANG Jie. Research on ANN-Based Machining Operation Selection for Rotational Parts [J]. Journal of University of Electronic Science and Technology of China 2010, 39(3)470-474.

[4] DOU Liu-ming, LIAO Ning-fang, WU Wen-min. The research of computer color matching of powder paints using BP neural networks [J]. Optical Technique 2008, 34(1)116-119.

[5] Cao Yibo, Xie Xiaopeng . Wear Loss Prediction Using Least Square Support Vector Machine [J]. Lubrication Engineering [J]. 2007, 32(2): 138-141.

[6] Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge: Cambridge University Press, 2000: 24−46.

DOI: 10.1017/cbo9780511801389

[7] Wu C H, Tzeng G H, Lin R H. A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression[J]. Expert Systems with Applications. 2009. 36(3): 4725-4735.

DOI: 10.1016/j.eswa.2008.06.046

[8] Fang S F, Wang M P, Qi W H, eta1. Hybrid genetic algorithms and support vector regression in forecasting atmospheric corrosion of metallic materials[J]. Computational Materials Science, 2008, 44(2): 647—655.

DOI: 10.1016/j.commatsci.2008.05.010

[9] Zhang Xue-gong. On statistical learning theory and support vector machine [J] . ACTA AUTOMATICA SINICA, 2000, 26( 1) : 32 -42.

[10] WANG Shu-zhou, SAN Ye. A survey on training algorithms for support vector machine [ J] . CAAL Transactions on Intelligent Systems, 2008, 3( 6) : 467 -475.

[11] Boser B E, Guyon I M, Vapnik V N. A Training Algorithm for Optimal Margin Classifiers [ C] / / Proceedings of the 5th Annual ACM Workshop on Computational Learning Theo ry. Pittsburg h, PA, 1992: 144-152.

DOI: 10.1145/130385.130401

[12] Zhou W D，Zhang L，Jiao L C． Adaptive support vector machine multi-user detection［J]. Electronic Journals，2002，31( 1) : 1-6.

[13] Yu Q X，Wang K. Study on pattern and control of gasemission at coal face in China［J］. Journal of China University of Mining ＆ Technology，2000，1( 1) : 9-14.

[14] Chang C C, Lin C J. Training v-support vector classifiers: theory and algorithms[J]．Neural Computation, 2001, 13( 9) : 2119-2147.

DOI: 10.1162/089976601750399335

[15] Chi W H，Chi J L. A simple decomposition method for support vector machines［J］. Machine Learning, 2002, 1( 46) : 291-314.