根据自蔓延高温合成法(SHS)制备多孔NiTi合金孔隙试验所获得的实测数据集,应用基于粒子群算法(PSO)寻优的支持向量回归(SVR)方法,建立不同反应参数(温度,粒度和压坯密度)下合成的多孔NiTi合金孔隙的SVR预测模型,并与基于误差反向传播神经网络(BPNN)回归模型的预测结果进行比较.结果表明:在相同的训练与测试样本集下所获的SVR预测结果的平均绝对百分误差(MAPE)比BPNN预测模型的要小,其预测精度更高,预测效果更好;SVR-LOOCV预测的MAPE也比BPNN略小,且其预测结果的相关系数达到了0.999.因此,该方法是一种预测SHS法制备多孔NiTi合金孔隙的有效方法,可为SHS合成多孔NiTi提供理论指导.
参考文献
[1] | Macedo Z S;Ferrari C R;Hernandes A C .[J].Power Technology,2004,139(02):175. |
[2] | Fu R L;Chen K X;Xu X et al.[J].Materials Letters,2005,59(19-20):2605. |
[3] | Hu Q D;Luo P;Qiao D et al.[J].Journal of Alloys and Compounds,2008,464(1-2):157. |
[4] | 张林,陈秀娟,夏天东.NiTi合金的自蔓延高温合成研究进展[J].粉末冶金工业,2007(03):48-51. |
[5] | 李强,于景媛,孙旭东,刘志刚.多孔NiTi合金工艺参数与孔隙关系的神经网络研究[J].材料科学与工艺,2007(03):316-318. |
[6] | 李强,于景媛,穆柏春,孙旭东.BP模型在预测多孔NiTi合金孔隙度和屈服强度上的应用[J].功能材料,2006(06):952-954,958. |
[7] | Vapnik V.The Nature of Statistical Learning Theory[M].New York:springer-verlag,1995 |
[8] | C. Z. Cai;L. Y. Han;Z. L. Ji;X. Chen;Y. Z. Chen .SVM-Prot: web-based support vector machine software for functional classification of a protein from its primary sequence[J].Nucleic Acids Research,2003(13):3692-3697. |
[9] | Song M H;Breneman C M;Bi J B et al.[J].Journal of Chemical Information and Computer Sciences,2002,42(06):1347. |
[10] | Cai CZ;Han LY;Ji ZL;Chen YZ .Enzyme family classification by support vector machines.[J].Proteins: Structure, Function, and Genetics,2004(1):66-76. |
[11] | Shen RM;Fu YG;Lu HT .A novel image watermarking scheme based on support vector regression[J].The Journal of Systems and Software,2005(1):1-8. |
[12] | Wen Y F;Cai C Z;Liu X H et al.[J].Corrosion Science,2009,51(02):349. |
[13] | Cai CZ.;Wang WL.;Chen YZ. .Support vector machine classification of physical and biological datasets[J].International Journal of Modern Physics, C. Physics and Computers,2003(5):575-585. |
[14] | Tang L J;Zhou Y P;Jiang J H et al.[J].Journal of Chemical Information and Modeling,2007,47(04):1438. |
[15] | Alatas B;Akin E .Rough particle swarm optimization and its applications in data mining[J].Soft computing: A fusion of foundations, methodologies and applications,2008(12):1205-1218. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分:
-
10%
-
20%
-
30%
-
40%
-
50%