All Title Author
Keywords Abstract


基于Takens理论和SVM的滑坡位移预测

, PP. 13-18

Keywords: 道路工程,滑坡位移预测,Takens理论,支持向量机,相空间重构

Full-Text   Cite this paper   Add to My Lib

Abstract:

?针对滑坡变形时序非线性,数据量少的特点,引入Takens理论,采用支持向量机(SVM)建立其预测模型,建模过程中,比较了由不同核函数获得的SVM模型的性能,同时将SVM与RBF、Elman神经网络模型进行外推7步预测试验比较。结果表明:RBF核函数具有更好的工程实用价值;在有限样本情况下,SVM预测模型具有更好的准确性和泛化性,其7步预测平均误差率控制在5%以内,可见该方法在滑坡变形预测方面极具潜力。

References

[1]  冯夏庭.智能岩石力学导论[M].北京:科学出版社, 2000.
[2]  蒋 鑫, 魏永幸, 邱延峻.斜坡软弱地基路堤填筑全过程稳定性[J].交通运输工程学报, 2003, 3(1):30-34.
[3]  石 刚, 王晋国, 支喜兰, 等.黄土地区公路工程地基承载力分区计算方法[J].交通运输工程学报, 2005, 5(4):48-52.
[4]  CRISTIANINI N, SHAWE-TAYLOR J.An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M].New York:Cambridge University Press, 2000.
[5]  VAPNIK V N.Statistical Learning Theory[M].New York:Wiley-interscience, 1998.
[6]  付仪祥, 刘志强.边坡位移的混沌时间序列分析方法及应用研究[J].武汉理工大学学报, 2003, 27(4):474-476.
[7]  SMOLA A, MURATA N, SCHOLKOPF B, et al.Asymptotically Optimal Choice of ε-loss for Support Vector Machines[C]//NIKLASSON L, BODEN M, ZIEMKE T.Proceedings of the 8th International Conference on Artificial Neural Networks.Berlin:Springer, 1998:105-110.
[8]  SCHOLKOPF B, BARTLETT P, SMOLA A, et al.Support Vector Regression with Automatic Accuracy Control[C]//NIKLASSON L, BODEN M, ZIEMKE T.Proceedings of the 8th International Conference on Artificial Neural Networks.Berlin:Springer, 1998:111-116.
[9]  CHERKASSKY V, MA Y.Selection of Meta-parameters for Support Vector Regression[C]//DORRONSORO J R.Proceedings of the International Conference on Artificial Neural Networks.Madrid:Springer, 2002:687-693.
[10]  LIU Kai-yun, QIAO Chun-sheng, TENG Wen-yan.Research on Nonlinear Time Sequence Intelligent Model Construction and Prediction of Slope Displacement by Using Support Vector Machine Algorithm[J].Chinese Journal of Geotechnical Engineering, 2004, 26(1):57-61.
[11]  FENG Xia-ting.Introduction of Intelligent Rock Mechanics[M].Beijing:Science Press, 2000.
[12]  JIANG Xin, WEI Yong-xing, QIU Yan-jun.Stability of Subgrade Embankment on Sloped Weak Ground[J].Journal of Traffic and Transportation Engineering, 2003, 3(1):30-34.
[13]  SHI Gang, WANG Jin-guo, ZHI Xi-lan, et al.Calculation Method of Foundation Bearing Capacity Based on Division in Loess Area for Highway Engineering[J].Journal of Traffic and Transportation Engineering, 2005, 5(4):48-52.
[14]  VAPNIK V N.The Nature of Statistical Learning Theory[M].New York:Springer Verlag, 1995.
[15]  FU Yi-xiang, LIU Zhi-qiang.Analytic Method and Application About Chaotic Slope Deformation Destruction Time-series[J].Journal of Wuhan University of Technology, 2003, 27(4):474-476.
[16]  CHERKASSKY V, MA Y.Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J].Neural Networks, 2004, 17(1):113-126.
[17]  CHALIMOURDA C, SCHOLKOPF B, SMOLA A.Experimentally Optimal V in Support Vector Regression for Different Noise Models and Parameter Settings[J].Neural Networks, 2004, 17(1):127-141.
[18]  刘开云, 乔春生, 滕文彦.边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究[J].岩土工程学报, 2004, 26(1):57-61.

Full-Text

comments powered by Disqus