登录
注册
E-alert
登录
注册
E-alert
STUDY ON PREDICTION METHOD OF VERTICAL ULTIMATE BEARING CAPACITY OF SINGLE PILE BASED ON SUPPORT VECTOR MACHINE
-
摘要: 提出了一种基于支持向量机理论的单桩竖向极限承载力预测方法,该方法以统计学理论为基础,避免了神经网络结构设计的盲目性和局部最优等非线性优化问题。仿真试验表明,它比基于混沌优化-神经网络的收敛速度快,预测精度高。Abstract: A new method bas ed on support vector machine for vertical ultimate bearing capacity of s ingle pile is presented. SVM algorithm is bas ed on statistical theory and avoids the blindness of framework designs for neural network and the problem of nonlinear optimizations, such as local optimization. Analysis of the experimental results shows that the convergence speed of support vector machine is faster and its prediction result is more accurate than that of chaos optimization_neural network.
-
[2] 刘勇健.基于遗传-BP神经网络的单桩竖向极限承载力预测方法研究.岩土力学,2004,25(1):59-63 王成华,张薇.人工神经网络在桩基础工程中的应用综述.岩土力学,2002(2):173-178 [3] 刘勇健,张伯友.基于混沌优化-神经网络的单桩竖向极限承载力预测方法.工业建筑,2005,35(3):38-41 [4] Vapnik V.The Nature of Statistical Learning Theory.New York:Springer Verlag,1995 [5] Tay F E H,Cao L J.Modified Support Vector Machines in Financial Time Series Forecasting.Neurocomputing,2002,48:847-861 [6] Van Gestel T,Suykens J A K.Financial Time Series Prediction Using Least Squares Support Vector Machines within the Evidence Framework.IEEE Transactions on Neural Networks,2001,12(4):809-821 [7] 邓乃扬,田英杰.数据挖掘中的新方法--支持向量机.北京:科学出版社,2004 [8] 杨位光.地基及基础.北京:中国建筑工业出版社,2000 [9] Barzilay O,Brailovsky,V L.On Domain Knowledge and Feature Selection Using a Support Vector Machine.Pattern Recognition Letters,1999,20:475-484 -
点击查看大图
计量
- 文章访问数: 60
- HTML全文浏览量: 3
- PDF下载量: 92
- 被引次数: 0
下载:
