PREDICTION OF VERTICAL ULTIMATE BEARING CAPACITY OF SINGLE PILE BASED ON GENETIC ALGORITHM AND SUPPORT VECTOR MACHINE
-
摘要: 通过将改进遗传算法与支持向量机相结合,建立一种用于单桩竖向极限承载力预测的进化支持向量机模型。这种方法基于实测数据,利用遗传算法搜索最优的支持向量机参数,用获得的最优模型进行学习,从而得到泛化能力更好的预测模型。结果表明,该算法可以有效地解决支持向量机的参数确定问题,给出的算例结果是令人满意的。Abstract: The prediction model of vertical ultimate bearing capacity of single pile is built by combining improved genetic algorithm and support vector regression machine.The practical data are used to train the support vector machine whose parameters are determined in global optimization by improved genetic algorithm.Thus,a prediction model with better generalizing capacity is built.The study shows that this method is effective for determining the parameters of support vector machine,and the results are satisfactory.
-
龚艳冰,陈森发. 基于支持向量机的单桩竖向极限承载力预测[J].工业建筑,2006,(02):49-53. 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研究[J].工业建筑,2005,(03):38-41. Burge C J C. A Tutorial on Support Vector Machines for Pattern Recognition[J].Data Mining and Knowledge Discovery,1998,(02):121-167. John C Platt. Sequential Minimal Optimization:A Fast Algorithm for Training Support Vector Machines[R].Technical Report MSR-TR-98-14,1998. 赵洪波,冯夏庭. 位移反分析的支持向量机研究[J].岩石力学与工程学报,2003,(10):1618-1622. Vapnik V. Nature of Statistical Learning Theory[M].New York:Springer-verlag,1995. 苏高利,邓芳萍. 关于支持向量回归机的模型选择[J].科技通报,2006,(02):154-158.doi: 10.3969/j.issn.1001-7119.2006.02.004. 李琳,张晓龙. 支持向量机学习方法的选择与应用[J].武汉科技大学学报(自然科学版),2006,(01):75-78. 刘福深,刘耀儒,杨强. 基于改进遗传算法的拱坝位移反分析[J].岩石力学与工程学报,2005,(23):4341-4345. 郏宣耀,王芳. 一种改进的小生境遗传算法[J].重庆邮电学院学报(自然科学版),2005,(01):721-763. Chih-Chung Chang,Chih-Jen Lin. LIBSVM:A Library for Support Vector Machines[Z].2001. 刘勇健. 基于遗传-神经网络的单桩竖向极限承载力预测方法研究[J].岩土力学,2004,(01):59-64. 杨位洸. 地基及基础[M].北京:中国建筑工业出版社,2000.
点击查看大图
计量
- 文章访问数: 82
- HTML全文浏览量: 6
- PDF下载量: 33
- 被引次数: 0