| 支持向量回归机在混凝土强度预测中的应用研究 |
| |
| 引用本文： | 武换娥,丁圣果,巩玉志,檀西乐,孟军波. 支持向量回归机在混凝土强度预测中的应用研究[J]. 工业建筑, 2007, 37(Z1) |
| |
| 作者姓名： | 武换娥 丁圣果 巩玉志 檀西乐 孟军波 |
| |
| 作者单位： | 1. 贵州大学,土木建筑工程学院,贵阳,550003
2. 河北省建筑科学院,石家庄,050021 |
| |
| 摘 要： | 利用支持向量回归机(SVR)算法,对在ε-insensitive和Quadratic两种损失函数下的两种核函数进行了研究与分析。在样本数据学习中,发现其预测精度远远高于BP神经网络的预测精度,且参数取值范围很大。针对支持向量回归机模型,给出了参数的取值范围,为SVM在类似工程上的应用提供了参考。
|
| 关 键 词： | 混凝土强度 支持向量回归机 预测 参数分析 |
RESEARCH ON SUPPORT VECTOR MACHINE''S PREDICTION OF CONCRETE STRENGTH |
| |
| Wu Huan'e,Ding Shengguo,Gong Yuzhi,Tan Xile,Meng Junbo. RESEARCH ON SUPPORT VECTOR MACHINE''S PREDICTION OF CONCRETE STRENGTH[J]. Industrial Construction, 2007, 37(Z1) |
| |
| Authors: | Wu Huan'e Ding Shengguo Gong Yuzhi Tan Xile Meng Junbo |
| |
| Abstract: | Two kinds of kernel functions were researched based on two different loss functions(ε-insensitive & quadratic).It was found that forecast precision calculated by SVR algorithm was much more higher than that by using BP,and the range of parameters could be chosed widely.Parameters range was obtained based on this model,which was important to similar engineering practice. |
| |
| Keywords: | concrete strength SVR forecast parameter analysis |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
