| 大坝变形预报的神经网络极限学习方法 |
| |
| 引用本文： | 范千.大坝变形预报的神经网络极限学习方法[J].江南大学学报(自然科学版),2011,10(4):435-438. |
| |
| 作者姓名： | 范千 |
| |
| 作者单位： | 福州大学土木工程学院,福建福州350108;东华理工大学江西省数字国土重点实验室,江西抚州344000 |
| |
| 基金项目： | 江西省数字国土重点实验室开放基金项目(DLLJ201102); 福建省教育厅科技项目(JA10045); 福州大学科研启动基金项目(XRC-1050) |
| |
| 摘 要： | 针对大坝变形具有强非线性的特点以及在采用传统BP神经网络模型进行预报时存在学习速度慢、易陷入局部极小等问题,提出将极限学习机(ELM)方法用于大坝变形预报。该方法不仅可以简化网络参数选择过程,而且可以明显提高网络的训练速度,并具有良好的泛化性能。工程实例结果分析表明了ELM方法应用于大坝变形预报具有可行性和有效性。
|
| 关 键 词： | 大坝变形预报 神经网络 极限学习方法 |
Extreme Learning Method of Neural Network for Dam Deformation Prediction |
| |
| FAN Qian.Extreme Learning Method of Neural Network for Dam Deformation Prediction[J].Journal of Southern Yangtze University:Natural Science Edition,2011,10(4):435-438. |
| |
| Authors: | FAN Qian |
| |
| Institution: | FAN Qian1,2(1.College of Civil Engineering,Fuzhou University,Fuzhou 350108,China,2.Digital Land Key Laboratory of Jiangxi Province,East China Institute of Technology,Fuzhou 344000,China) |
| |
| Abstract: | Because of the strong non-linear property of dam deformation,and the existence of slow learning speed,local minima of conventional BP neural network model,a new neural network learning model named extreme learning machine(ELM) method is applied to dam deformation prediction.The method can not only simplify the network parameter selection process,but also obviously improve the training speed of the network.Moreover,the ELM possesses favourable generalization performance.Through analyzing the results of an en... |
| |
| Keywords: | dam deformation prediction neural network extreme learning method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
