| 基于EKF的神经网络在变形预测中的应用 |
| |
| 引用本文： | 蒋霖,文鸿雁.基于EKF的神经网络在变形预测中的应用[J].桂林工学院学报,2006,26(1):66-68. |
| |
| 作者姓名： | 蒋霖 文鸿雁 |
| |
| 作者单位： | 桂林工学院,土木工程系,广西,桂林,541004 |
| |
| 基金项目： | 国家自然科学基金资助项目(40574002)，广西自然科学基金资助项目(桂科自0339072) |
| |
| 摘 要： | 给出了一种用于变形预测的基于扩展Kalman滤波的神经网络学习算法,与BP算法相比,该方法具有更好的收敛率和学习能力.实例计算表明,该方法具有较高的精度和较快的计算速度.
|
| 关 键 词： | 变形预测 神经网络 扩展Kalman滤波 |
| 文章编号： | 1006-544X(2006)01-0066-03 |
| 收稿时间： | 2005-05-18 |
| 修稿时间： | 2005年5月18日 |
Application of neural network based on the extended Kalman filter to deformation prediction |
| |
| JIANG Lin,WEN Hong-yan.Application of neural network based on the extended Kalman filter to deformation prediction[J].Journal of Guilin University of Technology,2006,26(1):66-68. |
| |
| Authors: | JIANG Lin WEN Hong-yan |
| |
| Affiliation: | Department of Civil Engineering, Guilin University of Technology, Guilin 541004, China |
| |
| Abstract: | A new learning algorithm for a multilayered neural network based on extended Kalman filter is proposed to predict the deformation of structure.The EKF learning algorithm is better than the BP algorithm as convergence is improved and can provide much more accuracy learning results.Experiments in forecasting the deformation of structure prove that the proposed algorithm has much more accuracy and faster speed. |
| |
| Keywords: | deformation prediction neural network extended Kalman filter |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
