| 基于动量BP算法的过渡段路基沉降预测 |
| |
| 引用本文： | 魏静,蒲兴波,钱耀峰,李军昌.基于动量BP算法的过渡段路基沉降预测[J].北方交通大学学报,2012(1):52-55,62. |
| |
| 作者姓名： | 魏静 蒲兴波 钱耀峰 李军昌 |
| |
| 作者单位： | [1]北京交通大学土木建筑工程学院,北京100044 [2]中铁二十一局集团公司,甘肃兰州730102 |
| |
| 基金项目： | 中央高校基本科研业务费专项资金资助（2009JBM079）;2010、2011年大学生创新实验项目资助 |
| |
| 摘 要： | 利用动量BP算法改进了BP神经网络的收敛性，建立了过渡段路基沉降预测模型．该模型可克服传统BP神经网络收敛速度慢、易陷入局部最优等的缺点．结合津秦客运专线路桥过渡段路基沉降实测数据，将该优化模型与传统BP神经网络预测模型进行了对比．计算表明，利用动量BP算法改进的神经网络具有较高的预测精度，同时考虑了多个影响因素，因而具有广阔的应用前景．
|
| 关 键 词： | 动量BP算法 过渡段 沉降预测 神经网络 |
Subgrade settlement prediction of transition section based on momentum back-propagation |
| |
| WEI Jing,PU Xingbo,QIAN Yaofeng,LI Junchang.Subgrade settlement prediction of transition section based on momentum back-propagation[J].Journal of Northern Jiaotong University,2012(1):52-55,62. |
| |
| Authors: | WEI Jing PU Xingbo QIAN Yaofeng LI Junchang |
| |
| Institution: | 1. School of Civil Engineering, Beijing J iaotong University, Beijing 100044, China; 2. China Railway 21st Bureau, Lanzhou Gansu 730102, China) |
| |
| Abstract: | With the momentum back-propagation method, this paper improved the convergence oi BP neural network and developed a prediction model for subgrade settlement of transition section. The model overcame the disadvantages of traditional BP neural network, such as slow convergence speed and easy running into local optimum. Based on test data of the transition section between bridge and subgrade in Tianjin-Qinhuangdao high speed railway, this paper compared the optimization model with the traditional BP neural network model. The results indicate that the neural network improved by momentum BP algorithm has higher predictive accuracy, and it can consider multiple influence factors simultaneously. As a consequence, it has broad application prospect. |
| |
| Keywords: | momentum back-propagation transition section prediction of settlement neural network |
| 本文献已被 维普 等数据库收录！ |
|
