| 基于改进BP神经网络模型的地面沉降预测及分析 |
| |
| 引用本文： | 李红霞,赵新华,迟海燕,张建军.基于改进BP神经网络模型的地面沉降预测及分析[J].天津大学学报(自然科学与工程技术版),2009,42(1):60-64. |
| |
| 作者姓名： | 李红霞 赵新华 迟海燕 张建军 |
| |
| 作者单位： | 李红霞,赵新华,迟海燕,LI Hong-xia,ZHAO Xin-hua,CHI Hai-yan(天津大学环境科学与工程学院,天津,300072);张建军,ZHANG Jian-jun(天津市环境保护科学研究院,天津,300191)
|
| |
| 基金项目： | 国家重点基础研究发展规划(973计划)，国家自然科学基金 |
| |
| 摘 要： | 针对区域性地面沉降问题，用遗传算法优化BP神经网络的初始权重，建立了地面沉降预测模型．该模型克服了BP神经网络模型存在的收敛速度慢、易陷入局部极小点的缺点采用后验差检验法对模型拟合结果进行了检验，结果表明模型具有很好地拟合与泛化能力．应用该模型对地下水位影响强度进行了分析，表明地面沉降与地下水位存在一致响应趋势．
|
| 关 键 词： | 地面沉降 BP神经网络 遗传算法 初始权值 后验差检验 |
Prediction and Analysis of Land Subsidence Based on Improved BP Neural Network Model |
| |
| LI Hong-xia,ZHAO Xin-hua,CHI Hai-yan,ZHANG Jian-jun.Prediction and Analysis of Land Subsidence Based on Improved BP Neural Network Model[J].Journal of Tianjin University(Science and Technology),2009,42(1):60-64. |
| |
| Authors: | LI Hong-xia ZHAO Xin-hua CHI Hai-yan ZHANG Jian-jun |
| |
| Institution: | LI Hong-xia, ZHAO Xin-hua, CHI Hai-yan, ZHANG Jian-jun ( 1. School of Environmental Science and Engineering, Tianjin University, Tianjin 300072, China; 2. Tianjin Academy of Environmental Sciences, Tianjin 300191, China) |
| |
| Abstract: | In order to control land subsidence efficiently, a coupling model of genetic algorithm and back-propagation （BP） neural network was applied to the simulation of land subsidence, aiming at overcoming shortcomings of the BP neural network model, such as falling into local minimum value easily and being slow in convergence. The coupling model passed the posterior-variance-test and good fitting and generalization were obtained. The results calculated through the proposed model indicate that the variation of land subsidence rate in the researched district has consistent tendency with underground water level. |
| |
| Keywords: | land subsidence BP neural network genetic algorithm primary weights posterior-variance-test |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
