基于RNN模型的坝体和岩基区间参数反演方法研究

›› 2011, Vol. 32 ›› Issue (2): 547-552.

基于RNN模型的坝体和岩基区间参数反演方法研究

雷鹏^{1, 2, 3}，苏怀智⁴，张贵金¹

1.长沙理工大学水利工程学院，长沙 410114；2.中国水电顾问集团中南勘测设计研究院，长沙 410014； 3.武汉大学水利水电学院，武汉 430072；4.河海大学水利水电工程学院，南京 210098

收稿日期:2010-03-27 出版日期:2011-02-10 发布日期:2011-02-16
作者简介:雷鹏，男，1979年生，博士，讲师，主要从事大坝安全监测和数值计算方面的研究。
基金资助:
湖南省教育厅项目（No. 09C087）；国家自然科学基金（No. 50809025）；国家科技支撑计划课题（No. 2008BAB29B03）；国家重点实验室专项经费资助项目（No. 2009586912）；长沙理工大学人才引进基金资助项目（No. 1004271）。

Study of interval parameters back analysis of dam body and rock foundation based on RNN model

LEI Peng ^1－3, SU Huai-zhi⁴, ZHANG Gui-jin¹

1. School of Water Conservancy, Changsha University of Science and Technology, Changsha 410114, China; 2. Mid-south Design and Research Institute, China Hydropower Engineering Consulting Group Co, Changsha 410014, China; 3. School of Water Resources and Hydropower, Wuhan University, Wuhan 430072, China; 4. College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing 210098, China

Received:2010-03-27 Online:2011-02-10 Published:2011-02-16

摘要/Abstract

摘要：

针对混凝土大坝坝体和岩基参数的区间不确定性，构造具有区间分析功能的RNN（粗糙神经网络）模型，并运用该模型反演坝体和岩基区间参数值。应用区间有限元对结构进行正分析，根据区间参数反演的需要选取相应的区间学习样本，利用RNN模型对样本进行模式学习直至网络收敛，最后通过网络回想和反归一法得到坝体和岩基力学参数的区间值。研究结果表明，该方法可用于反演混凝土坝坝体和岩基区间力学参数，反演得到的区间参数值是合理的。此外，基于RNN模型的区间参数反演方法经过一定的拓展和改进，理论上可应用于反演其他类型的区间参数。

关键词: 粗糙神经网络, 区间有限元, 区间反分析, 不确定性参数

Abstract:

In light of the uncertainty of concrete dam and rock foundation parameters, a rough neural network (RNN) model is constructed and applied to interval parameters inversion of dam body and rock foundation. The RNN model is a combination of rough sets and BP-NN, which has the interval input and output just as rough sets and has a similar network structure to BP-NN. The steps of this method are as follows. Firstly, the structure is analyzed with interval finite element method. Secondly, the corresponding interval samples are chosen from interval FEM results according to special requirements for interval parameters inversion. Thirdly, the interval samples are trained continuously by RNN model until the error is less than a given threshold. Lastly, the interval parameters of dam body and rock foundation are calculated by means of network recollection and back normalization. It is shown that this method can be used to interval mechanical parameters inversion of dam body and rock foundation and the result is reasonable. Moreover, this interval analysis method based on RNN model theoretically can also be used to other interval parameters inversion after some expansion and improvement.

Key words: rough neural network, interval finite elements, interval back analysis, uncertain parameters

中图分类号:

TU 452

雷鹏，苏怀智，张贵金. 基于RNN模型的坝体和岩基区间参数反演方法研究[J]. , 2011, 32(2): 547-552.

LEI Peng , SU Huai-zhi, ZHANG Gui-jin. Study of interval parameters back analysis of dam body and rock foundation based on RNN model[J]. , 2011, 32(2): 547-552.

参考文献

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

本文评价

推荐阅读 10

[1]	向天兵，冯夏庭，陈炳瑞，江权，张传庆. 三向应力状态下单结构面岩石试样破坏机制与真三轴试验研究[J]. , 2009, 30(10): 2908 -2916 .
[2]	张常光，张庆贺，赵均海. 非饱和土抗剪强度及土压力统一解[J]. , 2010, 31(6): 1871 -1876 .
[3]	杨天鸿，陈仕阔，朱万成，刘洪磊，霍中刚，姜文忠. 煤层瓦斯卸压抽放动态过程的气-固耦合模型研究[J]. , 2010, 31(7): 2247 -2252 .
[4]	胡秀宏，伍法权. 岩体结构面间距的双参数负指数分布研究[J]. , 2009, 30(8): 2353 -2358 .
[5]	李卫超，熊巨华，杨敏. 分层土中水泥土围护结构抗倾覆验算方法的改进[J]. , 2011, 32(8): 2435 -2440 .
[6]	张桂民，李银平，施锡林，杨春和，王李娟. 一种交互层状岩体模型材料制备方法及初步试验研究[J]. , 2011, 32(S2): 284 -289 .
[7]	王伟李小春李强石露王颖白冰. 小尺度原位瞬态压力脉冲渗透性测试系统及试验研究[J]. , 2011, 32(10): 3185 -3189 .
[8]	李术才，赵岩，徐帮树，李利平，刘钦，王育奎 . 海底隧道涌水量数值计算的渗透系数确定方法[J]. , 2012, 33(5): 1497 -1504 .
[9]	王洪新，孙玉永 . 考虑基坑开挖宽度的杆系有限元算法及试验研究[J]. , 2012, 33(9): 2781 -2787 .
[10]	陈志坚，陈欣迪，唐勇，张宁宁 . 超大型深水群桩基础的传感器保护技术[J]. , 2012, 33(11): 3509 -3515 .