Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2019, Vol. 59 Issue (5): 345-353    DOI: 10.16511/j.cnki.qhdxxb.2018.25.058
  水利水电工程 本期目录 | 过刊浏览 | 高级检索 |
碾压混凝土坝层面抗剪断强度的人工神经网络与模糊逻辑系统预测
申嘉荣, 徐千军
清华大学 水沙科学与水利水电工程国家重点实验室, 北京 100084
Prediction of interlayer shear strength parameters for RCC dams using artificial neural network and fuzzy logic system
SHEN Jiarong, XU Qianjun
State Key Laboratory of Hydroscience and Engineering, Tsinghua University, Beijing 100084, China
全文: PDF(1541 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 碾压混凝土坝层面抗剪断强度与其影响因素之间是不确定性和非线性的。该文基于人工神经网络与模糊逻辑系统方法对碾压混凝土坝层面抗剪断强度参数进行预测。将水胶比、胶凝材料含量、粉煤灰掺量、层面处理方式、层面间隔时间作为模型输入参数,抗剪断强度参数f'和c'作为输出参数,考虑室内试验和现场原位试验2种不同情况,建立人工神经网络与模糊逻辑系统预测模型。模型训练与测试结果表明:人工神经网络的预测精度优于模糊逻辑系统,室内试验的预测精度优于现场原位试验。人工神经网络与模糊逻辑系统模型预测值与试验值符合情况均较理想,可以作为层面抗剪断强度的预测方法,为混凝土层面结合性能评估提供依据。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
申嘉荣
徐千军
关键词 碾压混凝土坝人工神经网络模糊逻辑系统抗剪断强度    
Abstract:Predicting the shear strength of roller compacted concrete dams always involves uncertainty and nonlinearities that are influenced by various factors. This study used the artificial neural network and the fuzzy logic system to predict the interlayer shear strength parameters of RCC dams. The data input to the artificial neural network and the fuzzy logic system was divided into data sets from lab tests and data sets from in-situ shear strength tests with five input parameters for the water-binder ratio, total amount of binder, fly ash content, interlayer processing methods and time intervals with two output parameters for f' and c'. The training and testing results show that the lab tests have better correlations than the in-situ tests. Moreover, the artificial neural network has better prediction accuracy than the fuzzy logic system. The predicted values from both the artificial neural network and the fuzzy logic system are in good agreement with the test data. Thus, both models can be used to predict the shear strength parameters and can provide reference predictions for evaluating combinations of layers.
Key wordsroller compacted concrete dams    artificial neural networks    fuzzy logic systems    shear strength
收稿日期: 2018-07-20      出版日期: 2019-05-14
基金资助:国家重点研发计划课题(2017YFC0804602);国家自然科学基金资助项目(51839007,51879141);水沙科学与水利水电工程国家重点实验室自主科研课题(2016-KY-05)
通讯作者: 徐千军,教授,E-mail:qxu@tsinghua.edu.cn     E-mail: qxu@tsinghua.edu.cn
引用本文:   
申嘉荣, 徐千军. 碾压混凝土坝层面抗剪断强度的人工神经网络与模糊逻辑系统预测[J]. 清华大学学报(自然科学版), 2019, 59(5): 345-353.
SHEN Jiarong, XU Qianjun. Prediction of interlayer shear strength parameters for RCC dams using artificial neural network and fuzzy logic system. Journal of Tsinghua University(Science and Technology), 2019, 59(5): 345-353.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2018.25.058  或          http://jst.tsinghuajournals.com/CN/Y2019/V59/I5/345
  图1 BP网络结构图
  表1 碾压混凝土坝层面抗剪断强度实际样本数据
  图2 人工神经网络结构图
  图3 模糊系统组成
  图4 输入变量对应的隶属度函数
  图5 输出变量对应的隶属度函数
  图6 室内试验人工神经网络预测结果
  表2 室内试验模型误差分析
  图7 室内试验模糊逻辑预测结果
  图8 原位试验人工神经网络预测结果
  表3 原位试验模型误差分析
  图9 原位试验模糊逻辑预测结果
[1] 田育功. 碾压混凝土快速筑坝技术[M]. 北京:中国水利水电出版社, 2010. TIAN Y G. Rapid dam construction technology for roller compacted concrete dams[M]. Beijing:China Water & Power Press, 2010. (in Chinese)
[2] 张严明, 王圣培, 潘罗生. 中国碾压混凝土坝20年[M]. 北京:中国水利水电出版社, 2006. ZHANG Y M, WANG S P, PAN L S. 20 years of roller compacted dams in China[M]. Beijing:China Water & Power Press, 2006. (in Chinese)
[3] 张建文, 文家海, 申茂夏. 龙滩水电站碾压混凝土重力坝施工与管理[M]. 北京:中国水利水电出版社, 2007. ZHANG J W, WEN J H, SHEN M X. Longtan Hydropower Station construction and management of RCC gravity dam[M]. Beijing:China Water & Power Press, 2007. (in Chinese)
[4] 石妍, 方坤河, 高钟伟. 碾压混凝土强度特性的研究[J]. 水力发电学报, 2006, 25(1):85-89. SHI Y, FANG K H, GAO Z W. Research on strength of roller compacted concrete[J]. Journal of Hydroelectric Engineering, 2006, 25(1):85-89. (in Chinese)
[5] 王怀亮, 宋玉普. 多轴应力条件下碾压混凝土层面抗剪强度试验研究[J]. 水利学报, 2011, 42(9):1095-1101, 1109. WANG H L, SONG Y P. Mechanical properties of roller compacted concrete under multiaxial stress state[J]. Journal of Hydraulic Engineering, 2011, 42(9):1095-1101, 1109. (in Chinese)
[6] 林长农, 金双全, 涂传林. 龙滩有层面碾压混凝土的试验研究[J]. 水力发电学报, 2001(3):117-129. LIN C N, JIN S Q, TU C L. Experiment researches on RCC with layer surfaces for Longtan project[J]. Journal of Hydroelectric Engineering, 2001(3):117-129. (in Chinese)
[7] 刘数华, 曾力, 吴定燕. 提高碾压混凝土层面粘结性能的试验研究[J]. 水力发电学报, 2004, 23(3):61-65. LIU S H, ZENG L, WU D Y. Testing research on improvement of layer adhesion of roller compacted concrete[J]. Journal of Hydroelectric Engineering, 2004, 23(3):61-65. (in Chinese)
[8] 黄志强, 宋玉普, 王学志. 碾压混凝土层面拉伸破坏试验研究[J]. 大连理工大学学报, 2007, 47(3):387-391. HUANG Z Q, SONG Y P, WANG X Z. Experimental research on tensile failure process in rolled compacted concrete layer[J]. Journal of Dalian University of Technology, 2007, 47(3):387-391. (in Chinese)
[9] SARIDEMIR M, TOPÇU İ B, ÖZCAN F, et al. Prediction of long-term effects of GGBFS on compressive strength of concrete by artificial neural networks and fuzzy logic[J]. Construction and Building Materials, 2009, 23(3):1279-1286.
[10] PALA M, ÖZBAY E, ÖZTAŞ A, et al. Appraisal of long-term effects of fly ash and silica fume on compressive strength of concrete by neural networks[J]. Construction and Building Materials, 2007, 21(2):384-394.
[11] TOPÇU İ B, SARIDEMIR M. Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic[J]. Computational Materials Science, 2008, 41(3):305-311.
[12] TOPÇU İ B, SARIDEMIR M. Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic[J]. Computational Materials Science, 2008, 42(1):74-82.
[13] KEWALRAMANI M A, GUPTA R. Concrete compressive strength prediction using ultrasonic pulse velocity through artificial neural networks[J]. Automation in Construction, 2006, 15(3):374-379.
[14] ÖZTAŞ A, PALA M, ÖZBAY E, et al. Predicting the compressive strength and slump of high strength concrete using neural network[J]. Construction and Building Materials, 2006, 20(9):769-775.
[15] TAYFUR G, ERDEM T K, KIRCA Ö. Strength prediction of high-strength concrete by fuzzy logic and artificial neural networks[J]. Journal of Materials in Civil Engineering, 2014, 26(11):04014079.
[16] 石妍, 方坤河. 碾压混凝土耐久性的神经网络预测方法[C]//第五届碾压混凝土坝国际研讨会论文集. 贵阳:中国水利学会, 中国水力发电工程学会, 2007. SHI Y, FANG K H. Neural network prediction method for durability of roller compacted concrete[C]//Proceedings of the International Symposium on Roller Compacted Concrete Dams. Guiyang:Chinese Hydraulic Engineering Society, China Society for Hydropower Engineering, 2007. (in Chinese)
[17] 李国勇, 杨丽娟. 神经·模糊·预测控制及其MATLAB实现[M]. 第3版. 北京:电子工业出版社, 2013. LI G Y, YANG L J. Neural network·fuzzy logic·predictive control and realization by MATLAB[M]. 3rd ed. Beijing:Publishing House of Electronics Industry, 2013. (in Chinese)
[18] 毛剑英, 何先莉. 人工神经网络在化学和环境科学中应用的若干问题[J]. 中国环境监测, 2001, 17(5):48-50. MAO J Y, HE X L. The problems of application of artificial neural networks in chemistry and environmental science[J]. Environmental Monitoring in China, 2001, 17(5):48-50. (in Chinese)
[19] 王宏硕. 碾压混凝土坝层面抗剪断强度的探讨[J]. 湖北水利发电, 1995(3):17-21, 31. WANG H S. Discussion on shear strength of roller compacted concrete dams[J]. Hubei Water Power, 1995(3):17-21, 31. (in Chinese)
[20] 王迎春. 碾压混凝土层面结合特性和质量标准研究[D]. 杭州:浙江大学, 2007. WANG Y C. Study on specific characteristics and qualification requirements of lift joints in roller compacted concrete[D]. Hangzhou:Zhejiang University, 2007. (in Chinese)
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn