首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于GA-BP的渗透系数多目标反演分析模型研究
引用本文:高培培,章光,胡少华,武晓炜,文锋,刘志.基于GA-BP的渗透系数多目标反演分析模型研究[J].中国安全生产科学技术,2019,15(8):12-18.
作者姓名:高培培  章光  胡少华  武晓炜  文锋  刘志
作者单位:(1.武汉理工大学 安全科学与应急管理学院,湖北 武汉 430070;2.武汉理工大学 道路桥梁与结构工程湖北省重点实验室,湖北 武汉 430070)
基金项目:* 基金项目: 国家自然科学基金青年基金项目(51609184);道路桥梁与结构工程湖北省重点实验室(武汉理工大学)开放课题基金项目(DQJJ201705)
摘    要:针对渗透系数反演结果不唯一问题,以扬压力和渗流量2类渗流监测效应量为反演目标,建立了基于正交设计、有限元正分析和GA-BP相结合的渗透系数多目标反演分析模型。结合水口大坝2009—2018年渗流监测时间序列数据,开展了大坝坝体、坝基岩体渗透系数反演研究,并对反演结果进行了验证。研究结果表明:建立的渗透系数反演模型可较好地解决渗流单目标反演的缺陷,反演结果为绝对渗透系数,且反演结果真实可靠。

关 键 词:GA-BP神经网络  渗透系数  反演模型  正交设计

Research on multi objective inversion analysis model of permeability coefficient based on GA-BP
GAO Peipei,ZHANG Guang,HU Shaohua,' target="_blank" rel="external">,WU Xiaowei,WEN Feng,LIU Zhi.Research on multi objective inversion analysis model of permeability coefficient based on GA-BP[J].Journal of Safety Science and Technology,2019,15(8):12-18.
Authors:GAO Peipei  ZHANG Guang  HU Shaohua  " target="_blank">' target="_blank" rel="external">  WU Xiaowei  WEN Feng  LIU Zhi
Institution:(1.School of Safety Science and Emergency Management,Wuhan University of Technology,Wuhan Hubei 430070,China;2.Hubei Key Laboratory of Roadway Bridge and Structure Engineering,Wuhan University of Technology,Wuhan Hubei 430070,China)
Abstract:Aiming at the problem that the inversion results of permeability coefficient were not unique,two kinds of seepage monitoring effect quantities including the uplift pressure and the seepage quantity were used as the inversion objectives,and the multi objective inversion analysis model of permeability coefficient based on the combined methods of orthogonal design,finite element positive analysis and GA-BP was established.Combined with the time series data of the seepage monitoring in the Shuikou dam from 2009 to 2018,the inversion research on the permeability coefficients of the dam and dam foundation rock mass was carried out,and the inversion results were verified.The results showed that the inversion model of permeability coefficient could solve the defect of seepage single objective inversion better.The inversion results were the absolute permeability coefficients,which were true and reliable.
Keywords:GA-BP neural network  permeability coefficient  inversion model  orthogonal design
本文献已被 CNKI 等数据库收录!
点击此处可从《中国安全生产科学技术》浏览原始摘要信息
点击此处可从《中国安全生产科学技术》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号