基于SSA-MSVR的混凝土拱坝材料参数反演模型
作者:
作者单位:

(1.西安理工大学省部共建西北旱区生态水利国家重点实验室,陕西 西安 710048;2.西安理工大学水利水电学院,陕西 西安 710048 )

作者简介:

杨杰(1971—),男,教授,博士,主要从事水工结构与大坝安全监测研究。E-mail:xautyangj@126.com

通讯作者:

中图分类号:

TV37

基金项目:

国家自然科学基金项目(52109166)


Inversion model of material parameters for concrete arch dams based on SSA-MSVR
Author:
Affiliation:

(1.State Key Laboratory of Eco-Hydraulics in Northwest Arid Region, Xi’an University of Technology, Xi’an 710048, China;2.Institute of Water Resources and Hydroelectric Engineering, Xi’an University of Technology, Xi’an 710048, China)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 文章评论
    摘要:

    为进一步提高混凝土拱坝材料参数获取的准确性,构建了基于多输出支持向量回归(MSVR)和麻雀搜索算法(SSA)的混凝土拱坝材料参数反演模型。为了快速模拟坝体径向位移与材料参数的非线性关系,建立了高精度的MSVR模型代替有限元模型计算,并利用SSA对所需参数进行寻优反演。工程实例验证结果表明:构建的反演模型计算精度高,计算速度快,能快速反演坝体与坝基材料参数,可用于实际工程的材料参数反演分析。

    Abstract:

    To further improve the accuracy of obtaining material parameters for concrete arch dams, a material parameter inversion model based on multi-output support vector regression (MSVR) and sparrow search algorithm (SSA) was constructed. To quickly simulate the nonlinear relationship between radial displacement of dam body and material parameters, a high-precision MSVR model was established instead of the finite element model calculation, and SSA was used to optimize and invert the required parameters.The verification results of engineering examples show that the constructed inversion model has high calculation accuracy and fast calculation speed, which can quickly invert the material parameters of the dam body and dam foundation, and can be used for the inversion analysis of material parameters in actual engineering.

    参考文献
    相似文献
    引证文献
引用本文

杨杰,刘智,宋锦焘,等.基于SSA-MSVR的混凝土拱坝材料参数反演模型[J].水利水电科技进展,2023,43(5):53-57.(YANG Jie, LIU Zhi, SONG Jintao, et al. Inversion model of material parameters for concrete arch dams based on SSA-MSVR[J]. Advances in Science and Technology of Water Resources,2023,43(5):53-57.(in Chinese))

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-11-12
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2023-09-18
  • 出版日期: