基于稀疏环境监测点的流动时程重构模型精度研究  

Accuracy of environmental flows time history reconstruction model based on sparse observation

作　　者：战庆亮 刘鑫 晁阳 葛耀君[2] ZHAN Qing-liang;LIU Xin;CHAO Yang;GE Yao-jun(College of Transportation Engineering,Dalian Maritime University,Dalian 116026,China;College of Civil Engineering,Tongji University,Shanghai 200092,China)

机构地区：[1]大连海事大学交通运输工程学院,辽宁大连116026 [2]同济大学土木工程学院,上海200092

出　　处：《中国环境科学》2023年第12期6592-6600,共9页China Environmental Science

基　　金：桥梁结构抗风技术交通行业重点实验室(上海)开放课题(KLWRTBMC21-02);大连海事大学博联科研基金资助项目(3132023619);国家自然科学基金资助项目(51978527);辽宁教育厅研究计划项目(LJKZ0052)。

摘　　要：根据有限数量且稀疏分布的环境流场监测点处的观测数据,得到更多空间位置处的环境测点的流动时变信息,能够为大气监测、水体监测和污染物扩散等问题的控制与研究提供更加丰富的数据.本文研究了物理约束对机器学习流场时程表征模型的精度影响规律,研究了可用测点数以及物理约束权重对重构精度的影响.以低雷诺数方柱大气绕流为例,开展了基于稀疏环境监测点的数据进行高空间分辨率流场时程重构的精度研究.研究发现当监测点数量增至500时精度不再提高;当监测点数量仅有50时,约束权重为10可得到最优结果.结果表明,通过选择合适的物理约束影响权重,可以有效弥补可用数据较少的问题,为环境流动问题的数据处理和高分辨率流场重构提供了新的方法与依据.Obtaining more environmental flow data at more monitoring sites based on limited and sparse available flow monitoring points can provide data for the study of atmospheric monitoring,water monitoring and pollutant dispersion issues.In this study,the influence of physical constraints on the accuracy of the machine learning flow field time history representation model was investigated,and the results of different available measurement points and physical constraint influence weights were compared.The environmental flow around a low Reynolds number square column was tested as an example.Results show that when the number of monitoring points was increased to 500,the accuracy did not improve.When the number of monitoring points was reduced to only 50,the error was minimised when the physical constraint weights were set to 10.The results indicate that the problem of less available data can be effectively compensated by choosing appropriate physical constraint influence weights.Providing a new method and basis for data processing and high-resolution flow field reconstruction for environmental flow problems.

关 键 词：环境流场时程 稀疏监测点 环境流场重构 物理约束 测点数量 

分 类 号：X83[环境科学与工程—环境工程]