基于SSA-BP与SSA的地下水污染源反演识别

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1113 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要应用基于SSA-BP神经网络替代模型的模拟-优化方法和SSA研究了地下水污染源位置及释放历史的反演识别问题。并在建立地下水水流模型时,应用Cholesky分解方法建立含水层渗透系数连续场,该方法相比于普通的参数分区方法更好地描述了水文地质参数的非均质性。结果表明:SSA-BP神经网络替代模型对模拟模型具有较高的逼近精度,其平均相对误差仅有3.21%。应用SSA求解优化模型,能够快速准确地识别出点污染源的位置及释放历史。SSA对污染源位置的反演识别相对误差在10%左右,对污染源源强的反演识别相对误差不超过4%。因此,本文所提出的方法是一种有效的地下水污染源识别方法,可为污染责任认定及污染修复方案的优化提供参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	葛渊博
	卢文喜
	白玉堃
	潘紫东

关键词 ：污染源反演识别, 模拟-优化方法, 替代模型, 麻雀搜索算法, SSA-BP神经网络替代模型

Abstract：The simulation-optimization method based on SSA-BP neural network alternative model and SSA were applied to study the inverse identification of groundwater pollution source location and release history. And the Cholesky decomposition method was applied to establish the continuous field of aquifer permeability coefficients in the groundwater flow model, which better describes the non-homogeneity of hydrogeological parameters compared with the common parameter partitioning method. The results showed that the SSA-BP neural network alternative model has a high approximation accuracy for the simulation model, and its average relative error is only 3.21%. The relative error of SSA in the inverse identification of source location is about 10%, and the relative error of SSA in the inverse identification of source intensity does not exceed 4%. Therefore, the proposed method is an effective groundwater pollution source identification method, which can provide reference for pollution responsibility identification and pollution remediation plan optimization.

Key words： pollution source inversion identification simulation-optimization method alternative model sparrow search algorithm SSA-BP neural network alternative model

收稿日期: 2022-04-21

PACS:

X523

基金资助:国家自然科学基金资助项目(41972252);国家重点研发计划资助项目(2018YFC1800405)

通讯作者: 卢文喜,教授,luwenxi@jlu.edu.cn E-mail: luwenxi@jlu.edu.cn

作者简介: 葛渊博(1999-),男,甘肃定西人,吉林大学硕士研究生,主要从事地下水污染源反演识别研究。发表论文1篇。

引用本文:

葛渊博, 卢文喜, 白玉堃, 潘紫东. 基于SSA-BP与SSA的地下水污染源反演识别[J]. 中国环境科学, 2022, 42(11): 5179-5187. GE Yuan-bo, LU Wen-xi, BAI Yu-kun, PAN Zi-dong. Inversion and identification of groundwater pollution sources based on SSA-BP and SSA. CHINA ENVIRONMENTAL SCIENCECE, 2022, 42(11): 5179-5187.

链接本文:

http://www.zghjkx.com.cn/CN/ 或 http://www.zghjkx.com.cn/CN/Y2022/V42/I11/5179

[1]	王宝燕,肖巍.地下水污染现状与防治对策研究[J]. 环境与发展, 2020,32(10):38-39. Wang B Y, Xiao W. Study on the status of groundwater pollution and prevention measures[J]. Environment and Development, 2020,32(10):38-39.
[2]	杨贞,张振师.国内外地下水修复技术应用现状及发展趋势[C]//中国环境科学学会.2020中国环境科学学会科学技术年会论文集(第三卷).中国环境科学学会:中国环境科学学会, 2020:4. Yang Z, Zhang Z S. Current status and development trend of groundwater remediation technology application at home and abroad[C]//Proceedings of the 2020 Annual Scientific and Technical Conference of the Chinese Society for Environmental Sciences (Volume III). Chinese Society of Environmental Science:Chinese Society of Environmental Science, 2020:4.
[3]	李媛,王国锋,郑江,等.基于MOLDFLOW的某污染地块地下水重金属污染风险评价[J]. 江西科学, 2021,39(5):810-815,833. Li Y, Wang G F, Zheng J, et al. Risk assessment of heavy metal contamination in groundwater of a contaminated site based on MOLDFLOW[J]. Jiangxi Science, 2021,39(5):810-815,833.
[4]	徐亚宁,卢文喜,王梓博,等.考虑参数和边界条件不确定性的地下水污染随机模拟[J]. 中国环境科学, 2022,42(7):Xu Y N, Lu W X, Wang Z B, et al. Stochastic simulation of groundwater pollution considering parameter and boundary condition uncertainties[J]. China Environmental Science, 2022,42(7):
[5]	时延锋.SCEUA算法在地下水污染溯源中的应用研究[D]. 济南:济南大学, 2015. Shi Y F. Research on the application of SCEUA algorithm in groundwater pollution traceability[D]. Jinan:Jinan University, 2015.
[6]	王景瑞,胡立堂.地下水污染源识别的数学方法研究进展[J]. 水科学进展, 2017,28(6):943-952. Wang J R, Hu L T. Research progress of mathematical methods for groundwater pollution source identification[J]. Advances in Water Science, 2017,28(6):943-952.
[7]	袁乾,卢文喜,范越,等.基于替代模型的煤矸石堆地下水污染随机模拟[J]. 中国环境科学, 2019,39(6):2444-2451. Yuan Q, Lu W X, Fan Y, et al. Stochastic simulation of coal gangue pile groundwater pollution based on alternative models[J]. China Environmental Science, 2019,39(6):2444-2451.
[8]	仝晓霞,宁立波,董少刚.运用GMS模型对某垃圾场地下水污染的研究[J]. 环境科学与技术, 2012,35(7):197-201. Tong X X, Ning L B, Dong S G. Study of groundwater pollution in a landfill using GMS model[J]. Environmental Science and Technology, 2012,35(7):197-201.
[9]	杜守营,鹿帅,杜尚海.基于GMS的地下水流数值模拟及参数敏感性分析[J]. 中国农村水利水电, 2013,(8):77-80. Du S Y, Lu S, Du S H. Numerical simulation and parameter sensitivity analysis of groundwater flow based on GMS[J]. China Rural Water Conservancy and Hydropower, 2013,(8):77-80.
[10]	颜萍,邢芳,徐世光,等.基于GMS软件对保山某尾矿库地下水污染的数值模拟研究[J]. 地质灾害与环境保护, 2019,30(3):102-107. Yan P, Xing F, Xu S G, et al. Numerical simulation study of groundwater pollution in a tailing pond in Baoshan based on GMS software[J]. Geological Hazards and Environmental Protection, 2019,30(3):102-107.
[11]	Queipo N V, Haftka R T, Shyy W, et al. Surrogate-based analysis and optimization[J]. Progress in Aerospace Sciences, 2005,41(1):1-28.
[12]	Bhosekar A, Ierapetritou M. Advances in surrogate based modeling, feasibility analysis, and optimization:A review[J]. Computers & Chemical Engineering, 2018,108:250-267.
[13]	Yan S Q, Minsker B. Optimal groundwater remediation design using an Adaptive Neural Network Genetic Algorithm[J]. Water Resources Research, 2006,42(5):5407-5420.
[14]	王梓博,卢文喜,王涵,等.某钼矿尾矿库地下水污染的随机模拟[J]. 中国环境科学, 2020,40(5):2124-2131. Wang Z B, Lu W X, Wang H, et al. Stochastic simulation of groundwater pollution in a molybdenum mine tailing pond[J]. China Environmental Science, 2020,40(5):2124-2131.
[15]	侯泽宇,王宇,卢文喜.地下水DNAPLs污染修复多相流模拟的替代模型[J]. 中国环境科学, 2019,39(7):2913-2920. Hou Z Y, Wang Y, Lu W X. Alternative models for multiphase flow simulation of groundwater DNAPLs pollution remediation[J]. China Environmental Science, 2019,39(7):2913-2920.
[16]	王宇,卢文喜,卞建民,等.基于小波神经网络的地下水流数值模拟模型的替代模型研究[J]. 中国环境科学, 2015,35(1):139-146. Wang Y, Lu W X, Bian J M, et al. Alternative modeling of groundwater flow numerical simulation model based on wavelet neural network[J]. China Environmental Science, 2015,35(1):139-146.
[17]	Yoon J H, Shoemaker C A. Comparison of optimization methods for ground-water bioremediation[J]. Journal of Water Resources Planning and Management-Asce, 1999,125(1):54-63.
[18]	江思珉,张亚力,蔡奕,等.单纯形模拟退火算法反演地下水污染源强度[J]. 同济大学学报(自然科学版), 2013,41(2):253-257. Jiang S M, Zhang Y L, Cai Y, et al. Inversion of groundwater pollution source intensity by simplex simulated annealing algorithm[J]. Journal of Tongji University (Natural Science Edition), 2013,41(2):253-257.
[19]	王敬,韩忠,梁浩,等.地下水污染强度反演识别的SCE-UA算法[J]. 中国农村水利水电, 2020,(12):106-111. Wang J, Han Z, Liang H, et al. SCE-UA algorithm for groundwater pollution intensity inversion identification[J]. China Rural Water Conservancy and Hydropower, 2020,(12):106-111.
[20]	肖传宁,卢文喜,赵莹,等.基于径向基函数模型的优化方法在地下水污染源识别中的应用[J]. 中国环境科学, 2016,36(7):2067-2072. Xiao C N, Lu W x, Zhao Y, et al. Application of optimization method based on radial basis function model in groundwater pollution source identification[J]. China Environmental Science, 2016,36(7):2067-2072.
[21]	张江江.地下水污染源解析的贝叶斯监测设计与参数反演方法[D].杭州:浙江大学, 2017. Zhang J J. Bayesian monitoring design and parameter inversion method for groundwater pollution source analysis[D]. Hangzhou:Zhejiang University, 2017.
[22]	Xue J K, Shen B. A novel swarm intelligence optimization approach:sparrow search algorithm[J]. Systems Science & Control Engineering, 2020,8(1):22-34.
[23]	郭名诚,侯珂,李鑫浩.基于SSA-BPNN模型的Web服务质量评价[J]. 信息技术与信息化, 2021,(10):13-15. Guo M C, Huo K, Li X H. Web service quality evaluation based on SSA-BPNN model[J]. Information Technology and Informatization, 2021,(10):13-15.
[24]	孙全,孙渊.基于麻雀搜索算法的BP神经网络优化技术[J]. 上海电机学院学报, 2022,25(1):12-16. Sun Q, Sun Y. BP neural network optimization technique based on sparrow search algorithm[J]. Journal of Shanghai Institute of Electrical Engineering, 2022,25(1):12-16.