摘要
应用基于核极限学习机替代模型的模拟-优化理论和方法研究解决了地下水DNAPLs污染源及含水层参数的同步反演识别问题.结果表明:1)核极限学习机替代模型对模拟模型有较高的逼近精度,能够识别并模仿模拟模型的输入-输出关系,绝大部分相对误差小于5%,平均相对误差仅有2.98%;2)以替代模型代替模拟模型,大幅度地减小了模拟-优化过程的计算负荷,将反演识别时间由传统方法的83天减少到3小时,并能够保持较高的计算精度;3)应用基于模拟退火的粒子群优化算法求解优化模型,能够以较快的速度搜寻到全局最优,同时避免搜索过程陷于局部极小解.
Groundwater contamination source identification(GCSI) is critical for taking effective actions in designing remediation strategies, estimating risks, and confirming responsibility. Surrogate-based simulation-optimization technique was applied to source identification and parameter estimation of DNAPLs-contaminated aquifer in this article. The results showed that: 1) kernel extreme learning machines(KELM) surrogate model approximated the simulation model accurately. It could simulate the input/output relationship of the simulation model with most of the relative errors less than 5%, and the mean relative error was only 2.98%; 2) Replacing the simulation model with a KELM model considerably reduced the computational burden of the simulation-optimization process and maintained high computation accuracy, the identification time was reduced to 3hours from 83days; 3) Simulated annealing-based particle swarm optimization algorithm is efficient in searching the global optimal solution of the nonlinear programming optimization model, and avoiding the optimization process trapping into local optimum.
引文
[1]Qin X S,Huang G H,He L.Simulation and optimization technologies for petroleum waste management and remediation process control[J].Journal of Environmental Management,2009,90(1):54-76.
[2]Ayvaz M T.A linked simulation-optimization model for solving the unknown groundwater pollution source identification problems[J].Journal of Contaminant Hydrology,2010,117(1-4):46-59.
[3]赵莹.基于模拟-优化方法的地下水污染源反演识别[D].长春:吉林大学,2017.Zhao Y.Inversion identification of groundwater pollution source based on simulation-optimization method[D].Changchun:Jilin University,2017.
[4]Sun N Z.Inverse problems in groundwater modeling[M].Springer Netherlands,2009.
[5]张宇.基于随机统计方法的地下水污染源反演识别研究[D].长春:吉林大学,2016.Zhang Y.Inversion recognition of groundwater pollution source based on stochastic statistical method[D].Changchun:Jilin University,2016.
[6]Mahinthakumar G K,Sayeed M.Hybrid genetic algorithm-Local search methods for solving groundwater source identification inverse problems[J].Journal of Water Resources Planning and Management,2005,131(1):45-57.
[7]Liu X,Cardiff M A,Kitanidis P K.Parameter estimation in nonlinear environmental problems[J].Stochastic Environmental Research and Risk Assessment,2010,24(7):1003-1022.
[8]Wang H,Jin X.Characterization of groundwater contaminant source using Bayesian method[J].Stochastic Environmental Research and Risk Assessment,2013,27(4):867-876.
[9]Gurarslan G,Karahan H.Solving inverse problems of groundwaterpollution-source identification using a differential evolution algorithm[J].Hydrogeology Journal,2015,23(6):1109-1119.
[10]顾文龙.基于MCMC方法的地下水污染源反演识别[D].长春:吉林大学,2017.Gu W L.Inversion identification of groundwater pollution source based on MCMC method[D].Changchun:Jilin University,2017.
[11]Srivastava D,Singh R M.Breakthrough curves characterization and identification of an unknown pollution source in groundwater system using an artificial neural network(ANN)[J].Environmental Forensics,2014,15(2):175-189.
[12]Zhao Y,Lu W X,Xiao C N.A Kriging surrogate model coupled in simulation-optimization approach for identifying release history of groundwater sources[J].Journal of Contaminant Hydrology,2016,185:51-60.
[13]肖传宁.地下水污染源反演识别研究[D].长春:吉林大学,2017.Xiao C N.Inversion identification of groundwater pollution sources[D].Changchun:Jilin University,2017.
[14]李守巨,刘迎曦.基于蚁群算法的地下水污染源辨识方法[J].计算机科学,2005,32(8):289-291.Li S J,Liu Y X.Groundwater pollution source identification method based on ant colony algorithm[J].Computer Science,2005,32(8):289-291.
[15]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,Xai Y.Inversion of groundwater pollution source intensity by simplex simulated annealing algorithm[J].Journal of Tongji University(Natural Science Edition),2013,41(2):253-257.
[16]Jha M,Datta B.Application of dedicated monitoring-network design for unknown pollutant-source identification based on dynamic time warping[J].Journal of Water Resources Planning and Management,2015,141(11):04015022.
[17]肖传宁,卢文喜,安永凯,等.基于两种耦合方法的模拟-优化模型在地下水污染源识别中的对比[J].中国环境科学,2015,35(8):2393-2399.Xiao C N,Lu W X,An Y K,et al.Comparison of simulationoptimization models based on two coupling methods in the identification of groundwater pollution sources[J].China Environmental Science,2015,35(8):2393-2399.
[18]李敏强,寇纪淞,林丹,等.遗传算法的基本理论与应用[M].北京:科学出版社,2002:63-65.Li M Q,Kou J S,Lin D.The basic theory and application of genetic algorithm[M].Beijing:Science Press,2002:63-65.
[19]余丽.地理网络中求解TSP的并行混合算法研究[D].北京:中国地质大学,2013.Yu L.Research on Parallel Hybrid Algorithm for Solving TSP in Geographical Network[D].Beijing:China Geosciences University,2013.
[20]Sreekanth J,Datta B.Multi-objective management of saltwater intrusion in coastal aquifers using genetic programming and modular neural network based surrogate models[J].Journal of Hydrology,2010,393(3/4):245-256.
[21]Yao W,Chen X,Huang Y,et al.A surrogate-based optimization method with RBF neural network enhanced by linear interpolation and hybrid infill strategy[J].Optimization Methods and Software,2014,29(2):406-429.
[22]姜雪.DNAPLs污染含水层修复方案优选及不确定性分析[D].长春:吉林大学,2016.Jiang X.Optimization and uncertainty analysis of DNAPLs contaminated aquifer repair scheme[D].Changchun:Jilin University,2016.
[23]Manoochehri M,Kolahan F.Integration of artificial neural network and simulated annealing algorithm to optimize deep drawing process[J].International Journal of Advanced Manufacturing Technology,2014,73(1-4):241-249.
[24]侯泽宇.基于替代模型的DNAPLs污染含水层修复方案优选过程的不确定性分析[D].长春:吉林大学,2015.Hou Z Y.Uncertainty analysis of optimization process of DNAPLs contaminated aquifer restoration scheme based on surrogate model[D].Changchun:Jilin University,2015.
[25]Delshad M,Pope G A,Sepehrnoori K.A compositional simulator for modeling surfactant enhanced aquifer remediation,1.formulation[J].Journal of Contaminant Hydrology,1996,23(4):303-327.