用户名: 密码: 验证码:
基于智能计算的降雨径流模拟方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
降雨径流模拟是水文模拟的重要组成部分。到目前为止,人们对水文过程规律的认识还不十分清楚。近二十年人类活动的剧烈影响,土地利用/土地覆被变化日益加剧,使得对机理的认识更加困难,再加上数据有限这一瓶颈问题,使得传统的水文模拟方法面临更加严峻的挑战。因此,水文模拟的研究迫切需要引入新的理论和方法。在这种形势下,基于智能计算的水文模拟方法应运而生。作为该方法的探索,本文将主要工作放在基于智能计算方法的降雨径流的模拟上,大致开展了如下研究:
     (1) 分析我国目前水文水资源面临的新的形式以及水文模拟所面临的困难,介绍人的智能作用和人工智能的兴起,总结了智能计算在水文模拟中的应用。
     (2) 针对土地利用/土地覆被变化对水文过程的影响问题,结合潮河流域的实际情况,建立了加入土地覆被因子的BP网络模型模拟流域降雨径流过程,结果表明,加入土地覆被因子的BP网络比没有加入土地覆被因子的网络模型表现出更高的精度。
     (3) 针对降雨径流模拟中,由于大流量样本少而使模拟精度不高的问题,提出了基于模糊C均值和基于自组织映射两种流量分类方法的神经网络预报模型。针对分类过程中一些类与类之间的边缘样本在选择局部神经网络模型时出现的误判问题,在上面已经建立的模型的基础上,建立了加入专家经验的模糊逻辑选择模型。构成Fuzzy+ANN+专家经验的综合智能模型。以王家厂流域为例进行了方法的实现,计算结果表明,使用基于分类的网络模型比没有分类的总体模型有更高的模拟精度,而应用模糊逻辑选择的基于自组织映射分类的BP网络模型有最高的精度。
     (4) 遗传编程是新的智能计算方法,在国内尚未见到在模拟降雨-径流关系上的应用,本文尝试应用该方法建立了王家厂水库洪水预报,结果令人满意。
The simulation of rainfall-runoff is an important part of hydrology simulation. So far, the law of the hydrological cycle is still unclear. However, with the strong influence of human actions and land use and land cover change increasing rapidly, it has being becoming more difficult for us to understand it. Furthermore, the data sacristy makes the traditional hydrologic simulation facing the more rigorous challenge. So new theory and methods are being urgently needed for the study on hydrology process simulation. Under these conditions, the hydrologic simulation method based on the intelligent calculation emerges, as the times require. This thesis focuses on employing the intelligent calculation method to simulate the rainfall-runoff simulation and the following four parts are included:
    (1) At the first of this paper the new situation that the hydrology and water resource is facing and the difficulty that the hydrologic simulation are encountering in our country are analyzed, and the intelligent functions of the humans and the springs up of the artificial intelligence are introduced, then the intelligent calculation's application in hydrologic simulation is summarized.
    (2) Aimed to the influence that land use and land cover change has had on the hydrologic process, and taking Chao river basin for example, an BP networks model is established to simulate the basin rainfall-runoff process with the land cover factors. Compared with the simulation that didn't consider the factor of land use/land cover, the more accurate simulating result is obtained by the model considering the influence of land use/land cover.
    (3) Owing to the lack of the big runoff samples in hydrology series, good precision is seldom obtained in the simulation of big flow. To improve this problem, a kind of neural network forecasting model is brought forward. This model rank the runoffs firstly and is based on two runoff taxonomies: the fuzzy C mean and the self-organization mapping. However, when the samples on the border of two sorts choose the local neural network models, they tend to make mistakes. According to this problem, a fuzzy logic selection model based on expert experiences is established.
    
    Taking the Wangjia Chang basin for example, the calculation results shows that the simulation precision of neural network model with classification is higher than that of integrated model without classification, and the fuzzy logical selection based on self-organization mapping classification-BP network model has the highest accuracy of all.
    (4) The hydrologic development requires the continuous introduce of new methods. So this paper attempts to use a newer intelligent technology-genetic programming to establish the rainfall-runoff experiential formula. The data is from the Wangjia Chang basin and results are satisfying, then the new method should be recommended.
引文
[1] 张智星等著,张平安等译.神经-模糊和软计算[M].西安:西安交通大学出版社,2000.
    [2] 张颖,刘艳秋编著,软计算方法[M].北京:科学出版社,2002
    [3] 李敏强,寇纪淞,林丹,李书全.遗传算法的基本理论与应用[M].北京:科学出版社,2002.
    [4] 云庆夏编著.进化算法[M].北京:冶金工业出版社,2000.
    [5] L.A.扎德著.模糊集合、语言变量及模糊变量[M].北京:科学出版社,1982.
    [6] 陈守煜.模糊水文学与水资源系统模糊优化原理[M].大连:大连理工大学出版社,1990.
    [7] 冯夏庭.智能岩石力学导论[M].北京:科学出版社,2000.
    [8] 夏军.水文非线性系统理论与方法[M].湖北:武汉大学出版社,2002.
    [9] [日]玄光男,陈润伟.遗传算法与工程设计[M].北京:科学出版社,2000.
    [10] 金菊良,丁晶.水资源系统工程[M].四川:四川科学技术出版社,2002.
    [11] 徐扬.模糊模式识别及其应用[M].成都:西南交通大学出版社,1999.
    [12] 许东,吴铮.基于MATLAB6.x的系统分析设计——神经网络(第二版)[M].西安:西安电子科技大学出版社,2002.
    [13] 楼顺天,胡昌华,张伟.基于MATLAB的系统分析与设计——模糊系统[M].西安:西安电子科技大学出版社,2002.
    [14] 吴晓莉,林哲辉等编著.MATLAB辅助模糊系统设计[M].西安:西安电子科技大学出版社,2002.
    [15] 云舟工作室编著,MATLAB6数学建模基础教程[M].北京:人民邮电出版社,2001.
    [16] 叶守泽,詹道江.工程水文学[M].北京:中国水利水电出版社,2000
    [17] 胡铁松.神经网络预测与优化[M].大连.大连海事大学出版社,1997
    [18] 苑希民,李鸿雁,刘树坤,崔广涛.神经网络和遗传算法在水科学领域的应用[M],北京:中国水利水电出版社,2002
    [19] 刘苏霞.世纪之交的水文研究[J].水科学进展,2001,12(1):113-117.
    [20] 夏军,谈戈.全球变化与水文科学新的进展与挑战[J].资源科学.2002,24(3):1-7.
    [21] 叶守泽,夏军.水文科学研究的世纪回眸与展望[J].水科学进展.2002,13(1):93-104.
    [22] 夏军.华北地区水循环与水资源安全:问题与挑战(一)[J].海河水利.2003,3.
    [23] 夏军.华北地区水循环与水资源安全:问题与挑战(二)[J].海河水利.2003,4
    [24] 吴险峰,刘昌明.流域水文模型研究的若干进展[J].地理科学进展.2002,21(4):341-348.
    [25] 刘苏峡,刘昌明.90年代水文学研究的进展和趋势[J].水科学进展.1997,8(4):365-369.
    [26] 芮孝芳.中国的主要水问题及水文学的机遇[J].水利水电科技进展.1999,19(3):18-21.
    [27] 芮孝芳,孔凡哲,石朋.河流水文学若干研究领域的回顾与展望[J].水利水电科技进展.2001,21(2):8-11.
    [28] ’98洪水专家纵横谈.水科学进展[J].1998,9(3):303-311.
    [29] 刘贤赵.论水文尺度问题.干旱区地理[J].2004,27(1):61-65.
    [30] 任立良,张炜,李春红,王美荣.中国北方地区人类活动对地表水资源的影响研究[J].河海大学学报.2001,29(4):13-18.
    [31] 郭华明,王焰新,王润福,邓安利.人类活动影响下的大同市浅层地下水环境演化[J].地质科技情报.2002,21(4):65-72.
    [32] 李荣峰.人工神经网络及其在水科学研究中的应用[J].山西水利科技.2003,4.
    [33] 顾正华,唐洪武,李云,肖洋.水流模拟智能化问题的探讨[J].水科学进展.
    
    2004,15(1),129-133.
    [34] 张翔,丁晶.神经智能信息处理系统的研究现状及其在水文水资源中的应用展望[J].水科学进展,2000,11(1):105-110
    [35] 丁晶,邓育仁.水文水资源中不确定性分折与计算的耦合途径[J].水文.1996 1
    [36] 彭建,梁虹.我国洪水预报研究进展[J].贵州师范大学学报(自然科学版).2001,19(4),97-102.
    [37] 张小峰,许全喜,裴莹.流域产流产沙BP网络预报模型的初步研究[J].水科学进展.2001,12(1),17-22.
    [38] 熊立华,郭生练,王元.神经网络在洪水实时预报中的应用研究.水电能源科学.2002,20(3):28-31.
    [39] 熊立华,郭生练,庞博,姜广斌.三种基于神经网络的洪水实时预报方案的比较研究[J].水文.2003,23(5):1-4.
    [40] 陈科.基于神经网络的降雨径流预报[J].四川水力发电.1998,17(1),12-16.
    [41] 王栋,曹升乐.人工神经网络在水文水资源水环境系统中的应用研究进展[J].水利水电技术.1999,30(12),4-7.
    [42] 冯国章,李佩成.人工神经网络结构对径流预报精度的影响分析fJ].自然资源学报,1998,13(2):169-174
    [43] 高彦春,姚治君,刘宝勤,吕爱峰.密云水库入库径流变化趋势及动因分析[J].地理科学进展,2002,21(6):546-553
    [44] 吴超羽,张文.水文预报的人工神经网络方法[J].中山大学学报(自然科学版).1994,33(1),79-89.
    [45] 刘国东,丁晶.BP网络用于水文预测的几个问题探讨[J].水利学报.1999,1
    [46] 黄克明,张国忠.水文预报的神经网络模式分类预报方法.武汉大学学报(工学版).2003,36(1):21-23.
    [47] 袁飞,任立良,姜红梅,季成康.MATLAB神经网络工具箱在径流模拟中的应用[J].人民长江.2003,34(6),38-40.
    [48] 付强,王志良,梁川.自组织竞争人工神经网络在土壤分类中的应用.水土保持通报.2002,22(1):39-43.
    [49] 付凌晖,王惠文,Yves Lechevallier.自组织特征映射在鄱阳湖地区洪涝灾害研究中的应用[J].北京航空航天大学学报(社会科学版).2002,15(4):43-48.
    [50] Teuvo Kohonen. The Self-Organizing Map[J]. Proceedings of IEEE. 1990,78(9): 1464-1480.
    [51] N. Sajikumar, B.S. Thandaveswara. A non-linear rainfall-runoff model using an artificial neural network[J]. Journal of Hydrology 216(1999) 32-55.
    [52] C.E. Imrie, S. Durucan, A. Korre. River flow prediction using artificial neural networks: generalisation beyond the calibration range[J]. Journal of Hydrology 233(2000)138-153.
    [53] Y. B. Dibike and D. P. Solomatlne. River Flow Forecasting Using Artificial Neural Networks[J]. Phys. Chem. Earth(B), Vol. 26, No. 1, pp. 1-7, 2001
    [54] R. Barattia, B. Cannasb, A. Fannib, M. Pintusc, G.M. Sechic, N. Torenoa. River flow forecast for reservoir management through neural networks[J]. Neurocomputing. 2003, 55
    [55] A F Shapiro. The merging of neural networks, fuzzy logic, and genetic algorithms[J]. Insurance: Mathematics and Economics 31(2002): 115-131.
    [56] Y B Dibike, D P Solomatine. River flow forecasting using artificial neural networks[J]. Phys.Chem.Earth(B), 2001, 26(1): 1-7.
    [57] Linda See, Stan Openshaw. Applying soft computing approaches to river level
    
    forecasting.Hydrological Science Journal, 1999, 44(5): 763-778.
    [58] 陈守煜,王大刚.基于遗传算法的模糊优选BP网络模型及其应用[J].水利学报,2003,(5):116-121.
    [59] 朱承山,潘英杰.欧阳海水库径流量预报的模糊神经网络方法[J].水电能源科学,2000,18(3):16-18.
    [60] 王玲,黄国如.基于径流分类的日径流量预测神经网络模型[J].灌溉排水,2002,21(4):45-48.
    [61] 王德意,杨国清,姚李孝,王涛.模糊聚类在水轮发电机模糊神经励磁控制器设计中的应用[J].水利学报.2003,(3)
    [62] 赵奎,蔡美峰.模糊C均值聚类算法在结构面组识别中的应用[J].金属矿山.2002,307
    [63] 白素琴,惠长坤,吴小俊,王士同.一种基于遗传算法的模糊聚类算法及其与FCM算法的结合[J].华东船舶工业学院学报(自然科学版).2001,15(6),40-43.
    [64] 何建华,杨宗凯,王殊.基于神经网络和模糊逻辑的智能火灾探测[J].1997,25(2):9-12.
    [65] 潘辉,戴俊明,史金松.模糊评判在防洪调度中的应用研究[J].水利学报.1997,(6):48-52.
    [66] Lihua. Xiong, Asaad Y. Shamseldin, Kieran. M. O'connor. A non-line combination of the forecasts of rainfall-runoff models by first-order Takagi-Sugeno fuzzy system[J]. Journal of Hydrology. 2001, 245:196-217.
    [67] C.T. Cheng, C.P. Ou, K.W. Chau. Combining a fuzzy optimal model with a genetic algorithm to solve multi-objective rainfall-runoff model calibration[J]. Journal of Hydrology 2002,268:72-86
    [68] R. Pongracz, I. Bogardi, L. Duckstein, Application of fuzzy rule-based modeling technique to regional drought[J]. Journal of Hydrology. 1999,224:100-114.
    [69] Ertunga C.Ozelkan, Lucien Duckstein. Fuzzy conceptual rainfalt-runoff models[J]. Journal of Hydrology. 2001,253:41-68.
    [70] Pao-Shan Yu, Tao-Chang Yang. Fuzzy multi-objective function for rainfall-runoff model calibration[J]. Journal of Hydrology. 2000, 238:1-14.
    [71] K.Schutz, B.Huwe. Water flow modeling in the unsaturated zone with imprecise parameters using a fuzzy approach[J]. Journal of Hydrology. 1997, 201, 211-229.
    [72] 徐哲,白焰.遗传编程.自动化仪表.2002,23(10),1-7.
    [73] 陈志卫,王万良,万跃华,张聚,赵燕伟.遗传规划研究的现状及发展[J].浙江工业大学学报.2003,31(2):153-159.
    [74] 乐美龙,方奕.基于遗传规划方法的集装箱吞吐量预测[J].上海交通大学学报.2003,37(8):1246-1250.
    [75] 陈月辉,董吉文,史奎凡.利用遗传编程的符号表达式逼近任意非线性函数[J].山东建材学院学报.1998,12(2):142-145.
    [76] 翟宜峰,李鸿雁,刘寒冰.人工神经网络与遗传算法在多泥沙洪水预报中的应用[J].泥沙研究.2003,2.
    [77] Q.J. Wang. Using genetic algorithms to optimize model parameters[J]. Environment Modeling & software. 1997, 12(1): 27-34.
    [78] Dragan A. Savic, Godfrey A. Walters, Jamesw. Davidson. A Genetic Programming Approach to Rainfall-Runoff Modeling[J]. Water Resources Management 13: 219-231, 1999.
    
    
    [79] P. A. Whigham, P. F. Crapper. Modeling Rainfall-Runoff using Genetic Programming[J]. Mathematical and Computer Modeling 2001,33:707-721.
    [80] 席裕庚,柴天佑等.遗传算法综述[J].控制理论与运用.1996,13(6):697-708.
    [81] 张洪刚,郭生练,刘攀,彭定志.概念性水文模型多目标参数自动优选方法研究[J].水文.2002,22(1):12-16.
    [82] 陈求稳.模式自组在水生生态数据分析中的应用——太湖富营养化事例分析[J].水利学报.2001.6.
    [83] 卢世浪.神经网络与模糊集理论在实时洪水预报中的应用研究[D].大连理工大学硕士论文.2001.
    [84] 欧春平.智能算法在流域洪水预报系统建模中的应用及其软件集成体系[D],大连理工大学硕士论文.2001.
    [85] 夏新海,刘会林.MATLAB编程环境下GA的程序设计[J].计算机时代.2003,12.
    [86] Hjelmfelt, Allen T. Jr; Wang, Menghua. Artificial neural networks as unit hydrograph applications[J]. Proceedings of the Symposium on Engineering Hydrology, 1993, 756-759.
    [87] Achela, D.; Fernando, K.; Jayawardena, A.W. Runoff forecasting using RBF networks with OLS algorithm[J]. Journal of Hydrologic Engineering, 1998, 3: 203-209.
    [88] Hsu, Kuo-lin; Gupta, Hoshin V.; Sorooshian, Soroosh. Application of a recurrent neural network to rainfall-runoff modeling[J]. Proceedings of the Annual Water Resources Planning and Management Conference, Aesthetics in the Constructed Environment, 1997, 68-73.
    [89] Dorado, Julian; Rabunal, Juan R.; Pazos, Alejandro; Rivero, Daniel; Santos, Antonino; Puertas, Jeronimo. Prediction and modeling of the rainfall-runoff transformation of a typical urban basin using ANN and GP[J]. Applied Artificial Intelligence, 2003, 17: 329-343.
    [90] Delclaux, F. Approach for integrating fuzzy rule system in hydrological modeling[J]. International Conference on Hydraulic Engineering Software, Hydrosoft, Proceedings, 1998, 395-404.
    [91] Bogardi, Istvan, Reiter, Roland; Nachtnebel, Peter. Fuzzy rule-based estimation of flood probabilities under climatic fluctuations[J]. Risk-Based Decision Making in Water Resources, Proceedings of the Conference, 1996, 61-79.
    [92] Shu, Chang, Burn, Donald H. Homogeneous pooling group delineation for flood frequency analysis using a fuzzy expert system with genetic enhancement[J]. Journal of Hydrology,2004,291: 132-149.
    [93] Yu, Pao-Shan, Chen, Chia-Jung, Chen, Shiann-Jong. Application of gray and fuzzy methods for rainfall forecasting[J]. Journal of Hydrologic Engineering. 2000,5:339-345

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700