人工神经网络理论及其在泥沙科学中的应用研究
|
摘要
宽级配非均匀沙最大起动粒径d_(cmax)和推移质总输沙率的推求是刻画非均匀沙推移质输移规律的两个重要指标，也是研究非均匀沙运动规律的核心课题之一。人工神经网络是对生物神经系统的近似模拟，是把生物原型通过理论研究抽象成为具有某种特定算法的网络模型。它由大量简单的基本元件——神经元(Neuron)相互连接而成的自适应非线性动态系统。
对于d_(cmax)的推求，在本质上还是泥沙的起动问题，因为寻求某种床沙条件下某级泥沙的起动条件(如起动流速、起动切应力、起动功率)和寻求某种水流和床沙条件下的起动粒径是同一问题的两个方面而已；而对于推移质总输沙率推求也和泥沙起动问题中的起动标准选择紧密相关。故本文在回顾并总结泥沙输移研究成果的基础上，指出大多数泥沙起动公式和输沙率公式的推求是采用传统回归模型，即先根据输沙理论定出计算公式，再用实测资料或试验数据率定公式系数。笔者采用的途径则是根据人工神经网络理论，利用VB开发出界面友好、基于改进BP算法的多输入单输出三层神经网络生成器软件，并采用该生成器建模，对平衡输沙状态下的水槽输沙试验的d_(cmax)和总输沙率进行预测计算。
本文的主要内容包括：
泥沙输移理论部分：对前人的相关泥沙起动输移研究结果总结性的回顾，分析了采用最小二乘法的传统回归模型在泥沙起动公式和输沙率公式处理中的
四川大学硕士学位论文人工神经网络理论及其在泥沙科学中的应用研究
优点和缺点:收集并整理了两组平衡状态下的输沙试验资料。
神经网络理论及应用研究部分:
算法研究—对各种网络模型算法作出比较后，采用一种基于传统BP算
法的改进算法，即在计算过程中引入动量项a项以利用上一步学习结果，加快
了传统BP算法的学习速度。
改进BP算法实现—设计出基于改进BP算法的三层神经网络单输出通用
生成器软件。生成器功能是:网络结构中的第一、二层神经元个数和训练参数
中的学习速率粉，动量因子a和期望误差值:可由用户在一定范围内自定义;
各层的权值、阀值、网络初始样本值及教师值可在友好的界面下输入、修改。
改进BP算法在泥沙科学中的应用研究—将收集整理后的两次水槽试验
实测资料作为数据来源，利用生成器生成网络对水槽平衡输沙试验中的最大起
动粒径和总输沙率进行预测。最后从泥沙起动输移理论和神经网络理论的综合
角度，分析比较网络预测值和实测值、传统模型回归计算值。
本文的研究结论:对于平衡状态下的宽级配非均匀沙水槽输沙试验中d‘max
的推求，采用生成器的网络预测值比传统回归模型计算值更能逼近实测值;对
于平衡状态下的水槽输沙试验中总输沙率的推求，也和实测值符合较好。基于
改进BP算法的多输入单输出三层神经网络生成器是一个通用型工具软件，可以
作为泥沙基础理论研究的一个辅助性工具。
Computing the maximal grain size during incipient motion d_(cmax) and gross bed-load transport rate in Non-uniform sediment with a wide distribution are two important indexes for description its transport law, and it is also a core question for discussion in non-uniform sediment research. Artificial neural network (ANN) is a approximate simulation of biologic nerve system, which is a network model with a special algorithm got from biologic prototype after abstractly research. ANN is a adaptive and non-linear dynamic system made from superposition of many simple components which we call neuron.
The question for computation of d_(cmax) belongs to incipient motion of sediment in essence, which is the same question with two different sides, because computation of critical condition (including critical velocity critical shear stress critical power) for a grain size under a bed-load condition is equal to computation of a grain size during incipient motion under the bed-load condition and the water flow condition given before. And computation of gross bed-load transport rate has great relationship with standard of incipient motion. In this dissertation, on the basis of comprehensive review of the study achievements on sediment transport, we get the
fact that most of formula in sediment incipient motion and bed-load transport rate are established by classical regression analysis model, i.e. firstly establishing the formula according to related sediment transport theory, secondly computation for regression coefficients in formula by using field or laboratory experiment data. However, according to ANN's theory, making use of Visual Basic development tool, friendly-interface single output three layers' artificial neural network generator base on improved BP algorithm has been developed by the author, and after constructing the model, the value of d_(cmax), Finally the gross bed-load transport rate of Non-uniform sediment with a wide distribution in flume experiment of stead sediment transportation have been forecasted.
The main contents are as follows:
Section-of theory of sediment transportation-on the basis of comprehensive
review of the study achievements on sediment transport, pros and cons in using classical regression model based on LMS during establishing formula in sediment incipient motion and bed-load transport rate; experiment data in Non-uniform sediment with a wide distribution in flume experiment of stead sediment transportation are been collected and coordinated.
Section of ANN theory and its application study:
After comparing study various model's algorithm, an improved BP algorithm has been adopted, i.e. a momentum factor a has been inducted. It can utilize the learning result of previous step during the training process, which can accelerate the training process of traditional BP algorithm.
Realization of improved BP algorithm-Single output three layers' artificial
neural network generator base on improved BP algorithm has been developed by the author, and the generator has some functions that the number of neuron in first and second layer and theirs related training parameters such as learning rate η. momentum factor a and the value of sum error e can all be self-defined by the users; Connection weights and threshold in each layer's neuron training data and teaching signals can also be input or modified in the friendly interface.
The application study of improved BP algorithm in sediment science-using
two set of experiment data mentioned above, the value of d_(cmax) and gross bed-load transport rate in Non-uniform sediment with a wide distribution in flume experiment of stead sediment transportation have been forecasted by ANN generator. The data forecasted by network experiment data and data computed by classical regression model are compared and analysed from the comprehensive angel of sediment incipient motion theory and ANN theory.
The conclusion of this dissertation-the value of d_(cmax) simulating by
generator in Non-uniform sediment with a wide distr
对于d_(cmax)的推求，在本质上还是泥沙的起动问题，因为寻求某种床沙条件下某级泥沙的起动条件(如起动流速、起动切应力、起动功率)和寻求某种水流和床沙条件下的起动粒径是同一问题的两个方面而已；而对于推移质总输沙率推求也和泥沙起动问题中的起动标准选择紧密相关。故本文在回顾并总结泥沙输移研究成果的基础上，指出大多数泥沙起动公式和输沙率公式的推求是采用传统回归模型，即先根据输沙理论定出计算公式，再用实测资料或试验数据率定公式系数。笔者采用的途径则是根据人工神经网络理论，利用VB开发出界面友好、基于改进BP算法的多输入单输出三层神经网络生成器软件，并采用该生成器建模，对平衡输沙状态下的水槽输沙试验的d_(cmax)和总输沙率进行预测计算。
本文的主要内容包括：
泥沙输移理论部分：对前人的相关泥沙起动输移研究结果总结性的回顾，分析了采用最小二乘法的传统回归模型在泥沙起动公式和输沙率公式处理中的
四川大学硕士学位论文人工神经网络理论及其在泥沙科学中的应用研究
优点和缺点:收集并整理了两组平衡状态下的输沙试验资料。
神经网络理论及应用研究部分:
算法研究—对各种网络模型算法作出比较后，采用一种基于传统BP算
法的改进算法，即在计算过程中引入动量项a项以利用上一步学习结果，加快
了传统BP算法的学习速度。
改进BP算法实现—设计出基于改进BP算法的三层神经网络单输出通用
生成器软件。生成器功能是:网络结构中的第一、二层神经元个数和训练参数
中的学习速率粉，动量因子a和期望误差值:可由用户在一定范围内自定义;
各层的权值、阀值、网络初始样本值及教师值可在友好的界面下输入、修改。
改进BP算法在泥沙科学中的应用研究—将收集整理后的两次水槽试验
实测资料作为数据来源，利用生成器生成网络对水槽平衡输沙试验中的最大起
动粒径和总输沙率进行预测。最后从泥沙起动输移理论和神经网络理论的综合
角度，分析比较网络预测值和实测值、传统模型回归计算值。
本文的研究结论:对于平衡状态下的宽级配非均匀沙水槽输沙试验中d‘max
的推求，采用生成器的网络预测值比传统回归模型计算值更能逼近实测值;对
于平衡状态下的水槽输沙试验中总输沙率的推求，也和实测值符合较好。基于
改进BP算法的多输入单输出三层神经网络生成器是一个通用型工具软件，可以
作为泥沙基础理论研究的一个辅助性工具。
Computing the maximal grain size during incipient motion d_(cmax) and gross bed-load transport rate in Non-uniform sediment with a wide distribution are two important indexes for description its transport law, and it is also a core question for discussion in non-uniform sediment research. Artificial neural network (ANN) is a approximate simulation of biologic nerve system, which is a network model with a special algorithm got from biologic prototype after abstractly research. ANN is a adaptive and non-linear dynamic system made from superposition of many simple components which we call neuron.
The question for computation of d_(cmax) belongs to incipient motion of sediment in essence, which is the same question with two different sides, because computation of critical condition (including critical velocity critical shear stress critical power) for a grain size under a bed-load condition is equal to computation of a grain size during incipient motion under the bed-load condition and the water flow condition given before. And computation of gross bed-load transport rate has great relationship with standard of incipient motion. In this dissertation, on the basis of comprehensive review of the study achievements on sediment transport, we get the
fact that most of formula in sediment incipient motion and bed-load transport rate are established by classical regression analysis model, i.e. firstly establishing the formula according to related sediment transport theory, secondly computation for regression coefficients in formula by using field or laboratory experiment data. However, according to ANN's theory, making use of Visual Basic development tool, friendly-interface single output three layers' artificial neural network generator base on improved BP algorithm has been developed by the author, and after constructing the model, the value of d_(cmax), Finally the gross bed-load transport rate of Non-uniform sediment with a wide distribution in flume experiment of stead sediment transportation have been forecasted.
The main contents are as follows:
Section-of theory of sediment transportation-on the basis of comprehensive
review of the study achievements on sediment transport, pros and cons in using classical regression model based on LMS during establishing formula in sediment incipient motion and bed-load transport rate; experiment data in Non-uniform sediment with a wide distribution in flume experiment of stead sediment transportation are been collected and coordinated.
Section of ANN theory and its application study:
After comparing study various model's algorithm, an improved BP algorithm has been adopted, i.e. a momentum factor a has been inducted. It can utilize the learning result of previous step during the training process, which can accelerate the training process of traditional BP algorithm.
Realization of improved BP algorithm-Single output three layers' artificial
neural network generator base on improved BP algorithm has been developed by the author, and the generator has some functions that the number of neuron in first and second layer and theirs related training parameters such as learning rate η. momentum factor a and the value of sum error e can all be self-defined by the users; Connection weights and threshold in each layer's neuron training data and teaching signals can also be input or modified in the friendly interface.
The application study of improved BP algorithm in sediment science-using
two set of experiment data mentioned above, the value of d_(cmax) and gross bed-load transport rate in Non-uniform sediment with a wide distribution in flume experiment of stead sediment transportation have been forecasted by ANN generator. The data forecasted by network experiment data and data computed by classical regression model are compared and analysed from the comprehensive angel of sediment incipient motion theory and ANN theory.
The conclusion of this dissertation-the value of d_(cmax) simulating by
generator in Non-uniform sediment with a wide distr
引文
[1] 曾庆华．泥沙研究进展综述，泥沙研究,No．1，1999．2．
[2] 鄂竞平等，中国河流泥沙公报(长江、黄河)2000．8
[3] 钱宁，万兆惠．泥沙运动力学．北京：科学出版社，1983．p．382．
[4] 王兆印．泥沙研究的发展趋势和新课题．地理学报，Vol．53，N0．3 1998．5
[5] 秦荣昱．不均匀沙的推移质输移规律的研究，泥沙研究，No．1，1993．3
[6] 秦荣昱．王崇浩．河流推移质运动理论及应用，北京：中国铁道出版社，1996
[7] 何其修．我国河流推移质泥沙和床沙测验技术现状．水电站设计，1993．9(2)
[8] 钱宁，戴定忠．中国河流泥沙问题，第一届河流泥沙国际会议论文集，1980，北京，pp．19-39．
[9] 吴道喜．复杂河网洪水调度数学模型研究，武汉水利电力大学硕士论文，1997．
[10] 刘兴年，曹叔尤，何文社等．山区河流卵石推移质非线性报告，2002．4
[11] 许唯临，双峰型床沙推移运动，成都科技大学研究生毕业论文，1987．4
[12] Bagnold, R.A., "The Nature of Saltation and of Bed load Transport in Water" ,proc. Royal Soc. London, Series A, Vol. 332, 1973.
[13] J. F. Kennedy, Proceedings of 4th International Symposium on River Sedimentation. November 1-5, 1989, Beijing, China. pp. 18-36
[14] Shields, A., Anwendung der Aechlichkeitsmechanik und der Turbulen Zforschung auf die Geschicbc-Wegung. Mitt. Preussische Verschsanstalt rue Wasserbau und Schiffbam, Berlin, 1936.
[17] WANG Guang-qian, A Review of Sediment Research in China, Vol.10, No.3 Sep.,1999
[18] 张绪进 非均匀推移质输移问题，成都科技大学研究生毕业论文，1987．4
[19] 何文社．非均匀沙运动特性研究，四川大学博士学位论文，2002．5
[20] 王平义．泥沙起动条什的模糊分析，成都科技大学学报，1992．6
[21] 韩其为，何明民．泥沙起动规律及起动流速．北京：科学出版社，1999．
[22] 张瑞瑾，谢鉴衡．王明甫，黄金堂．河流泥沙动力学．水利电力出版社，1988．
[23] 窦国仁．再论泥沙起动流速．泥沙研究．1999年，No．6，pp．1-9．
[24] 窦国仁．论泥沙起动流述．水利学报，No．4，1960．
[25] 万兆惠．宋天成，何青。水压力对细颗粒泥沙起动流速影响的试验研究。泥沙研究，1990，(4)．62-69．
[26] 刘兴年．黄尔，曹叔尤等．宽级配推移质输移特性研究．泥沙研究．No．4 2002．8
[27] ALquier M．等．颗粒形态对起始输移的随机影响．曹祥明译，1982
[28] 李贞懦等，作用于床面球体的推力及举力的试验研究．第一次河流泥沙国际学术讨论会论文集．水利电力出版社．1983年
[29] 候穆堂等．起动流速的试验研究、大连工学院学刊，第4期．1957年
[30] 陈嫒儿，谢鉴衡．非均匀沙起动规律初探．武汉水利电力学院学报，No．3，1988．
[31] 秦荣昱．不均匀沙的推移质输移规律研究．泥沙研究，1993，No．1，pp．29-32．
[32] 刘兴年，曹叔尤，黄尔等．粗细化过程中的非均匀沙起动流速．泥沙研究．No．4 2002．8
[33] 王协康，泥沙起动条件及机理的非线性研究．长江科学院院报．No．4 1999．8
[34] 唐造造．宽级配非均匀沙输移规律的试验研究，四川联合大学博士学位论文，1996．
[35] 刘大友，王光谦，李洪洲，泥沙运动的受力分析——关于碰撞力的讨论，泥沙研究，NO．3 1993．
[36] 华国祥．泥沙的起动流速，成都工学院报，1965年第一期
[37] Egiazaroff I. V. Calculation of non- uniform sediment concentration. J. Hyd. Div ASCE, 1965, 191 (4): 1256-1260.
[38] Garde F. Bed- load transport of coarse non- uniform sediment. J. Hyd. Engr, 1984, 110(8): 2270-2281.
[39] Hirrano M. River bed degradation with amoring. Proceeding of the Japan Society of Civil Engineering, 1971, (195): 55-65.
[40] Pemberton E. L., Einstein's bed load function applied to channel design and degradation, sedimentation (Einstein). In: hen H W ed. [M] Littleton Colo: Water Resources Publications, 1972.
[41] Shen H. W., Lu Jan Yan, Development and prediction of bed amoring. J. Hyd. Engr, 1983,109(4): 1250-1261.
[42] 吴宪生．宽级配非均匀沙床沙双峰型的形成条件及起动规律．成都科技大学硕士论文，1984．
[43] 杜国翰等．都江堰工程改建和卵石推移质问题，泥沙研究，复刊号，pp．12-22，1980．
[44] Allen, J. R. L.,"Current Ripples: Their Relation to Pattern of Water and Sediment
Motion", Amsterdam North Holland, 1968, p. 433
[45] Chien, Ning(钱宁), "The Present Status of Research on Sediment Trasport", Trans., Amer. Soc. Civil Engrs., Vol. 121, 1973, pp833～884
[46] Sahgal, P.B., "Effect of Characteristics of Bed Material and Fluid in Ripple Formation", Intern. Symp. on River Mech., 1969, pp. 653～666
[47] Colman, J.M., "Brahmaputra River: Channel Processes and Sedimentation', Sedim., Geol., Vol. 3, No. 2/3, 1969, ,pp. 129～239.
[48] Raudikivi, A.J., Loose Boundary Hydraulics, 2nd ed., Pergamon Press, 1976, p. 397
[49] Paintal, A.S.,A stochastic model of bed load transport,J. Hydr. Res.,Vol.9, No.4,1971.
[50] 韩其为，何明心．泥沙起动规律及起动流速．北京：科学出版社，1999．
[51] 刘兴年．非均匀沙推移质输沙率及其粗化稳定．成都科技大学硕士论文。1986，P14～32。
[52] 何文社．非均匀沙运动特性研究．四川大学博士学位论文．2002．4 P38～47
[53] 王兴奎，任裕民，杨铁笙等．推移质泥沙运动的脉动流速．消华大学水利水电工程系．1991．12
[54] 李福田．推移质运动队水流紊动结构的影响．华东水利学院院报．1985．9．13
[55] 候晖吕．河流动力学基本问题．水利出版社，1982
[56] 李贞儒、陈嫒儿、赵云，作用于床面球阵的推力及举力试验研究．第二次河道泥沙国际学术讨沦会论文集，1983年
[57] Krammer,H., "Sand Mixtures and Sand Movement in Fluvial Models", Trans.,Amer. Soc. Civil Engrs., Yol. 100,1935, pp798～838
[58] 张瑞瑾、谢鉴衡、王明甫、黄金堂．河道泥沙动力学，水利电力出版社．1989年
[59] Yalin, M. S., Mechanics of Sediment Transport, Oxford Pergaman Press, 1972.
[60] 冷魁．非均匀沙卵石起动流速及输沙率的试验研究．武汉水利电力大学博士论文，1993．
[61] Gessler, J.. Beginning and Ceasing of Sediment Motion. In River Mechanics,by H.W. Shen, Vol. 1, 1971. pp. 22.
[62] 王兴奎，陈稚聪，张仁．长江寸滩站卵石推移质的运动规律．水利学报，1992，(4)：32～38
[63] 彭凯，陈远信．非均匀沙的起动问题．成都科技大学学报，No．2，1986．
[64] 黄才安，奚斌．推移质输沙率公式的统一形式．南京水利科学研究院水利水运科学研
究．No．2 2000．6
[65] 张书农，华国祥．河流动力学．水利电力出版社．1985年
[66] Yalin, M. S., Mechanics of Sediment Transport, Oxford Pergaman Press, 1972.
[67] 吴宪生，非均匀泥沙的起动规律，水电工程研究．1985年第一期
[68] 彭凯．非均匀沙起动规律．成都科技大学硕士论文，1984．
[69] 孙志林，谢鉴衡，段文忠等．非均匀沙分级起动规律研究，水利学报，No．10，pp．25-32。1997．
[70] 秦荣昱，不均匀沙的起动规律．水电工程研究．1985年第一期．
[71] 方红卫．不均匀沙组成及起动．水利学报．No．4，pp．43-49，1992．
[72] Einstein, H.A., The bed load function for sediment transportation in open channel flows, Tech. Bulletin 1026,USDA Soil Conservation Service, 1950.
[73] Gessler, J., The beginning of bed load movement of mixture investigated as natural armoring in channels, W.M.Keck Lab. of Hydraulics and water resources, California Inst. of Technology, Pasadena, 1967.
[74] Benedict, B. A. and Christensen, B.A., Discussion of self stabilizing tendencies of alluvial channels by J.Gessler, J.Waterways, Harbors and Coastal Eng. Div. ASCE, 97(1), 1971.
[75] W C. Mclulloch and w. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 1943, Vol. 5
[76] D. O. Hebb, The Organization og behavior, John Wiley, New York, 1949.
[77] Rosenblatt F, Principle of neurodynamics, Spartan, New York 1949
[78] Hopfield J.J, Neural Networks and physical system with emergent collective computational abilities, Proc. Natr. Acad. Sci, USA, 1982
[79] D.E. Rumehart and J.L. McClelland, Parallel Distributed Processing, Vol. 1～ Vol. 2, MIT Press, 1986
[80] 徐秉铮，张百灵，韦岗．神经网络理论与应用．华南理工大学出版社．1994．3
[81] 焦李成．神经网络计算 西安：西安电子科技大学出版社，1993
[82] 王彦春．段云卿．改进的快速BP算法．物探化探计算技术．Vol．19 No．3Aug．1997
[83] 杨建刚．人工神经网络实用教程．浙江大学出版社 2001．1
[84] 彭清娥、曹叔尤、刘兴年等．流域年均含沙量BP模型问题分析．泥沙研究．2000年，No. 4
[85] 焦李成．神经网络系统理论．西安：西安电子科技大学出版社，1990
[86] Raman H, Sunilkumar N.Multivariate modeling of water resources time series using artificial neural networks[J]. Hydrological Sciences Journal, 1995,40(2): 145-163.
[87] 李义天、李荣、黄伟．基于神经网络的水沙运动预报模型与回归模型比较及应用．泥沙研究．2001年，No．1
[88] 王协康．人工神经网络理论及其在水沙环境灾害中的应用 四川大学博士后研究工作报告。2002．9
[89] 刘炳文．精通Visual Basic 6．0中文版．电子工业出版社．北京．1999
[90] Nick Snowdon Oracle与VisualBasic编程指南．北京：电子工业出版社，2000
[91] 董永华．非均匀沙推移质若干输沙规律的实验教育，武汉水利电力大学研究生论文，1996
[92] Gessler, J., Stochastic Aspects of incipient motion on riverbeds, in Stochastic Approach to Water Resource, Vol.2, by H.W. Shen(ed), p.26, 1976,
[93] 陆永军等．非均匀沙推移质输沙率及其级配计算，水动力学研究与进展，No．4，1991．
[94] 陆永军．宽级配河床粗化稳定结构．水道港口．No．4，1990．
[95] 回归分析及其试验设计．上海教育出版社．1978年2月
[96] R.L Misri, R.J. Garde, and K.G.Ranga Raju, Bed Load Transport of Coarce Nonuniform Sediment, Journal of Hydraulic Engineering, ASCE, Vol.110, No.3, 198.8.
[97] 王东，刘兴年，曹叔尤．数据库技术在“三峡工程泥沙信息系统”中的应用．四川大学学报．2003
[2] 鄂竞平等，中国河流泥沙公报(长江、黄河)2000．8
[3] 钱宁，万兆惠．泥沙运动力学．北京：科学出版社，1983．p．382．
[4] 王兆印．泥沙研究的发展趋势和新课题．地理学报，Vol．53，N0．3 1998．5
[5] 秦荣昱．不均匀沙的推移质输移规律的研究，泥沙研究，No．1，1993．3
[6] 秦荣昱．王崇浩．河流推移质运动理论及应用，北京：中国铁道出版社，1996
[7] 何其修．我国河流推移质泥沙和床沙测验技术现状．水电站设计，1993．9(2)
[8] 钱宁，戴定忠．中国河流泥沙问题，第一届河流泥沙国际会议论文集，1980，北京，pp．19-39．
[9] 吴道喜．复杂河网洪水调度数学模型研究，武汉水利电力大学硕士论文，1997．
[10] 刘兴年，曹叔尤，何文社等．山区河流卵石推移质非线性报告，2002．4
[11] 许唯临，双峰型床沙推移运动，成都科技大学研究生毕业论文，1987．4
[12] Bagnold, R.A., "The Nature of Saltation and of Bed load Transport in Water" ,proc. Royal Soc. London, Series A, Vol. 332, 1973.
[13] J. F. Kennedy, Proceedings of 4th International Symposium on River Sedimentation. November 1-5, 1989, Beijing, China. pp. 18-36
[14] Shields, A., Anwendung der Aechlichkeitsmechanik und der Turbulen Zforschung auf die Geschicbc-Wegung. Mitt. Preussische Verschsanstalt rue Wasserbau und Schiffbam, Berlin, 1936.
[17] WANG Guang-qian, A Review of Sediment Research in China, Vol.10, No.3 Sep.,1999
[18] 张绪进 非均匀推移质输移问题，成都科技大学研究生毕业论文，1987．4
[19] 何文社．非均匀沙运动特性研究，四川大学博士学位论文，2002．5
[20] 王平义．泥沙起动条什的模糊分析，成都科技大学学报，1992．6
[21] 韩其为，何明民．泥沙起动规律及起动流速．北京：科学出版社，1999．
[22] 张瑞瑾，谢鉴衡．王明甫，黄金堂．河流泥沙动力学．水利电力出版社，1988．
[23] 窦国仁．再论泥沙起动流速．泥沙研究．1999年，No．6，pp．1-9．
[24] 窦国仁．论泥沙起动流述．水利学报，No．4，1960．
[25] 万兆惠．宋天成，何青。水压力对细颗粒泥沙起动流速影响的试验研究。泥沙研究，1990，(4)．62-69．
[26] 刘兴年．黄尔，曹叔尤等．宽级配推移质输移特性研究．泥沙研究．No．4 2002．8
[27] ALquier M．等．颗粒形态对起始输移的随机影响．曹祥明译，1982
[28] 李贞懦等，作用于床面球体的推力及举力的试验研究．第一次河流泥沙国际学术讨论会论文集．水利电力出版社．1983年
[29] 候穆堂等．起动流速的试验研究、大连工学院学刊，第4期．1957年
[30] 陈嫒儿，谢鉴衡．非均匀沙起动规律初探．武汉水利电力学院学报，No．3，1988．
[31] 秦荣昱．不均匀沙的推移质输移规律研究．泥沙研究，1993，No．1，pp．29-32．
[32] 刘兴年，曹叔尤，黄尔等．粗细化过程中的非均匀沙起动流速．泥沙研究．No．4 2002．8
[33] 王协康，泥沙起动条件及机理的非线性研究．长江科学院院报．No．4 1999．8
[34] 唐造造．宽级配非均匀沙输移规律的试验研究，四川联合大学博士学位论文，1996．
[35] 刘大友，王光谦，李洪洲，泥沙运动的受力分析——关于碰撞力的讨论，泥沙研究，NO．3 1993．
[36] 华国祥．泥沙的起动流速，成都工学院报，1965年第一期
[37] Egiazaroff I. V. Calculation of non- uniform sediment concentration. J. Hyd. Div ASCE, 1965, 191 (4): 1256-1260.
[38] Garde F. Bed- load transport of coarse non- uniform sediment. J. Hyd. Engr, 1984, 110(8): 2270-2281.
[39] Hirrano M. River bed degradation with amoring. Proceeding of the Japan Society of Civil Engineering, 1971, (195): 55-65.
[40] Pemberton E. L., Einstein's bed load function applied to channel design and degradation, sedimentation (Einstein). In: hen H W ed. [M] Littleton Colo: Water Resources Publications, 1972.
[41] Shen H. W., Lu Jan Yan, Development and prediction of bed amoring. J. Hyd. Engr, 1983,109(4): 1250-1261.
[42] 吴宪生．宽级配非均匀沙床沙双峰型的形成条件及起动规律．成都科技大学硕士论文，1984．
[43] 杜国翰等．都江堰工程改建和卵石推移质问题，泥沙研究，复刊号，pp．12-22，1980．
[44] Allen, J. R. L.,"Current Ripples: Their Relation to Pattern of Water and Sediment
Motion", Amsterdam North Holland, 1968, p. 433
[45] Chien, Ning(钱宁), "The Present Status of Research on Sediment Trasport", Trans., Amer. Soc. Civil Engrs., Vol. 121, 1973, pp833～884
[46] Sahgal, P.B., "Effect of Characteristics of Bed Material and Fluid in Ripple Formation", Intern. Symp. on River Mech., 1969, pp. 653～666
[47] Colman, J.M., "Brahmaputra River: Channel Processes and Sedimentation', Sedim., Geol., Vol. 3, No. 2/3, 1969, ,pp. 129～239.
[48] Raudikivi, A.J., Loose Boundary Hydraulics, 2nd ed., Pergamon Press, 1976, p. 397
[49] Paintal, A.S.,A stochastic model of bed load transport,J. Hydr. Res.,Vol.9, No.4,1971.
[50] 韩其为，何明心．泥沙起动规律及起动流速．北京：科学出版社，1999．
[51] 刘兴年．非均匀沙推移质输沙率及其粗化稳定．成都科技大学硕士论文。1986，P14～32。
[52] 何文社．非均匀沙运动特性研究．四川大学博士学位论文．2002．4 P38～47
[53] 王兴奎，任裕民，杨铁笙等．推移质泥沙运动的脉动流速．消华大学水利水电工程系．1991．12
[54] 李福田．推移质运动队水流紊动结构的影响．华东水利学院院报．1985．9．13
[55] 候晖吕．河流动力学基本问题．水利出版社，1982
[56] 李贞儒、陈嫒儿、赵云，作用于床面球阵的推力及举力试验研究．第二次河道泥沙国际学术讨沦会论文集，1983年
[57] Krammer,H., "Sand Mixtures and Sand Movement in Fluvial Models", Trans.,Amer. Soc. Civil Engrs., Yol. 100,1935, pp798～838
[58] 张瑞瑾、谢鉴衡、王明甫、黄金堂．河道泥沙动力学，水利电力出版社．1989年
[59] Yalin, M. S., Mechanics of Sediment Transport, Oxford Pergaman Press, 1972.
[60] 冷魁．非均匀沙卵石起动流速及输沙率的试验研究．武汉水利电力大学博士论文，1993．
[61] Gessler, J.. Beginning and Ceasing of Sediment Motion. In River Mechanics,by H.W. Shen, Vol. 1, 1971. pp. 22.
[62] 王兴奎，陈稚聪，张仁．长江寸滩站卵石推移质的运动规律．水利学报，1992，(4)：32～38
[63] 彭凯，陈远信．非均匀沙的起动问题．成都科技大学学报，No．2，1986．
[64] 黄才安，奚斌．推移质输沙率公式的统一形式．南京水利科学研究院水利水运科学研
究．No．2 2000．6
[65] 张书农，华国祥．河流动力学．水利电力出版社．1985年
[66] Yalin, M. S., Mechanics of Sediment Transport, Oxford Pergaman Press, 1972.
[67] 吴宪生，非均匀泥沙的起动规律，水电工程研究．1985年第一期
[68] 彭凯．非均匀沙起动规律．成都科技大学硕士论文，1984．
[69] 孙志林，谢鉴衡，段文忠等．非均匀沙分级起动规律研究，水利学报，No．10，pp．25-32。1997．
[70] 秦荣昱，不均匀沙的起动规律．水电工程研究．1985年第一期．
[71] 方红卫．不均匀沙组成及起动．水利学报．No．4，pp．43-49，1992．
[72] Einstein, H.A., The bed load function for sediment transportation in open channel flows, Tech. Bulletin 1026,USDA Soil Conservation Service, 1950.
[73] Gessler, J., The beginning of bed load movement of mixture investigated as natural armoring in channels, W.M.Keck Lab. of Hydraulics and water resources, California Inst. of Technology, Pasadena, 1967.
[74] Benedict, B. A. and Christensen, B.A., Discussion of self stabilizing tendencies of alluvial channels by J.Gessler, J.Waterways, Harbors and Coastal Eng. Div. ASCE, 97(1), 1971.
[75] W C. Mclulloch and w. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 1943, Vol. 5
[76] D. O. Hebb, The Organization og behavior, John Wiley, New York, 1949.
[77] Rosenblatt F, Principle of neurodynamics, Spartan, New York 1949
[78] Hopfield J.J, Neural Networks and physical system with emergent collective computational abilities, Proc. Natr. Acad. Sci, USA, 1982
[79] D.E. Rumehart and J.L. McClelland, Parallel Distributed Processing, Vol. 1～ Vol. 2, MIT Press, 1986
[80] 徐秉铮，张百灵，韦岗．神经网络理论与应用．华南理工大学出版社．1994．3
[81] 焦李成．神经网络计算 西安：西安电子科技大学出版社，1993
[82] 王彦春．段云卿．改进的快速BP算法．物探化探计算技术．Vol．19 No．3Aug．1997
[83] 杨建刚．人工神经网络实用教程．浙江大学出版社 2001．1
[84] 彭清娥、曹叔尤、刘兴年等．流域年均含沙量BP模型问题分析．泥沙研究．2000年，No. 4
[85] 焦李成．神经网络系统理论．西安：西安电子科技大学出版社，1990
[86] Raman H, Sunilkumar N.Multivariate modeling of water resources time series using artificial neural networks[J]. Hydrological Sciences Journal, 1995,40(2): 145-163.
[87] 李义天、李荣、黄伟．基于神经网络的水沙运动预报模型与回归模型比较及应用．泥沙研究．2001年，No．1
[88] 王协康．人工神经网络理论及其在水沙环境灾害中的应用 四川大学博士后研究工作报告。2002．9
[89] 刘炳文．精通Visual Basic 6．0中文版．电子工业出版社．北京．1999
[90] Nick Snowdon Oracle与VisualBasic编程指南．北京：电子工业出版社，2000
[91] 董永华．非均匀沙推移质若干输沙规律的实验教育，武汉水利电力大学研究生论文，1996
[92] Gessler, J., Stochastic Aspects of incipient motion on riverbeds, in Stochastic Approach to Water Resource, Vol.2, by H.W. Shen(ed), p.26, 1976,
[93] 陆永军等．非均匀沙推移质输沙率及其级配计算，水动力学研究与进展，No．4，1991．
[94] 陆永军．宽级配河床粗化稳定结构．水道港口．No．4，1990．
[95] 回归分析及其试验设计．上海教育出版社．1978年2月
[96] R.L Misri, R.J. Garde, and K.G.Ranga Raju, Bed Load Transport of Coarce Nonuniform Sediment, Journal of Hydraulic Engineering, ASCE, Vol.110, No.3, 198.8.
[97] 王东，刘兴年，曹叔尤．数据库技术在“三峡工程泥沙信息系统”中的应用．四川大学学报．2003