臺灣博碩士論文加值系統

本研究採用以模擬人類依經驗的學習法則及判斷方式所創建的水文模式，應用包括巢狀超矩形演算法及模糊反傳遞類神經網路及輻狀基底函數類神經網路等方法，配合區域化變數理論的空間分析能力，建立大甲溪流域水文資訊系統，以期提供大甲溪流域水資源管理及決策者準確且適宜的水文訊息，作為管理及決策之用，其主要內容包括：1.流域雨量站網分析：依區域化變數理論評估大甲溪流域之雨量觀測站網，並提供最佳化設站之建議，以供決策者未來增刪站之依據。2.水文資料補遺模式之建立：應用巢狀超矩形演算法完成基本資料補遺系統建構，提供水文資料補遺分析，以彌補資料蒐集之缺失與不足。3.模糊類神經網路模式應用於旬流量預測系統：利用模糊類神經網路建構可行之降雨－逕流模式，以自我學習的方式，架構適宜的降雨－逕流關係，並將此模式應用於旬流量之預測，以提供決策者中長期的水庫用水規劃及操作依據。4.輻狀基底函數類神經網路應用於洪水流量預測：應用輻狀基底函數類神經網路於洪水事件的即時流量預測，並藉由準確的預測即時流量，以提供決策者洪水時期即時的水庫操作決策依據。以上模擬人類依經驗的學習法則及判斷方式所創建的水文模式，均能達到相當的準確性，且不涉艱澀的水文物理機制或高深的統計理論，因此在應用及操作上較傳統水文的定率式概念模式或序率式統計模式容易瞭解，更由於其對水文、地文因子的變化可藉由模式對新增資料的學習加以反應，使其更具實用性及可攜性，因此應用以模擬人類依經驗的學習法則及判斷方式來創建水文模式是非常實用且適宜的。

This study presents some models that can automatically construct hydrological models by learning the experience and historical data. These models include hyper-rectangles learning algorithm, counterpropagation fuzzy-neural network, and radial basis function neural network. The Kriging starting from a statistical model of nature is introduced to cooperate with those models in constructing the hydrological information system of the Da-chia River. The system can provide reliable and accurate hydrological information for the reservoir operators and decision makers. The Kriging is used for estimating the rain gage stations. It suggests the locations for establishing or removing the rain gage stations. The hyper rectangles learning algorithm is employed to reconstruct the missing hydrological data. The rainfall-runoff model using the counterpropagation fuzzy neural network can estimate the streamflow of every ten-day. It provides very useful information for water resources planning and development. The radial basis function neural network is used for flood forecasting. It makes the accurate flood forecasting possible. Thus the reservoir operators and decision makers can count on the hydrological information system. The constructed models do not use complicate mathematics and hydrological processes. These models have certain performance characteristics in common with simulating the human nervous system and brain activity. They learn through the repeated experience. They will be easier to be used than the traditional hydrological models. Some of the hydrographic and physiographic factors are not needed to be estimated. To reconstruct hydrological models by learning the experience makes the application of models become practice.

封面
目錄
頁碼
表錄
圖錄
中文摘要
英文摘要
第一章、前言
第二章、流域水文資訊系統描述
第三章、流域雨量站網分析
3.1 研究目的
3.2 文獻回顧
3.3 研究方法
3.4 研究地區與資料選取
3.5 降雨空間變異分析與站網評估
3.5.1 無因次試驗半變異元
3.5.2 站網評估程序
3.5.3 站網評估結果
第四章、巢狀超矩形模式應用於資料補遺系統
4.1 流量資料補遺方法與理論架構
4.1.1 巢狀超矩形學習模式之重要特質
4.1.2 巢狀超矩形學習模式之基本演算法
4.2 應用巢狀超矩形學習模式於大甲溪之流量補遺
4.2.1 研究地區與資料選取
4.2.2 評判標準與結果
第五章、模糊類神經網路模式應用於流量預測系統
5.1 規則庫控制(Rule Base Control)
5.2 模糊控制(Fuzzy Control)
5.3 反傳遞類神經網路
5.3.1 Kohonen層學習演算法
5.3.2 Grossberg層的學習演算法
5.3.3 網路模式預測階段
5.4 修正型模糊CPN模式
5.5 修正型模糊CPN應用於旬流量
第六章、幅狀基底函數類神經網路應用於洪水流量預測
6.1 RBFN架構
6.2 模式訓練
6.3 模式驗證
第七章、結論與建議
7.1 結論
7.2 建議
參考文獻

Bastin, G., Lorent, B. Duque, C. and Gevers, M., “ Optimal Estimation of the Average Rainfall and Optimal Selection of Rainagae Locations”, Water Resources Research, 20(4), p463-470, 1984.
Chang F-J, Hwang Y-Y. 1999. A self-organization algorithm for real-time flood forecast. Hydrological Processes 13: 123-138.
Fiering, M.B., 1962, “On the use of correlation to augment data”, J. Am, Stat. Assoc, 57, pp.20-32
Fiering, M.B., 1967, “ Streamflow synthesis”, Harvard University Press. Cambridge, Massachusetts
Fukushima K. 1988. Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural Networks 1: 119-130.
Hirsh, R.M., 1914, “ An evaluation of some record reconstruction techniques”, Water Resour. Res.,15.1781-1790
Hecht-Nielsen R. 1987. Counterpropagation network. Applied Optics. 26: 4979-4984.
Hecht-Nielsen R. 1990. Applications of counterpropagation network. Neural Networks 1: 131-139.
Hopfield JJ. 1982. Neural networks and physical systems with emergent collective computational abilities. Proceeding of the National Academy of Scientists 79:2554-2558.
J. Park, I. W. Sandberg, “Universal Approximation Using Radial-Basis-Function Networks”, Neural Computation, 3, pp.246-257, 1991.
Kohonen T. 1998. Self-organization and associative memory. 2nd edition, Springer-Verlag.: New York.
Martheron, G., Theory of Regionalized Variables and Its Applications, Ecole National Superieure des Mines, Paris, 1971.
Matals, N.C., & B. Jacobs, 1964, “ A correlation Procedure for augmentating hydrologic data”, U.S. Geol. Surv. Prof. Pap., 434-E, E1-E7
McCulloch WS, Pitts W. 1943. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5: 115-133.
Nie J. 1997. Nonlinear time-series forecasting: A fuzzy-neural approach. Neurocomputing 16: 63-76.
Nie J, Linkens DA. 1994. Fast self-learning multivariable fuzzy controllers constructed from a modified CPN network. International Journal on Control 60: 369-393.
Nowlan SJ, Hinton FE. 1992. Simplifying neural networks by soft weight-sharing. Neural Comput. 4: 473-491.
Riggs, H.C., 1972, “Low-flow investigations”, U.S. Geol. Surv. Tech. Water Resour. Invest., 4
Rumelhart DE, Hinton GE, Willianms RJ. 1986. Learning internal representation by error propagation. Parallel Distributed Processing 1: 318-362.
Shaw, E.M., “Hydrology in Practice”, Second Edition, Van Nostrand Reinhold, London, 1989.
Schalkoff RJ. 1997. Artificial neural network. McGraw-Hill: New York.
Shamseldin AY. 1997. Application of a neural network technique to rainfall-runoff modelling. Journal of Hydrology 199: 272-294.
Sajikumar N Thandaveswara BS. 1999. A non-linear rainfall-runoff model using an artificial network. Journal of Hydrology 216: 32-55.
S. Chen, S. A. Billings, and P. M. Grant, “Recursive hybird algorithm for non-linear system identification using radial basis function networks”, INT. J. Control, Vol.55, No.5, pp.1051-1070, 1992.
S. Chen, C. F. N. Cowan, and P. M. Grant, “Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks”, IEEE Transactions on Neural Networks, Vol.2, No.2, pp.302-309, 1991.
S. Chen, C. F. N. Cowan, S. A. Billings, and P. M. Grant, “Parallel recursive prediction error algorithm for training layered neural networks”, INT. J. Control, Vol.51, No.6, pp.1215-1228, 1990.
Tianping Chen, and Hong Chen, “Approximation Capability to Function of Several Variables, Nonlinear Functionals, and Operators by Radial Basis Function Neural Networks”, IEEE Transactions on Neural Networks, Vol.6, No.4, pp.904-910, 1995.
Tianping Chen, and Hong Chen, “Universal Approximation to Nonlinear Operators by Neural Networks with Arbitrary Activation Functions and Its Application to Dynamical Systems”, IEEE Transactions on Neural Networks, Vol.6, No.4, pp.911-917, 1995.
Tomaso Poggio, and Federico Girosi, “Networks for Approximation and Learning”, Proceedings of the IEEE, Vol.78, No.9, pp.1481-1496, 1990.
Virdee, T. S., and Kottegoda, N. T., “A Brief Review of Kriging and Its Application Journal, 29(4), 1984.
Vassilas N, Tiran P, Ienne P. 1996. On modifications of Kohonen’s feature map algorithm for an efficient parallel implementation. IEEE : 932-937.
Weigend AS, Rumelhart DE, Huberman GA. 1991. Generalization by weight-elimination with application to forecasting. Advances in Neural Information Processing System 3: 875-882.
Yager RR. 1984. Approximate reasoning as a basis for rule based expert systems. IEEE Transactions on Systems, Man and Cybernetics 14: 636-673.
張斐章、黃源義，降雨在空間變異之研究，第八屆水利工程研討會，1996。
張斐章，孫建平，類神經網路及其應用於降雨─逕流過程之研究，中國農業工程學報，第43卷，第1期，pp.9-25，1997。
張斐章，黃源義，梁晉銘，「模糊推論模式之建立及其應用於水文系統之研究」，中國農業工程學報，第39卷，第1期，pp.71-83，1993。
陳莉、張斐章，1992，「巢狀超矩形學習模式於水資源系統之研究」，中國農業工程學報，Vol.38，No.3，pp.27-37。
張斐章、胡湘帆、黃源義，「應用模糊類神經網路於流量推估之研究」，八十六年度農業工程研討會，pp.37-43，1997。
鄭克聲、葉惠中，雨量站網設計與評估─區域化變數理論之應用，第八屆水利工程研討會，1996，p113-122
鄭士仁，降雨深度最佳估計方法之研究及其應用於區域雨量站網之規劃設計，國立臺灣大學農工研究所碩士論文，1993。
易任、黃文政，1984，擴展是卡門濾波理論應用於降雨逕流模式之研究-濁水溪流域，國立台灣大學農業工程研究所。
易任、王如意，1983，應用水文學，茂昌圖書有限公司。
易任、鄭克聲，1984，「脊迴歸分析法應用於河流水文特性及洪水流量預測之研究」，防災科技研究報告第73-03號。
易任、許榮庭，1987，「HEC-1洪水套裝程式檢討及修訂應用-複站洪水流量分析」，台灣水利，33卷4期。
吳戒秦，「利用具有地增近似功能的RBF類神經網路壓縮立體曲面的數據」，國立台灣大學電機工程研究所碩士論文，1996。
吳茂正，「演化輻狀基底函數網路與非線性時間序列預測」，國立台灣大學資訊工程研究所碩士論文，1997。
葉怡成，類神經網路模式應用與實作，儒林圖書有限公司，台北，1993。
大甲溪水力普查報告，經濟部能源委員會，HS-025-7504，民國75年6月。