臺灣博碩士論文加值系統

在預測颱洪事件的流量歷線時，流量歷線的漲水段與退水段有著不同的雨量與流量的對應關係，故本研究為了探討兩者不同的水文特性，建立出上升段與退水段模糊關係矩陣，並應用兩個模糊關係矩陣預測降雨事件所造成之逕流量，提供相關的訊息給予決策者參考，並作出合適之方案。本文首先依據流量歷線的漲水與退水趨勢將雨量資料分成上升段雨量資料與退水段雨量資料，並透過兩種雨量資料建立上升段與退水段模糊關係矩陣，利用檢定資料各別率定上升段與退水段模糊關係矩陣的參數，再利用驗證資料檢視參數的設定是否正確，故本研究建構出完整的上升段與退水段模糊關係矩陣後，接續設計兩段式模糊關係模式，在雨量資料輸入至模式前加入一個判斷式，讓每筆輸入的雨量資料依據判斷式選擇上升段或退水段模糊關係矩陣進行流量推估，結果顯示兩段式模糊關係模式之流量推估結果優於單一模糊關係模式與倒傳遞類神經網路模式，模式建立不需要大量的歷史資料，亦能簡化模式計算難易度。

When forecasting the flow of typhoon flood event,the corresponding relationship between the rainfall and the discharge of the rising limb and falling limb are different. In this study, in order to explore the different hydrological characteristics of the rising fuzzy relation matrix and the falling fuzzy relation matrix. The two fuzzy relation matrix are used to predict the runoff by rainfall data, and provide related information to the policy-maker for reference. According to the trend of flow, this paper divide rainfall data into the rising limb and the falling limb of rainfall data. Using the rainfall data corresponded to the rising limb and the falling limb to construct the rising fuzzy relation matrix and the falling fuzzy relation matrix. Using the test data to adjust the parameters of the rising fuzzy relation matrix and the falling fuzzy relation matrix, and using verification data to check that the parameters are set correctly. And this paper designs the two-stage fuzzy relation model. This model add a judgment, so that each input data of rainfall based on the judgments choose rising fuzzy relation matrix or the falling fuzzy relation matrix to estimate the discharge. The results show that performance of the two-stage fuzzy relation model is better than the single fuzzy relational model and Back-Propagation Network model.

誌謝 I
摘要 II
Abstract III
表目錄 VII
圖目錄 VIII
第一章 前言 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 研究架構 2
第二章 文獻回顧 5
第三章 理論分析 9
3.1 模糊理論 9
3.1.1 模糊集合 9
3.1.2 模糊集合運算 10
3.1.3 模糊隸屬函數之形式 10
3.1.4 模糊關係 12
3.2 模糊時間數列基礎定義 13
3.3 線性轉換函數 17
3.4 倒傳遞類神經網路 18
3.4.1 BPN學習過程的建立 19
3.4.2 BPN回想過程的建立 23
第四章 研究區域與模式建立 25
4.1 研究區域概述 25
4.2 研究資料處理 26
4.3 單一模糊關係模式建構 28
4.3.1 單一模糊關係模式之論域與參數設定 30
4.3.2 單一模糊關係模式 32
4.3.3 退水係數 35
4.4 上升退水段模糊關係矩陣建構 36
4.4.1 上升退水段模糊關係矩陣之論域與參數設定 37
4.4.2 上升退水段已知之模糊關係模式 38
4.5 倒傳遞類神經網路架構與參數訂定 42
4.6 兩段式模糊關係模式之應用 45
4.7 模式評鑑指標 47
第五章 結果與討論 49
5.1 單一模糊關係模式預測結果 49
5.1.1 單一模糊關係模式檢定 49
5.1.2 單一模糊關係模式驗證 53
5.2 上升退水段已知之模糊關係模式預測結果 56
5.2.1 上升退水段已知之模糊關係模式檢定 56
5.2.2 上升退水段已知之模糊關係模式驗證 60
5.3 倒傳遞類神經網路模式預測結果 63
5.3.1 倒傳遞類神經網路模式檢定 63
5.3.2 倒傳遞類神經網路模式驗證 67
5.4 兩段式模糊關係模式預測結果 70
5.4.1 兩段式模糊關係模式檢定 70
5.4.2 兩段式模糊關係模式驗證 74
5.4.3 判斷式對於判斷上升與退水趨勢之準確度分析 77
5.5 系集模式之比較結果 78
5.5.1 單一模糊關係模式與上升退水段已知之模糊關係模式比較 78
5.5.2 兩段式模糊關係模式與BPN模式比較 80
5.5.3 兩段式模糊關係模式與單一模糊關係模式、BPN模式比較 81
5.5.4 兩段式模糊關係模式與上升退水段已知之模糊關係模式比較 82
第六章 結論與建議 85
6.1 結論 85
6.2 建議 85
參考文獻 87

1.Adamowski, K., G.-C. Liang and G. G. Patry. (1998). "Annual maxima and partial duration flood series analysis by parametric and non-parametricmethods." Hydrological Processes,12(10-11), 1685-
1699.
2.Borga, M. (2002). "Accuracy of radar rainfall estimates for streamflow simulation." Journal of Hydrology, 267(1–2), 26-39.
3.Chen, S.-M. (1996). "Forecasting enrollments based on fuzzy time series." Fuzzy Sets and Systems, 81(3), 311-319.
4.Chen, Shyi-Ming and Hwang, Jeng-Ren. (2000). "Temperature prediction using fuzzy time series." Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 30(2), 263-275.
5.Cheng, C.-H., S.-F. Huang and H.-J. Teoh. (2011). "Predicting daily ozone concentration maxima using fuzzy time series based on a two-stage linguistic partition method." Computers & Mathematics with Applications, 62(4), 2016-2028.
6.Chiew, F. and T. McMahon. (1994). "Application of the daily rainfall-runoff model MODHYDROLOG to 28 Australian catchments." Journal of Hydrology, 153(1–4), 383-416.
7.Chow, V. T. M. D. R. M. L. W. (1988). Applied hydrology. New York, McGraw-Hill.
8.Dorado J , Rabunal J and Pazos A. (2003). "Prediction and modeling of the rainfall –runoff transformation of a typical urban basin using ANN and GP ", Applied Artificial Intelligence, vol.17, no.4 , 329-343.
9.Dawson, C. W., R. J. Abrahart, A. Y. Shamseldin and R. L. Wilby. (2006). "Flood estimation at ungauged sites using artificial neural networks." Journal of Hydrology, 319(1–4), 391-409.
10.Huarng, K. (2001). "Effective lengths of intervals to improve forecasting in fuzzy time series." Fuzzy Sets and Systems, 123(3), 387-394.
11.Hsu, K.L., V.G. Hoshin, and S. Soroosh. (1995). "Artificial neural network modeling of the rainfall-runoff process ",Water Resources Research, Vol.31, No.10, 2517-2530.
12.Hwang, Jeng-Ren, Chen, Shyi-Ming and Lee, Chia-Hoang. (1998). "Handling forecasting problems using fuzzy time series." Fuzzy Sets and Systems, 100(1–3), 217-228.
13.Jakeman, A. J., I. G. Littlewood and P. G. Whitehead. (1990). "Computation of the instantaneous unit hydrograph and identifiable component flows with application to two small upland catchments." Journal of Hydrology, 117(1–4), 275-300.
14.Lee, Li-Wei, Wang, Li-hui and Chen, Shyi-Ming. (2006). "Handling forecasting problems based on two-factors high-order fuzzy time series." Fuzzy Systems, IEEE Transactions on ,14(3), 468-477.
15.Pritpal, Singh and Bhogeswar, Borah. (2013). "High-order fuzzy-neuro expert system for time series forecasting." Knowledge-Based Systems, 46(2013), 12-21.
16.Reed, D. W., Robson, A.J. (1999). Flood Estimation Handbook. Wallingford, UK.
17.Riad, S and Mania, J. (2004) . "Rainfall-Runoff Model Using an Artificial Neural Network Approach ", Mathematical and Computer Modelling, 40(7), 839-846.
18.Shu, C. and T. B. M. J. Ouarda. (2008). "Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system." Journal of Hydrology, 349(1–2), 31-43.
19.Song, Q. and B. S. Chissom. (1993). "Forecasting enrollments with fuzzy time series — Part I." Fuzzy Sets and Systems, 54(1), 1-9.
20.Song, Q. and B. S. Chissom. (1993). "Fuzzy time series and its models." Fuzzy Sets and Systems, 54(3), 269-277.
21.Song, Q. and B. S. Chissom (1994). "Forecasting enrollments with fuzzy time series — Part II." Fuzzy Sets and Systems, 62(1), 1-8.
22.Thirumalaiah, K. and C.D. Makarand. (2000). "Hydrological Forecating Using Neural Networks ", Journal Of Hydrologic Engineering, Vol.5, No.2 , 180-189.
23.Teemu, S., Kokkonen, A. J. J. (2001). "A comparison of metric and conceptual approaches in rainfall-runoff modeling and its implications." Water Resources Research , 3737, 2345-2352.
24.Yu, H.-K. (2005). "Weighted fuzzy time series models for TAIEX forecasting." Physica A: Statistical Mechanics and its Applications, 349(3–4), 609-624.
25.王俊翰(2013)。利用模糊時間數列推估未設測站流量。未出版之碩士論文，逢甲大學土木及水利工程研究所，臺中市。
26.張嘉玲、王傳益、李孟遠(2012)。應用倒傳遞類神經網路於集水區流 量預測-以台北水源特定區為例。臺灣水利期刊，60(2)，98-104。
27.葉怡成(1995)。類神經網路模式應用與實作。臺中市:儒林圖書有限公司。