臺灣博碩士論文加值系統

本研究採用7種GM (1, 1) 模型，預測舊濁水溪溶氧 (Dissolved Oxygen, DO) 、生化需氧量 (biochemical oxygen demand, BOD) 、化學需氧量(chemical oxygen, COD) 、懸浮固體物 (suspended solids, SS) 及氨氮 (ammonia, NH3-N) 之濃度。灰色系統理論利用系統少數 (至少4個)之輸出資料建立灰色模型 (Grey Model；GM) 近似灰色系統之動態行為，進而對此少量輸出數資料之系統進行灰預測 (Grey Prediction) 。因此可利用灰色系統理論進行灰預測。結果顯示，在預測DO時，建模的均方根誤差 (root mean squared error, RMSE) 介於1.3185至3.9834之間，預測時的RMSE介於1.0890至5.8013之間。對於R值而言，建模時的相關係數 (correlation coefficient, R) 介於-0.01至0.30之間，預測時的R值介於-0.07至0.73之間。在預測BOD時，建模時的RMSE介於7.2444至16.4952之間，預測時的RMSE介於4.0016至6.8901之間。對於R值而言，建模時的R介於0.09至0.50之間，預測時的R值介於-0.46至0.52之間。在預測COD時，建模時的RMSE介於22.5040至161.6450之間，預測時的RMSE介於23.6303至219.9561之間。對於R值而言，建模時的R介於-0.06至0.45之間，預測時的R值介於-0.68至0.46之間。在預測SS時，建模時的RMSE介於16.1784至129.2348之間，預測時的RMSE介於11.6261至50.8907之間。對於R值而言，建模時的R介於-0.11至0.19之間，預測時的R值介於-0.55至0.13之間。在預測NH3-N時，建模時的RMSE介於5.7104至6.9602之間，預測時的RMSE介於2.3144至8.5405之間。對於R值而言，建模時的R介於0.15至0.57之間，預測時的R值介於-0.68至0.37之間。無論預測DO、BOD、COD、SS或NH3-N，皆以GM (1, 1, x(0)) 、GM (1, 1, a) 、GM (1, 1, b) 三種GM (1, 1) 模型較佳。在預測DO時，RMSE介於1.0890至1.1357之間，R值介於0.39至0.73之間。在預測BOD時，RMSE介於4.0016至5.5776之間，R值介於0.02至0.52之間。在預測COD時，RMSE介於23.6303至219.9561之間，R值介於-0.11至0.46之間。在預測SS時，RMSE介於16.8088至29.3383之間，R值介於-0.08至0.13之間。在預測NH3-N時，RMSE介於2.3144至8.3636之間，R值介於0.29至0.37之間。

In this study, seven types of first-order and one-variable grey differential equation model (abbreviated as GM (1, 1) model) were used to predict the water quality of Old Zhuoshui River including dissolved oxygen (DO), biochemical oxygen demand (BOD), chemical oxygen demand (COD), suspended solids (SS), and ammonia (NH3-N). Their prediction performance was also compared. The results indicated that the root mean squared error (RMSE) was between 1.3185 and 3.9834 at constructing models when simulating DO. When predicting, they were between 1.0890 and 5.8013. The correlation coefficient (R) was between -0.01 and 0.30 when constructing models. When predicting, they were between -0.70 and 0.73. In the aspect of BOD, the RMSE was between 7.2444 and 16.4952 when constructing models. When predicting, they were between 4.0016 and 6.8901. The R was between 0.09 and 0.50 when constructing models. When predicting, they were between -0.46 and 0.52. In the aspect of COD, the RMSE was between 22.5040 and 161.6450 when constructing models. When predicting, they were between 23.6303 and 219.9561. The R was between -0.06 and 0.45 when constructing models. When predicting, they were between -0.68 and 0.46. In the aspect f SS, the RMSE was between 16.1784 and 129.2348 when constructing models. When predicting, they were between 11.6261 and 50.8907. The R was between -0.11 and 0.19 when constructing models. When predicting, they were between -0.55 and 0.13. In the aspect of NH3-N, the RMSE was between 5.7104 and 6.9602 when constructing models. When predicting, they were between 2.3144 and 8.5405. The R was between 0.15 and 0.57 when constructing models. When predicting, they were between -0.68 and 0.37. All statistical values revealed that the predicting performance of GM (1, 1, x(0)), GM (1, 1, a), and GM (1, 1, b) outperformed other GM (1, 1) models.

目錄
第一章 前言 1
1.1 研究緣起 1
1.2 研究目的 5
第二章 文獻回顧 7
2.1 灰色系統理論之發展 7
2.2 灰色系統理論之應用 10
第三章 研究方法 17
3.1 數據來源 17
3.2 GM建模 18
3.3 GM (1, 1) 派生模型 20
3.3.1 GM (1, 1) 派生模型GM (1, 1, x(1)) 20
3.3.2GM (1, 1) 派生模型GM (1, 1, x(0)) 21
3.3.3 GM (1, 1) 派生模型GM (1, 1, b) 21
3.3.4 GM (1, 1) 派生模型GM (1, 1, exp) 23
3.3.5 GM (1, 1) 派生模型GM (1, 1, C) 24
3.3.6 GM (1, 1) 模型匯總 26
3.4 GM預測效能評估 28
第四章 結果與討論 29
4.1天盛橋模擬結果分析 29
4.1.1 DO模擬結果分析 29
4.1.2 BOD模擬結果分析 34
4.1.3 COD模擬結果分析 39
4.1.4 SS模擬結果分析 44
4.1.5 NH3-N模擬結果分析 49
4.2 三和橋模擬結果分析 54
4.2.1 DO模擬結果分析 54
4.2.2 BOD模擬結果分析 59
4.2.3 COD模擬結果分析 64
4.2.4 SS模擬結果分析 69
4.2.5 NH3-N模擬結果分析 74
4.3福寶橋模擬結果分析 79
4.3.1 DO模擬結果分析 79
4.3.2 BOD模擬結果分析 84
4.3.3 COD模擬結果分析 89
4.3.4 SS模擬結果分析 94
4.3.5 NH3-N模擬結果分析 99
4.4 綜合討論 104
第五章 結論與建議 105
5.1 結論 105
5.2 建議 107
參考文獻 108
附錄 114


表目錄
表1.1　舊濁水溪流域污染來源及污染量推估 4
表4.1　天盛橋GM (1, 1) 模型預測DO的效能 30
表4.2　天盛橋GM (1, 1) 模型預測BOD的效能 35
表4.3　天盛橋GM (1, 1) 模型預測COD的效能 40
表4.4　天盛橋GM (1, 1) 模型預測SS的效能 45
表4.5　天盛橋GM (1, 1) 模型預測NH3-N的效能 50
表4.6　三和橋GM (1, 1) 模型預測DO的效能 55
表4.7　三和橋GM (1, 1) 模型預測BOD的效能 60
表4.8　三和橋GM (1, 1) 模型預測COD的效能 65
表4.9　三和橋GM (1, 1) 模型預測SS的效能 70
表4.10　三和橋GM (1, 1) 模型預測NH3-N的效能 75
表4.11　福寶橋GM (1, 1) 模型預測DO的效能 80
表4.12　福寶橋GM (1, 1) 模型預測BOD的效能 85
表4.13　福寶橋GM (1, 1) 模型預測COD的效能 90
表4.14　福寶橋GM (1, 1) 模型預測SS的效能 95
表4.15　福寶橋GM (1, 1) 模型預測NH3-N的效能 100


圖目錄
圖1.1　舊濁水溪流域圖 3
圖1.2　研究架構圖 6
圖4.1　GM (1, 1, W) DO模式模擬結果 30
圖4.2　GM (1, 1, C) DO模式模擬結果 31
圖4.3　GM (1, 1, x(1)) DO模式模擬結果 31
圖4.4　GM (1, 1, x(0)) DO模式模擬結果 32
圖4.5　GM (1, 1, a) DO模式模擬結果 32
圖4.6　GM (1, 1, b) DO模式模擬結果 33
圖4.7　GM (1, 1, e) DO模式模擬結果 33
圖4.8　GM (1, 1, W) BOD模式模擬結果 35
圖4.9　GM (1, 1, C) BOD模式模擬結果 36
圖4.10　GM (1, 1, x(1)) BOD模式模擬結果 36
圖4.11　GM (1, 1, x(0)) BOD模式模擬結果 37
圖4.12　GM (1, 1, a) BOD模式模擬結果 37
圖4.13　GM (1, 1, b) BOD模式模擬結果 38
圖4.14　GM (1, 1, e) BOD模式模擬結果 38
圖4.15　GM (1, 1, W) COD模式模擬結果 40
圖4.16　GM (1, 1, C) COD模式模擬結果 41
圖4.17　GM (1, 1, x(1)) COD模式模擬結果 41
圖4.18　GM (1, 1, x(0)) COD模式模擬結果 42
圖4.19　GM (1, 1, a) COD模式模擬結果 42
圖4.20　GM (1, 1, b) COD模式模擬結果 43
圖4.21　GM (1, 1, e) COD模式模擬結果 43
圖4.22　GM (1, 1, W) SS模式模擬結果 45
圖4.23　GM (1, 1, C) SS模式模擬結果 46
圖4.24　GM (1, 1, x(1)) SS模式模擬結果 46
圖4.25　GM (1, 1, x(0)) SS模式模擬結果 47
圖4.26　GM (1, 1, a) SS模式模擬結果 47
圖4.27　GM (1, 1, b) SS模式模擬結果 48
圖4.28　GM (1, 1, e) SS模式模擬結果 48
圖4.29　GM (1, 1, W) NH3-N模式模擬結果 50
圖4.30　GM (1, 1, C) NH3-N模式模擬結果 51
圖4.31　GM (1, 1, x(1)) NH3-N模式模擬結果 51
圖4.32　GM (1, 1, x(0)) NH3-N模式模擬結果 52
圖4.33　GM (1, 1, a) NH3-N模式模擬結果 52
圖4.34　GM (1, 1, b) NH3-N模式模擬結果 53
圖4.35　GM (1, 1, e) NH3-N模式模擬結果 53
圖4.36　GM (1, 1, W) DO模式模擬結果 55
圖4.37　GM (1, 1, C) DO模式模擬結果 56
圖4.38　GM (1, 1, x(1)) DO模式模擬結果 56
圖4.39　GM (1, 1, x(0)) DO模式模擬結果 57
圖4.40　GM (1, 1, a) DO模式模擬結果 57
圖4.41　GM (1, 1, b) DO模式模擬結果 58
圖4.42　GM (1, 1, e) DO模式模擬結果 58
圖4.43　GM (1, 1, W) BOD模式模擬結果 60
圖4.44　GM (1, 1, C) BOD模式模擬結果 61
圖4.45　GM (1, 1, x(1)) BOD模式模擬結果 61
圖4.46　GM (1, 1, x(0)) BOD模式模擬結果 62
圖4.47　GM (1, 1, a) BOD模式模擬結果 62
圖4.48　GM (1, 1, b) BOD模式模擬結果 63
圖4.49　GM (1, 1, e) BOD模式模擬結果 63
圖4.50　GM (1, 1, W) COD模式模擬結果 65
圖4.51　GM (1, 1, C) COD模式模擬結果 66
圖4.52　GM (1, 1, x(1)) COD模式模擬結果 66
圖4.53　GM (1, 1, x(0)) COD模式模擬結果 67
圖4.54　GM (1, 1, a) COD模式模擬結果 67
圖4.55　GM (1, 1, b) COD模式模擬結果 68
圖4.56　GM (1, 1, e) COD模式模擬結果 68
圖4.57　GM (1, 1, W) SS模式模擬結果 70
圖4.58　GM (1, 1, C) SS模式模擬結果 71
圖4.59　GM (1, 1, x(1)) SS模式模擬結果 71
圖4.60　GM (1, 1, x(0)) SS模式模擬結果 72
圖4.61　GM (1, 1, a) SS模式模擬結果 72
圖4.62　GM (1, 1, b) SS模式模擬結果 73
圖4.63　GM (1, 1, e) SS模式模擬結果 73
圖4.64　GM (1, 1, W) NH3-N模式模擬結果 75
圖4.65　GM (1, 1, C) NH3-N模式模擬結果 76
圖4.66　GM (1, 1, x(1)) NH3-N模式模擬結果 76
圖4.67　GM (1, 1, x(0)) NH3-N模式模擬結果 77
圖4.68　GM (1, 1, a) NH3-N模式模擬結果 77
圖4.69　GM (1, 1, b) NH3-N模式模擬結果 78
圖4.70　GM (1, 1, e) NH3-N模式模擬結果 78
圖4.71　GM (1, 1, W) DO模式模擬結果 80
圖4.72　GM (1, 1, C) DO模式模擬結果 81
圖4.73　GM (1, 1, x(1)) DO模式模擬結果 81
圖4.74　GM (1, 1, x(0)) DO模式模擬結果 82
圖4.75　GM (1, 1, a) DO模式模擬結果 82
圖4.76　GM (1, 1, b) DO模式模擬結果 83
圖4.77　GM (1, 1, e) DO模式模擬結果 83
圖4.78　GM (1, 1, W) BOD模式模擬結果 85
圖4.79　GM (1, 1, C) BOD模式模擬結果 86
圖4.80　GM (1, 1, x(1)) BOD模式模擬結果 86
圖4.81　GM (1, 1, x(0)) BOD模式模擬結果 87
圖4.82　GM (1, 1, a) BOD模式模擬結果 87
圖4.83　GM (1, 1, b) BOD模式模擬結果 88
圖4.84　GM (1, 1, e) BOD模式模擬結果 88
圖4.85　GM (1, 1, W) COD模式模擬結果 90
圖4.86　GM (1, 1, C) COD模式模擬結果 91
圖4.87　GM (1, 1, x(1)) COD模式模擬結果 91
圖4.88　GM (1, 1, x(0)) COD模式模擬結果 92
圖4.89　GM (1, 1, a) COD模式模擬結果 92
圖4.90　GM (1, 1, b) COD模式模擬結果 93
圖4.91　GM (1, 1, e) COD模式模擬結果 93
圖4.92　GM (1, 1, W) SS模式模擬結果 95
圖4.93　GM (1, 1, C) SS模式模擬結果 96
圖4.94　GM (1, 1, x(1)) SS模式模擬結果 96
圖4.95　GM (1, 1, x(0)) SS模式模擬結果 97
圖4.96　GM (1, 1, a) SS模式模擬結果 97
圖4.97　GM (1, 1, b) SS模式模擬結果 98
圖4.98　GM (1, 1, e) SS模式模擬結果 98
圖4.99　GM (1, 1, W) NH3-N模式模擬結果 100
圖4.100　GM (1, 1, C) NH3-N模式模擬結果 101
圖4.101　GM (1, 1, x(1)) NH3-N模式模擬結果 101
圖4.102　GM (1, 1, x(0)) NH3-N模式模擬結果 102
圖4.103　GM (1, 1, a) NH3-N模式模擬結果 102
圖4.104　GM (1, 1, b) NH3-N模式模擬結果 103
圖4.105　GM (1, 1, e) NH3-N模式模擬結果 103

參考文獻
白子易，「下水道系統生化動力模式建立之研究」，博士論文，國立中央大學環境工程研究所，中壢 (2001) 。
白子易，黃愷俊，李昭政，王順成，張迪惠，黃榮德，呂鴻光，「利用QUAL2K進行大裏溪水質自然淨化工法評選」，台灣環境資源永續發展協會研討會論文集，台灣環境資源永續發展協會/中央大學，中壢 (2008) 。
行政院環境保護署，「98年中部地區河川污染整治推動、輔導及評析計畫」，臺北 (2010) 。
余呂豐，「以灰色多目標規劃進行工業區廢水廠最佳控制之研究」，碩士論文，朝陽科技大學環境工程與管理系，台中 (2008)。
何欣憲，「柔性計算應用於都市及工業廢污水廠出流水水質預測之研究」，碩士論文，朝陽科技大學環境工程與管理系，台中 (2006)。
何佳祥、莊淳元、林玉萍、陳建穀、萬騰州，「應用類神經網路系統及灰色系統理論於USAB 廢水處理程式放流水質預測」，第14 屆環工年會論文光碟 (2002) 。
林東陞、何欣憲、白子易、蔡勇斌、劉俊志、曹志安，「以BNN及RGM (1,1) 模式預測處理實際廢水TNCU3程式之出流TCOD及SCOD 」，第14屆下水道及水環境再生研討會論文集，臺北，第110-117頁 (2004) 。
胡漢強「以線上水質監控參數預測工業廢水廠出流水水質-灰色系統及類神經之應用」，碩士論文，朝陽科技大學環境工程與管理系研究所，台中 (2007) 。
陳宜清、柳孟宏，「QUAL2K 模式應用於河川水質管理－以筏子溪為例」，環境與管理研究，8 (2) ，第89-113頁 (2007) 。
張鈞凱、張慶源，「利用QUAL2K模擬河川廊道上之水稻田對水質的影響−以三峽河為例」，水稻田農業多樣性機能研討會，農業工程研究中心/僑光技術學院，台中，(2005)。
蔡勇斌、邢治宇、萬騰州，「灰色系統理論應用於廢水處理預測之研究」，第24屆廢水處理技術研討會論文光碟，新竹 (1999) 。
蔡嘉和，「以活性污泥模式2d、類神經網路及灰色理論預測廢水生物處理程式出流水水質之研究」，碩士論文，朝陽科技大學環境工程與管理系研究所，台中 (2003) 。
蘇漢昌，「應用適應性模糊推論系統改善類神經網路預測工業廢水廠出流水水質之研究」，碩士論文，朝陽科技大學環境工程與管理系研究所，台中 (2008)。
Chang S.C., Pai T.Y., Ho H.H., Leu H.G. and Shieh Y.R. Evaluating Taiwan’s air quality variation trends using grey system theory. Journal of the Chinese Institute of Engineers, 30(2), 361-367 (2007).
Pai T.Y., Ouyang C.F., Su J.L. and Leu H.G. Modelling the steady-state effluent characteristics of the TNCU process with ASM2d under varied SRT conditions. Journal of the Chinese Institute of Environmental Engineering, 10(1), 35-42 (2000a).
Pai T.Y., Ouyang C.F., Liao Y.C. and Leu H.G. Oxygen transfer in gravity flow sewer. Water Science and Technology, 42(3-4), 417-422 (2000b).
Pai T.Y., Ouyang C.F., Su J.L. and Leu H.G. Modeling the stable effluent qualities of the A2O process with Activated Sludge Model 2d under different return supernatant. Journal of the Chinese Institute of Engineers, 24(1), 75-84 (2001a).
Pai T.Y., Ouyang C.F., Su J.L. and Leu H.G. Modelling the steady-state effluent characteristics of the TNCU process under different return mixed liquid. Applied Mathematical Modelling, 25(12), 1025-1038 (2001b).
Pai T.Y., Chuang S.H., Tsai Y.P. and Leu H.G. Development of two-stage nitrification/denitrification model (TaiWan Extension Activated sludge model NO.1) for BNR process. Journal of the Chinese Institute of Environmental Engineering, 14(1), 51-60 (2004a).
Pai T.Y., Tsai Y.P., Chou Y.J., Chang H.Y., Leu H.G. and Ouyang C.F. Microbial kinetic analysis of three different types of EBNR process. Chemosphere, 55(1), 109-118 (2004b).
Pai T.Y., Chuang S.H., Tsai Y.P. and Ouyang C.F. Modelling a combined anaerobic/anoxic oxide and rotating biological contactors process under dissolved oxygen variation by using an activated sludge - biofilm hybrid model. Journal of Environmental Engineering-ASCE, 130(12), 1433-1441 (2004c).
Pai T.Y. Modeling nitrite and nitrate variations in A2O process under different return oxic mixed liquid using an extended model. Process Biochemistry, 42(6), 978-987 (2007).
Pai T.Y., Hanaki K., Ho H.H. and Hsieh C.M. Using grey system theory to evaluate transportation on air quality trends in Japan, Transportation Research Part D: Transport and Environment, 12 (3), 158-166 (2007a).
Pai T.Y., Tsai Y.P., Lo H.M., Tsai C.H. and Lin C.Y. Grey and neural network prediction of suspended solids and chemical oxygen demand in hospital wastewater treatment plant effluent, Computers & Chemical Engineering, 31(10), 1272-1281 (2007b).
Pai T.Y. Gray and neural network prediction of effluent from the wastewater treatment plant of industrial park using influent quality. Environmental Engineering Science, 25(5), 757-766 (2008).
Pai T.Y., Chuang S.H., Ho H.H., Yu L.F., Su H.C. and Hu H.C. Predicting performance of grey and neural network in industrial effluent using online monitoring parameters. Process Biochemistry, 43(2), 199-205 (2008a).
Pai T.Y., Chuang S.H., Wan T.J., Lo H.M., Tsai Y.P., Su H.C., Yu L.F., Hu H.C. and Sung P.J. Comparisons of grey and neural network prediction of industrial park wastewater effluent using influent quality and online monitoring parameters. Environmental Monitoring and Assessment, 146(1-3), 51-66 (2008b).
Pai T.Y., Chiou R.J. and Wen H.H. Evaluating impact level of different factors in environmental impact assessment for incinerator plants using GM (1, N) model. Waste Management, 28(10), 1915-1922 (2008c).
Pai T.Y., Wang S.C., Lo H.M., Chiang C.F., Liu M.H., Chiou R.J., Chen W.Y., Hung P. S., Liao W.C., Leu H.G. Novel modeling concept for evaluating the effects of cadmium and copper on heterotrophic growth and lysis rates in activated sludge process. Journal of Hazardous Materials, 166(1), 200-206 (2009a).
Pai T.Y., Wan T.J., Hsu S.T., Chang T.C., Tsai Y.P., Lin C.Y., Su H.C. and Yu L.F. Using fuzzy inference system to improve neural network for predicting hospital wastewater treatment plant effluent. Computers & Chemical Engineering, 33(7), 1272-1278 (2009b).
Pai T.Y., Wang S.C., Chiang C.F., Su H.C., Yu L.F., Sung P.J., Lin C.Y. and Hu H.C. Improving neural network prediction of effluent from biological wastewater treatment plant of industrial park using fuzzy learning approach. Bioprocess and Biosystems Engineering, 32(6), 781-790 (2009c).
Pai T.Y., Chang H.Y., Wan T.J., Chuang S.H. and Tsai Y.P. Using an extended activated sludge model to simulate nitrite and nitrate variations in TNCU2 process. Applied Mathematical Modelling, 33(11), 4259-4268 (2009d).
Pai T.Y., Wang S.C., Lin C.Y., Liao W.C., Chu H.H., Lin T.S., Liu C.C. and Lin S.W. Two types of organophosphate pesticides and their combined effects on heterotrophic growth rates in activated sludge process. Journal of Chemical Technology and Biotechnology, 84(12), 1773-1779 (2009e).
Pai T.Y., Wan T.J., Tsai Y.P., Tzeng C.J., Chu H.H., Tsai Y.S. and Lin C.Y. Effect of sludge retention time on biomass and kinetic parameter of two nitrifying species in anaerobic/oxic process. CLEAN-Soil Air Water, 38(2), 167-172 (2010a).
Pai T.Y., Chiou R.J., Tzeng C.J., Lin T.S., Yeh S.C., Sung P.J., Tseng C.H., Tsai C.H., Tsai Y.S., Hsu W.J. and Wei Y.L. Variation of biomass and kinetic parameter for nitrifying species in TNCU3 process at different aerobic hydraulic retention time. World Journal of Microbiology & Biotechnology, 26(4), 589-597 (2010b).
Pai T.Y., Huang J.D., Wang S.C., Chang D.H., Huang K.J., Lee C.C., Lin S.R., Tseng C.H., Sung P.J. and Leu H.G. Evaluate the establishment site of ecological water purification processes in Dali River using QUAL2K. Suatainable Environment Research, 20(4), 239-243 (2010c).
Pai T.Y., Chen C.L., Chung H., Ho H.H. and Shiu T.W. Monitoring and assessing variation of sewage quality and microbial functional groups in a trunk sewer line. Environmental Monitoring and Assessment, 171(1-4), 551-560 (2010d).
Pai T.Y., Lin K.L., Shie J.L., Chang T.C. and Chen B.Y. Predicting the co-melting temperatures of municipal solid waste incinerator fly ash and sewage sludge ash using grey model and neural network. Waste Management & Research (2011a). (In press)
Pai T.Y., Ho C.L., Chen S.W., Lo H.M., Sung P.J., Lin S.W., Lai W.J., Tseng S.C., Ciou S.P., Kuo J.L. and Kao J.T. Using seven types of GM (1, 1) model to forecast hourly particulate matter concentration in Banciao City of Taiwan. Water, Air, and Soil Pollution (2011b). (In press)
Pai T.Y., Hanaki K., Su H.C. and Yu L.F. A 24-h forecast of oxidant concentration in Tokyo using neural network and fuzzy learning approach. CLEAN-Soil Air Water (2011c). (In press)
Pai T.Y., Yang P.Y., Wang S.C., Lo H.M., Chiang C.F., Kuo J.L., Chu H.H., Su H.C., Yu L.F., Hu H.C. and Chang Y.H. Predicting effluent from the wastewater treatment plant of industrial park based on fuzzy network and influent quality. Applied Mathematical Modelling (2011d). (In press)