Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/45425
Full metadata record
???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
---|---|---|
dc.contributor.advisor | 駱尚廉 | |
dc.contributor.author | Guan-De Wu | en |
dc.contributor.author | 吳冠德 | zh_TW |
dc.date.accessioned | 2021-06-15T04:19:28Z | - |
dc.date.available | 2011-10-03 | |
dc.date.copyright | 2009-12-29 | |
dc.date.issued | 2009 | |
dc.date.submitted | 2009-11-10 | |
dc.identifier.citation | Adeney, K.M., and Korenberg, M.J., 2000. Iterative fast orthogonal search algorithm for MDL-based training of generalized single-layer network. Neural Networks, Vol. 13, No. 7, 787-799.
Alpsan, D., Towsey, M., Ozdamar, O., Tsoi, A.C., and Ghista, D.N., 1995. Efficacy of modeified backpropagation and optimization methods on a real-world medical problem. Neural Networks, Vol. 8, No. 6, 945-962. Akira, S., 1991.1. An analytical study of the momentum term in a back-propagation algorithm. Proceedings of the 1991 International Conference on Artificial Neural Networks - ICANN-91, Finland, 617-622. Baba, N., 1989. A new approach for finding the global minimum of error function of neural networks. Neural Networks, Vol. 2, No. 5, 367-373. Bae, H., Kim S., and Kim, Y.J., 2006. Decision algorithm based on data mining for coagulant type and dosage in water treatment systems, Water Science & Technology. Vol. 53, No. 4-5, 321-329. Baxter, C.W., Stanley, S.J., and Zhang, Q., 1999. Development of a fullscale artificial neural network model for the removal of natural organic matter by enhanced coagulation. Journal of Water Supply: Research and Technology - Aqua Vol. 48, No. 4, 129-136. Benardos, P.G., and Vosniakos, G.-C., 2007. Optimizing feedforward artificial neural network architecture. Engineering Applications of Artificial Intelligence, Vol. 20, No. 3, 365-382. Bochereau L., and Boutgine P., 1990.1. Extraction of semantic features and logical reules from a multilayer neural network. International Joint Conference on Neural Networks, Washington DC, Vol. 2, 579-582. Cammarata, G., Cavalieri, S., and Fichera A., 1995. A Neural Network Architecture for Noise Prediction. Neural Networks, Vol. 8, No. 6, 963-973. Chelani, A.B., Chalapati Rao, C.V., Phadke, K.M., and Hasan, M.Z., 2002. Prediction of sulphur dioxide concentration using artificial neural networks. Environmental Modelling and Software, Vol. 17, No. 2, 159-166. Chelouah, R., and Siarry, R., 2000. Tabu search applied to global optimization. European Journal of Operational Research, Vol. 123, No. 2, 256-270. Chen, C.L., and Hou, P.L., 2006. Fuzzy model identification and control system design for coagulation chemical dosing of potable water. Water Science & Technology: Water Supply, Vol. 6, No. 3, 97-104. Choy, M.C., Srinivasan, D., and Cheu, R.L., 2006. Neural networks for continuous online learning and control. IEEE Transactions on Neural Networks, Vol. 17, No. 5, 1511-1531. Chun, M.G., Kwak, K.C., and Ryu, J.W., 1999.8. Application of ANFIS for coagulant dosing process in a water purification plant. Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99, Seoul, Korea, 1743-1748. Cichocki, A., and Unbehauen, R., 1993. Neural networks for optimization and signal processing. John Wiley & Sons, New York. Collins, A.G., Nix, S.J., Tsay, T.K., Gera, A., and Hopkins, M.A., 1990. The potential for expert systems in water utility operation and management. Journal of American Water Works Association, Vol. 82, No. 9, 44-51. Corzo, G., Solomatine, D., 2007. Knowledge-based modularization and global optimization of artificial neural network models in hydrological forecasting. Neural Networks, Vol. 20, No. 4, 528-536. Cybenko, G., 1989. Approximations by superpositons of a sigmoidal function, Mathematics of Control, Signals and Systems. Vol. 2, No. 4, 303-314 Czerniczyniec, M., Farías, S., Magallanes, J., and Cicerone, D., 2007. Arsenic(V) adsorption onto biogenic hydroxyapatite: solution composition effects. Water Air Soil Pollution, Vol. 180, No. 1-4, 75-82. Deveughele, S., and Do-Quang, Z., 2004. Neural networks: an efficient approach to predict on-line the optimal coagulant dose. Water Science and Technology: Water Supply, Vol. 4, No. 5-6, 87-94. Duch, W., and Jankowski, N., 1999. Survey of neural transfer functions. Neural Computing Surveys, Vol. 2, 163-212. French, M.N., Krajewski, W.F., and Cuykendall, R.R., 1992. Rainfall forecasting in space and time using a neural network. Journal of Hydrology, Vol. 137, No. 1-4, 1-33. Funahashi, K., 1989. On the approximate realization of continuous mappings by neural networks. Neural Networks, Vol. 2, No. 3, 183-192. Gagnon, C., Grandjean, B.P.A., and Thibault, J., 1997. Modelling of coagulant dosage in a water treatment plant. Artificial Intelligence in Engineering, Vol. 11, No. 4, 401-404. Guler, I., and Ubeyli, E.D., 2005. Automatic detection of ophthalmic artery stenosis using the adaptive neuro-fuzzy inference system. Engineering Applications of Artificial Intelligence, Vol. 18, No. 4, 413-422. Han, T.H., Nahm, E.S., Woo, K.B., Kim, C.J., and Ryu, J.W., 1997.7. Optimization of coagulant dosing process in water purification system. Proceedings of the 1997 36th SICE annual conference. South Korea, 1105-1109. Hebb, D.O., 1949. The Organization of Behavior,Wiley, New York. Hecht-Nielsen, R., 1987.6. Kolmogorov’s mapping neural network existence theorem. IEEE First International Joint Conference on Neural Networks, San Diego, California, 11-14. He, Y., Liu, G.P., Rees, D., and Wu, M., 2007. Stability analysis for neural networks with time-varying interval delay. Transactions on Neural Networks, Vol. 18, No. 6, 1850-1854. Hinton G.E., Sejnowskii J.J., and Ackley D.H., 1984. Boltzmann machine: constraint satisfaction networks that learn. Technical Report CMU-CS-84-119, Carnegie Mellon University, 1984. Hirose, Y., Yamashita, K., and Hijiya, S., 1991. Back-Propagation Algorithm Which Varies the Number of Hidden Units. Neural Networks, Vol. 4, No. 1, 61-66. Hopfield J.J, 1982. Neural Networks and Physical Systems with emergent collective computerational abilities. Proc. Natl. Acad, USA, Vol. 79, pp2554-2558 Hornik, K., Stinchcombe, M., White, H., 1989. Multilayer feedforward networks are universal approximators. Neural Networks, Vol. 2, No. 5, 359-366. Huang, G.B., Saratchandran, P., and Sundararajan, N., 2005. A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Transactions on Neural Networks, Vol. 16, No. 1, 57-67. Huang, S., Tan, K., and Lee, T., 2006. Nonlinear adaptive control of interconnected systems using neural networks. IEEE Transactions on Neural Networks, Vol.17, No. 1, 243-246. Jang, J. S. R., 1993. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetics, Vol. 23, No. 3, 665-685. Joo, D.S., Choi, D.J., and Park, H., 2000. The effects of data preprocessing in the determination of coagulant dosing rate. Water Research, Vol. 34, No. 13, 3295-3302. Jordanov, I., and Georgieva, A., 2007. Neural network learning with global heuristic search. IEEE Transactions on Neural Networks, Vol. 18, No. 3, 937-942. Karaca, F., and Ozkaya, B., 2006. NN-LEAP: A neural network-based model for controlling leachate flow-rate in a municipal solid waste landfill site. Environmental Modelling and Software, Vol. 21, No. 8, 1190-1197. Kim, H.S., and Kim, S.H., 1993. The experimental study of prediction optimum dosage of PAC using jar-test results. Journal of Water and Wastewater, Vol. 2, 39-45. KrishnaKumar, K., 1993. Optimization of the neural net connectivity pattern using a backpropagation algorithm. Neurocomputing, Vol. 5, No. 6, 273-286. Larmrini, B., Benhammou, A., Le Lann, M.V., and Karama., A., 2005. A neural software sensor for online prediction of coagulant dosage in a drinking water treatment plant. Transactions of the Institute of Measurement and Control, Vol. 27, No. 3, 195-213. Leung, H., Lo, T., and Wang, S., 2001. Prediction of noisy chaotic time series using an optimal radial basis function neural network. IEEE Transactions on Neural Networks, Vol. 12, No. 5, 1163–1172. Li, C., Liao, X., Zhang, R., and Prasad, A., 2005. Global robust exponential stability analysis for interval neural networks with time-varying delays. Chaos, Solitons and Fractals, Vol. 25, No. 3, 751-757. Liu S., and Wang, J., 2006. A simplified dual neural network for quadratic programming with its KWTA application. IEEE Transactions on Neural Networks, Vol. 17, No. 6, 1500-1510. Lu, H., and He, Z., 2005. Global exponential stability of delayed competitive neural networks with different time scales. Neural Networks, Vol. 18, No. 3, 243-250. Maier, H.R., Margan, N., and Chow, C.W.K., 2004. Use of artificial neural networks for predicting optimal alum doses and treated water quality parameters. Environmental Modeling and Software, Vol. 19, No. 5, 485-494. McCollister G.M., and Wilson, K.R., 1975. Linear Stochastic Models for Forecasting Daily Maxima and Hourly Concentrations of Air Pollutants. Atmospheric Environment, Vol. 9, No. 4, 417-423. McCulloch, W.S., and Pitts, W., 1943. A logical calculs of the ideas immanent in nervous activity. Bulletin of Mathematical Biology, Vol. 5, No. 4, 115-133. Minsky, M., and Papert, S., 1969. Perceptrons, Cambridge, MIT Press. Mirsepassi, A., Cathers, B., and Dharmappa, H.B., 1995. Application of artificial neural networks to the real time operation of water treatment plants. IEEE International Conference on Neural Networks - Conference Proceedings, Vol. 1, 516-521. Ossenbruggen, P.J., 1985. Time series models for treatment of surface waters. Jounal of Environmental Engineering, ASCE, Vol. 111, No. 1, 27-44. Peng, J.X., Li, K., and Huang, D.S., 2006. A hybrid forward algorithm for RBF neural network construction. IEEE Transactions on Neural Networks, Vol. 17, No. 6, 1439-1451. Qin, S.Z., Su, H.T., and McAvoy, T.J., 1992. Comparison of Four Neural Net Learning Methods for Dynamic System Identification. IEEE Transactions on Neural Networks, Vol. 3, No. 1, 122-130. Ranaweera, D.K., 1994. Comparison of neural network Models for fault diagnosis of power systems. Electric Power System Research, Vol. 29, No. 2, 99-104. Reinschmidt, K.F., and Ling, B., 1994. Neural Networks with Multiple-State Neurons for Nitrogen Oxide (NOx) Emissions Modeling and Advisory Control. 1994 IEEE International conference on Neural Networks, Vol. 6, 3834-3839. R.O.C. Environmental Protection Administration, 2007.5. Drinking Water Quality Standards. http://law.epa.gov.tw/en/laws/359367440.html Rosenblatt F., 1958. The Perceptron : A Probabilistic Model for Information Storage and Organization in the Brain. Psychological Review, Vol. 65, 386-408 Rumelhart, D.E., and McClelland, J.L., 1986. Parallel distribution processing: explorations in the microstructure of cognition. Cambridge, MIT Press. Rumelhart, D.E., Hinton, G.E., and Williams, R.J., 1986. Learning Representations by Back-Propagating Errors. Nature, Vol. 323, 533-536. Saint-Donat, J., Bhat, N., and McAvoy, T.J., 1991. Neural net based model predictive control. International Journal of Control, Vol. 54, No. 6, 1453-1468. Shih, W.K., and Chiang, C.L., 1997.5. The development and implementation of automatic dosing system in Taipei water department. Proceedings 3th International Workshop on Drinking Water Quality Management and Treatment Technology, 139-158. Su, H.T., McAvoy, T.J., and Werbos, P., 1992. Long-term Prediction of Chemical Processes Using Recurrent Neural Networks: A Parallel Training Approach. Industrial and Engineering Chemistry Research, Vol. 31, No. 5, 1338-1352. Trejo, L.A., and Sandoval, C., 1995. Improved Back-Propagation: Epsilon-back-Propagation. Lecture Notes in Computer Science, n 930, From Natural to Artificial Neural Computation, 427-432. Tsai, J.T., Chou, J.H., and Liu, T.K., 2006. Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm. IEEE Transactions on Neural Networks, Vol. 17, No. 1, 69-80. van Leeuwen, J., Chow, C.W.K., Bursill, D., and Drikas, M., 1999. Empirical mathematical models and artificial neural networks for the determination of alum doses for treatment of southern Australian surface waters. Journal of Water Supply: Research and Technology - Aqua, Vol. 48, No. 3, 115-127. White, H., 1989. Learning in neural networks: a statistical perspective. Neural Computation, Vol. 1, No. 4, 425-464. Widrow, E., and Hoff, M., 1960.8. Adaptive switching circuits. 1960 IRE WESCON Convention Record, New York, 96-104. Young, D., and Cheng, L.M., 1994.4. Autonomous Hidden Node Determination using Dynamic Expansion & Contraction Approach. 1994 International Symposium on speech, Image processing and Neural Networks, Hong Kong, 13-16. Yu, R.-F., Kang, S.F., Liaw, S.L., Chen, M.C., 2000. Application of artificial neural network to control the coagulant dosing in water treatment plant. Water Science and Technology, Vol. 42, No. 3-4, 403-408. Zebulum, R.S., Guedes, K., Vellasco, M., and Pacheco, M.A., 1995. Short term load forecasting using neural nets. From Natural to Artificial Neural Computation, Vol. 930, 1001-1008. Zhang, Z., Li, C., and Liao, X., 2007. Delay-dependent robust stability analysis for interval linear time-variant systems with delays and application to delayed neural networks. Neurocomputing, Vol. 70, No.16-18, 2980-2995. Zhang, Q., and Stanley, S.J., 1999. Real-time water treatment process control with artificial neural networks. Journal of Environmental Engineering, ASCE Vol. 125, No. 2, 153-160. Zheng, R.T., Ngo, N.Q., Shum, P., Tjin, S.C., and Binh, L.N., 2005. A staged continuous tabu search algorithm for global optimization and its applications to the design of fiber Bragg gratings. Computational Optimization and Applications, Vol. 30, No.3, 319-335. Zhu, A.M., and Yang, S.X., 2006. A neural network approach to dynamic task assignment of multirobots. IEEE Transactions on Neural Networks, Vol. 17, No. 5, 1278-1287. Zurada, J.M., 1992. Introduction to artificial neural systems, PWS, Info Access Distribution Ptr Ltd., Singapore, 195-196. Xie, N., and Leung, H., 2005. Blind equalization using a predictive radial basis function neural network. IEEE Transactions on Neural Networks, Vol. 16, No. 3, 709-720. 李崇德、莊銘棟,1996.11,以時間序列法進行臭氧濃度的預報,第十三屆空氣污染控制技術研討會,台北市,21-28。 洪名莘、王啟明、洪達朗、史午康,1993,自來水設施操作維護手冊,中華民國自來水協會。 倪榮興,1996,污水處理廠水質管理專家系統之研究,國立雲林技術學院,資訊管理技術研究所,碩士論文。 高肇藩,1990,給水工程,成功大學環境工程學系,台南。 高全興,1997,類神經網路於空氣品質短期預測之研究,國立雲林技術學院,環境與安全工程技術研究所,碩士論文。 孫建平,1996,類神經網路及其應用於降雨及逕流過程之研究,國立台灣大學,農業工程學研究所,碩士論文。 莊源鍵,1998,類神經網路應用於一般廢棄物焚化廠煙道氣品質預測之研究,國立雲林技術學院,環境與安全工程技術研究所,碩士論文。 黃志彬,甘其銓,張進興,1997,淨水場混凝監測及加藥之研究,第十四屆自來水研究發表會報告,台北,61-71。 黃尚雄,1995,應用類神經網路預測空氣品質之研究,國立交通大學,環境工程研究所,碩士論文。 黃智顯,1996,水文時間序列類神經網絡之研究及其應用於流量之預測,國立台灣大學,農業工程學研究所,碩士論文。 陳美枝,1998,應用類神經網路於混凝加藥量之研究,淡江大學,水資源及環境工程學研究所,碩士論文。 葉怡成,1998,類神經網路模式應用與實作,儒林圖書有限公司,台北。 焦李成,1991,類神經網路系統理論,格致圖書公司,台北。 蔡瑞煌,1995,類神經網路概論,三民書局,台北,2-4。 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/45425 | - |
dc.description.abstract | 類神經網路已成功應用在自來水場混凝加藥量之預測,然而如何提升預測能力,正是本研究探討的重點。本研究針對模糊理論、自身因子、資料正規化、時間區間對於類神經網路預測自來水場混凝加藥量之影響進行分析探討。為了解模糊理論之影響,本研究採用適應性模糊類神經網路與類神經網路進行比較有無模糊理論之影響。自身因子為預測目標值之前幾個單位時間的實測值。當使用的轉換函數不同時,則會影響資料正規化的需要性。
本研究資料分別來自台北縣某淨水場和台北市某淨水場。在可得到水質資料時,比較適合採用類神經網路模式來建立即時最佳混凝加藥量預測模式。在無法獲得進流水水質之情況下,則必須使用自身預測模式來預測即時最佳混凝加藥量,適應性模糊類神經網路模式較類神經網路模式佳。自身因子可提升類神經網路的預測能力,但增加自身因子的數目對於提升預測能力並不顯著。當隱藏層的轉換函數為雙彎曲線正切函數,輸出層的轉換函數為線性函數時,則輸入資料沒有正規化可使類神經網路得到較好的預測能力。短時間間距輸入資料可以提升類神經網路的預測能力。 當大雨導致高濁度時,類神經網路提供了操作者可以快速的改變最佳混凝加藥量,其模式輸入變數可透過Pearson相關係數分析來篩選,而在隱藏層的轉換函數為雙彎曲線正切函數,輸出層的轉換函數為線性函數,輸入資料不需要正規化。其輸入變數在台北縣某淨水場為原水濁度和自身因子(PAC(t-1)),在台北市某淨水場為原水濁度、分水井濁度、沉澱池濁度以及自身因子(D(t-1), D(t-2), D(t-3), 和 D(t-4))。 | zh_TW |
dc.description.abstract | In the past, artificial neural network (ANN) has been used successfully for the prediction of coagulant dosage. Recent developments of ANN with the addition of fuzzy theory have also been reported. In this study, research focus is placed on how to improve the predictability of ANN, considering the effect of fuzzy theory, inherent factor, data normalization, and time interval on predicting the coagulant dosage in drinking water treatment. Performance of ANN and Adaptive Network based Fuzzy Inference System (ANFIS) approaches is compared in order to understand the effect of fuzzy theory in ANN. Inherent factor is defined as the past time object value. The use of different transfer functions determines the necessity of data normalization in ANN.
Experimental coagulant dosage data are collected from the drinking water treatment stations in Taipei County and Taipei City, Taiwan. With raw water quality data made available in the analysis, ANN is suitable for building the real-time optimal coagulant dosage. On the other hand, the inherent predicting approach is useful to decide the real time optimal coagulant dosage, and the predictability of ANFIS is better than ANN. The inherent factor can improve the predictability of ANN, but increasing the amount of inherent factor is not significant for increasing the predictability of ANN. The predictability of ANN can be improved by 1) using a hyperbolic-tangent transfer function in the hidden layer, 2) using a linear transfer function in the output layer, 3) using the input data without data normalization, and 4) using short time interval input data. When a heavy rain let the raw water have high turbidity, ANN provides operators to decide the optimal coagulant dosage immediately. The input variables of ANN can be selected by the Pearson correlation coefficient, and the transfer function in the hidden layer is a hyperbolic-tangent function, and the transfer function in the output layer is a linear function, and input data is without data normalization. The input variables of drinking water treatment in Taipei County are raw water turbidity and inherent factor (PAC(t-1)), and the input variables of drinking water treatment in Taipei City are raw water turbidity, distribution water turbidity, sedimentation water turbidity, and inherent factor ((D(t-1), D(t-2), D(t-3), D(t-4)). | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T04:19:28Z (GMT). No. of bitstreams: 1 ntu-98-D92541011-1.pdf: 2210510 bytes, checksum: 927fdb209d698483c9d75995905b766c (MD5) Previous issue date: 2009 | en |
dc.description.tableofcontents | 中文摘要 Ⅲ
英文摘要 IV 目錄 V 圖目錄 VIII 表目錄 XII 符號說明 XIII 第一章 緒論 1 1.1 研究緣起 1 1.2 研究目的 1 1.3 研究內容 2 第二章 文獻回顧 4 2.1 類神經網路 4 2.1.1 類神經網路的發展與應用 5 2.1.2 神經元模型 11 2.1.3 網路架構 14 2.1.4 倒傳遞類神經網路 16 2.2 適應性模糊類神經網路 20 2.2.1 適應性模糊類神經網路原理 20 2.2.2 適應性模糊類神經網路基本架構之建立 20 2.2.3 適應性模糊類神經網路學習演算法 22 2.3 自來水處理程序控制系統 27 2.4 類神經網路應用於自來水場混凝加藥之相關研究 29 第三章 研究方法 32 3.1 研究範疇界定與資料收集 32 3.2 資料補遺 37 3.3 資料正規化 53 3.4 輸入參數之決定 53 3.5 類神經網路模式建構 54 3.5.1 網路模式選擇 54 3.5.2 網路設計 54 3.5.3 網路最佳化 55 3.6 適應性模糊類神經網路模式建構 55 3.7 網路功能測試 56 第四章 研究結果與討論 57 4.1 類神經網路模式與適應性模糊類神經網路模式 57 4.1.1 類神經網路模式 57 4.1.2 適應性模糊類神經網路模式 79 4.1.3 類神經網路模式與適應性模糊類神經網路模式之比較 99 4.2 自身因子及資料正規化對類神網路預測能力之影響 101 4.2.1 資料分析和模式建立 101 4.2.2 選擇參數 102 4.2.3 資料有無正規化之比較 102 4.2.4 輸入項有無自身因子之比較 108 4.2.5 不同的隱藏層單元數之比較 108 4.2.6 不同輸入參數的比較 108 4.2.7 最佳混凝加藥量模式 108 4.2.8 最佳混凝加藥量自身預測模式 116 4.3 自身因子及時間區間對類神網路預測能力之影響 117 4.3.1 資料分析和模式建立 117 4.3.2 自身因子 119 4.3.3 不同時間間距的比較 119 4.3.4 輸入變數有無自身因子之影響 126 4.3.5 自身因子預測模式之影響 126 4.3.6 最佳混凝加藥模式之評估 126 第五章 結論與建議 135 5.1 結論 135 5.2 建議 136 參考文獻 137 圖目錄 圖1.1 研究架構 3 圖2.1 生物神經元結構示意圖 11 圖2.2 類神經網路神經元構造示意圖 12 圖2.3 網路架構示意圖 14 圖2.4 倒傳遞網路架構圖 16 圖2.5 適應性網路模糊推論系統結構圖 21 圖2.6 台北縣某淨水場處理流程示意圖 27 圖3.1 研究流程圖 33 圖3.2 台北縣某淨水場一、二期流程之處理量之時間分佈圖 38 圖3.3 台北縣某淨水場一、二、三期水溫之時間分佈圖 38 圖3.4 台北縣某淨水場一、二期混泥加藥量之時間分佈圖 38 圖3.5 台北縣某淨水場一、二、三期原水濁度時間分佈圖 39 圖3.6 台北縣某淨水場一、二期膠羽水濁度時間分佈圖 39 圖3.7 台北縣某淨水場一、二期沈澱水濁度時間分佈圖 39 圖3.8 台北縣某淨水場一、二期清水濁度時間分佈圖 40 圖3.9 台北縣某淨水場一、二、三期原水色度時間分佈圖 40 圖3.10 台北縣某淨水場一、二期膠羽水色度時間分佈圖 40 圖3.11 台北縣某淨水場一、二、三期原水pH時間分佈圖 41 圖3.12 台北縣某淨水場一、二期膠羽水pH時間分佈圖 41 圖3.13 台北縣某淨水場一、二期沈澱水pH時間分佈圖 41 圖3.14 台北縣某淨水場一、二期清水時間分佈圖 42 圖3.15 台北縣某淨水場一、二期加氯量時間分佈圖 42 圖3.16 台北縣某淨水場一、二期膠羽水自由餘氯量時間分佈圖 42 圖3.17 台北縣某淨水場一、二期沈澱水自由餘氯量時間分佈圖 43 圖3.18 台北縣某淨水場一、二期清水自由餘氯量時間分佈圖 43 圖3.19 台北縣某淨水場一、二期膠羽水結合餘氯量時間分佈圖 43 圖3.20 台北縣某淨水場一、二期沈澱水結合餘氯量時間分佈圖 44 圖3.21 台北縣某淨水場三期混凝加藥量時間分佈圖 44 圖3.22 台北縣某淨水場三期加氯量時間分佈圖 44 圖3.23 台北縣某淨水場三期處理量時間分佈圖 45 圖3.24 台北縣某淨水場三期膠沈水濁度時間分佈圖 45 圖3.25 台北縣某淨水場三期清水濁度時間分佈圖 45 圖3.26 台北縣某淨水場三期膠沈水pH時間分佈圖 46 圖3.27 台北縣某淨水場三期清水pH時間分佈圖 46 圖3.28 台北縣某淨水場三期自由餘氯膠沈水時間分佈圖 46 圖3.29 台北縣某淨水場三期清水自由餘氯時間分佈圖 47 圖3.30 台北縣某淨水場三期膠沈水結合餘氯時間分佈圖 47 圖3.31 台北市某淨水場原水濁度時間序列圖 48 圖3.32 台北市某淨水場分水井濁度時間序列圖 48 圖3.33 台北市某淨水場沉澱水濁度時間序列圖 49 圖3.34 台北市某淨水場清水濁度時間序列圖 49 圖3.35 台北市某淨水場原水導電度時間序列圖 50 圖3.36 台北市某淨水場分水井導電度時間序列圖 50 圖3.37 台北市某淨水場原水pH時間序列圖 51 圖3.38 台北市某淨水場分水井pH時間序列圖 51 圖3.39 台北市某淨水場分水井SC時間序列圖 52 圖3.40 台北市某淨水場混凝加藥量時間序列圖 52 圖4.1 AN001預測結果(選用參數:原水濁度、膠羽水濁度、原水色度、膠羽水色度) 62 圖4.2 AN001n預測結果(選用參數:原水濁度、膠羽水濁度、原水色度、膠羽水色度、PAC(t-1)) 63 圖4.3 AN001nn預測結果(選用參數:原水濁度、膠羽水濁度、原水色度、膠羽水色度、PAC(t-1)、PAC(t-2)) 64 圖4.4 AN002預測結果(選用參數:原水濁度、膠羽水濁度、膠羽水色度) 65 圖4.5 AN002n預測結果(選用參數:原水濁度、膠羽水濁度、膠羽水色度、PAC(t-1)) 66 圖4.6 AN002nn預測結果(選用參數:原水濁度、膠羽水濁度、膠羽水色度、PAC(t-1)、PAC(t-2)) 67 圖4.7 AN003預測結果(選用參數:原水濁度、膠羽水濁度) 68 圖4.8 AN003n預測結果(選用參數:原水濁度、膠羽水濁度、PAC(t-1)) 69 圖4.9 AN003nn預測結果(選用參數:原水濁度、膠羽水濁度、PAC(t-1)、PAC(t-2)) 70 圖4.10 AN004預測結果(選用參數:膠羽水濁度) 71 圖4.11 AN004n預測結果(選用參數:膠羽水濁度、PAC(t-1)) 72 圖4.12 AN004nn預測結果(選用參數:膠羽水濁度、PAC(t-1)、PAC(t-2)) 73 圖4.13 AN005預測結果(選用參數:原水濁度) 74 圖4.14 AN005n預測結果(選用參數:原水濁度、PAC(t-1)) 75 圖4.15 AN005nn預測結果(選用參數:原水濁度、PAC(t-1)、PAC(t-2)) 76 圖4.16 AN006n預測結果(選用參數:PAC(t-1)) 77 圖4.17 AN006nn預測結果(選用參數:PAC(t-1)、PAC(t-2)) 78 圖4.18 FN001預測結果(選用參數:原水濁度、膠羽水濁度、原水色度、膠羽水色度) 82 圖4.19 FN001n預測結果(選用參數:原水濁度、膠羽水濁度、原水色度、膠羽水色度、PAC(t-1)) 83 圖4.20 FN001nn預測結果(選用參數:原水濁度、膠羽水濁度、原水色度、膠羽水色度、PAC(t-1)、PAC(t-2)) 84 圖4.21 FN002預測結果(選用參數:原水濁度、膠羽水濁度、膠羽水色度) 85 圖4.22 FN002n預測結果(選用參數:原水濁度、膠羽水濁度、膠羽水色度、PAC(t-1)) 86 圖4.23 FN002nn預測結果(選用參數:原水濁度、膠羽水濁度、膠羽水色度 、PAC(t-1)、PAC(t-2)) 87 圖4.24 FN003預測結果(選用參數:原水濁度、膠羽水濁度) 88 圖4.25 FN003n預測結果(選用參數:原水濁度、膠羽水濁度、PAC(t-1)) 89 圖4.26 FN003nn預測結果(選用參數:原水濁度、膠羽水濁度、PAC(t-1)、PAC(t-2)) 90 圖4.27 FN004預測結果(選用參數:膠羽水濁度) 91 圖4.28 FN004n預測結果(選用參數:膠羽水濁度、PAC(t-1)) 92 圖4.29 FN004nn預測結果(選用參數:膠羽水濁度、PAC(t-1)、PAC(t-2)) 93 圖4.30 FN005預測結果(選用參數:原水濁度) 94 圖4.31 FN005n預測結果(選用參數:原水濁度、PAC(t-1)) 95 圖4.32 FN005nn預測結果(選用參數:原水濁度、PAC(t-1)、PAC(t-2)) 96 圖4.33 FN006n預測結果(選用參數:PAC(t-1)) 97 圖4.34 FN006nn預測結果(選用參數:PAC(t-1)、PAC(t-2)) 98 圖4.35 各類神經網路模式與適應性模糊類神經網路模式之R2 及RMSE,(a) 為R2;(b)為RMSE 100 圖4.36 水質參數和混凝加藥量時間序列圖 105 圖4.37 資料有無正規化之比較 107 圖4.38 輸入項有無自身因子之比較 109 圖4.39 不同的隱藏層單元數之比較 110 圖4.40 最佳混凝加藥模式(G0103d model) 114 圖4.41 最佳混凝加藥模式(GM204d model) 115 圖4.42 最佳混凝加藥量自身預測模式 116 圖4.43 水質特性和混凝加藥量時間序列圖 121 圖4.44 時間區間的影響 124 圖4.45 輸入變數有無自身因子之影響 128 圖4.46 自身因子預測模式之影響 130 圖4.47 最佳混凝加藥量模式(H0310d4 model) 132 圖4.48 最佳混凝加藥量自身預測模式(H0504d4 model) 134 圖5.1 最佳類神經網路即時混凝加藥量預測模式之建構 136 表目錄 表2.1 類神經網路應用於自來水場混凝加藥之相關研究 30 表3.1 台北縣某淨水場處理流程(一、二期)與水質項目及監測點 34 表3.2 台北縣某淨水場處理流程(三期)與水質項目及監測點 35 表3.3 台北縣某淨水場各水質參數數值範圍及數目 36 表4.1 一週內水質參數與PAC加藥量之Pearson相關係數 59 表4.2 ANN模式選用之輸入參數 60 表4.3 ANN模式之相關係數、均方根誤差 61 表4.4 較佳的ANN模式 61 表4.5 ANFIS模式選用之輸入參數 80 表4.6 ANFIS模式之相關係數、均方根誤差 81 表4.7 較佳之ANFIS模式 81 表4.8 每個輸出和輸入參數的Pearson相關係數 102 表4.9 每個模式的輸入參數 103 表4.10 各類神經網路模式架構 104 表4.11 每個類神經網路的最佳演算法 113 表4.12 每一個輸入和輸出的Pearson相關係數 118 表4.13 四種學習和訓練的資料 119 表4.14 每一個類神經網路模式的輸入變數 120 表4.15 每一個類神經網路模式較佳的結構 131 表4.16 每一個自身預測加藥模式之較佳結構 133 | |
dc.language.iso | zh-TW | |
dc.title | 以類神經網路預測自來水場混凝加藥量及其影響因子之研究 | zh_TW |
dc.title | Investigation on the Effect Factors in Artificial Neural Networks for Predicting the Coagulant Dosage in Drinking Water Treatment Plants | en |
dc.type | Thesis | |
dc.date.schoolyear | 98-1 | |
dc.description.degree | 博士 | |
dc.contributor.oralexamcommittee | 張尊國,葉欣誠,李公哲,馬鴻文 | |
dc.subject.keyword | 模糊理論,自身因子,資料正規化,時間區間,類神經網路,自來水場,混凝加藥量, | zh_TW |
dc.subject.keyword | fuzzy theory,inherent factor,data normalization,time interval,artificial neural network,drinking water treatment plants,coagulant dosage, | en |
dc.relation.page | 144 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2009-11-10 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 環境工程學研究所 | zh_TW |
Appears in Collections: | 環境工程學研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-98-1.pdf Restricted Access | 2.16 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.