整合類神經網路與遺傳演算法於水庫水質管理之研究

A Hybrid Neural-genetic Algorithm for Reservoir Water Quality Management

王英義(Ying-Yi Wang)

指導教授 ： 郭振泰

國立臺灣大學/工學院/土木工程學研究所/博士(2006年)

https://doi.org/10.6342/NTU.2006.10212

摘要

本研究目的：(1)發展簡化的類神經網路水質模式，以模擬、預測水庫水質。(2)整合類神經網路模式與遺傳演算法，應用於水庫優養之控制。並以翡翠水庫為研究案例。
研究內容包括：
(1)首先，建立類神經網路水質（總磷與葉綠素）模式，將類神經網路模式的模擬結果與水庫每月的採樣值做比較，也同時與參考模式（總磷模式、WASP/EUTRO模式）的模擬結果比較，以完成模式之檢定與驗證。
(2)接著，將驗證完成的類神經網路模式取代一般常用的水質模式，與遺傳演算法做結合，進行水庫水質的優養管理。
(3)在水質管理上分別以總磷及葉綠素作為水庫優養指標，以建立的管理模式在最小處理率的目標下，對水庫集水區所需削減的磷負荷量提出建議方案，以改善目前的水質，達到所訂定的水質標準。
(4)最後，將建議的磷負荷削減方案，以WASP/EUTRO水質模式進行模擬驗證，以確認所建立模式的正確性與適用性。

本研究所建立的水質管理模式具有實用性，能夠提供有效、即時的控制策略，以防止水庫優養化現象的發生。在翡翠水庫的優養控制規劃上，建議採用點源與非點源污染負荷聯合削減的方式。首先，在水庫集水區設置適當的最佳管理作業方法(BMPs)，以削減非點源污染量，再者，配合污水處理廠時變性的點源污染控制操作，以達到水庫優養即時控制所需削減的污染負荷總量。

關鍵字

類神經網路 ； 遺傳演算法 ； 翡翠水庫 ； WASP/EUTRO ； 優養控制 ； 水質模擬/管理

並列摘要

There has been concern over the water quality in Feitsui Reservoir, particularly since the beginning of Taipei-Ilan highway construction in 1991. In the present study, a combined artificial neural network (ANN) and genetic algorithms (GAs) approach was proposed for water quality management of Feitsui Reservoir in Taiwan. First, two simplified water quality models based on ANN were developed and used as universal approximators to imitate the cause-and-effect relationships between phosphorus loads from the watershed and water quality concentrations (total phosphorus and chlorophyll a, respectively) in Feitsui Reservoir. A six-year (1992-1997) record of water quality data was used for network training, and additional data collected in 1998-2000 was used for model verification. The performance and validity of the proposed ANN models were evaluated using two conventional water quality models, including a total phosphorus model and an eutrophication model (WASP/EUTRO). Further, a GA with water quality prediction produced by the ANN model was used to optimize the control of watershed nutrient loads. The GA was applied to the problem of reservoir water quality management to provide an alternative when searching for an optimal control strategy. The study results reveal that the ANN model can effectively simulate the dynamics of reservoir water quality, indicating that an ANN model can replace the conventional water quality model in this water quality management analysis, and the GA is able to identify control schemes that improve the current trophic levels to achieve water quality standards. Finally, the time-variable control schemes derived from the ANN-GA method were applied to the WASP/EUTRO model to assess the impact on eutrophication in Feitsui Reservoir following phosphorus load reductions in its watershed. The modeling results suggest that adequate control of phosphorus loads into the reservoir is needed for preserving the water quality of Feitsui Reservoir from eutrophication. In practice, the time-varying reductions in phosphorus loads for controlling reservoir eutrophication can be achieved by way of the joint reduction of point and nonpoint source pollution loads.

並列關鍵字

Artificial neural network ； Genetic algorithms ； Feitsui Reservoir ； Nutrient model ； WASP/EUTRO ； Eutrophication control ； Water quality modeling/management

參考文獻

Aguilera, P.A., Frenich, A.G., Torres, J.A., Castro, H., Vidal, J.L.M., Canton, M., 2001. Application of the Kohonen neural network in coastal water management: Methodological development for the assessment and prediction of water quality. Water Res. 35 (17), 4053-4062.

Aly, A.H., Peralta, R.C., 1999. Optimal design of aquifer cleanup systems under uncertainty using a neural network and a genetic algorithm. Water Resour. Res. 35 (8), 2523-2532.

ASCE Task Committee on Application of Artificial Neural Network in Hydrology, 2000. Artificial neural network in hydrology. I: Preliminary Concepts. J. Hydrologic Engrg. 5 (2), 115-123.

ASCE Task Committee on Application of Artificial Neural Networks in Hydrology, 2000. Artificial neural networks in hydrology, II: Hydrologic applications. J. Hydrologic Engrg. 5 (2), 124-137.

Burn, D.H., Yulianti, J.S., 2001. Waste-load allocation using genetic algorithms. J. Water Resour. Plan. Manage.-ASCE 127 (2), 121-129.