以倒傳遞類神經網路及多元線性迴歸模擬建築工地對 台中市粒狀污染物之影響

PM10 IMPACT SIMULATION OF CONSTRUCTION SITES ON TAICHUNG CITY USING BACK-PROPAGATION NEURAL NETWORK (BNN) METHOD AND MULTIPLE LINEAR REGRESSION (MLR) METHOD

蘇志朋(Chih-Peng Su)

指導教授 ： 白子易

朝陽科技大學/理工學院/環境工程與管理系/碩士(2010年)

摘要

本研究應用倒傳遞類神經網路(Back-Propagation Neural Network, BNN)與多元線性回歸(Multiple Linear Regression, MLR)建立台中市空氣品質之預測模式，類神經網路分別以懸浮微粒 (PM10) 為其變數因子及PM10、PM2.5及建築 (房屋) 工程 (RC) 、建築 (房屋) 工程 (SRC) 、建築 (房屋) 工程 (拆除) 、道路工程、區域開發(社區)等條件，以2008年1月~11月為網路輸入參數建立最適化網路，對2008年12月之PM10作預測，並與MLR''作比較。研究結果顯示其中台中市訓練方面:以BNN之MAPE最佳為24.87%、R 值為0.3； MLR之MAPE最佳為 30.20%、其 R 值為0.7；預測值方面 BNN之MAPE最佳為24.87%、R 值為0.3； MLR之MAPE模式最佳為23.63%、R 值為0.4。而本模式所得預測效果良好，可提供相關管理者即時污染之因應對策。

關鍵字

類神經

並列摘要

This study employed Back-Propagation Neural Network(BNN) method and Multiple Linear Regression (MLR) method to establish an air quality prediction model of Taichung city. We used PM10 as the variable factor and PM2.5, building constructions using reinforced concrete(RC), building constructions using Steel Reinforced Concerte(SRC), Building dismantling and tunnel constructions as input parameters in BNN method for an optimizing network. We inputted data from January to November 2008 as parameters, then used the model to predicted the air quality of December, 2008. The prediction result of BNN method was compared to MLR method. As best prediction result using BNN method of simulating for Taichung city. R value is 0.3.Mape value is 24.87%. As best prediction result using MLR method of simulating for Taichung city. R value is 0.7.Mape value is30.2%. As best prediction result using BNN method: R value is 0.3.Mape value is 24.87%. As best prediction result using MLR method: R value is 0.4.Mape value is 23.63%. separately. This study shows that these prediction models will be a supportive tool for air pollution management decision-making process of the authorities.

並列關鍵字

BNN

參考文獻

上境科技股份有限公司，「97年臺中縣營建工程污染管制計畫」，臺中市環境保護局委辦計畫，台中（2008）。

Pai T.Y., T.J. Wan, S.T. Hsu, T.C. Chang, Y.P. Tsai, C.Y. Lin, H.C. Su and L.F. Yu, “Using fuzzy inference system to improve neural network for predicting hospital wastewater treatment plant effluent,” Computers & Chemical Engineering. (2009A).

Pai T.Y., S.C. Wang, C.F. Chiang, H.C. Su, L.F. Yu, P.J. Sung, C.Y. Lin and H.C. Hu , “Improving neural network prediction of effluent from biological wastewater treatment plant of industrial park using fuzzy learning approach,” Bioprocess and Biosystems Engineering. (2009B).

Pai T.Y., H.Y. Chang, T.J. Wan, S.H. Chuang and Y.P. Tsai, “Using an extended activated sludge model to simulate nitrite and nitrate variations in TNCU2 process,” Applied Mathematical Modelling. (2009C).

Pai T.Y., S.H. Chuang, T.J. Wan, H.M. Lo, i Y.P. Tsa, H.C. Su, L.F. Yu, H.C. Hu and P.J. Sung, “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 (2008A).