环境科学研究
環境科學研究
배경과학연구
RSEARCH OF ENUIRONMENTAL SCIENCES
2009年
12期
1460-1465
,共6页
韩耀宗%黄亮亮%宋新山%曹家枞
韓耀宗%黃亮亮%宋新山%曹傢樅
한요종%황량량%송신산%조가종
芦苇人工湿地%小波神经网络%水质指标%预测
蘆葦人工濕地%小波神經網絡%水質指標%預測
호위인공습지%소파신경망락%수질지표%예측
Phragmites australis constructed wetlands%wavelet neural networks%water quality index%prediction
人工湿地系统对污水的处理效果好,工艺简单,投资运行费用低,但影响其出水水质的因素很多,并且往往是非线性的,因此目前很难将这些影响因素模型化并用于水质预测. 已有的预测方法不是过于复杂就是预测精度不高. 神经网络是一种具有较强预测能力的新方法,适用于各种非线性模型的预测. 在小试研究的基础上,使用3种不同的、经过训练的小波神经网络,对芦苇潜流人工湿地沿程各采样口的水温,ρ(DO),pH,E_h和ρ(COD_(Cr))等水质指标进行了预测. 结果显示,各指标的平均相对误差分别为:水温≤4.21%,pH≤1.36%,ρ(DO)≤9.77%,E_h≤6.50%,ρ(COD_(Cr))≤17.76%,表明小波神经网络模型适用于人工湿地模型的预测.
人工濕地繫統對汙水的處理效果好,工藝簡單,投資運行費用低,但影響其齣水水質的因素很多,併且往往是非線性的,因此目前很難將這些影響因素模型化併用于水質預測. 已有的預測方法不是過于複雜就是預測精度不高. 神經網絡是一種具有較彊預測能力的新方法,適用于各種非線性模型的預測. 在小試研究的基礎上,使用3種不同的、經過訓練的小波神經網絡,對蘆葦潛流人工濕地沿程各採樣口的水溫,ρ(DO),pH,E_h和ρ(COD_(Cr))等水質指標進行瞭預測. 結果顯示,各指標的平均相對誤差分彆為:水溫≤4.21%,pH≤1.36%,ρ(DO)≤9.77%,E_h≤6.50%,ρ(COD_(Cr))≤17.76%,錶明小波神經網絡模型適用于人工濕地模型的預測.
인공습지계통대오수적처리효과호,공예간단,투자운행비용저,단영향기출수수질적인소흔다,병차왕왕시비선성적,인차목전흔난장저사영향인소모형화병용우수질예측. 이유적예측방법불시과우복잡취시예측정도불고. 신경망락시일충구유교강예측능력적신방법,괄용우각충비선성모형적예측. 재소시연구적기출상,사용3충불동적、경과훈련적소파신경망락,대호위잠류인공습지연정각채양구적수온,ρ(DO),pH,E_h화ρ(COD_(Cr))등수질지표진행료예측. 결과현시,각지표적평균상대오차분별위:수온≤4.21%,pH≤1.36%,ρ(DO)≤9.77%,E_h≤6.50%,ρ(COD_(Cr))≤17.76%,표명소파신경망락모형괄용우인공습지모형적예측.
Constructed wetland systems are effective in treating sewage. They have simple process and low investment/operation costs. However, there are many factors influencing the water quality, and these factors are often nonlinear. Therefore, it is difficult to model these factors so as to predict water quality. Some prediction methods are too complicated, while others have a relatively low prediction accuracy. The artificial neural network is an efficient, new method in predicting a variety of non-linear models. On the basis of laboratory experiments, three kinds of trained wavelet neural networks were used to predict water quality along the Phragmites australis subsurface flow constructed wetlands, including water temperature, ρ(DO), pH, E_h and ρ(COD_(Cr)). The prediction results showed that the average relative error of the water temperature≤4.21%, pH≤1.36%, ρ(DO)≤9.77%, E_h≤6.50%, ρ(COD_(Cr))≤17.76%. The results indicated that the wavelet neural networks model can effectively predict various items in water quality of constructed wetlands.