CAJ | 학술논문

神经网络具有强大的非线性映射能力和并行处理能力,近年来在水处理领域中被广泛地应用.利用神经网络算法对某污水处理厂的污水处理系统进行了出水水质预测.结果表明,基于BP神经网络的水质预测模型拟合效果较好,模拟出来的化学需氧量(COD)、pH、固体悬浮物(SS)及生物需氧量(BOD)的数值范围均较接近于实际值,其平均相对标准差分别为6.96%、1.31%、12.09%、15.18%.
신경망락구유강대적비선성영사능력화병행처리능력,근년래재수처리영역중피엄범지응용.이용신경망락산법대모오수처리엄적오수처리계통진행료출수수질예측.결과표명,기우BP신경망락적수질예측모형의합효과교호,모의출래적화학수양량(COD)、pH、고체현부물(SS)급생물수양량(BOD)적수치범위균교접근우실제치,기평균상대표준차분별위6.96%、1.31%、12.09%、15.18%.
Artificial Neural Networks (ANN) are widely used in the field of wastewater treatment because of its strong nonlinear mapping and parallel processing ability.The effluent stream quality is predicted at a wastewater treatment plant by using BP ANN model in this paper.The results indicate that the BP ANN model provides the satisfactory fitting effects for the following four variables,in terms of chemical oxygen demand (COD),pH value,suspended solids (SS) and biological oxygen demand (BOD).The simulative results of COD,pH,SS and BOD are very close to the detected values;the average relative standard variation(RSD) are 6.96%,1.31%,12.09% and 15.18%,respectively.