基于人工神经网络与回归分析的水质预测  

The Forecast of Water Quality Based on Artificial Neural Networks and Regression Analysis

作　　者：李亦芳[1] 程万里[1] 刘建厅[1] 程银行[2] 

机构地区：[1]华北水利水电学院数学与信息科学学院,河南郑州450011 [2]中国地质调查局天津地质矿产研究所,天津300170

出　　处：《盐城工学院学报（自然科学版）》2008年第1期45-48,53,共5页Journal of Yancheng Institute of Technology:Natural Science Edition

摘　　要：针对人工神经网络(Artificial Neural Networks,缩写ANN)在预测中出现的异常值现象,采用了回归分析模型得到的预测区间来控制异常值现象的方法。并且应用在黄河三门峡河段的水质预测中,氨氮通量预测的ANN模型控制前平均精度仅有50.05%,控制后该月的相对精度为90.08%,平均精度达到80.79%,整体预测精度明显提高。化学需氧量(COD)浓度的预测也有类似情况。实践表明该方法对于消除ANN模型预测中出现的异常值现象是较为有效的。As to the abnormal phenomenon in the forecast of artificial neural networks（Artificial Neural Networks,acronym ANN）,the method,in which the forecast range from the regression analysis model is used to control the abnormal phenomenon,has been adopted.In the forecast of the water quality of Yellow River in San Menxia,the average accuracy of the quantity of Ammonia and Nitrogen before the control of ANN is only 50.05 percent,this is because the forecast number is very different of the accurate number in June 2006,the relative error of the forecast number reach up to 214.88 percent,beyond the forecast range of regression,in order to have effect on the whole accuracy.The accuracy of this month is 90.08 percent,the average accuracy reaches up to 80.79 percent;the whole forecast accuracy is proved obviously.The practice shows that the method is effective to eliminate the abnormal phenomenon in the artificial neural networks.

关 键 词：回归分析 人工神经网络 水质预测 

分 类 号：O212.5[理学—概率论与数理统计] O29[理学—数学]