数据挖掘技术在松花江水质预测中的应用  

Application of data mining technology in water quality forecast of Songhua River

作　　者：赵英[1] 崔福义[1] 郭亮[1] 

机构地区：[1]哈尔滨工业大学城市水资源与水环境国家重点实验室,哈尔滨150090

出　　处：《哈尔滨工业大学学报》2011年第10期33-39,共7页Journal of Harbin Institute of Technology

基　　金：中国博士后基金资助项目(20110491056);黑龙江省博士后基金资助项目(LBH-Z10172);2011年哈尔滨工业大学科研创新基金资助项目

摘　　要：为更好地实现松花江水质预测,对水质的科学管理起到指导作用,应用人工神经网络技术(ANN,Artifical Neural Networts),利用松花江四方台监测站某连续3年水质数据,建立水质预测模型,实现对松花江主要污染指标CODMn的预测.为保证预测模型具有较高的预测精度,将数据按月分期,应用聚类分析法对数据进行处理,剔除异常数据,使有效数据能够均匀分布.并通过测试研究验证聚类分析法处理数据后对预测精度的影响效果.结果表明,将聚类分析法应用到水质预测中后,可较大地改善模型预测效果,成绩显著.To better achieve water quality forecast of Songhua River and instruct scientific management of water quality, a water quality forecasting model is set up by ANN technology and is trained by water - quality data from Sifangtai Monitoring Station of the Songhua River. The model could be applied to forecast CODMnthat is one of the main pollution indicators in Songhua River. To improve forecasting accuracy, the data is divided into 12 groups and handled by excluding abnormal data based on clustering analysis. At last a test is carried out to verify the effect of clustering analysis, and the results indicate that the clustering analysis in water - quality forecasting model can improve the forecasting effect significantly.

关 键 词：水质预测 预测模型 聚类分析法 人工神经网络 

分 类 号：X321[环境科学与工程—环境工程]