基于人工神经网络的长江水质评价模型  

Water quality assessment model of Yangtze River based on artificial neural network

作　　者：郭庆春[1,2,3] 何振芳[3,4] 李力[2] 

机构地区：[1]陕西广播电视大学,西安710068 [2]中国科学院地球环境研究所,西安710075 [3]中国科学院研究生院,北京100049 [4]中国科学院寒区旱区环境与工程研究所,兰州730000

出　　处：《信息技术》2013年第8期54-56,60,共4页Information Technology

基　　金：国家重点基础研究发展计划(973计划)项目(2010CB833406);国家自然科学基金项目(40825008;41075067);陕西省高等继续教育教学改革研究重点项目(11J40);全国教育科学"十二五"规划单位资助课题(FJB110131);陕西省教育厅科学研究计划项目(12JK0123;12JK0414)

摘　　要：为了能够客观地对长江水质进行评价,在分析人工神经网络原理的基础上,通过对水质污染指标浓度生成样本的方法,生成了适用于人工神经网络模型训练的样本,并应用基于误差反向传播原理的前向多层神经网络,建立了用于长江水质评价的人工神经网络模型。将该模型用于长江水环境评价,通过模型的计算,得到长江水质类别。评价结果表明该模型设计合理、泛化能力强,对长江水质评价具有较好的客观性、通用性和实用性。In order to carry out water quality assessment of Yangtze River objectively, this paper based on the principle of artificial neural network, generated appropriate training samples for artificial neural network model through the method of producing samples to the concentration of various pollution index of water quality, established the artificial neural network model of water quality assessment using multi-layer neural network with error back-propagation algorithm. This model was used to assess water environment and obtain water quality categories of Yangtze River through calculating. The assessed results show that the model was reasonable in design and higher in generalization, meanwhile, it was common, objective and practical to water quality assessment of Yangtze River.

关 键 词：人工神经网络 水质 评价 长江 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]