基于神经网络的水厂原水水质的综合评价

Comprehensive assessment of quality of raw water from water factory based on neural network model

基于BP神经网络的改进算法,提出了以Matlab 7.0为平台的算法程序的人工神经网络水质评价模型。参照《地表水环境质量标准》(GB3838-2002),确定神经网络学习和训练的样本并确定了模型的相应参数。以连云港市海州水厂原水取水口水质数据为样本,进行水质综合评价分析。与单因子评价法和模糊综合评价法进行了比较,结果表明神经网络模型所获得的结果更加客观、合理。

A Comprehensive assessment model of water quality was set up based on BP neural network and algorithm program improved in the language of Matlab 7.0. The training samples of neural network and model parameters were gained according to the environmental quality standards for surface water （GB3838-2002）. The model was applied to analyze and assess the quality of raw water from Lianyungang＇s Haizhou water factory. Comparing with fuzzy synthetic and single factor evaluation methods, the assessment results of the model are more reasonable and objective.