基于BP神经网络的三峡库区小流域水质评价

Water Quality Evaluation of Small Basin in Three Gorges Reservoir Based on BP Neural Networks

在阐述BP人工神经网络原理的基础上,运用我国地表水环境质量标准(GB3838-2002)作为训练样本,建立了一个多因子水质综合评价的3层BP网络模型,以溶解氧、氨态氮、总磷、砷、汞和铬为评价因子,对三峡库区小流域-嘉陵江的次级支流流域进行了水质综合评价。结果表明:该河中上游水质状况良好,而下游水质状况较差,汇入嘉陵江、长江后将对三峡水库的水质造成不良影响。为了保证三峡水库的水质安全,建议加强库区小流域的地表水环境管理。

Based on the expound of rationale of BP artificial neural network, taking the standards for environmental quality of surface water of China（GB3838-2002） as training samples ,a three-layer BP network model for water quality comprehensive evaluation is established in this paper. Taking DO,NH3-N , TP, As, Hg and Cr as the evaluation factors, the water quality evaluation of a small basin, which is a branch of Jialing River in the Three Gorges Reservoir, is carried out. The result indicated that the water quality in the middle and upper reaches of the river is good, but the downstream water quality is bad. So after the river converge to Jiangling River and Changjiang River, it will cause bad influence on the water quantity of the Three Gorges reservoir. In order to guarantee the water quality security of the Three Gorges reservoir, it is suggested to strengthen the surface water environmental management of the small basin in the Three Gorges Reservoir.