用BP神经网络评价地浸砂岩型铀矿床某退役采区地下水水质  

Application of BP neural network model to evaluation of groundwater quality in a decommissioned field of in-situ leaching of uranium

作　　者：李锦鹏[1] 胡凯光[1] 李小军[1] 肖素丽[1] 

机构地区：[1]南华大学核资源与核燃料工程学院,湖南衡阳421001

出　　处：《铀矿冶》2010年第4期199-203,共5页Uranium Mining and Metallurgy

基　　金：国家自然科学基金项目(50774047);湖南省教育厅重点项目(10A103)

摘　　要：以我国GB/T 14848—1993《地下水质量标准》作为学习样本,选取U、SO42-、∑Fe、Ca2+、NO3-、Cl-和矿化度7个指标作为评价因子,用建立的基于地下水水质评价的BP神经网络模型,对地浸砂岩铀矿床某退役采区地下水水质进行评价。为更有效地验证评价模型的准确性,将该模型与综合指数法的评价结果进行比较。结果表明:建立的BP神经网络模型评价精度高,能有效描述评价因子与水质等级间复杂的非线形关系,拓宽了BP神经网络应用研究领域。Quality standard for groundwater of China（GB/T14848—1993） acted as training samples,and seven indexes such as U,SO4^2-,∑Fe,Ca^2＋,NO3^-,Cl^-and mineralization were selected as the evaluation factors.A BP neural network model was used to evaluate the groundwater quality in a decommissioned field of in-situ leaching of uranium.To validate the accuracy of this model,the results obtained by BP neural network model are compared with the results of the composite index evaluation.The result shows that the BP neural network model can resolve the complicated nonlinear relation between evaluation factors and water quality grade.The method has high precision and it broadened the application field of BP neural network.

关 键 词：地浸砂岩铀矿床 BP神经网络 地下水水质 水质评价 

分 类 号：X523[环境科学与工程—环境工程] TP183[自动化与计算机技术—控制理论与控制工程]