基于动态RBF神经网络的地下水质量评价  

Groundwater Quality Evaluation Based on Dynamic RBF Neural Network

作　　者：刘保平[1] 韩莎莎[1] 

机构地区：[1]安徽省环保局,安徽合肥230061

出　　处：《污染防治技术》2009年第2期8-10,共3页Pollution Control Technology

摘　　要：提出一种基于动态RBF神经网络的地下水质综合评价方法。该方法采用最近邻聚类算法,构建动态RBF神经网络,利用神经网络对待测水质进行分类识别,根据网络输出,实现水质等级的确定。应用结果表明,该方法具有训练速度快、评价准确度高的优点,提高了水质综合评价的精度和客观性。A method of comprehensive evaluation of groundwater quality based on dynamic RBF neural network is presented. The RBF neural network is construeted by means of adopting the nearest neighbor - clustering algorithm in this method. Quality of pending requested water can be classified using neural network and obtained the water quality grade. Application results show that the method has faster training speed and higher accuracy of groundwater quality evaluation, and can improve the precision and objectivity of underground water environment quality evaluation.

关 键 词：RBF神经网络 最近邻聚类算法 地下水 环境质量评价 

分 类 号：X823[环境科学与工程—环境工程] X524