基于MATLAB实现的ANN方法在巢湖水质评价中的应用  

The application of ANN realized by MATLAB to Chaohu Lake water quality assessment

作　　者：孙莉宁[1] 张之源[1] 罗定贵[2] 

机构地区：[1]合肥工业大学资源与环境系,安徽合肥230009 [2]北京大学环境学院,北京100871

出　　处：《安徽大学学报（自然科学版）》2005年第2期90-94,共5页Journal of Anhui University(Natural Science Edition)

摘　　要：MATLAB6. 5工具箱提供了径向基网络的实现函数,该算法具有自适应确定网络结构和无需人为确定网络初始权值的特点。将其应用于巢湖水质评价,并尝试利用MATLAB的PRES TD函数进行原始数据预处理、利用RAND函数在水质评价标准等级间内插构造足够数量的训练样本、检测样本及其目标输出、确立水质评价等级界限,取得良好的评价结果,对提高水质评价的精度与客观性具有积极意义。The realizing function of RBF network is provided in the toolbox of MATLAB6.5 and the method of calculating this function possesses properties such as adaptation for determining the construction network and independence of initial weight value on person. A favorable outcome appeared after we apply this function to evaluating the water quality of Chaohu Lake, attempting to use the RAND function in MATLAB to construct enough training samples, checking samples and outputs of their targets through interpolation between grades of the water quality evaluation standard, use the PRESTD function to pretreat the original data,determine the limits of water quality grades. The methods in this paper is meaningful in improving the precision and objectivity of surface water quality evaluation.

关 键 词：水质评价 湖水 巢湖 预处理 ANN 原始数据 工具箱 径向基网络 训练样本 MATLAB6 

分 类 号：N941.5[自然科学总论—系统科学] X824[环境科学与工程—环境工程]