基于RBF的指标规范化的水安全评价模型

为了建立科学合理、计算简便和普适通用的水安全评价模型,在适当设定指标参照值cj0和指标值的规范变换式基础上,提出了基于径向基函数网络的指标规范化的水安全评价模型。采用具有全局优化的猴王遗传算法对模型中的参数进行优化,得出优化后对任意m(1≤m≤23)项水安全指标共同适用的水安全评价模型。应用模型对山东省水安全状况进行了评价分析,其评价结果与其它方法的评价结果基本一致,从而表明:指标规范值的径向基函数网络模型为水安全评价提供了一个简单实用、结果可靠的新方法。

Assessment Model of Water Safety Represented with Normalized Indices Values Based on Radial Basis Function Neural Network

In order to design a scientific, reasonable, universal, common, and easy-operating water safety assessment model, we proposed this model based on the setting reference values and normalized transformation form of indexes. The assessment model of water safety represented with normalized indices values was proposed based on radial basis function network （RBF）. At the same time, the parameter involved in the model was also optimized by using Mon- key Genetic algorithm. The results show that the optimized universal water safety assessment model is suitable to rn （1≤m≤23） index items. The water security of Shandong Province was evaluated with this model. The evaluation results are consistent with the results of other methods. It shows that the NV-RBF model is simple and practical so as to be a useful evaluating method for water security.