摘要
基于投影寻踪技术的基本原理和求解过程,建立了水质评价模型。大样本数据应用到模型中.使模型的精度大大提高。该模型既能根据样本本身寻求出各因子的重要程度,即客观权重,又能根据决策者对某个(些)影响因子的偏好,对样本进行分类。将遗传算法和传统优化方法相结合,以解决遗传算法求解带约束问题能力差的问题,并将其用于本文建立的模型的目标函数优化中,解决了高维数据全局寻优的难题。实例分析表明,该模型能够很好地对水质进行评价,能有效地解决多因素带来的高维复杂性,是一种处理多因素复杂评价问题的有效途径。
A water quality assessment model is built based on projection pursuit technique. A great quantity of sample data is applied to increase the model＇s precision. A new genetic algorithm combined with conditional optimization method is proposed and applied to the model optimization, which can deal with global optimization problem with various restrictions effectively. The case study shows that this model can give appropriate assessment of water quality. And more important, it can determine the index weights in an objective way or in the way of taking decision makers＇ bias into account, which is difficult in other assessment methods.
出处
《水文》
CSCD
北大核心
2005年第4期14-17,共4页
Journal of China Hydrology
关键词
水质评价
评价模型
投影寻踪
遗传算法
water quality
assessment model
projection pursuit
genetic algorithm
