基于遗传程序设计的水质评价模型

Comprehensive Evaluation of Water Quality Based on Genetic Programming

为在水质评价模型的结构未确知时,建立合适的模型来反映以评价指标为系统输入与以评价等级值为系统输出之间所隐含的复杂关系,提出了基于遗传程序设计的水质评价新方法。研究结果说明:新方法可在较大的程序空间中搜索一个最佳函数表达式,来描述水质评价系统的输入与输出样本数据系列所隐含的关系;新方法在水资源系统建模、预测、评价和控制等计算机程序自动设计中具有推广应用价值。

Exact comprehensive evaluation of water quality can be used in scientific decision-making of regional water environmental management and pollution control. Key problem is how to establish a correct model for describing the complex relation hidden in input and output data series of water quality evaluation system when the model structure of the complex water quality evaluation has been unknown. For this reason, a new method, named GP-CEWQ for short, is presented in this paper for comprehensive evaluation of water quality based on genetic programming. The study results show that a good function expression can be obtained within large programming search space using GP-CEWQ method, which expression can reflect the complex relation hidden in system input and output data series of water quality evaluation system, and that the method can be widely used in computer programming automation of system modeling, prediction, evaluation and control of water resource systems engineering.