基于改进萤火虫算法的投影寻踪太湖水质综合评价

针对水质评价中指标的多样性及不相容性,提出了基于改进的萤火虫算法的投影寻踪水质评价方法。该方法根据水质标准等级样本集所划分的标准,构建投影指标函数,并用改进的萤火虫算法进行优化,使搜索步长逐步减小,寻优后期也可具有良好的局部搜索能力,得到最佳投影方向,使综合评价结果能够客观准确地反映出水质状况。运用该方法对太湖的水质数据进行综合评价,并与传统方法综合评分法(F值法)得到的结果进行对比,评价结果更符合当地水质状况实际情况,且对水质等级划分更为清晰。

Projection Pursuit Model for Assessment of Taihu Lake Water Quality Based on Improved Firefly Algorithm

In order to solve the problems of the diversity and incompatibility of water quality index in water quality evaluation of, a water quality assessment method is proposed based on the projection pursuit method with the improved firefly algorithm (FA).Based on the classification standard of surface water environment, the projection index function is established.With the optimization of the improved firefly algorithm, the searching step length is reduced gradually, better local search ability at the later stage is gained, the best projection direction is gotten, and the correct, objective and comprehensive evaluation results reflecting the true water quality is acquired.The Taihu lake water quality data is comprehensively evaluated with this method and the evaluated results are compared with those of the comprehensive scoring method (F method).The results approve that the assessment method matches the actual local water quality circumstances better and are clearer in water quality hierarchy.