基于投影寻踪和粒子群优化算法的南宁市内河水质综合评价研究

Study on Water Quality Evaluation of Nanning Inland River Based on Projection Pursuit and Particle Swarm Optimization

针对目前我国城市内河普遍遭到污染的问题,在分析影响内河水质因素的基础上,选取BOD5(五日生化需氧量)、CODcr(化学需氧量)、石油类、挥发酚、NH3-N(氨氮)和总磷等6个主要因素作为评价因子,建立了城市内河水质评价的投影寻踪分析模型,采用粒子群算法对该评价模型进行优化,并将其应用于南宁市10条内河水质的评价与排序。研究表明:用投影寻踪回归分析法进行水质评价,避免了传统评价方法由于主观原因造成的误差,方法简单、评价结果合理可信,为我国城市内河水质的评价提供了新途径。

Pollution problem is getting worse in China＇ s urban fiver at present. BODs, CODe,, petroleum, volatile phenol , NH3-N and total phosphorus for the evaluation factor were selected by analyzing inland fiver water quality affecting factors, a water quality evaluation method was established, optimized its project direction used Particle Swarm Optimization, and the model was applied to Nanning inland fiver. The e- valuation results were accurate, and some errors were eliminated because of the subjective factors for traditional methods. Projection Pursuit was a new evaluation method of urban inland fiver water quality,it was simple,reasonable,credible and has a wide application prospect.