中文摘要：

根据我国湖泊富营养化特性，选择总磷（TP）、总氮（TN）、耗氧量（CODMn）、透明度（SD）、微生物数量等5个主要指标作为评价因子，建立了湖泊富营养化评价的投影寻踪分析模型，采用人工鱼群算法寻求最优投影方向．并将该模型应用于我国8个湖泊富营养化程度的评价，结果表明，经改进的投影寻踪回归算法，避免了传统评价方法由于主观原因造成的误差，评价结果合理可信、方法简单，是湖泊水体营养化状态评价的新方法。

英文摘要：

Based on characteristics of lake eutrophication, total phosphorus （TP）, total nitrogen （TN）, oxygen consumption （CODmn）, transparency（SD）, microbial population numbers, etc. Five evaluation indicators were chosen as the evaluation factors. Projection Pursuit analysis model of evaluation of the lake eutrophication was established, the evaluation model was optimized using Artificial Fish-Swarm Algorithm, and the model was applied to analysis of eight lakes. The evaluation results ware accurate, the method was simple, and some errors were eliminated because of the subjective factors for traditional methods. Projection Pursuit was a new evaluation method of the lake eutrophication, it had a wide application prospect.