Optimization of Computer in the Projection Pursuit Model of Comprehensive Evaluation of Water Pollution

In this paper, the differential evolution algorithm (DE) was used to search for the optimal projection direction of projective pursuit (PP) model, and a DE-PP comprehensive water quality evaluation model was proposed. In this paper, based on a simple projection index, a multivariate data classification model is established with a new optimization approach, and it is applied to the classification of standard water quality with multiple indexes. The water quality evaluation results of two examples show that this model can map high-dimensional data to low-dimensional subspace through the optimal projection direction. The model is convenient for sample classification and comprehensive evaluation. The model proposed in this paper provides a new idea and method for the research of water quality evaluation.