基于主成分分析法与人工神经网络耦合模型的水质评价

Study on water quality evaluation of Luhe District based on principal component analysis and artificial neural network coupling model

为了解决水质评价中评价指标权重难以合理确定、评价模型过于复杂、评价结果不合理等问题,将改进的主成分分析降维能力与人工神经网络自学习能力相结合,提出PCA-BP神经网络水质评价模型。实例分析表明,PCA-BP神经网络在避免了传统的单因子评价法评价结果过于悲观、神经网络法模型复杂的同时,能够确定主要污染物,所得评价结果的合理性、准确性均能够得到保证。

In order to solve the problems in water quality evaluation,such as difficulty in determining the weight of evaluation indexes,too complicated evaluation model and unreasonable evaluation results,the improved dimension-reduction ability of principal component analysis was combined with the self-learning ability of artificial neural network,and the PCA-BP neural network model for water quality evaluation was proposed.The case analysis showed that PCA-BP neural network could avoid the pessimistic evaluation result of the traditional single factor evaluation method,and the model of the neural network method was complex.At the same time,it could determine the main pollutants,and the rationality and accuracy of the evaluation results could be guaranteed.