基于组合权重-TOPSIS的海水水质综合评价方法

A Comprehensive Evaluation Method of Seawater Quality Based on Combination Weight-TOPSIS

针对神经网络网络结构的选择尚无统一而完整的理论指导以及训练样本多样性不足等问题,提出了一种新的基于组合权重-TOPSIS的海水水质评价模型。该模型在权重选取时为了避免主观因素的干扰,分别采用熵权法与CRITIC赋权法计算客观权重,然后利用最小鉴别信息原理计算出组合权重,最后结合TOPSIS方法对胶州湾采集的数据进行实例分析并与其它方法进行对比。实验结果表明,该评价模型能充分利用样本信息,评价结果与相关文献中的结果基本一致,所提模型为海水水质评价提供了一种新的参考。

Aiming at the lack of unified and complete theoretical guidance for the selection of neural network structure and insufficient diversity of training samples, a new seawater quality evaluation model based on combined weight-TOPSIS is proposed. In order to avoid the interference of subjective factors in weight selection, the model uses the entropy weight method and the CRITIC empowerment method to calculate the objective weights, and then uses the principle of least identification information to calculate the combined weights, and finally combines the TOPSIS method to analyze the data collected in Jiaozhou Bay by example and compare with other methods. The experimental results show that the evaluation model can make full use of the sample information, and the evaluation results are basically consistent with the results in the relevant literature, and the proposed model provides a new reference for the evaluation of seawater quality.