空气质量预报系统的效果评估  

Evaluation of the Effect of Air Quality Forecasting System

作　　者：蔡哲贵 丁佳铭 丁佳乐 

机构地区：[1]上海理工大学机械工程学院,上海

出　　处：《建模与仿真》2022年第3期572-583,共12页Modeling and Simulation

摘　　要：大气与人类生活息息相关,社会对大气污染的准确预报需求迫切。本文对模型进行优化,降低各种参数的不确定性,采用拉格朗日插值法和均值法进行数据处理,利用灰色关联度进行降维得出回归方程、分析相关性,基于EM算法的K-Means聚类结果可视化,实现气象的合理分类。基于A监测点的实测数据样本,建立二次预报模型。结合过去值预测未来数据,进行数据纠正,再将预测得到的数据加入原有数据中,重新构造传递方程。最后采用卡尔曼滤波算法,进行去噪,进而实现噪声的压制,将模型结果与真实值和一次预报数据相比较,提高了模型的有效性与准确性。There is an urgent need for accurate prediction of air pollution since the atmosphere is closely related to human life. In the paper, the model is optimized to reduce the uncertainty of various parameters and the Lagrange interpolation method and mean method are used for data processing;the grey correlation degree is used to reduce the dimension, obtain the regression equation and analyze the correlation. Besides, the K-Means clustering results based on EM algorithm are visualized to realize the reasonable classification of meteorology. In addition, a secondary prediction model is established based on the measured data samples of monitoring point A. Then predict the future data in combination with the past value and correct the data;then add the predicted data to the original data and reconstruct the transfer equation. Finally, Kalman filter algorithm is adopted to denoise, which realizes the suppression of the noise. In the end, the effectiveness and accuracy of the model are improved by comparing model results with the real value and one-time prediction data.

关 键 词：拉格朗日插值法 灰色关联度 K-MEANS聚类 二次预报 卡尔曼滤波 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]