基于遗传算法和BP神经网络的空气质量预测模型研究  

Research on Air Quality Prediction Model Based on Genetic Algorithm and BP Neural Network

作　　者：牛玉霞 

机构地区：[1]南通科技职业学院,江苏南通226007

出　　处：《软件》2017年第12期49-53,共5页Software

基　　金：南通市科技局科技计划项目"基于物联网的化工园区VOCs在线监控系统研究"(MS12016028)

摘　　要：随着雾霾天气频发,大气污染和环境管理引起了人们越来越多的关注。能够精确监测化工园区厂企排放污染物,并能根据周边环境变化对空气质量做出相应预测,对广大民众健康甚至生命安全而言,具有重要的现实意义。本文利用遗传算法优化BP神经网络的权重和阙值,根据天气预报的相关变量,构建了空气质量预测模型,使预测模型的网络收敛速度、预测精度、拟合度以及泛化能力都有所w提高。With the frequent haze and haze, more and more attention has been paid to the air pollution and envi-ronmental management. It can accurately monitor pollutants emitted by factories and enterprises in chemical indus-trial parks, and predict air quality according to the changes of surrounding environment, which is of great practical significance for the health and even life safety of the masses. In this paper, we use genetic algorithm to optimize the weights and threshold values of BP neural network. According to the relevant variables of weather forecast, we build the prediction model of air quality, so that the prediction speed, prediction accuracy, fitting degree and generaliza-tion ability of the prediction model are all improved.

关 键 词：BP神经网络 遗传算法 VOCS 空气质量预测 

分 类 号：TP391.8[自动化与计算机技术—计算机应用技术]