论文部分内容阅读
PM2.5作为大气首要污染物,严重影响着人们的身体健康.为了研究影响PM2.5的相关指标,以武汉市的空气数据为研究对象,通过多元线性回归、偏最小二乘回归、基于MIV的RBF神经网络回归等方法对AQI中6个基本监测指标的PM2.5(含量)与其它5项分指标及其对应污染物(含量)之间的相关性进行分析;通过比较,基于MIV的RBF神经网络回归模型拟合度达到0.9302,效果最好,而且也优于BP人工神经网络回归算法,因此得出了精确可靠的影响PM2.5的指标权重大小,为减排PM2.5提供了可靠的理论依据.
PM2.5 as a major pollutant in the atmosphere, seriously affecting people’s health.In order to study the impact of PM2.5 related indicators, the air data in Wuhan as the research object, by multiple linear regression, partial least-squares regression, based on MIV The correlation between PM2.5 (content) and other five sub-indexes and their corresponding pollutants (content) of 6 basic monitoring indicators in AQI were analyzed by RBF neural network regression and other methods. By comparison, RBF neural network regression model fitting degree of 0.9302, the best, but also better than the BP artificial neural network regression algorithm, and thus come to an accurate and reliable indicators of PM2.5 weight of the size, to provide a PM2.5 emission reduction Reliable theoretical basis.