模糊时序与支持向量机建模相结合的PM_(2.5)质量浓度预测  

Prediction model of PM_(2.5) mass concentrations based on fuzzy time series and support vector machine

作　　者：刘杰[1] 杨鹏[2] 吕文生[1] 刘阿古达木 刘俊秀[2] 

机构地区：[1]北京科技大学土木与环境工程学院,北京100083 [2]北京联合大学北京市信息服务工程重点实验室,北京100101

出　　处：《北京科技大学学报》2014年第12期1694-1702,共9页Journal of University of Science and Technology Beijing

基　　金：北京市属高等学校高层次人才引进与培养--"长城学者"培养计划项目"基于无线传感器网络的城市空气质量实时监测系统研究"资助项目(CIT&TCD20130320)

摘　　要：为解决进行PM2.5质量浓度预测中多因素回归模型的不稳定、神经网络模型的过拟合及局部最小等问题,提出应用支持向量机和模糊粒化时间序列相结合的方法,对PM2.5质量浓度未来变化趋势和范围进行预测.根据PM2.5不同季节的日变化周期模式,确定以24 h为周期的粒化窗宽,利用三角型隶属函数对数据样本进行特征提取作为支持向量机的输入,并在k重交叉验证法下采用网格划分寻找出模型的最佳参数.以2013年3月—2014年2月北京市海淀区万柳监测点四个季节PM2.5的1 h质量浓度监测值为样本数据,应用该方法建立PM2.5质量浓度的时间序列预测模型,并在MATLAB平台下应用LIBSVM工具实现计算过程.结果表明,基于模糊粒化时间序列的预测模型,能较好解决PM2.5机理性建模方式下由于影响因素考虑不全而造成的预测结果不稳定,对模糊粒子拟合效果较好.To solve the instability of multiple-factor regression models and the existence of over-learning and local minima of neural network models in predicting PM2. 5mass concentration,a method was proposed by combining support vector machine with fuzzy granulation of time series to predict the variation trend and range of PM2. 5mass concentration. According to the daily periodic variation of PM2. 5in different seasons,a 24-h pattern was determined to be the window length of granulating. Feature extraction of data samples proceeded by a triangular membership function was applied to support vector machine inputs for regressive modeling,and the optimum parameters of models were selected by grid search based on k-fold cross validation. Then a time series prediction model was established by using 1-h PM2. 5mass concentration obtained by Wanliu monitoring station at Haidian district of Beijing in 4 seasons from March2013 to February 2014,and its resolving was realized by LIBSVM tool in MATLAB platform. The results show that the prediction model of PM2. 5mass concentration based on fuzzy granulation of time series can solve the instability caused by uncertain factors in mechanism modeling and get a good fitting effect on fuzzy granulation parameters.

关 键 词：细颗粒物 质量浓度 预测模型 支持向量机 时间序列 

分 类 号：X823[环境科学与工程—环境工程]