基于PCA-OS-ELM的大气PM_(2.5)浓度预测  

PM_(2.5) Concentration Prediction Based on PCA-OS-ELM

作　　者：李济瀚 李晓理 王康 崔桂梅[3] LI Jihan;LI Xiaoli;WANG Kang;CUI Guimei(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;Beijing Key Laboratory of Computational Intelligence and Intelligent System,Engineering Research Center of Digital Community,Ministry of Education,Beijing 100124,China;School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou,Inner Mongolia 014010,China)

机构地区：[1]北京工业大学信息学部,北京100124 [2]北京市计算智能与智能系统重点实验室,教育部数字社区工程研究中心,北京100124 [3]内蒙古科技大学信息工程学院,内蒙古包头014010

出　　处：《北京理工大学学报》2021年第12期1262-1268,共7页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(61873006,61673053);国家重点研发计划资助项目(2018YFC1602704,2018YFB1702704)。

摘　　要：为了提高细颗粒物PM_(2.5)浓度预测精度,提出一种主元成分分析与在线序列极限学习机相结合(PCA-OS-ELM)的PM_(2.5)浓度预测方法.首先,通过主成分分析方法(PCA)提取高维大气数据中影响空气质量的关键变量,并去除不必要的冗余变量;其次,利用提取的关键变量建立在线序列极限学习机(OS-ELM)网络预测模型,将批处理和逐次迭代相结合,不断更新训练数据和网络参数实现大气PM_(2.5)浓度快速预测.研究结果表明,PCA-OS-ELM预测方法采用不同批次训练数据更新模型的方式,能够快速实现大气PM_(2.5)浓度预测,证明了该方法的有效性.与其他方法相比,该方法预测误差小,预测精度高,具有更好的实用价值.In order to improve the prediction accuracy of PM_(2.5)concentration,a method based on the principal component analysis and online sequential extreme learning machine(PCA-OS-ELM)was proposed to predict PM_(2.5)concentration in this paper.Firstly,principal component analysis(PCA)was used to extract the key variables affecting air quality in high-dimensional atmospheric data,and remove unnecessary redundant variables.Secondly,an online sequential extreme learning machine(OS-ELM)network prediction model was established by using the extracted key variables.Finally,the training data and network parameters were continuously updated to realize the rapid prediction of PM_(2.5)concentration by combining batch processing with successive iteration.The results show that,taking different batches of training data to update the model,the PCA-OS-ELM prediction method can quickly realize the prediction of atmospheric PM_(2.5)concentration,proving the effectiveness of the proposed method.Compared with other methods,this method shows little prediction error,higher prediction accuracy and better practical value.

关 键 词：PM_(2.5) 主成分分析 相关性 在线序列极限学习机 预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]