PSO Hammerstein Model Based PM2.5 Concentration Forecasting

With the continuous improvement of living standards and the progress of science and technology, the problems of air pollution are very serious and research on the forecasting of PM2.5 concentration is particularly important. In this paper, we describe the development of a method to forecast the daily average PM2.5 concentration of Ningbo. The research is based upon the measurements from eight urban center monitoring sites during the period of 2013–2014. By normalizing the sample data and using the PCA method to reduce the its dimension, a multi-input single-output Hammerstein model for forecasting the concentration of PM2.5 is established by using PSO algorithm to identify the parameters of the model. According to the results reported here, the PSO Hammerstein model can be used to predict the PM2.5 concentration of regional air well.

[1]  Junfei Qiao,et al.  Prediction of PM2.5 based on Elman neural network with chaos theory , 2016, CCC 2016.

[2]  Ganapati Panda,et al.  Development of immunized pso algorithm and its application to hammerstein model identification , 2009, 2009 IEEE Congress on Evolutionary Computation.

[3]  Badong Chen,et al.  Multiple adaptive kernel size KLMS for Beijing PM2.5 prediction , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[4]  Xiaoguang Rui,et al.  A hybrid model for short-term air pollutant concentration forecasting , 2015, 2015 IEEE International Conference on Service Operations And Logistics, And Informatics (SOLI).

[5]  Dong Yang,et al.  PM2.5 concentration prediction using hidden semi-Markov model-based times series data mining , 2009, Expert Syst. Appl..

[6]  Weidong Zhang,et al.  Prediction of 24-hour-average PM(2.5) concentrations using a hidden Markov model with different emission distributions in Northern California. , 2013, The Science of the total environment.

[7]  Halife Kodaz,et al.  A new hybrid method based on Particle Swarm Optimization, Ant Colony Optimization and 3-Opt algorithms for Traveling Salesman Problem , 2015, Appl. Soft Comput..

[8]  Xiuhua Lu,et al.  The Prediction of PM2.5 Value Based on ARMA and Improved BP Neural Network Model , 2016, 2016 International Conference on Intelligent Networking and Collaborative Systems (INCoS).

[9]  Hui Wang,et al.  An improved model for PM2.5 inference based on support vector machine , 2016, 2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).

[10]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[11]  Xu Lin,et al.  PM2.5 measuring method using RBF neural network combined with PSO algorithm , 2015, The 27th Chinese Control and Decision Conference (2015 CCDC).