基于CEEMDAN-SE和LSTM神经网络的PM<sub>10</sub>浓度预测

梁涛; 谢高锋; 米大斌; 姜文

doi:10.13205/j.hjgc.202002015

基于CEEMDAN-SE和LSTM神经网络的PM₁₀浓度预测

doi: 10.13205/j.hjgc.202002015

梁涛^1, ,,
谢高锋¹,
米大斌²,
姜文²

1. 河北工业大学人工智能与数据科学学院, 天津 300401;
2. 河北建投能源投资股份有限公司, 石家庄 050001

基金项目:

河北省科技计划项目（16214510D，17214304D，19210108D）；石家庄科技局重点研发项目（181060481A）。

详细信息

通讯作者:
梁涛(1975-),男,博士,教授,主要研究方向为新能源、大数据分析。liangtao@hebut.edu.cn

计量
- 文章访问数: 154
- HTML全文浏览量: 11
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2019-07-07

PREDICTION OF PM₁₀ CONCENTRATION BASED ON CEEMDAN-SE AND LSTM NEURAL NETWORK

1. School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China;
2. Jointo Energy Investment Co., Ltd, Hebei, Shijiazhuang 050001, China

摘要

摘要: 针对PM₁₀浓度时间序列具有明显的非线性和波动性特征，提出一种基于自适应噪声的完整集成经验模态分解（complete ensemble empirical mode decomposition with adaptive noise，CEEMDAN）-样本熵（sample entropy，SE）和长短期记忆神经网络（long short-term memory，LSTM）的组合预测模型。首先利用CEEMDAN-SE将原始PM₁₀浓度时间序列分解为若干个复杂度差异明显的子序列；然后针对各子序列的内在特性结合气象因素分别建立适当参数空间的LSTM预测模型；最后将预测结果进行叠加得到最终预测结果。以唐山市4个空气质量监测站的实测PM₁₀浓度数据进行模型验证分析，结果表明：所提预测模型对比其他几种预测模型显示出较高的预测精度，以及良好的普适性。
- PM₁₀ /
- 浓度预测 /
- 集成经验模态分解 /
- 样本熵 /
- 时间序列
Abstract: In view of the nonlinear and volatility characteristics of PM₁₀ concentration time series, this paper presented a prediction model of PM₁₀ concentration based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)-sample entropy (SE)-long short-term memory (LSTM). The original PM₁₀ concentration time series were decomposed into several sub-sequences with obvious complexity differences by CEEMDAN-SE. Then, an appropriate LSTM prediction model was built by adding meteorological parameters to each different sub-sequence. The final results were got by adding the prediction results. The data of four monitoring stations in Tangshan was used to implement simulation experiment, and the results confirmed that the proposed prediction model showed high prediction precision, and good universality, comparing with other prediction models.
- PM₁₀ /
- concentration prediction /
- ensemble empirical mode decomposition /
- sample entropy /
- time series

HTML全文

参考文献(17)

KHANIABADI Y O, GOUDARZI G, DARYANOOSH S M, et al. Exposure to PM₁₀, NO₂, and O₃ and impacts on human health[J]. Environmental Science and Pollution Research, 2017,24(3):2781-2789.

LI Y, CHEN Q L, ZHAO H J, et al. Variations in PM₁₀, PM_2.5 and PM₁₀ in an urban area of the Sichuan basin and their relation to meteorological factors[J]. Atmosphere,2015,6(1):150-163.

VLACHOGIANNI A, KASSOMENOS P, KARPPINEN A, et al. Evaluation of a multiple regression model for the forecasting of the concentrations of NO_x and PM₁₀ in Athens and Helsinki[J]. Science of the Total Environment,2011,409(8):1559-1571.

LI W D, KONG D M, WU J. A new hybrid model FPA-SVM considering cointegration for particular matter concentration forecasting:a case study of Kunming and Yuxi, China[J]. Computational Intelligence and Neuroscience, 2017:2843651.

冯晓秀,高志文,李风军,等.基于LS-SVR、BP-ANN和MLR模型的PM₁₀浓度预测[J].中国环境监测,2014,30(6):138-141.

DEDOVIC M M, AVDAKOVIC S, TURKOVIC I, et al. Forecasting PM₁₀ concentrations using neural networks and system for improving air quality[J]. 2016 XI International Symposium on Telecommunications (BIHTEL), Sarajevo, 2016:1-6.

QU X Y, KANG X N, ZHANG C, et al. Short-term prediction of wind power based on deep Long Short-Term Memory[C]//2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Xi'an, 2016:1148-1152.

王平,张红,秦作栋,等.基于wavelet-SVM的PM₁₀浓度时序数据预测[J].环境科学,2017,38(8):3153-3161.

邓翱,金敏.基于EMD的时标特征提取方法及其在短期电力负荷预测中的应用[J].计算机应用研究,2017,35(10):2952-2955.

秦喜文,刘媛媛,王新民,等.基于整体经验模态分解和支持向量回归的北京市PM_2.5预测[J].吉林大学学报(地球科学版),2016,46(2):563-568.

BAI Y, LI Y, WANG X X, et al. Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions[J]. Atmospheric Pollution Research,2016,7(3).:557-566.

郭飞,谢立勇.基于气象因素和改进支持向量机的空气质量指数预测[J].环境工程,2017,35(10):151-155.

HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A:Mathematical, Physicaland Engineering Sciences,1998,454(12):903-995.

WU Z H, HUANG N E. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41.

RICHMAN J S, MOORMAN J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology Heart Circulatory Physiology,2000,278(6):2039-2049.

GRAVES A, MOHAMED A, HINTON G. Speech recognition with deep recurrent neural networks[C]//Proceedings of International Conference on Acoustics, Speech and Signal Processing Acoustics. Vancouver, Canada:IEEE,2013:6645-6649.

HOCHREITE S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.

施引文献

资源附件(0)

访问统计