Abstract：It is difficult to accurately measure the inlet NOx concentration in selective catalytic reduction flue gas denitration system (SCR) for the combustion system of thermal power plant due to complex operating conditions and large delay. Therefore, a method to predict NOx concentration at SCR inlet of thermal power plant based on ARIMA-OSELM neural network combination model was proposed. The method was compared from two combination perspectives: optimal weight and residual optimization. The above method was applied to the prediction of SCR inlet concentration in a thermal power plant. The results show that the combined model based on ARIMA-OSELM residual optimization has the highest prediction accuracy, and its effect is better than that of ARIMA-OSELM optimal weight combined prediction model and single ARIMA and OSELM neural network prediction model. The obtain evaluation indexes FMAPE, MRMSE and R2 are 0.190, 1.364 and 0.978, respectively.
金秀章,陈佳政,李阳峰. 基于ARIMA-OSELM的火电厂SCR入口NOx浓度预测建模研究[J]. 计量学报, 2023, 44(9): 1458-1466.
JIN Xiu-zhang,CHEN Jia-zheng,LI Yang-feng. SCR Inlet of Thermal Power Plant Based on ARIMA-OSELM Prediction of NOx Concentration. Acta Metrologica Sinica, 2023, 44(9): 1458-1466.
Lu J C, Wang L. Study ofshort-term load forecasting based on ANN and time series［J］. Electric Power, 2005(7): 15-18.
Dong Z, Yan L Q. Modelling and Simulation for NOx Emission Concentration of SCR Denitrification System［J］. Journal of System Simulation, 2020, 32(2): 172-181.
Fu J, Xiao H, Wang T, et al. Prediction Model of Desulfurization Efficiency of Coal-Fired Power Plants Based on Long Short-Term Memory Neural Network［C］// 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData). Atlanta, USA, 2019.
Wang X, Li A G, Li Y, et al. Multivariate load prediction and wind-solar resource characteristic quantity prediction of integrated energy system based on ARIMA-LSTM model［J］. Journal of Xi’an University of Architecture & Technology (Natural Science Edition), 2022, 54(5): 762-769.
［10］
Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: A new learning scheme of feed-forward neural networks［C］//IEEE International Joint Conference on Neural Network. Montreal, Canada, 2005.
Liang T Q, Xu H, Zheng T L, et al. Measurement Uncertainty in Flue Gas Pollutants from Thermal Power
Fan J D, Huang Y X, Yan Z G, et al. Research on gas concentration prediction driven by ARIMA-SVM combined model［J］. Journal of Mine Automation, 2022, 48(9): 134-139.
Ma Z H, Yu H Y, Zhu R C. Disturbance Compensation Control of SCR Denitration Based on Mutual Information and PID Neural Network［J］. Thermal Power Engineering, 2020, 35(5): 281-288.
Song G J, Guo X D, Yang X, et al. ARIMA-SVM combination prediction of PM2.5 concentration in Shenyang ［J］. China Environmental Science, 2018, 38(11): 4031-4039.
Yan H S, Zhao W J. Prediction of SO2 Concentration at Desulfurization Outlet Based on MIC and MPA-KELM［J］. Acta Metrologica Sinica, 2023, 44(2): 271-278.
Lü Y, Liu J Z, Yang T T, et al. NOx emission characteristic modeling based on feature extraction using PLS and LS-SVM［J］. Chinese Journal of Scientific Instrument, 2013, 34(11): 2418-2424.
［9］
Fan D Y, Sun H, Yao J, et al. Well production forecasting based on ARIMA-LSTM model considering manual operations［J］. Energy, 2021, 220: 119708.
［11］
Zeng Q S, Quan S P, Jin Z Q. Short-term traffic flows forecasting by fusing BP neural network and ARIMA ［J］. Journal of Zhengzhou University Engineering Scienc, 2015, 32(4): 60-63.
Yue J G, Yang Z M, Sun Q, et al. Hybrid model for interval-valued time series［J］. Control and Decision, 2013, 28(12): 1915-1920.
Li Y Z, Yue C F. Stability Test of Runoff Extreme Time Series in Jingou River Basin［J］. Water Resources and Power, 2019, 37(10): 21-24.
Liu Y, Yu J, Jin X Z. NOx Concentration Prediction Based on Feature Optimization and Improved LSTM Network［J］. Thermal Power Generation, 2021, 50(7): 162-169.
Ji X Y, Yang K, Chen Y N, et al. An ensemble learning model for water quality forecast based on ARIMA and Prophet［J］. Water Resources Protection, 2022, 38(6): 111-115.
2023, Vol. 44 
