Abstract：In the process of thermal power generation, the operation condition of combustion system is complicated and the delay is large, which makes it difficult to accurately measure the inlet NOx mass concentration in the selective catalytic reduction (SCR) flue gas denitration system. To solve this problem, a prediction model based on feature optimization and radial basis (RBF) neural network is proposed. Firstly, the variable after feature optimization is taken as the final input variable of the model. Secondly, the beetle swarm optimization (BSO) is used to optimize the neural network hyperparameters. Finally, a prediction model of inlet NOx concentration is established. The results show that the predictive results of the optimized variables are better than those of the original variables. After feature optimization and timely delay, the SRMSE of the model decreased by 44.5%, and the R2 increased by 2.3%. The neural network hyperparameters determined by BSO also improved the accuracy of the model.
WU K L, HUANG J, LI Z H, et al. Dynamic prediction of the NOx concentration at SCR system outlet based on MIC-CFS-LSTM model［J］. Clean Coal Technology, 2023,29(6):1-10.
LI Q Y, CAO Q S, WANG T T. Parameter optimization of sliding mode controller for fleet based on particle swarm optimization［J］. Computer Engineering and Design, 2022, 43(3): 808-813.
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.
SHAN B B, LI H, GU R Z, et al. Short-term wind power combination prediction based on beetle antennae search algorithm［J］. Science Technology and Engineering, 2022, 22( 2): 540-546.
［10］
HONG D, BALZANO L, FESSLER J A. Towards a theoretical analysis of PCA for heteroscedastic data［C］//2016 54th Annual Allerton Conference on Communication, Control, and Computing(Allerton). Monticello, IL, USA, 2017.
XIE L R, WANG B, BAO H Y, et al. Super-short-term wind power forecasting based on EEMD-WOA-LSSVM［J］. Acta Energiae Solaris Sinica, 2021, 42(7): 290-296.
WANG F, MA S X, WANG H. Prediction model of carbon content in fly ash using random forest variable selection method［J］. Thermal Power Generation, 2018, 47(11): 89-95.
［3］
LI Q W, ZHOU K Y, YAO G H. Combustion optimization model for NOx reduction with an improved particle swarm optimization［J］. Journal of Shanghai Jiaotong University(Science), 2016, 21(5): 569-575.
TANG Z H, CHAI X Y, CAO S X, et al. Deep Learning Modeling for the NOx Emissions of Coal-fired Boiler Considering Time-delay Characteristics［J］. Proceedings of the CSEE, 2020, 40(20): 6633-6644.
LIU C L, WU Y J, ZHEN C G. Fault diagnosis of rolling bearing based on variational mode decomposition and fuzzy C-means clustering［J］. Proceedings of the CSEE, 2015, 35(13): 3358-3365.
［19］
JIANG X, LI S. BAS: beetle antennae search slgorithm for optimi-zation problems［J］. Internation Journal of Robotics and Control, 2018, 1 (1): 1－8.
WU L, KANG Y W. Prediction model of SO2 concentration in desulfurization system based on improved particle swarm optimization LSTM［J］. Thermal Power Generation, 2021, 50(12): 66-73.
ZHAO W J, ZHANG K. NARX neural network modeling of SCR denitration system based on mutual information variables selection［J］. Thermal Power Generation, 2018, 47(9): 22-26.
JIN X Z, LIU Y, ZHAO W J, et al. Prediction of SO2 Mass Concentration at Outlet of the Thermal Power Plant Based on mRMR and MA-RELM［J］. Journal of Chinese Society of Power Engineering, 2022, 42(7): 664-670.
YAN L Q, DONG Z. Dynamic Prediction Model of SCR Denitrification System Based on k-nearest Neighbor Mutual Information and WKOPLS［J］. Proceedings of the CSEE, 2019, 39(10): 2970-2980.
［4］
FU J, XIAN 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(i Things) and IEEE Green Computing and Communications(Green Com) and IEEE Cyber, Physical and Social Computing(CPSCom) and IEEE Smart Data(Smart Data). Atlanta, USA, 2019.
LI Z, QIN Z G, LIU Z J, et al. Phase-sensitive optical time domain reflectometry assisted by total variation techniques［J］. Acta Optica Sinica, 2021, 42(17): 32-39.
JIN X Z, LIU Y, YU J, et al. Prediction of Outlet SO2 Concentration Based on Variable Selection and EMD-LSTM Network［J］. Proceedings of the CSEE, 2021, 41(24): 8475-8484.
［12］
QIU X H, REN Y, SUGANTHAN P N, et al. Empirical mode decomposition based ensemble deep learning for load demand time series forecasting［J］. Applied Soft Computing, 2017(54): 246-255.
YU T F, LIU R. NOx emission prediction for coal-fired boilers based on RBF Neural network and BP Neural network［J］. Thermal Power Generation, 2016, 45(8): 94-98.
［14］
KRASKOV A, STGBAUER H, GRASSBERGER P. Estimating Mu-tual Information［J］. Physical Review E, 2004, 69 (6 Pt 2): 066138.
STREETS D G, WALDHOFF S T, Present and future emissions of air pollu-tants in China: SO2, NOx, and CO［J］. Atmospheric Environment, 2000, 34( 3): 363－374.
2024, Vol. 45 
