|Table of Contents|

[1] Ma Ning, Liu Lei, Yang Zhenyong, Yan Laiqing, et al. Dynamic model for predicting nitrogen oxide concentrationat outlet of selective catalytic reduction denitrificationsystem based on kernel extreme learning machine [J]. Journal of Southeast University (English Edition), 2022, 38 (4): 383-391. [doi:10.3969/j.issn.1003-7985.2022.04.007]
Copy

Dynamic model for predicting nitrogen oxide concentrationat outlet of selective catalytic reduction denitrificationsystem based on kernel extreme learning machine()
基于核极限学习机的SCR脱硝系统出口NOx浓度动态建模
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
38
Issue:
2022 4
Page:
383-391
Research Field:
Energy and Power Engineering
Publishing date:
2022-12-20

Info

Title:
Dynamic model for predicting nitrogen oxide concentrationat outlet of selective catalytic reduction denitrificationsystem based on kernel extreme learning machine
基于核极限学习机的SCR脱硝系统出口NOx浓度动态建模
Author(s):
Ma Ning1;  Liu Lei1;  Yang Zhenyong1;  Yan Laiqing2;  Dong Ze3
1North China Electric Power Research Institute Co., Ltd., Beijing 100045, China
2School of Electric Power, Civil Engineering and Architecture, Shanxi University, Taiyuan 030006, China
3Hebei Technology Innovation Center of Simulation and Optimized Control for Power Generation, North China Electric Power University, Baoding 071003, China
马宁1;  刘磊1;  杨振勇1;  闫来清2;  董泽3
1华北电力科学研究院有限责任公司, 北京 100045; 2山西大学电力与建筑学院, 太原 030006; 3华北电力大学河北省发电过程仿真与优化控制技术创新中心, 保定 071003
Keywords:
selective catalytic reduction;  nitrogen oxides;  principal component analysis;  kernel extreme learning machine;  dynamic model
选择性催化还原;  氮氧化物;  主成分分析;  核极限学习机;  动态模型
PACS:
TK22
DOI:
10.3969/j.issn.1003-7985.2022.04.007
Abstract:
To solve the increasing model complexity due to several input variables and large correlations under variable load conditions, a dynamic modeling method combining a kernel extreme learning machine(KELM)and principal component analysis(PCA)was proposed and applied to the prediction of nitrogen oxide(NOx)concentration at the outlet of a selective catalytic reduction(SCR)denitrification system. First, PCA is applied to the feature information extraction of input data, and the current and previous sequence values of the extracted information are used as the inputs of the KELM model to reflect the dynamic characteristics of the NOx concentration at the SCR outlet. Then, the model takes the historical data of the NOx concentration at the SCR outlet as the model input to improve its accuracy. Finally, an optimization algorithm is used to determine the optimal parameters of the model. Compared with the Gaussian process regression, long short-term memory, and convolutional neural network models, the prediction errors are reduced by approximately 78.4%, 67.6%, and 59.3%, respectively. The results indicate that the proposed dynamic model structure is reliable and can accurately predict NOx concentrations at the outlet of the SCR system.
为解决变负荷工况下因模型输入变量较多、相关性大导致模型复杂度增加的问题, 提出了一种将核极限学习机(KELM)和主成分分析(PCA)相结合的动态建模方法, 并应用于选择性催化还原(SCR)脱硝系统出口处的氮氧化物(NOx)浓度预测.首先, 将主成分分析应用于输入数据特征信息提取, 并将提取信息的当前和过往序列值用作KELM模型的输入, 以反映SCR出口处NOx浓度的动态特征;然后, 将SCR出口的NOx浓度历史数据作为模型的输入, 以提升模型精度;最后, 利用优化算法确定模型最优参数.结果表明, 与GPR、LSTM、CNN模型相比, 所建动态模型的预测误差分别减少约78.4%、67.6%和59.3%, 说明该模型结构可靠, 能够准确预测SCR系统出口NOx浓度.

References:

[1] Yang G, Wang Y, Li X. Prediction of the NOx emissions from thermal power plant using long-short term memory neural network[J]. Energy, 2020, 192:116597. DOI:10.1016/j.energy.2019.116597.
[2] Kang J, Niu Y, Hu B. Dynamic modeling of SCR denitration systems in coal-fired power plants based on a Bi-directional long short-term memory method[J]. Process Saf Environ Prot, 2021, 192: 867-878. DOI:10.1016/j.psep.2021.02.009.
[3] Fu J, Xiao H, Wang H, et al. Control strategy for denitrification efficiency of coal-fired power plant based on deep reinforcement learning[J]. IEEE Access, 2020, 8: 65127-65136. DOI:10.1109/ACCESS.2020.2985233.
[4] Dong Z, Ma N. A novel nonlinear partial least square integrated with error-based extreme learning machine[J]. IEEE Access, 2019, 7: 59903-59912. DOI:10.1109/ACCESS.2019.2911741.
[5] Wu X, Shen J, Li Y et al. Steam power plant configuration, design and control[J].Wiley Interdiscip Rev: Energy Environ, 2015, 4: 537-563.
[6] Niu Y, Pan Y, Huang W. Artificial fish swarm and feedback linearization of flue gas denitration control based on neural network[J]. Journal of System Simulation, 2018, 30:2707-2714.(in Chinese)
[7] Pham B, Shirzadi A, Bui D, et al. A hybrid machine learning ensemble approach based on a radial basis function neural network and rotation forest for landslide susceptibility modeling: A case study in the Himalayan area[J]. India Int J Sediment Res, 2018, 2: 157-170. DOI:10.1016/j.ijsrc.2017.09.008.
[8] Huang G, Zhu Q, Siew C. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70: 489-501. DOI:10.1016/j.neucom.2005.12.126.
[9] Huang G, Wang D, Lan Y. Extreme learning machines: a survey[J]. Int J Mach Learn Cybern, 2011, 2: 107-122. DOI:10.1007/s13042-011-0019-y.
[10] Dong Z, Ma N, Meng L.Model improvement for boiler NOx emission based on DEQPSO algorithm[J]. Journal of Chinese Society of Power Engineering, 2019, 39: 191-197.(in Chinese)
[11] Kadlec P, Grbic R, Gabrys B. Review of adaptation mechanisms for data-driven soft sensors[J]. Comput Chem Eng, 2011, 35: 1-24.
[12] Geladi P. Notes on the history and nature of partial least squares(PLS)modeling[J]. J Chemom, 1988, 2: 231-246. DOI:10.1002/cem.1180020403.
[13] Sj�F6;vall H, Blint R, Gopinath, A. A kinetic model for the selective catalytic reduction of NOx with NH3 over an Fe-zeolite catalyst[J]. Ind Eng Chem Res, 2010, 49: 39-52. DOI:10.1021/ie9003464.
[14] Liu J, Qin T, Yang T, et al. SCR denitration system modeling based on self-adaptive multi-scale kernel partial least squares[J]. Proceedings of the CSEE, 2015, 35: 6083-6088.(in Chinese)
[15] Feng Z, Niu W, Cheng C. Multi-objective quantum-behaved particle swarm optimization for economic environmental hydrothermal energy system scheduling[J]. Energy, 2017, 131:165-178. DOI:10.1016/j.energy.2017.05.013.
[16] Farjoudi S, Alizadeh Z. A comparative study of total dissolved solids in water estimation models using Gaussian process regression with different kernel functions[J]. Environmental Earth Sciences, 2021, 80: 1-14. DOI:10.1007/s12665-021-09798-x.
[17] Xiang L, Wang P, Yang X, et al. Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism[J]. Measurement, 2021, 175: 109094. DOI:10.1016/j.measurement.2021.109094.
[18] Liu Y, Chen H, Wang B. DOA estimation based on CNN for underwater acoustic array[J].Applied Acoustics, 2021, 172: 107594.DOI:10.1016/j.apacoust.2020.107594.

Memo

Memo:
Biography: Ma Ning(1992—), male, doctor, engineer, maningncepu@163.com.
Foundation items: The National Natural Science Foundation of China(No.71471060), the Natural Science Foundation of Hebei Province(No. E2018502111).
Citation: Ma Ning, Liu Lei, Yang Zhenyong, et al.Dynamic model for predicting nitrogen oxide concentration at outlet of selective catalytic reduction denitrification system based on kernel extreme learning machine[J].Journal of Southeast University(English Edition), 2022, 38(4):383-391.DOI:10.3969/j.issn.1003-7985.2022.04.007.
Last Update: 2022-12-20