Application of Neural Network Predictive Control in SCR Flue Gas Denitration System

doi:10.12068/j.issn.1005-3026.2017.06.004

Abstract

Abstract: Based on the data collected from selective catalytic reduction (SCR) reaction system of a 350MW coal-fired unit in a thermal power plant， neural network predictive control method was used to study the prediction and control of nitrogen oxides emission in power plant tail gas. Firstly， the non-linear model of SCR denitrification system was modeled and nonlinear autoregressive model was used to estimate the model. Then， by using the predictive control method to control the ammonia injection， the tail gas could achieve the standard of discharge limitation， and the amount of ammonia and ammonia escape could also be reduced， resulting in the enhancement of economic efficiency. The controller was optimized by the steepest gradient method and the control variable was constrained by the performance function to achieve the expected output. Finally， compared with the measured date in the field， the simulation results show that the neural network predictive control scheme can predict the amount of ammonia sprayed in the future at a finite time.

Key words: selective catalytic reduction (SCR), neural networks, predictive control, nonlinear auto regressive algorithm, model identification

CLC Number:

TP273

MENG Fan-wei， XU Bo， LYU Xiao-yong ， LIU Yin-qi. Application of Neural Network Predictive Control in SCR Flue Gas Denitration System[J]. Journal of Northeastern University:Natural Science, 2017, 38(6): 778-782.

References

[1]Jiang N，Shang K F，Lu N，et al.High-efficiency removal of NO_○x from flue gas by multitooth wheel-cylinder corona discharge plasma facilitated［J］.IEEE Transactions on Plasma Science，2016，44(11):2738-2744.
[2]罗子湛，孟立新.燃煤电站SCR烟气脱硝喷氨自动控制方式优化［J］.电站系统工程，2010，26(4):29-31.(Luo Zi-zhan，Meng Li-xin.Ammonia flow automatic control mode optimization of SCR flue gas DeNO_○x for coal-fired power plant［J］.Power System Engineering，2010，26(4):29-31.)
[3]Peng H，Ozaki T，Toyoda Y，et al.RBF-ARX model based nonlinear system modeling and predictive control with application to a NO_○x decomposition process［J］.Control Engineering Practice，2004，12(2):191-203.
[4]周洪煜，张振华，张军，等.超临界锅炉烟气脱硝喷氨量混结构-径向基函数神经网络最优控制［J］.中国电机工程学报，2011，31(5):108-113.(Zhou Hong-yu，Zhang Zhen-hua，Zhang Jun，et al.Mixed structure-radial basis function neural network optimal control on spraying smmonia flow for supercritical boiler flue gas denitrification［J］.Proceedings of the CSEE，2011，31(5):108-113.)
[5]姜家国，郭为民，刘延泉，等.选择性催化还原脱硝系统Smith预估自抗扰控制［J］.热力发电，2016，45(1):54-59.(Jiang Jia-guo，Guo Wei-min，Liu Yan-quan，et al.Auto disturbance rejection control based on Smith predictor in SCR denitrification system［J］.Thermal Power Generation，2016，45(1):54-59.)
[6]周洪煜，赵乾，张振华，等.烟气脱硝喷氨量SA-RBF神经网络最优控制［J］.控制工程，2012，19(6):947-951.(Zhou Hong-yu，Zhao Qian，Zhang Zhen-hua，et al.Sensitivity analysis radial basis function neural network control on spraying ammonia flow denitrification［J］.Control Engineering of China，2012，19(6):947-951.)
[7]Wu X，Shen J，Sun S，et al.Data-driven disturbance rejection predictive control for SCR denitrification system［J］.Industrial & Engineering Chemistry Research，2016，55:5923-5930.
[8]McKinley T L，Alleyne A G.Adaptive model predictive control of an SCR catalytic converter system for automotive applications［J］.IEEE Transactions on Control Systems Technology，2012，20(6):1533-1547.
[9]Hunt K J，Sbarbaro D，Zbikowski R，et al.Neural networks for control systems a survey ［J］.Automatica，1992，28(6):1083-1112.
[10]Golshan M，Macgregor J F.Latent variable model predictive control (LV-MPC) for trajectory tracking in batch processes［J］.Journal of Process Control，2010，20(4):538-550.
[11]Yang T T，Gao Y.Neural networks control on spraying ammonia flow of SCR system［C］//2016 Chinese Control and Decision Conference.Shanghai，2016:838-842.
[12]Baljit S R，James S，Udaya K M.Model predictive direct slope control for power converters［J］.IEEE Transactions on Power Electronics，2017，32(3):2278-2289.
[13]Camacho D E F，Bordons D C.Model predictive control［M］.New York:Springer，2004.