基于神经网络的鱼群寻优和反馈线性化烟气脱硝控制

doi:10.16182/j.issn1004731x.joss.201807034

摘要/Abstract

摘要： 针对火力发电厂单元机组SCR烟气脱硝控制系统现状,提出了在SCR反应器入口加装调节阀与测点的优化方案,并相应提出了SCR反应器入口烟气预处理和总阀控制方案。在SCR反应器入口,采用单神经元自适应-人工鱼群滚动寻优控制算法(RSNAAFS)控制喷氨支管调节阀,对烟气中NO_X进行预处理;在SCR反应器出口,采用神经网络反馈线性化算法(NNFL)控制喷氨总管调节阀,对烟气中NO_X进行优化控制,使其达到排放标准。结果表明：新控制方案在控制品质上优于传统控制方案,系统有很强的实用性。

关键词: SCR烟气脱硝, 神经网络, 反馈线性化, 单神经元自适应, 人工鱼群, 优化

Abstract: According to the present situation of SCR flue gas dentration control system in thermal power plant, an optimum proposal that control valve and concentration transmitter are added in the inlet of the SCR reactor is presented, and the corresponding control strategy is given. At the entrance of the SCR reactor, the receding horizon algorithm combined with the single neuron adaptive algorithm and the artificial fish swarm algorithm (RSNAAFS) is used to control branch valves to pretreat NO_X in the exhaust flue gas. At the outlet of the SCR reactor, the neural network based on feedback linearization algorithm (NNFL) is used to control the general valve to limit the concentration of NO_X under the obligatory standard. The simulation result indicates that the presented strategy has a better effect on control quality compared with traditional control strategy, and has important practical significance.

Key words: SCR flue gas denitration, neural network, feedback linearization algorithm, single neuron adaptive algorithm, artificial fish swarm algorithm, optimization

中图分类号:

TP27

牛玉广, 潘岩, 黄文渊. 基于神经网络的鱼群寻优和反馈线性化烟气脱硝控制[J]. 系统仿真学报, 2018, 30(7): 2707-2714.

Niu Yuguang, Pan Yan, Huang Wenyuan. Artificial Fish Swarm and Feedback Linearization of Flue Gas Denitration Control Based on Neural Network[J]. Journal of System Simulation, 2018, 30(7): 2707-2714.

参考文献

[1] Taewha Park, Yonmo Sung, Taekyung Kim, et al.Effect of static mixer geometry on flow mixing and pressure drop in marine SCR applications[J]. Ocean (S2092-6782), 2014(6): 27-38.
[2] M Aliramezani, C R Koch, R E Haves.Estimating tailpipe NO_x concentration using a dynamic NOx/ammonia cross sensitivity model coupled to a three stste control oriented SCR model[J]. International Federation of Automatic Control (S2405-8963), 2016, 49(11): 8-13.
[3] 张圣杰, 孙翔, 王景成, 等. 火电站烟气脱硝大流量高速混合过程仿真研究[J]. 系统仿真学报, 2009, 21(23): 7652-7654.
Zhang Shengjie, Sun Xiang, Wang Jingcheng, et al.Sim-ulation research of fast mixing process of ultra-high flow rate in de Nox reactor of thermal power station[J]. Journal of system simulation, 2009, 21(23): 7652-7654.
[4] 胡学聪, 李柠, 李少远, 等. 基于Matlab的SCR烟气脱硝仿真平台设计[J]. 系统仿真学报, 2010, 22(1): 71-74.
Hu Xuecong, Li ning, Li Shaoyuan, et al. Development of simulation platform based on Matlab for SCR flue gas denitration[J]. Journal of system simulation, 2010, 22(1): 71-74.
[5] 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 (S1063-6536), 2012, 20(6): 1533-1547.
[6] Bora Jeong, Bora Ye, Eok-Soo Kim, et al.Characteristic of selective catalytic reduction (SCR) catalyst adding grapheme- tungsten nanocomposite[J]. Catalysis Communications (S1566-7367), 2017(93): 15-19.
[7] 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(5): 108-113.
Zhou Hongyu, Zhang Zhenhua, Zhang Jun, et al.Mixed Structure-radial Basis Function Neural Network Optimal Control on Spraying Ammonia Flow for Supercritical Boiler Flue Gas Denitrification[J]. Proceedings of the CSEE, 2011, 31(5): 108-113.
[8] 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 Jiaguo, Guo Weimin, Liu Yanquan, et al.Auto disturbance rejection control based on Smith predictor in SCR denitrification system[J]. Thermal Power Generation, 2016, 45(1): 54-59.
[9] 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 Hongyi, Zhao Qian, Zhang Zhenhua, 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.
[10] 刘吉臻, 秦天牧, 杨婷婷, 等. 基于自适应多尺度核偏最小二乘的SCR烟气脱硝系统建模[J]. 中国电机工程学报, 2015, 35(23): 6083-6088.
Liu Jizhen, Qin Tianmu, Yang Tingting, et al.SCR Denitration System Modeling Based on Self-adaptive Multi-scale Kernel Partial Lest Squares[J]. Proceedings of the CSEE, 2015, 35(23): 6083-6088.
[11] 秦天牧, 刘吉臻, 杨婷婷, 等. 火电厂SCR烟气脱硝系统建模与运行优化仿真[J]. 中国电机工程学报, 2016, 36(10): 2699-2703.
Qin Tianmu, Liu Jizhen, Yang Tingting, et al.SCR Denitration System Modeling and Optimization Simulation foe Thermal Power Plant[J]. Proceedings of the CSEE, 2016, 36(10): 2699-2703.
[12] 武宝会, 崔利. 火电厂SCR烟气脱硝控制方式及其优化[J]. 热力发电, 2013, 42(10): 116-119.
Wu Baohui, Cui Li.SCR Flue Gas Denitrification Control and Optimization in Thermal Power Plants[J]. Thermal Power Generation, 2013, 42(10): 116-126.
[13] 王勇, 徐东超, 林涛, 等. 基于子空间辨识和增广模型的烟气脱硝系统预测控制[J]. 热力发电, 2016, 45(6): 26-32.
Wang Yong, Xu Dongchao, Lin Tao, et al.Predictive control of flue gas denitration system based on subspace identification and augmented model[J]. Thermal Power Generation, 2016, 45(6): 26-32.
[14] 赵大周, 李允超, 郑文广, 等. 660 MW机组SCR喷氨策略的模拟研究[J]. 热能动力工程, 2016, 31(8): 81-86.
Zhao Dazhou, Li Yunchao, Zheng Guangwen, et al.The Research of SCR ammonia injection strategy in 600 MW unit[J]. Journal of engineer for thermal energy and power, 2016, 31(8): 81-86.
[15] 魏立新, 张峻林, 刘青松. 基于改进人工鱼群算法的神经网络优化[J]. 控制工程, 2014, 21(1): 84-93.
Wei Lixin, Zhang Junlin, Liu Qingsong.Optimization of Neural Network Based on Improved Fish Algorithm[J]. Control Engineering of China, 2014, 21(1): 84-93.
[16] 耿超, 王丰华, 苏磊, 等. 基于人工鱼群与蛙跳混合算法的变压器Jiles-Atherton模型参数辨识[J]. 中国电机工程学报, 2015, 35(18): 4799-4807.
Geng Chao, Wang Fenghua, Su Lei, et al.Parameter Identification of Jiles-Atherton Model for Transformer Based on Hybrid Artificial Fish Swarm and Shuffled Frog Leaping Algorithm[J]. Proceedings of the CSEE, 2015, 35(18): 4799-4807.
[17] 潘月斗, 陈继义, 徐杰, 等. 矩阵变换器输入电流的状态反馈线性化控制[J]. 高电压技术, 2014, 40(8): 2497-2503.
Pan Yuedou, Chen Jiyi, Xu Jie, et al.State Feedback Linearization Control for Current of Input Side in the Matrix Convertor[J]. High Voltage Engineering, 2014, 40(8): 2497-2503.
[18] 刘吉臻, 吕游, 杨婷婷. 基于变量选择的锅炉NOx排放的最小二乘支持向量机建模[J]. 中国电机工程学报, 2012, 32(20): 102-107.
Liu Jizhen, Lü You, Yang Tingting.Least squares support vector machine modeling on NOx emission of boilers based on variable selection[J]. Proceedings of the CSEE, 2012, 32(20): 102-107.
[19] Irfan M F, Mjalli F S, Kim S D.Modeling of NH3-NO-SCR reaction over CuO/γ-AL2O3 catalyst in a bubbling fluidized bed reactor using artificial intelligence techniques[J]. Fuel (S0016-2361), 2012, 93(1): 254-251.
[20] Chu Fei, Wang Fuli, Wang Xiaogang, et al.Performance modeling of centrifugal compressor using kernel partial least squares[J]. Applied Thermal Engineering (S1359-4311), 2012, 44: 90-99.
[21] 龙文, 梁昔明, 龙祖强, 等. 基于蚁群算法和LSSVM的锅炉燃烧优化预测控制[J]. 电力自动化设备, 2011, 31(11): 89-93.
Long Wen, Liang Ximing, Long Zuqiang, et al.Predictive control based on LSSVM and ACO for boiler combustion optimization[J]. Electric Power Automation Equipment, 2011, 31(11): 89-93.
[22] 席裕庚, 李德伟, 林姝. 模型预测控制—现状与挑战[J]. 自动化学报, 2013, 39(3): 222-236.
Xi Yugeng, Li Dewei, Lin Shu.Model predictive control-status and challenges[J]. Acta Automatics Sinica, 2013, 39(3): 222-236.