Prediction method for NOx discharged from SCR denitrification systems based on IQGA-GRNN model

doi:10.3969/j.issn.1674-1951.2021.05.002

Abstract

Abstract:

According to the complex craftwork and non-linear characteristic of SCR denitrification systems, a mathematical model for NO_x discharged from coal-fired power plants was created based on Improved Quantum Genetic Algorithm （IQGA） and General Regression Neural Network （GRNN）. Firstly, QGA was modified by revolving door to get the search results more accurate. Secondly, the smoothness factor in GRNN was optimized to improve the approximation ability of the algorithm. Taking a 300 MW heat-supply unit as an example, an IQGA-GRNN model was created and trained by the training data of the unit. The maximum error between the predicted value made by the model and the measured value is within 8.0%, and the average error is within 0.2%. The IQGA-GRNN model is supportive for precise control on NH₃ spray.

Key words: IQGA, GRNN, coal-fired power plant, denitrification system, NO_x mass concentration, prediction

CLC Number:

TP18：X701

CAO Xiguo, ZHANG Yongtao, LI Yatian. Prediction method for NO_x discharged from SCR denitrification systems based on IQGA-GRNN model[J]. Huadian Technology, 2021, 43(5): 9-14.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Tab.1

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Tab.2

References 18

[1]	孙哲, 刘振波. 基于智慧模型的脱硝控制系统优化[J]. 华电技术, 2020,42(9):37-44.
	SUN Zhe, LIU Zhenbo. Application of intelligent model in denitration control system optimization[J]. Huadian Technology, 2020,42(9):37-44.
[2]	郝正, 胡小夫, 王云, 等. 火电机组SCR脱硝系统精准喷氨优化研究[J]. 华电技术, 2019,41(10):8-11.
	HAO Zheng, HU Xiaofu, WANG Yun, et al. Research on precise ammonia injection retrofit for SCR denitration systems in thermal powers[J]. Huadian Technology, 2019,41(10):8-11.
[3]	王争荣, 汪洋, 夏怀鹏, 等. 1 000 MW燃煤机组SCR脱硝系统喷氨精细化改造[J]. 华电技术, 2019,41(10):1-7.
	WANG Zhengrong, WANG Yang, XIA Huaipeng, et al. Delicacy control on ammonia injection for SCR denitration system in a 1 000 MW coal-fired unit[J]. Huadian Technology, 2019,41(10):1-7.
[4]	董泽, 马宁, 任林, 等. 基于变量相关性自适应即时学习算法的火电厂SCR脱硝系统建模[J]. 华北电力大学学报, 2019,46(2):83-90.
	DONG Ze, MA Ning, REN Lin, et al. Modeling of SCR denitrification system in thermal power plant based on variable correlation adaptive real-time learning algorithm[J]. Journal of North China Electric Power University, 2019,46(2):83-90.
[5]	姚楚, 龙东腾, 吕游, 等. 火电厂SCR脱硝系统机理建模与控制研究[J]. 热能动力工程, 2018,33(5):78-84.
	YAO Chu, LONG Dongteng, LV You, et al. Mechanism of SCR denitration system modeling and control study[J]. Journal of Thermal Power Engineering, 2018,33(5):78-84.
[6]	付忠广, 高学伟, 李闯, 等. 基于改进模糊聚类与IPSO-SVM的燃煤电站NO_x排放多模型预测[J]. 热能动力工程, 2019,39(5):387-408.
	FU Zhongguang, GAO Xuewei, LI Chuang, et al. Multi-model NO_x emission prediction based on IGASA-FCM and IPSO-SVM for coal-fired power plants[J]. Journal of Chinese Society of Power Engineering, 2019,39(5):387-408.
[7]	翟永杰, 张志超. 基于现场数据的SCR脱硝反应器建模[J]. 计算机仿真, 2014,31(10):141-144.
	ZHAI Yongjie, ZHANG Zhichao. Modeling for SCR denitration reactor based on field data[J]. Computer Simulation, 2014,31(10):141-144.
[8]	周鑫, 吴佳. 火电厂SCR烟气脱硝系统建模与喷氨量最优控制[J]. 浙江电力, 2015,34(11):15-19.
	ZHOU Xin, WU Jia. Modeling of SCR flue gas denitration system and optimal control of spraying ammonia flow in thermal power plant[J]. Zhejiang Electric Power, 2015,34(11):15-19.
[9]	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 operation optimization simulation for thermal power plant[J]. Proceedings of the CSEE, 2016,36(10):2699-2703.
[10]	秦天牧, 尤默, 张瑾哲, 等. 基于自适应智能前馈的SCR脱硝系统优化控制[J]. 中国电机工程学报, 2019,39:186-192.
	QIN Tianmu, YOU Mo, ZHANG Jinzhe, et al. Optimal control of SCR denitration system based on self-adaptive intelligent feed forward[J]. Proceedings of the CSEE, 2019,39(8):186-192.
[11]	徐晶, 迟福建, 葛磊蛟, 等. 基于SARIMA-GRNN-SVM 的短期商业电力负荷组合预测方法[J]. 电力系统及其自动化学报, 2020,32(2):85-91.
	XU Jing, CHI Fujian, GE Leijiao, et al. A short-term commercial load forecasting method based on SARIMA- GRNN-SVM[J]. Proceedings of the CSU-EPSA, 2020,32(2):85-91.
[12]	王慧莹, 吴亮红, 梅盼盼, 等. 果蝇优化广义神经网络的风电功率短期预测[J]. 电子测量与仪器学报, 2019,33(6):177-183.
	WANG Huiying, WU Lianghong, MEI Panpan, et al. Short term prediction of wind power based on generalized neural network optimized by drosophila melanogaster[J]. Journal of Electronic Measurement and Instrument, 2019,33(6):177-183.
[13]	HOU K, SHAO G H, WANG H M, et al. Research on practical power system stability analysis algorithm based on modified SVM[J]. Protection and Control of Modern Power Systems, 2018,3(3):119-125.
[14]	PATEL G K, DABHI V K, PRAJAPATI H B. Clustering using a combination of particle swarm optimization and K-means[J]. Journal of Intelligent Systems, 2017,12(3):457-469.
[15]	李昆仑, 关立伟. 实数编码量子共生演算法及其在云任务调度中的应用[J]. 计算机应用研究, 2019,36(3):786-791.
	LI Kunlun, GUAN Liwei. Real-coded quantum SOS algorithm and its application in cloud task scheduling[J]. Application Research of Computers, 2019,36(3):786-791.
[16]	董晨, 周浩杰, 宫铭举, 等. 基于神经网络的换热站二次回水温度预测方法[J]. 计算机应用与软件, 2020,37(6):83-87.
	DONG Chen, ZHOU Haojie, GONG Mingju, et al. Prediction method of secondary backwater temperature of heat exchange station based on neural network[J]. Computer Applications and Software, 2020,37(6):83-87.
[17]	高明明, 杨磊, 于浩洋, 等. 量子计算在火电机组优化控制中的应用综述[J]. 华电技术, 2020,42(8):90-96.
	GAO Mingming, YANG Lei, YU Haoyang, et al. Review on the application of quantum computing in optimization control on thermal power units[J]. Huadian Technology, 2020,42(8):90-96.
[18]	邓淑敏, 刘金清, 肖金超, 等. 基于量子遗传算法的冷藏集装箱功率平衡调度方法[J]. 计算机系统应用, 2018,27(12):101-108.
	DENG Shumin, LIU Jinqing, XIAO Jinchao, et al. Scheduling algorithm for power balancing in refrigerated containers based on quantum genetic algorithm[J]. Application of Computer System, 2018,27(12):101-108.

算法	最优值	最劣值	平均值
GA	17.650 1	16.839 2	17.461 26
QGA	17.650 1	17.543 6	17.604 64
IQGA	17.650 1	17.650 1	17.650 10

算法	E_max/(mg·m^-3)	E_ave/(mg·m^-3)	运行时间/s
GRNN	5.953 8	2.602 9	12.57
QGA-GRNN	4.325 8	-0.624 7	8.22
IQGA-GRNN	2.336 0	0.069 5	6.88