Study on Optimization of Prediction Model of Flue Gas Oxygen Content in Thermal Power Plant Based on Least Squares Support Vector Machine

doi:10.12096/j.2096-4528.pgt.21088

Abstract

Abstract:

The oxygen content in flue gas is an important monitoring parameter of boiler operation, and also an important basis that reflects the perfection of combustion equipment and boiler operation. Quickly and accurately measuring the oxygen content in flue gas according to operating conditions has important guiding significance for optimizing boiler combustion process. Based on the operation data of a 1 000 MW ultra-supercritical boiler in a power station, 31 factors affecting flue gas emission were selected, and cross validation (CV), particle swarm optimization (PSO) algorithm, and genetic algorithm (GA) were used to find the optimal parameters of the least squares support vector machine (LSSVM) model, and the prediction model of flue gas oxygen content was established. The research results show that, compared with PSO-LSSVM and CV-LSSVM models, GA-LSSVM prediction model has better prediction ability for flue gas oxygen content, and has the advantages of high prediction accuracy, good generalization ability, and strong robustness. The relative error and mean square error of fitting prediction are 0.54% and 0.23% respectively, and the relative error and mean square error of generalization prediction are 1.66% and 2.13% respectively. It can accurately measure the oxygen content of boiler flue gas in thermal power plants, which lays a foundation for further optimal operation of boiler combustion system.

Key words: thermal power plant, least squares support vector machine (LSSVM), particle swarm optimization (PSO) algorithm, genetic algorithm (GA), cross validation (CV)

CLC Number:

TK 227

Guoqin ZHAO, Maowei LAN, Yang LI, Yuanxiang ZHOU, Zhengwei JIANG, Yunhua GAN. Study on Optimization of Prediction Model of Flue Gas Oxygen Content in Thermal Power Plant Based on Least Squares Support Vector Machine[J]. Power Generation Technology, 2023, 44(4): 534-542.

Figures/Tables 8

References 25

1	LUO J， WU L， WAN W J ．Optimization of the exhaust gas oxygen content for coal-fired power plant boiler[J]．Energy Procedia，2017，105：3262-3268． doi:10.1016/j.egypro.2017.03.730
2	苏涛．燃煤电厂烟气含氧量软测量方法研究[D]．西安：西安科技大学，2020． doi:10.1177/0142331220932390
	SU T ．Study on soft sensor method of oxygen content in flue gas ofcoal-fired power plant[D]．Xi’an：Xi’an University of Science and Technology，2020． doi:10.1177/0142331220932390
3	吴坡，段松涛，张江南，等．数据驱动型实时燃烧优化控制架构及应用[J]．电力工程技术，2021，40(2)：197-204． doi:10.12158/j.2096-3203.2021.02.028
	WU P， DUAN S T， ZHANG J N，et al ．Architecture and application of data-driven on-line combustion optimization control[J]．Electric Power Engineering Technology，2021，40(2)：197-204． doi:10.12158/j.2096-3203.2021.02.028
4	李建强，张莹莹，牛成林．基于PSO-LSSVM模型的火电厂烟气含氧量预测[J]．热能动力工程，2018，33(7)：49-55． doi:10.16146/j.cnki.rndlgc.2018.07.009
	LI J Q， ZHANG Y Y， NIU C L ．Prediction of the oxygen content in flue gas of powerplant based on PSO-LSSVM model[J]．Journal of Engineering for Thermal Energy and Power，2018，33(7)：49-55． doi:10.16146/j.cnki.rndlgc.2018.07.009
5	任怡睿，林济铿，宁剑，等．一种基于占优度和Choquet积分的电力系统故障诊断方法综合评估策略[J]．电力系统保护与控制，2021，49(6)：145-154．
	REN Y R， LIN J K， NING J，et al ．A comprehensive evaluation strategy of a power system fault diagnosis method based on dominance and the Choquet integral[J]．Power System Protection and Control，2021，49(6)：145-154．
6	黄树帮，陈耀，金宇清．碳中和背景下多通道特征组合超短期风电功率预测[J]．发电技术，2021，42(1)：60-68． doi:10.12096/j.2096-4528.pgt.20103
	HUANG S B， CHEN Y， JIN Y Q ．A multi-channel feature combination model for ultra-short-term wind power prediction under carbon neutral background[J]．Power Generation Technology，2021，42(1)：60-68． doi:10.12096/j.2096-4528.pgt.20103
7	苏涛，潘红光，黄向东，等．基于改进PSO-SVM的燃煤电厂烟气含氧量软测量[J]．西安科技大学学报，2020，40(2)：342-348．
	SU T， PAN H G， HUANG X D，et al ．Soft sensor of flue gas oxygen content based on improved PSO-SVM in coal-fired powerplant[J]．Journal of Xi’an University of Science and Technology，2020，40(2)：342-348．
8	县国成，王永攀，高俊，等．基于ELM-SVM模型与电能计量大数据的窃电识别技术研究[J]．智慧电力，2022，50(9)：82-89．
	XIAN G C， WANG Y P， GAO J，et al ．Power theft identification technology based on ELM-SVM model and big data of electric energy measurement[J]．Smart Power，2022，50(9)：82-89．
9	刘敦楠，张悦，彭晓峰，等．计及相似日与气象因素的电动汽车充电负荷聚类预测[J]．电力建设，2021，42(2)：43-49． doi:10.12204/j.issn.1000-7229.2021.02.006
	LIU D N， ZHANG Y， PENG X F，et al ．Clustering prediction of electric vehicle charging load considering similar days and meteorological factors[J]．Electric Power Construction，2021，42(2)：43-49． doi:10.12204/j.issn.1000-7229.2021.02.006
10	李志军，王硕，张家安，等．基于变论域模糊逻辑的互联电力系统负荷频率控制[J]．电力系统保护与控制，2021，49(16)：151-160．
	LI Z J， WANG S， ZHANG J A，et al ．Variable universe fuzzy logic-based load frequency control in an interconnected power system[J]．Power System Protection and Control，2021，49(16)：151-160．
11	徐艳春，阚锐涵，高永康，等．混合动力系统电能质量扰动分析及治理[J]．电力建设，2021，42(4)：17-26． doi:10.12204/j.issn.1000-7229.2021.04.003
	XU Y C， KAN R H， GAO Y K，et al ．Research on power quality improvement of hybrid power system[J]．Electric Power Construction，2021，42(4)：17-26． doi:10.12204/j.issn.1000-7229.2021.04.003
12	王子馨，胡俊杰，刘宝柱．基于长短期记忆网络的电力系统量测缺失数据恢复方法[J]．电力建设，2021，42(5)：1-8． doi:10.12204/j.issn.1000-7229.2021.05.001
	WANG Z X， HU J J， LIU B Z ．Short-term wind power forecasting based on LSTM[J]．Electric Power Construction，2021，42(5)：1-8． doi:10.12204/j.issn.1000-7229.2021.05.001
13	张华赢，吴显，游奕弘．基于循环神经网络的配电网非线性负荷建模[J]．电网与清洁能源，2022，38(2)：53-60． doi:10.3969/j.issn.1674-3814.2022.02.008
	ZHANG H Y， WU X， YOU Y H ．Modeling of nonlinear loads in the distribution network based on recurrent neural network[J]．Power System and Clean Energy，2022，38(2)：53-60． doi:10.3969/j.issn.1674-3814.2022.02.008
14	VAPNIK V N ．Statistical learning theory[M]．New Jersey：Wiley-Inter Science，1998．
15	VAPNIK V N ．The nature of statistical learning theory[M]．New York：Springer Verlag，1999：3-21． doi:10.1007/978-1-4757-3264-1_8
16	TANG Z H， LI Y Y， KUSIAK A ．A deep learning model for measuring oxygen content of boiler flue gas[J]．IEEE Access，2020，8：12268-12278． doi:10.1109/access.2020.2965199
17	PAN H G， SU T， HUANG X D，et al ．LSTM-based soft sensor design for oxygen content of flue gas in coal-fired power plant[J]．Transactions of the Institute of Measurement and Control，2021，43(1)：78-87． doi:10.1177/0142331220932390
18	刘长良，李淑娜．基于LS-SVM和单纯形的烟气含氧量软测量[J]．热能动力工程，2010，25(3)：292-296．
	LIU C L， LI S N ．Soft measurements of flue-gas oxygen content based on LS-SVM and a simplex algorithm[J]．Journal of Engineering for Thermal Energy and Power，2010，25(3)：292-296．
19	周霞，柳善建．基于多目标LSSVM回归的火电厂烟气含氧量软测量[J]．计算机测量与控制，2014，22(10)：3101-3104． doi:10.3969/j.issn.1671-4598.2014.10.006
	ZHOU X， LIU S J ．Soft-sensing method based on multiobjective LSSVM for oxygen content in flue gas of a coal-fired power plant[J]．Computer Measurement & Control，2014，22(10)：3101-3104． doi:10.3969/j.issn.1671-4598.2014.10.006
20	龙文，梁昔明，龙祖强．基于混合PSO优化的LSSVM锅炉烟气含氧量预测控制[J]．中南大学学报(自然科学版)，2012，43(3)：980-985．
	LONG W， LIANG X M， LONG Z Q ．O₂ content in flue gas of boilers predictive control based onhybrid PSO and LSSVM[J]．Journal of Central South University (Science and Technology)，2012，43(3)：980-985．
21	李建强，赵凯，陈星旭，等．600 MW燃煤机组最优氧量与配风方式的联合优化[J]．中国电机工程学报，2017，37(15)：4422-4429．
	LI J Q， ZHAO K， CHEN X X，et al ．Combined optimization of optimal oxygen content and second air distribution in 600 MW coal-fired unit[J]．Proceedings of the CSEE，2017，37(15)：4422-4429．
22	SUYKENS J A K， GESTEL T V， BRABANTER J D，et al ．Least squares support vector machines[M]．Singapore：World Scientific Publishing Company，2002． doi:10.1142/5089
23	SUYKENS J A K， VANDEWALLE J ．Least squares support vector machine classifiers[J]．Neural Processing Letters，1999，9(3)：293-300． doi:10.1023/a:1018628609742
24	KENNEDY J， EBERHART R ．Particle swarm optimization[C]//Proceedings of IEEE Conference on Neural Networks．Perth，Australia：IEEE，1995：1942-1948．
25	SHAPIRO J ．Genetic algorithms in machine learning[M]．Heidelberg：Springer-Verlag，2001：146-168． doi:10.1007/3-540-44673-7_7

序列	负荷/MW	运行氧量/%	热一次风母管压力/kPa	空预器入口风温度加权/℃	总煤量/ (t·h^-1)	A/B侧热二次风流量/ (t·h^-1)	A—F磨煤机进口一次风量/(t·h^-1)	A—F磨煤机动态分离器速度/(r·min^-1)	燃尽风风门开度前(后)墙A/B侧/%	外二次风风门开度1—8/%	排烟含氧量/%
1	560.41	4.63	9.40	24.60	220.15	568.06/ 602.12	26.64/139.88/ 156.23/0.00/ 107.05/159.99	11.68/776.53/ 713.17/28.87/ 575.45/762.13	50.17/99.76 (50.08/99.86)	16.01/50.06/ 99.61/99.69/ 99.54/99.86/ 50.06/15.88	7.26
2	919.49	3.65	9.54	26.20	330.45	868.35/ 935.25	18.59/153.71/ 157.17/139.01/ 164.01/154.43	11.22/776.26/ 647.75/774.17/ 751.13/765.09	100.19/99.83 (99.91/99.90)	15.77/50.04/ 99.60/99.99/ 99.53/99.87/ 50.08/15.90	5.43
3	455.68	6.90	9.58	25.20	169.31	460.71/ 523.45	0.00/136.81/ 140.72/0.00/ 132.52/156.11	11.43/778.16/ 653.86/30.47/ 25.60/766.30	35.37/99.82 (35.30/99.90)	16.02/50.05/ 99.61/99.82/ 99.54/99.84/ 50.08/15.92	9.81
⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞
141	782.72	3.66	9.15	25.80	283.48	687.23/ 750.31	0.00/149.39/ 144.29/125.53/ 156.21/153.13	11.68/775.11/ 651.19/770.95/ 750.74/765.03	51.94/99.82 (52.47/99.90)	16.03/50.06/ 99.59/99.71/ 99.54/99.86/ 50.07/15.90	5.56
142	509.40	4.52	9.18	24.60	188.03	497.61/ 539.36	27.74/139.93/ 162.46/0.00/ 36.20/156.87	11.18/777.50/ 650.44/27.93/ 24.70/764.87	50.31/99.81 (50.16/99.89)	15.90/50.05/ 99.62/99.84/ 99.54/99.86/ 50.07/15.88	7.14
143	765.74	3.29	9.75	25.90	295.35	720.35/ 863.09	0.00/147.25/ 155.16/0.00/ 172.35/168.64	11.18/775.85/ 650.96/29.38/ 760.78/764.13	32.91/99.81 (31.24/99.89)	15.99/50.06/ 99.59/99.81/ 99.53/99.86/ 50.08/15.95	5.57

序列	负荷/MW	运行氧量/%	热一次风母管压力/kPa	空预器入口风温度加权/℃	总煤量/ (t·h^-1)	A/B侧热二次风流量/ (t·h^-1)	A—F磨煤机进口一次风量/(t·h^-1)	A—F磨煤机动态分离器速度/(r·min^-1)	燃尽风风门开度前(后)墙A/B侧/%	外二次风风门开度1—8/%	排烟含氧量/%
1	560.41	4.63	9.40	24.60	220.15	568.06/ 602.12	26.64/139.88/ 156.23/0.00/ 107.05/159.99	11.68/776.53/ 713.17/28.87/ 575.45/762.13	50.17/99.76 (50.08/99.86)	16.01/50.06/ 99.61/99.69/ 99.54/99.86/ 50.06/15.88	7.26
2	919.49	3.65	9.54	26.20	330.45	868.35/ 935.25	18.59/153.71/ 157.17/139.01/ 164.01/154.43	11.22/776.26/ 647.75/774.17/ 751.13/765.09	100.19/99.83 (99.91/99.90)	15.77/50.04/ 99.60/99.99/ 99.53/99.87/ 50.08/15.90	5.43
3	455.68	6.90	9.58	25.20	169.31	460.71/ 523.45	0.00/136.81/ 140.72/0.00/ 132.52/156.11	11.43/778.16/ 653.86/30.47/ 25.60/766.30	35.37/99.82 (35.30/99.90)	16.02/50.05/ 99.61/99.82/ 99.54/99.84/ 50.08/15.92	9.81
⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞	⁞
141	782.72	3.66	9.15	25.80	283.48	687.23/ 750.31	0.00/149.39/ 144.29/125.53/ 156.21/153.13	11.68/775.11/ 651.19/770.95/ 750.74/765.03	51.94/99.82 (52.47/99.90)	16.03/50.06/ 99.59/99.71/ 99.54/99.86/ 50.07/15.90	5.56
142	509.40	4.52	9.18	24.60	188.03	497.61/ 539.36	27.74/139.93/ 162.46/0.00/ 36.20/156.87	11.18/777.50/ 650.44/27.93/ 24.70/764.87	50.31/99.81 (50.16/99.89)	15.90/50.05/ 99.62/99.84/ 99.54/99.86/ 50.07/15.88	7.14
143	765.74	3.29	9.75	25.90	295.35	720.35/ 863.09	0.00/147.25/ 155.16/0.00/ 172.35/168.64	11.18/775.85/ 650.96/29.38/ 760.78/764.13	32.91/99.81 (31.24/99.89)	15.99/50.06/ 99.59/99.81/ 99.53/99.86/ 50.08/15.95	5.57

模型	σ	γ
CV-LSSVM	1.634 3	2.296 80
PSO-LSSVM	99.733 3	66.229 20
GA-LSSVM	100.000 0	80.368 54

模型	σ	γ
CV-LSSVM	1.634 3	2.296 80
PSO-LSSVM	99.733 3	66.229 20
GA-LSSVM	100.000 0	80.368 54

[1]	Anan ZHANG, Qi ZHOU, Qian LI, Ning DING, Chao YANG, Yan MA. Research Status and Prospect of CO₂ Accounting Technology in Thermal Power Plants Under the Goal of Dual Carbon [J]. Power Generation Technology, 2024, 45(1): 51-61.
[2]	Lifeng ZHANG, Jing LI, Zhi WANG. Reconstruction of Temperature Distribution by Acoustic Tomography Based on Principal Component Analysis and Deep Neural Network [J]. Power Generation Technology, 2023, 44(3): 399-406.
[3]	Cunqin RUAN, Zhigang HONG, Peican LAI, Jianhua ZHANG, Xikun LIN, Jiang ZHOU, Qianwei FENG, Yang ZHANG. Research on Performance Prediction of Coal-fired Power Plant Denitrification Device Based on Online Monitoring Data [J]. Power Generation Technology, 2023, 44(1): 100-106.
[4]	Hui ZHANG, Xiufang GU, Yanning CHEN, Zhenpeng LUO, Chen WANG. Benefit Cost Analysis of Thermal Storage Tank in Thermal Power Plant Considering Wind Power Consumption [J]. Power Generation Technology, 2022, 43(4): 664-672.
[5]	Hao SHI, Haiping XIAO, Yanpeng LIU. Prediction and Comparison of Ash Fusion Temperatures Based on BP Neural Network and Least Squares Support Vector Machine [J]. Power Generation Technology, 2022, 43(1): 139-146.
[6]	Dong GUO, Yinjia JIN, Yue ZHU. Design and Construction of Wastewater Zero Liquid Discharge Treatment System for Pilot Experiment in Thermal Power Plant [J]. Power Generation Technology, 2021, 42(3): 357-362.
[7]	Weidong LI,Hongpeng HE. Source-load Cooperative Optimization Dispatch Strategy Considering Wind Power Accommodation [J]. Power Generation Technology, 2020, 41(2): 126-130.
[8]	Jinlong SUN. Optimization Study of Denitrification System for 330 MW Coal-fired Thermal Power Unit [J]. Power Generation Technology, 2019, 40(6): 570-579.
[9]	Fei SUN,Ye LIU,Gaosheng WEI,Wenjiang YOU. Scheme and Economic Analysis of Waste Heat Utilization of Screw Air Compressor in Thermal Power Plant [J]. Power Generation Technology, 2018, 39(3): 240-243.
[10]	Yangjun LI,Zichun HE,Qiang ZHANG,Wei TU. Test and Evaluation of Power Quality in Thermal Power Plant [J]. Power Generation Technology, 2018, 39(2): 135-139.