Abstract
Circulating fluidized bed (CFB) boilers with wet flue gas desulfurization (WFGD) system is a popular technology for SO2 removal in the coal-fired thermal power plant. However, the long response time of continues emission monitoring system (CEMS) and the hardness of continuously monitoring the coal properties leads to the difficulties for controlling WFGD. It is important to build a model that is adaptable to the fluctuation of load and coal properties, which can obtain the SO2 concentration ahead CEMS, without relying on coal properties. In this paper, a prediction model of inlet SO2 concentration of WFGD considering the delay between the features and target based on long-short term memory (LSTM) network with auto regression feature is established. The SO2 concentration can be obtained 90 s earlier than CEMS. The model shows good adaptability to the fluctuation of SO2 concentration and coal properties. The root-mean-squared error (RMSE) and R squared (R2) of the model are 30.11 mg/m3 and 0.986, respectively. Meanwhile, a real-time prediction system is built on the 220 t/h unit. A field test for long-term operation has been conducted. The prediction system is able to continuously and accurately predict the inlet SO2 concentration of the WFGD, which can provide the operators with an accurate reference for the control of WFGD.
Similar content being viewed by others
Data availability
The datasets analyzed during the current study are not publicly available for the sake of safety and privacy of power plant related, but are available from the corresponding author on reasonable request.
Abbreviations
- A :
-
Ash content of the coal, %
- bc :
-
Bias vector of the cell output
- bf :
-
Bias vector of the forget gate
- bi :
-
Bias vector of the input gate
- bo :
-
Bias vector of the output gate
- Ca/S:
-
Moler ratio of Ca and S
- c t :
-
Cell output at moment t
- FBT:
-
Temperature at bottom of furnace, °C
- FMT:
-
Temperature at middle of furnace, °C
- FNP:
-
Furnace pressure, Pa
- FOT:
-
Flue gas temperature, °C
- FTT:
-
Temperature at top of furnace, °C
- f t :
-
Forget gate e at moment t
- h t :
-
Hidden state of the LSTM cell at moment t
- i t :
-
Input gate at moment t
- MSP:
-
Main steam pressure, Pa
- n :
-
Number of sample
- OCF:
-
O2 concentration in the flue gas, %
- o t :
-
Output gate at moment t
- PAF:
-
Primary air flow rate, m3/h
- R 2 :
-
R Squared
- RMSE:
-
Root-mean-squared error
- SAF:
-
Secondary air flow rate, m3/h
- Sash :
-
Weight fractions of sulfur in the ash, %
- SCF:
-
SO2 concentration in the flue gas, mg/m3
- Scoal :
-
Weight fractions of sulfur in the coal, %
- TCF:
-
Total coal feeder rate, t/h
- tanh:
-
Tanh function, \(\mathrm{tan}h\left(x\right)=({e}^{x}-{e}^{-x})/({e}^{x}+{e}^{-x})\)
- W c :
-
Weight of the cell output
- W i :
-
Weight of the input gate
- W o :
-
Weight of the output gate
- W f :
-
Weight of the forget gate
- x t :
-
Input vector at moment t
- \({y}_{i}\) :
-
SO2 concentration measured by CEMS
- \({\widehat{y}}_{i}\) :
-
Predicted SO2 concentration
- \(\overline{y}\) :
-
Average value of measured SO2 concentration
- \({\Delta }_{r}{G}^{o}\) :
-
Standard Gibbs free energy change of reaction, kJ/mol
- \({\eta }_{\mathrm{SR}}\) :
-
Sulfur retention percentage, %
- \(\sigma\) :
-
Sigmoid function, \(\sigma \left(x\right)=1/(1+{e}^{-x})\)
References
Abel DW, Holloway T, Martínez-Santos J, Harkey M, Tao M, Kubes C, Hayes S (2019) Air quality-related health benefits of energy efficiency in the United States. Environ Sci Technol 53:3987–3998
Adams D, Oh DH, Kim DW, Lee CH, Oh M (2020) Prediction of SOx-NOx emission from a coal-fired CFB power plant with machine learning: plant data learned by deep neural network and least square support vector machine. J Clean Prod 270:122310
Ahmed F, Cho HJ, Kim JK, Seong NU, Yeo YK (2015) A real-time model based on least squares support vector machines and output bias update for the prediction of NOx emission from coal-fired power plant. Korean J Chem Eng 32:1029–1036
Al-Malak A, Elshafei M, Habib MA, Al-Zaharnah I (2016) Soft analyzer for monitoring NOx emissions from a gas turbine combustor. J Energ Resour-Asme 138:031101
Basu P (1999) Combustion of coal in circulating fluidized-bed boilers: a review. Chem Eng Sci 54:5547–5557
Basumallik S, Ma R, Eftekharnejad S (2019) Packet-data anomaly detection in PMU-based state estimator using convolutional neural network. Int J Elec Power 107:690–702
BP (2022) BP statistical review of world energy 2022, BP. https://www.bp.com/content/dam/bp/business-sites/en/global/corporate/pdfs/energy-economics/statistical-review/bp-stats-review-2022-full-report.pdf. Accessed 7 Dec 2022
Carletti C, Blasio CD, Mäkilä E, Salonen J, Westerlund T (2015) Optimization of a wet flue gas desulfurization scrubber through mathematical modeling of limestone dissolution experiments. Ind Eng Chem Res 54:9783–9797
Carletti C, De Blasio C, Miceli M, Pirone R, Westerlund T (2017) Ultrasonic enhanced limestone dissolution: experimental and mathematical modeling. Chem Eng Process 118:26–36
Córdoba P (2015) Status of Flue Gas Desulphurisation (FGD) systems from coal-fired power plants: overview of the physic-chemical control processes of wet limestone FGDs. Fuel 144:274–286
Council C.E (2022) Annual report of China power, Council, C.E. https://www.cec.org.cn/upload/zt/2022ndfz/index.html. Accessed 7 Dec 2022
Czakiert T, Muskala W, Jankowska S, Krawczyk G, Borecki P, Jesionowski L, Nowak W (2012) Combustible matter conversion in an oxy-fuel circulating fluidized-bed (CFB) Environment. Energy Fuels 26:5437–5445
Engin B, Atakül H, Ünlü A, Olgun Z (2019) CFB combustion of low-grade lignites: Operating stability and emissions. J Energy Inst 92:542–553
Flagiello D, Erto A, Lancia A, Di Natale F (2018) Experimental and modelling analysis of seawater scrubbers for sulphur dioxide removal from flue-gas. Fuel 214:254–263
Gong Y, Yang Z-G (2018) Corrosion evaluation of one wet desulfurization equipment — flue gas desulfurization unit. Fuel Process Technol 181:279–293
Gu S, Yang Z, Chen Z, You C (2020) Dissolution reactivity and kinetics of low-grade limestone for wet flue gas desulfurization. Ind Eng Chem Res 59:14242–14251
Gu Y, Zhao W, Wu Z (2011) Online adaptive least squares support vector machine and its application in utility boiler combustion optimization systems. J Process Control 21:1040–1048
Gungor A (2009a) Prediction of SO2 and NOx emissions for low-grade Turkish lignites in CFB combustors. Chem Eng J 146:388–400
Gungor A (2009b) Simulation of NOx emission in circulating fluidized beds burning low-grade fuels. Energy Fuels 23:2475–2481
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780
Hong F, Long D, Chen J, Gao M (2020) Modeling for the bed temperature 2D-interval prediction of CFB boilers based on long-short term memory network. Energy 194:116733
Hoteit A, Bouquet E, Schönnenbeck C, Gilot P (2007) Sulfate decomposition from circulating fluidized bed combustors bottom ash. Chem Eng Sci 62:6827–6835
Hrastel I, Gerbec M, Stergaršek A (2007) Technology optimization of wet flue gas desulfurization process. Chem Eng Technol 30:220–233
Hu Y, Naito S, Kobayashi N, Hasatani M (2000) CO2, NOx and SO2 emissions from the combustion of coal with high oxygen concentration gases. Fuel 79:1925–1932
Katalambula H, Bawagan A, Takeda S (2001) Mineral attachment to calcium-based sorbent particles during in situ desulfurization in coal gasification processes. Fuel Process Technol 73:75–93
Ke X, Li D, Li Y, Jiang L, Cai R, Lyu J, Yang H, Zhang M, Jeon C-H (2021) 1-Dimensional modelling of in-situ desulphurization performance of a 550 MWe ultra-supercritical CFB boiler. Fuel 290:120088
Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-normalizing neural networks. Adv Neur In 30. http://papers.nips.cc/paper/6698-self-normalizing-neural-networks
Krzywanski J, Czakiert T, Blaszczuk A, Rajczyk R, Muskala W, Nowak W (2015) A generalized model of SO2 emissions from large- and small-scale CFB boilers by artificial neural network approach: part 1. The mathematical model of SO2 emissions in air-firing, oxygen-enriched and oxycombustion CFB conditions. Fuel Process Technol 137:66–74
Krzywanski J, Nowak W (2016) Artificial intelligence treatment of SO2 emissions from CFBC in air and oxygen-enriched conditions. J Energy Eng 142:04015017
Li JY, Xu QZ, Wu MX, Huang T, Wang YD (2020) Pan-cancer classification based on self-normalizing neural networks and feature selection. Front Bioeng Biotech 8:766
Li S, Li W, Xu M, Wang X, Li H, Lu Q (2015) The experimental study on nitrogen oxides and SO2 emission for oxy-fuel circulation fluidized bed combustion with high oxygen concentration. Fuel 146:81–87
Liang P, Jiang W-M, Zhang Y-Q, Wang X-H, Zhu J-L (2016) Effect of circulating ash on sulfur conversion characteristics in the coal polygeneration process. Fuel Process Technol 150:16–22
Liu P, Yang LK, Sun L (2021) Multi-objective economic model predictive control of wet limestone flue gas desulfurisation system. Process Saf Environ Prot 150:269–280
Lv Y, Liu JZ, Yang TT, Zeng DL (2013) A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler. Energy 55:319–329
National Development and Reform Commission of PRC (2014) MoEPoP, National Energy Administration of PRC. The upgrade and transformation action plan for coal-fired power energy saving and emission reduction (2014–2020). http://www.gov.cn/gongbao/content/2015/content_2818468.htm. Accessed 7 Dec 2022
Perales ALV, Ortiz FJG, Ollero P, Gil FM (2008) Controllability analysis and decentralized control of a wet limestone flue gas desulfurization plant. Ind Eng Chem Res 47:9931–9940
Perales ALV, Ollero P, Ortiz FJG, Gomez-Barea A (2009) Model predictive control of a wet limestone flue gas desulfurization pilot plant. Ind Eng Chem Res 48:5399–5405
Qiao Z, Wang X, Gu H, Tang Y, Si F, Romero CE, Yao X (2019) An investigation on data mining and operating optimization for wet flue gas desulfurization systems. Fuel 258:116178
Regucki P, Krzyżyńska R, Szeliga Z (2022) Mathematical model for a single screw ash cooler of a circulating fluidized bed boiler. Powder Technol 396:50–58
Safdarnejad SM, Tuttle JF, Powell KM (2019) Dynamic modeling and optimization of a coal-fired utility boiler to forecast and minimize NOx and CO emissions simultaneously. Comput Chem Eng 124:62–79
Scheffknecht G, Al-Makhadmeh L, Schnell U, Maier J (2011) Oxy-fuel coal combustion—a review of the current state-of-the-art. Int J Greenhouse Gas Control 5:S16–S35
Seshadri B, Bolan NS, Naidu R, Wang HL, Sajwan K (2013) Clean coal technology combustion products: properties, agricultural and environmental applications, and risk management. Adv Agron 119:309–370
Shen J, Zheng C, Xu L, Zhang Y, Zhang Y, Liu S, Gao X (2019) Atmospheric emission inventory of SO3 from coal-fired power plants in China in the period 2009–2014. Atmos Environ 197:14–21
Sheng C, Xu M, Zhang J, Xu Y (2000) Comparison of sulphur retention by coal ash in different types of combustors. Fuel Process Technol 64:1–11
Shi Y, Zhong W, Chen X, Yu AB, Li J (2019) Combustion optimization of ultra supercritical boiler based on artificial intelligence. Energy 170:804–817
Song C, Li M, Zhang F, He Y-L, Tao W-Q (2015) A data envelopment analysis for energy efficiency of coal-fired power units in China. Energy Convers Manage 102:121–130
Sun W, Zhong W, Yu A, Liu L, Qian Y (2016) Numerical investigation on the flow, combustion, and NOX emission characteristics in a 660 MWe tangential firing ultra-supercritical boiler. Adv Mech Eng 8:1–13
Tan P, Xia J, Zhang C, Fang Q, Chen G (2014) Modeling and optimization of NOX emission in a coal-fired power plant using advanced machine learning methods. Energy Procedia 61:377–380
Tang L, Xue XD, Qu JB, Mi ZF, Bo X, Chang XY, Wang SY, Li SB, Cui WG, Dong GX (2020a) Air pollution emissions from Chinese power plants based on the continuous emission monitoring systems network. Sci Data 7:325
Tang R, Liu Q, Zhong W, Lian G, Yu H (2020b) Experimental study of SO2 emission and sulfur conversion characteristics of pressurized oxy-fuel co-combustion of coal and biomass. Energy Fuels 34:16693–16704
Tuttle JF, Vesel R, Alagarsamy S, Blackburn LD, Powell K (2019) Sustainable NOx emission reduction at a coal-fired power station through the use of online neural network modeling and particle swarm optimization. Control Eng Pract 93:104167
Wang H, Yuan B, Hao R, Zhao Y, Wang X (2019) A critical review on the method of simultaneous removal of multi-air-pollutant in flue gas. Chem Eng J 378:122155
Warych J, Szymanowski M (2001) Model of the wet limestone flue gas desulfurization process for cost optimization. Ind Eng Chem Res 40:2597–2605
Wen J, Yan J, Zhang D, Chi Y, Ni M, Cen K (2006) SO2 emission characteristics and BP neural networks prediction in MSW/coal co-fired fluidized beds. J Therm Sci 15:281–288
Yin G, Li Q, Zhao Z, Li L, Yao L, Weng W, Zheng C, Lu J, Gao X (2022) Dynamic NOx emission prediction based on composite models adapt to different operating conditions of coal-fired utility boilers. Environ Sci Pollut Res Int 29:13541–13554
Yin ZL, Li J, Zhang Y, Ren AF, Von Meneen KM, Huang LY (2017) Functional brain network analysis of schizophrenic patients with positive and negative syndrome based on mutual information of EEG time series. Biomed Signal Process Control 31:331–338
Yu H, Gao M, Zhang H, Chen Y (2021) Dynamic modeling for SO2-NOx emission concentration of circulating fluidized bed units based on quantum genetic algorithm — extreme learning machine. J Clean Prod 324:129170
Zhang XH, Schreifels J (2011) Continuous emission monitoring systems at power plants in China: improving SO2 emission measurement. Energ Policy 39:7432–7438
Zhao LZ, Du YF, Zeng YS, Kang ZZ, Sun BM (2020) Sulfur conversion of mixed coal and gangue during combustion in a CFB boiler. Energies 13:553
Zheng C, Wang Y, Liu Y, Yang Z, Qu R, Ye D, Liang C, Liu S, Gao X (2019) Formation, transformation, measurement, and control of SO3 in coal-fired power plants. Fuel 241:327–346
Zhong Y, Gao X, Huo W, Luo Z-y, Ni M-j, Cen K-f (2008) A model for performance optimization of wet flue gas desulfurization systems of power plants. Fuel Process Technol 89:1025–1032
Zhou W, Zhao C, Duan L, Liu D, Chen X (2011) CFD modeling of oxy-coal combustion in circulating fluidized bed. Int J Greenhouse Gas Control 5:1489–1497
Zou R, Luo G, Fang C, Zhang H, Li Z, Hu H, Li X, Yao H (2020) Modeling study of selenium migration behavior in wet flue gas desulfurization spray towers. Environ Sci Technol 54:16128–16137
Funding
This work is supported by the National Key Research and Development Plan (2022YFC3701500) and the Fundamental Research Funds for the Central Universities (2022ZFJH004).
Author information
Authors and Affiliations
Contributions
Zhongyang Zhao: conceptualization, investigation, methodology, visualization, validation, writing — original draft, writing — review and editing. Qinwu Li: validation, methodology. Yuhao Shao: investigation, methodology. Chang Tan: investigation. Can Zhou: investigation. Haidong Fan: investigation. Lianming Li: validation. Chenghang Zheng: conceptualization, supervision, Writing — review and editing, funding acquisition. Xiang Gao: conceptualization, supervision.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare no competing interests.
Additional information
Responsible Editor: Shimin Liu
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, Z., Li, Q., Shao, Y. et al. Prediction of inlet SO2 concentration of wet flue gas desulfurization (WFGD) by operation parameters of coal-fired boiler. Environ Sci Pollut Res 30, 53089–53102 (2023). https://doi.org/10.1007/s11356-023-25988-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-023-25988-5