Abstract
NOx emission in iron and steel enterprises mainly comes from sintering flue gas. Traditional artificial neural networks cannot meet the requirements of computational accuracy and convergence speed. In order to reduce and predict NOx emission, back propagation neural network model and radial basis function neural network model were established to predict the NOx in sintering flue gas. On this basis, combined with the characteristics of strong adaptive learning ability of back propagation model and rapid convergence of radial basis function model, the method of optimizing model structure and setting up connection layer were used, a new hybrid neural network model was constructed for NOx prediction research, and the prediction results of the three models were compared and analyzed. The results showed that the hybrid neural network based on connection layer structure optimization had the best evaluation indexes among the three models, which root mean square error and mean absolute error reached 11.37 and 7.14 mg/m3, respectively. The maximum and minimum absolute errors reduced to 35.47 and 0.0083 mg/m3, respectively. The hybrid neural network model had better stability of prediction data, higher fitting degree of results and convergence speed was the fastest. Predicting NOx by using mixed model can effectively eliminate the feedback delay caused by NOx and provide guidance for the control of sintering site process.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aalizadeh B (2019) Comparison of neural network and neurofuzzy identification of vehicle handling under uncertainties. Trans Inst Meas Control 41:4230–4239. https://doi.org/10.1177/0142331219854572
Adams D, Oh D, Kim D, Lee C, 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. https://doi.org/10.1016/j.jclepro.2020.122310
Ahn H, Choi S, Cho B (2013) Process simulation of iron ore sintering bed with flue gas recirculation part 1—modelling approach. Ironmak Steelmak 40:120–127. https://doi.org/10.1179/1743281212Y.0000000071
Bai JY, Zhu ZJ, Qi W (2018) Realization of BP neural network modeling based on NOx of CFB boiler in DCS. Iop Conf 121. https://doi.org/10.1088/1755-1315/121/5/052025
Chen Y, Guo Z, Feng G (2011a) NOx reduction by coupling combustion with recycling flue gas in iron ore sintering process. Int J Min Metall Mater 18:390–396. https://doi.org/10.1007/s12613-011-0452-7
Chen YG, Guo ZC, Feng GS (2011b) NOx reduction by coupling combustion with recycling flue gas in iron ore sintering process. Int J Min Metall Mater 18:390–396. https://doi.org/10.1007/s12613-011-0452-7
Chen XW, Chen HQ, Xu H (2020) Vehicle detection based on multifeature extraction and recognition adopting RBF neural network on ADAS System. Complexity. https://doi.org/10.1155/2020/8842297
Fan X, Zhiyun JI, Gan M, Chen X, Yin L, Jiang T (2015) Characteristics of prepared Coke-biochar composite and its influence on reduction of NOx emission in iron ore sintering. ISIJ Int 55:521–527. https://doi.org/10.2355/isijinternational.55.521
Gan M, Fan X, Lv W, Chen X, Ji Z, Jiang T (2016) Fuel pre-granulation for reducing NOx emissions from the iron ore sintering process. Power Technol 301:478–485. https://doi.org/10.1016/j.powtec.2016.05.043
Han JW, Li QX, Wu HR, Zhu HJ, Song YL (2019) Prediction of cooling efficiency of forced-air precooling systems based on optimized differential evolution and improved BP neural network. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2019.105733
Haykin S (2008) Neural networks and learning machines. Pearson Schwz Ag, Zug
Lanzerstorfer C, Xu Q, Neuhold R (2015) Leaching of the residue from the dry off-gas de-dusting and desulfurization process of an iron ore sinter plant. Int J Min Metall Mater 22:116–121. https://doi.org/10.1007/s12613-015-1051-9
Li L, Liu JK (2020) Neural-network-based adaptive fault-tolerant vibration control of single-link flexible manipulator. Trans Inst Meas Control 42:430–438. https://doi.org/10.1177/0142331219874157
Li XG, Wang JF (2018) Traffic detection of transmission of botnet threat using bp neural network. Neural Netw World 28:511–521. https://doi.org/10.14311/NNW.2018.28.028
Liang Z, Nie Z, An A, Gong J, Wang X (2019) A particle shape extraction and evaluation method using a deep convolutional neural network and digital image processing. Powder Technol 353:156–170. https://doi.org/10.1016/j.powtec.2019.05.025
Lin C, Yi Z, Jiang Z (2019) An alumina rotary kiln monitoring system based on flame image processing. Trans Inst Meas Control 41:2764–2771. https://doi.org/10.1177/0142331218810085
Liu R (2015) Experimental study on nitrogen oxide emissions and its factors during iron ore sintering. Zhejiang University, Hangzhou (in Chinese)
Liu SY, Xu LQ, Chen J (2013) Erratum: Water temperature forecasting in sea cucumber aquaculture ponds by rbf neural network model. In: Li D, Chen Y (eds) Computer and computing technologies in agriculture VI. Springer, Berlin Heidelberg
Liu CJ, Ding WF, Li Z (2017a) Prediction of high-speed grinding temperature of titanium matrix composites using bp neural network based on pso algorithm. Int J Adv Manuf Tech 89:2277–2285. https://doi.org/10.1007/s00170-016-9267-z
Liu DH, Liu H, Zhang JL, Liu ZJ, Xue X, Wang GW (2017b) Basic characteristics of Australian iron ore concentrate and its effects on sinter properties during the high-limonite sintering process. Int J Min Met Mater 24:991–998. https://doi.org/10.1007/s12613-017-1487-1
Mo CL, Teo CS, Hamilton I, Morrison J (1997) Admixing hydrocarbonsd in raw mix to reduce NOx emission in iron ore sintering process. ISIJ Int 37:350–357. https://doi.org/10.2355/isijinternational.37.350
Nikezic DP, Loncar BB, Grsic ZJ, Dimovic SD (2014) Mathematical modeling of environmental impacts of a reactor through the air. Nucl Technol Radiat Prot 29(4):268–273. https://doi.org/10.2298/NTRP1404268N
Nikezic DP, Grsic ZJ, Dramlic DM, Dramlic SD, Loncar BB (2016) Modeling air concentration of fly ash in belgrade, emitted from thermal power plants TNTA and TNTB. Process Safe Environ. https://doi.org/10.1016/j.psep.2016.06.009
Oyedepo SO, Fakeye BA, Mabinuori B, Babalola PO, Leramo RO, Kilanko O et al (2020) Thermodynamics analysis and performance optimization of a reheat—regenerative steam turbine power plant with feed water heaters. Fuel. https://doi.org/10.1016/j.fuel.2020.118577
Pei Y, Zhang S, Wu S, Shi J, Yin Y (2018) Sintering surface spraying steam to reduce NOx and dioxin emissions in shougang. Springer, Cham, pp 53–58. ISBN: 978-3-319-72137-8. http://refhub.elsevier.com/S0959-6526(20)32999-1/sref35
Qiao J, Meng X, Li W (2018) An incremental neuronal-activity-based RBF neural network for nonlinear system modeling. Neurocomputing 302:1–11. https://doi.org/10.1016/j.neucom.2018.01.001
Qie JM, Zhang CX, Shangguan FQ, Li XP (2019a) Effect of iron-bearing by-products on the emission of SO2 and NOx in the iron ore sintering process. Trans Indian Inst Metals 73:35–45. https://doi.org/10.1007/s12666-019-01801-1
Qie JM, Zhang CX, Guo YH, Wang HF, Wu SL (2019b) Reducing the sintering flue gas pollutants emissions based on the accumulation heat effect in iron ore sintering process. Trans Indian Inst Metals 72:581–589. https://doi.org/10.1007/s12666-018-1456-z
Shao HJ, Yi ZM, Chen Z et al (2020) Application of artificial neural networks for prediction of sinter quality based on process parameters control. Trans Inst Measur Control 42:422–429. https://doi.org/10.1177/0142331219883501
Shi Z, Li XN, Su Z (2018) Power missing data filling based on improved k-means algorithm and rbf neural network. In: Sun X, Pan Z, Bertino E (eds) Cloud Computing and Security. Springer, Cham, pp 551–562
Shimizu T, Sazawa Y, Adschiri T, Furusawa T (1992) Conversion of char-bound nitrogen to nitric oxide during combustion. Fuel 71:361–365. https://doi.org/10.1016/0016-2361(92)90022-G
Tatar A, Barati A, Najafi A, Mohammadi AH (2019) Radial basis function (RBF) network for modeling gasoline properties. Petrol Sci Technol 37:1306–1313. https://doi.org/10.1080/10916466.2019.1575878
Tuttle JF, Blackburn LD, Powell KM (2020) On-line classification of coal combustion quality using nonlinear SVM for improved neural network NOx emission rate prediction. Comput Chem Eng. https://doi.org/10.1016/j.compchemeng.2020.106990
Wang RB, Xu HY, Li B (2018) Research on method of determining hidden layer nodes in BP neural network. Comput Technol Dev 28:31–35 (in Chinese)
Wang Y, Liu Z, Zhang J, Zhang Y, Cheng Q (2019) Study of stand-support sintering to achieve high oxygen potential in iron ore sintering to enhance productivity and reduce CO content in exhaust gas. J Clean Prod 252:119855. https://doi.org/10.1016/j.jclepro.2019.119855
Wen H, Xie W, Pei J, Guan L (2016) An incremental learning algorithm for the hybrid RBF-BP network classifier. Eurasip J Adv SigNal Process. https://doi.org/10.1186/s13634-016-0357-8
Wu SL, Que ZG, Su B (2017) Research progress of the “in-bed-denox” technology in iron ore sintering. J Eng Stud 9:61–67 (in Chinese)
Yan S, He Y, Tang T, Wang T (2019) Drag coefficient prediction for non-spherical particles in dense gas-solid two-phase flow using artificial neural network. Powder Technol 354:115–124. https://doi.org/10.1016/j.powtec.2019.05.049
Yang GT, Wang YN, Li XL (2020) Prediction of the NOx emissions from thermal power plant using long-short term memory neural network. Energy. https://doi.org/10.1016/j.energy.2019.116597
Yu ZY, Fan XH, Gan M, Chen XL (2017a) Effect of Ca-Fe oxides additives on NOx reduction in iron ore sintering. J Iron Steel Res Int 24:1184–1189. https://doi.org/10.1016/S1006-706X(18)30016-5
Yu Z, Fan X, Gan M, Chen X, Lv W (2017b) NOx reduction in the iron ore sintering process with flue gas recirculation. JOM 69:1570–1574. https://doi.org/10.1007/s11837-017-2268-z
Zhang J, Xie A, Shen F (2007) Multi-objective optimization and analysis model of sintering process based on bp neural network. J Iron Steel Res Int 14:1–5. https://doi.org/10.1016/S1006-706X(07)60018-1
Zhou H, Zhao J, Loo C (2012) Numerical modeling of the iron ore sintering process. ISIJ Int 52:1550–1558. https://doi.org/10.2355/isijinternational.52.1550
Zhou H, Liu Z, Cheng M, Zhou M, Liu R (2015) Influence of coke combustion on NOx emission during iron ore sintering. Energy Fuel 29:974–984. https://doi.org/10.1021/ef502524y
Zhou H, Ming C, Jia-Pei Z, Ming-Xi Z, Zi-Hao L (2018a) Evaluation of the adhering layer ratio of iron ore granules and its influence on combustion-generated NOx emission in iron ore sintering. J Zhejiang Univ Sci A 19:479–490. https://doi.org/10.1631/jzus.A1700193
Zhou H, Pengnan MA, Cheng M, Zhou M, Yawei LI (2018b) Effects of temperature and circulating flue gas components on combustion and NOx emissions characteristics of four types quasi-particles in iron ore sintering process. ISIJ Int 58:1650–1658. https://doi.org/10.2355/isijinternational.ISIJINT-2018-185
Zhou S, Liu N, Shen C, Zhang L, Li J (2019) An adaptive Kalman filtering algorithm based on back-propagation (BP) neural network applied for simultaneously detection of exhaled CO and N2O. Spectrochim Acta A. https://doi.org/10.1016/j.saa.2019.117332
Zhu WW, Chen DB, Du HB, Wang X (2020) Position control for permanent magnet synchronous motor based on neural network and terminal sliding mode control. Trans Inst Meas Control. https://doi.org/10.1177/0142331219893799
Acknowledgements
The authors acknowledge the support of the National Natural Science Foundation of China (No. 11402180) and WUST the State Key Laboratory of Refractories and Metallurgy of China (No. 2016QN20).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Editorial responsibility: J Aravind.
Rights and permissions
About this article
Cite this article
Yi, Z., Qin, J., Deng, Z. et al. Prediction NOx emission from sintering plant with a radial basis function and back propagation hybrid neural network. Int. J. Environ. Sci. Technol. 19, 5049–5058 (2022). https://doi.org/10.1007/s13762-021-03379-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13762-021-03379-y