An Artificial Intelligence Regression Model for Prediction of NOx Emission from Flame Image

Yıl 2022, Cilt: 3 Sayı: 2, 93 - 101, 28.12.2022

Sedat Golgiyaz , Mahmut Daşkın , Cem Onat , Muhammed Fatih Talu

https://doi.org/10.55195/jscai.1213863

Cited By: 5

Öz

In this study, NOx emission has been estimated by processing the flame image of visible wavelength and its experimental verification has been presented. The experimental study has been performed by using a domestic coal boiler with a capacity of 85000 Kcal / h. The real NOx value has been measured from a flue gas analyzer device. The flame image has been taken by CCD camera from the observation hole on the side of the burner. The data set which is related to instantaneous combustion performance and flame images was recorded simultaneously on the same computer with time stamps once a second. The color flame image has been transformed into a gray scale. Features have been extracted from the gray image of flame. The features are extracted by using the cumulative projection vectors of row and column matrices. ANN regression model has been used as the learning model. The relationship between flame image and NOx emission has been obtained with the accuracy of R = 0.9522. Highly accurate measurement results show that the proposed NOx prediction model can be used in combustion monitor and control systems.

Anahtar Kelimeler

Regression model, Emission prediction, Image processing, ANN regression, Combustion control, NOx

Proje Numarası

117M121

Kaynakça

• The U.S. Energy Information Administration (EIA), “International Energy Outlook 2017.” Accessed: Oct. 22, 2018. [Online]. Available: www.eia.gov/ieo.
• J. Diefenderfer, M. assumptions Vipin Arora, and L. E. Singer, International Energy Outlook 2016, vol. 0484, no. May. 2016.
• X. Qiu, L. Duan, Y. Duan, B. Li, D. Lu, and C. Zhao, “Ash deposition during pressurized oxy-fuel combustion of Zhundong coal in a lab-scale fluidized bed,” Fuel Process. Technol., vol. 204, p. 106411, Jul. 2020, doi: 10.1016/j.fuproc.2020.106411.
• R. Weber and M. Mancini, “On scaling and mathematical modelling of large scale industrial flames,” J. Energy Inst., vol. 93, no. 1, pp. 43–51, Feb. 2020, doi: 10.1016/j.joei.2019.04.010.
• W. Wójcik, B. Suleimenov, M. J.-J. of Ecological …, and undefined 2017, “Employing Optical Measurements for Monitoring and Diagnostics of Combustion Process in Industrial Conditions,” yadda.icm.edu.pl, vol. 18, no. 1, pp. 273–283, 2017, doi: 10.12911/22998993/67107.
• C. Onat and M. Daskin, “A basic ANN system for prediction of excess air coefficient on coal burners equipped with a CCD camera,” Math. Stat., vol. 7, no. 1, pp. 1–9, 2019, doi: 10.13189/ms.2019.070101.
• C. Onat, M. Daşkin, S. Toraman, S. Golgiyaz, and M. F. Talu, “Prediction of combustion states from flame image in a domestic coal burner,” Meas. Sci. Technol., vol. 32, no. 7, p. 075403, Jul. 2021, doi: 10.1088/1361-6501/abe446.
• S. Golgiyaz, M. F. Talu, and C. Onat, “Estimation of Excess Air Coefficient for Automated Feed Coal Burners with Image-Based Gauss Model,” in International Artificial Intelligence and Data Processing Symposium (IDAP’16), 2016, pp. 528–531, [Online]. Available: https://www.researchgate.net/publication/333650492.
• C. Onat, “A new concept on PI design for time delay systems: weighted geometrical center,” J. Innov. Comput. Inf. Control, 2013.
• C. Onat, “WGC Based Robust and Gain Scheduling PI Controller Design for Condensing Boilers,” 2014, doi: 10.1155/2014/659051.
• C. Onat, “A new design method for PI–PD control of unstable processes with dead time,” ISA Trans., vol. 84, pp. 69–81, 2019, doi: 10.1016/j.isatra.2018.08.029.
• C. Katzer, K. Babul, M. Klatt, and H. J. Krautz, “Quantitative and qualitative relationship between swirl burner operatingconditions and pulverized coal flame length,” Fuel Process. Technol., vol. 156, pp. 138–155, 2017, doi: 10.1016/j.fuproc.2016.10.013.
• S. Taamallah, N. W. Chakroun, H. Watanabe, S. J. Shanbhogue, and A. F. Ghoniem, “On the characteristic flow and flame times for scaling oxy and air flame stabilization modes in premixed swirl combustion,” Proc. Combust. Inst., vol. 36, no. 3, pp. 3799–3807, 2017, doi: 10.1016/j.proci.2016.07.022.
• J. Li, M. M. Hossain, J. Sun, Y. Liu, … B. Z.-A. T., and undefined 2019, “Simultaneous measurement of flame temperature and absorption coefficient through LMBC-NNLS and plenoptic imaging techniques,” Elsevier.
• T. Lockwood, “Advanced sensors and smart controls for coal-fired power plant controls for coal-fired power plant,” no. June, 2015, [Online]. Available: https://www.usea.org/sites/default/files/media/Advance sensors and smart controal for coal fired power plants - ccc251.pdf.
• J. Ballester and T. García-Armingol, “Diagnostic techniques for the monitoring and control of practical flames,” Prog. Energy Combust. Sci., vol. 36, no. 4, pp. 375–411, 2010, doi: 10.1016/j.pecs.2009.11.005.
• S. Golgiyaz, M. F. Talu, and C. Onat, “Artificial neural network regression model to predict flue gas temperature and emissions with the spectral norm of flame image,” Fuel, vol. 255, p. 115827, Nov. 2019, doi: 10.1016/j.fuel.2019.115827.
• S. Golgiyaz, M. F. Talu, and C. Onat, “Estimation of Flue Gas Temperature by Image Processing and Machine Learning Methods,” Eur. J. Sci. Technol., pp. 283–291, Aug. 2019, doi: 10.31590/ejosat.568348.
• A. González-Cencerrado, B. Peña, and A. Gil, “Coal flame characterization by means of digital image processing in a semi-industrial scale PF swirl burner,” Appl. Energy, vol. 94, pp. 375–384, 2012, doi: 10.1016/j.apenergy.2012.01.059.
• A. González-Cencerrado, A. Gil, and B. Peña, “Characterization of PF flames under different swirl conditions based on visualization systems,” Fuel, vol. 113, pp. 798–809, Nov. 2013, doi: 10.1016/j.fuel.2013.05.077.
• Z. Xiangyu, Z. Shu, Z. Huaichun, Z. Bo, W. Huajian, and X. Hongjie, “Simultaneously reconstruction of inhomogeneous temperature and radiative properties by radiation image processing,” Int. J. Therm. Sci., vol. 107, pp. 121–130, 2016, doi: 10.1016/j.ijthermalsci.2016.04.003.
• Z. Liu, S. Zheng, Z. Luo, and H. Zhou, “A new method for constructing radiative energy signal in a coal-fired boiler,” Appl. Therm. Eng., vol. 101, pp. 446–454, 2016, doi: 10.1016/j.applthermaleng.2016.01.034.
• P. Tóth, A. Garami, and B. Csordás, “Image-based deep neural network prediction of the heat output of a step-grate biomass boiler,” Appl. Energy, vol. 200, pp. 155–169, Aug. 2017, doi: 10.1016/j.apenergy.2017.05.080.
• F. Wang et al., “The research on the estimation for the NOxemissive concentration of the pulverized coal boiler by the flame image processing technique,” Fuel, vol. 81, no. 16, pp. 2113–2120, 2002, doi: 10.1016/S0016-2361(02)00145-X.
• W. B. Baek, S. J. Lee, S. Y. Baeg, and C. H. Cho, “Flame image processing & analysis for optimal coal firing of thermal power plant,” {ISIE 2001 IEEE Int. Symp. Ind. Electron. proceedeing, Vols I-III}, p. {928-931}, 2001, doi: 10.1109/ISIE.2001.931596.
• X. Li, D. Sun, G. Lu, J. Krabicka, and Y. Yan, “Prediction of NOx emissions throughflame radical imaging and neural network based soft computing,” IST 2012 - 2012 IEEE Int. Conf. Imaging Syst. Tech. Proc., vol. 44, no. 0, pp. 502–505, 2012, doi: 10.1109/IST.2012.6295594.
• N. Li, G. Lu, X. Li, and Y. Yan, “Prediction of NOx Emissions from a Biomass Fired Combustion Process Based on Flame Radical Imaging and Deep Learning Techniques,” Combust. Sci. Technol., vol. 188, no. 2, pp. 233–246, 2016, doi: 10.1080/00102202.2015.1102905.
• Q. Tang, H. Zhou, G. Lu, Y. Yan, and Y. Li, “Combining flame monitoring techniques and support vector machine for the online identification of coal blends,” J. Zhejiang Univ. A, pp. 671–689, 2017, doi: 10.1631/jzus.a1600454.
• Z. Xiangyu, L. Xu, Y. yu, Z. Bo, and X. Hongjie, “Temperature measurement of coal fired flame in the cement kiln by raw image processing,” Meas. J. Int. Meas. Confed., 2018, doi: 10.1016/j.measurement.2018.07.063.
• T. Li, C. Zhang, Y. Yuan, Y. Shuai, and H. Tan, “Flame temperature estimation from light field image processing,” Appl. Opt., vol. 57, no. 25, p. 7259, 2018, doi: 10.1364/ao.57.007259.
• B. Huang, Z. Luo, and H. Zhou, “Optimization of combustion based on introducing radiant energy signal in pulverized coal-fired boiler,” Fuel Process. Technol., vol. 91, no. 6, pp. 660–668, Jun. 2010, doi: 10.1016/j.fuproc.2010.01.015.
• Z. Huaichun and C. han, “An Exploratory Investigation of the Computer-Based Control of Utility Coal-Fired Boiler Furnace Combustion,” J. Eng. Therman Enegry Power, 1994.
• D. Castiñeira, B. C. Rawlings, and T. F. Edgar, “Multivariate image analysis (MIA) for industrial flare combustion control,” Ind. Eng. Chem. Res., vol. 51, no. 39, pp. 12642–12652, 2012, doi: 10.1021/ie3003039.
• M. F. Talu, C. Onat, and M. Daskın, “Prediction of Excess Air Factor in Automatic Feed Coal Burners by Processing of Flame Images,” Chinese J. Mech. Eng., vol. 30, no. 3, pp. 722–731, May 2017, doi: 10.1007/s10033-017-0095-3.
• C. Moon, Y. Sung, S. Eom, and G. Choi, “NOx emissions and burnout characteristics of bituminous coal, lignite, and their blends in a pulverized coal-fired furnace,” Exp. Therm. Fluid Sci., vol. 62, no. 1, pp. 99–108, 2015, doi: 10.1016/j.expthermflusci.2014.12.005.
• J. Krabicka, G. Lu, and Y. Yan, “A spectroscopic imaging system for flame radical profiling,” in 2010 IEEE Instrumentation & Measurement Technology Conference Proceedings, 2010, pp. 1387–1391, doi: 10.1109/IMTC.2010.5488056.
• N. Li, G. Lu, X. Li, Y. Y.-I. T. on Instrumentation, and undefined 2015, “Prediction of pollutant emissions of biomass flames through digital imaging, contourlet transform, and support vector regression modeling,” ieeexplore.ieee.org.
• S. Zheng, Z. Luo, Y. Deng, and H. Zhou, “Development of a distributed-parameter model for the evaporation system in a supercritical W-shaped boiler,” Appl. Therm. Eng., vol. 62, no. 1, pp. 123–132, 2014, doi: 10.1016/j.applthermaleng.2013.09.029.
• H. C. Zeng, Combustion and pollution. Wuhan: Publishing Company of Huazhong University of Science and Technology, 1992.
• J. A. Dean, Flame photometry. McGraw-Hill series in advanced chemistry., 1960.