CLC number: TK3
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2017-08-16
Cited: 0
Clicked: 5248
Hao Zhou, Yuan Li, Qi Tang, Gang Lu, Yong Yan. Combining flame monitoring techniques and support vector machine for the online identification of coal blends[J]. Journal of Zhejiang University Science A, 2017, 18(9): 677-689.
@article{title="Combining flame monitoring techniques and support vector machine for the online identification of coal blends",
author="Hao Zhou, Yuan Li, Qi Tang, Gang Lu, Yong Yan",
journal="Journal of Zhejiang University Science A",
volume="18",
number="9",
pages="677-689",
year="2017",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A1600454"
}
%0 Journal Article
%T Combining flame monitoring techniques and support vector machine for the online identification of coal blends
%A Hao Zhou
%A Yuan Li
%A Qi Tang
%A Gang Lu
%A Yong Yan
%J Journal of Zhejiang University SCIENCE A
%V 18
%N 9
%P 677-689
%@ 1673-565X
%D 2017
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A1600454
TY - JOUR
T1 - Combining flame monitoring techniques and support vector machine for the online identification of coal blends
A1 - Hao Zhou
A1 - Yuan Li
A1 - Qi Tang
A1 - Gang Lu
A1 - Yong Yan
J0 - Journal of Zhejiang University Science A
VL - 18
IS - 9
SP - 677
EP - 689
%@ 1673-565X
Y1 - 2017
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A1600454
Abstract: The combustion behavior of two single coals and three coal blends in a 300 kW coal-fired furnace under variable operating conditions was monitored by a flame monitoring system based on image processing and spectral analysis. A similarity coefficient was defined to analyze the similarity of combustion behavior between two different coal types. A total of 20 flame features, extracted by the flame monitoring system, were ranked by weights of their importance estimated using ReliefF, a feature selection algorithm. The mean of the infrared signal was found to have by far the highest importance weight among the flame features. support vector machine (SVM) was used to identify the coal types. The number of flame features used to build the SVM model was reduced from 20 to 12 by combining the methods of ReliefF and SVM, and computational precision was guaranteed simultaneously. A threshold was found for the relationship between the error rate and similarity coefficient, which were positively correlated. The success rate decreased with increasing similarity coefficient. The results obtained demonstrate that the system can achieve the online identification of coal blends in industry.
The paper is a very good paper indicating reliable methodologies for identification of coal blends. The paper describes the application of two algorithms (SVM and ReliefF) for the processing of images and radiation signals captured from coal flames, with the objective of identifying the coal blend used in different tests. The paper is, in general, well written and the results are good in terms of success rate in the identifications
[1]Ballester, J., García-Armingol, T., 2010. Diagnostic techniques for the monitoring and control of practical flames. Progress in Energy and Combustion Science, 36(4):375-411.
[2]Biswas, S., Choudhury, N., Sarkar, P., et al., 2006. Studies on the combustion behaviour of blends of Indian coals by TGA and drop tube furnace. Fuel Processing Technology, 87(3):191-199.
[3]Chang, C.C., Lin, C.J., 2011. LibSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3):27.
[4]Chi, T., Zhang, H., Yan, Y., et al., 2010. Investigations into the ignition behaviors of pulverized coals and coal blends in a drop tube furnace using flame monitoring techniques. Fuel, 89(3):743-751.
[5]Cloke, M., Lester, E., Thompson, A.W., 2002. Combustion characteristics of coals using a drop-tube furnace. Fuel, 81(6):727-735.
[6]Cortes, C., Vapnik, V., 1995. Support-vector networks. Machine Learning, 20(3):273-297.
[7]Haas, J., Tamura, M., Weber, R., 2001. Characterisation of coal blends for pulverised fuel combustion. Fuel, 80(9):1317-1323.
[8]Hsu, C.W., Lin, C.J., 2002. A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks, 13(2):415-425.
[9]Huang, B.Y., Luo, Z.X., Zhou, H.C., 2010. Optimization of combustion based on introducing radiant energy signal in pulverized coal-fired boiler. Fuel Processing Technology, 91(6):660-668.
[10]Huang, H.W., Zhang, Y., 2008. Flame colour characterization in the visible and infrared spectrum using a digital camera and image processing. Measurement Science and Technology, 19(8):085406.
[11]Huang, Y., Yan, Y., 2000. Transient two-dimensional temperature measurement of open flames by dual-spectral image analysis. Transactions of the Institute of Measurement and Control, 22(5):371-384.
[12]Huang, Y., Yan, Y., Riley, G., 2000. Vision-based measurement of temperature distribution in a 500-kW model furnace using the two-colour method. Measurement, 28(3):175-183.
[13]Jiang, Z.W., Luo, Z.X., Zhou, H.C., 2009. A simple measurement method of temperature and emissivity of coal-fired flames from visible radiation image and its application in a CFB boiler furnace. Fuel, 88(6):980-987.
[14]Kira, K., Rendell, L.A., 1992. A practical approach to feature selection. Proceedings of the 9th International Workshop on Machine Learning, p.249-256.
[15]Kononenko, I., Simec, E., Robniksikonja, M., 1997. Overcoming the myopia of inductive learning algorithms with ReliefF. Applied Intelligence, 7(1):39-55.
[16]Leslie, C., Eskin, E., Noble, W.S., 2002. The spectrum kernel: a string kernel for SVM protein classification. Pacific Symposium on Biocomputing, p.564-575.
[17]Li, X.L., Wu, M.J., Lu, G., et al., 2015. On-line identification of biomass fuels based on flame radical imaging and application of radical basis function neural network techniques. IET Renewable Power Generation, 9(4):323-330.
[18]Lu, G., Yan, Y., Colechin, M., et al., 2006. Monitoring of oscillatory characteristics of pulverized coal flames through image processing and spectral analysis. IEEE Transactions on Instrumentation and Measurement, 55(1):226-231.
[19]Molcan, P., Lu, G., Bris, T.L., et al., 2009. Characterisation of biomass and coal co-firing on a 3 MWth combustion test facility using flame imaging and gas/ash sampling techniques. Fuel, 88(12):2328-2334.
[20]Moon, C., Sung, Y., Ahn, S., et al., 2013. Thermochemical and combustion behaviors of coals of different ranks and their blends for pulverized-coal combustion. Applied Thermal Engineering, 54(1):111-119.
[21]Osorio, E., Ghiggi, M.L.F., Vilela, A.C.F., et al., 2008. Non-isothermal combustion behaviour of coal blends in a thermobalance as seen by optical microscopy. Thermochimica Acta, 475(1-2):1-7.
[22]Peralta, D., Paterson, N.P., Dugwell, D.R., et al., 2001. Coal blend performance during pulverised-fuel combustion: estimation of relative reactivities by a bomb-calorimeter test. Fuel, 80(11):1623-1634.
[23]Piramuthu, S., 2003. On learning to predict web traffic. Decision Support Systems, 35(2):213-229.
[24]Qiu, T., Yan, Y., Lu, G., 2012. An autoadaptive edge-detection algorithm for flame and fire image processing. IEEE Transactions on Instrumentation and Measurement, 61(5):1486-1493.
[25]Sarkar, P., Mukherjee, A., Sahu, S.G., et al., 2013. Evaluation of combustion characteristics in thermogravimetric analyzer and drop tube furnace for Indian coal blends. Applied Thermal Engineering, 60(1-2):145-151.
[26]Sun, D., Lu, G., Zhou, H., et al., 2011. Flame stability monitoring and characterization through digital imaging and spectral analysis. Measurement Science and Technology, 22(11):114007.
[27]Tan, C., Xu, L.J., Li, X.M., et al., 2012. Independent component analysis-based fuel type identification for coal-fired power plants. Combustion Science and Technology, 184(3):277-292.
[28]Wang, F., Wang, X., Ma, Z., et al., 2002. The research on the estimation for the NOx emissive concentration of the pulverized coal boiler by the flame image processing technique. Fuel, 81(16):2113-2120.
[29]Xu, L.J., Yan, Y., Cornwell, S., et al., 2005. Online fuel tracking by combining principal component analysis and neural network techniques. IEEE Transactions on Instrumentation and Measurement, 54(4):1640-1645.
[30]Zhou, H., Tang, Q., Yang, L.B., et al., 2014. Support vector machine based online coal identification through advanced flame monitoring. Fuel, 117:944-951.
[31]Zhou, H., Li, L.T., Zhang, H.L., et al., 2015. Research on the slagging characteristics of blended coals in a pilot-scale furnace. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 16(3):204-216.
Open peer comments: Debate/Discuss/Question/Opinion
<1>