|Generate QR code
Open Access
Subscription Access
Intelligent Proximate Analysis of Coal Based on NearInfrared Spectroscopy
Abstract
The proximate analysis of coal, which aims to estimate the moisture, volatile matter, and caloric value, is of great importance for coal processing and evaluation. However, traditional methods for proximate analysis in the laboratory are not only time-consuming and labor-intensive but also expensive. The near-infrared spectroscopy (NIRS) technique provides a rapid and nondestructive method for coal proximate analysis. We exploit two regression methods, random forest (RF) and extreme learning machine (ELM), to model the relationships among spectral data and proximate analysis parameters. In addition, given the poor stability and robustness caused by the random selection of parameters in ELM, we employ the particle swarm optimization algorithm (PSO) to optimize the structure of ELM (PSO-ELM). A total of 384 coal samples from Inner Mongolia are collected for model training and validation. The experimental results show that the proposed PSO-ELM algorithm achieves the best performance in terms of accuracy and efficiency, which indicates that NIRS combined with PSO-ELM has significant potential for accurate and rapid proximate analysis.
About the Authors
W. Liu
School of Information and Control Engineering at China University of Mining and Technology
China
China
Xuzhou.
B. Peng
School of Information and Control Engineering at China University of Mining and Technology
China
China
Xuzhou.
X. Liu
School of Information and Control Engineering at China University of Mining and Technology
China
China
Xuzhou.
F. Ren
School of Information and Control Engineering at China University of Mining and Technology
China
China
Xuzhou.
L. Zhang
School of Law at Tsinghua University
China
China
Beijing.
References
1. Y. Wolde-Rufael, Appl. Energ., 87, 160-167 (2010).
2. L. Perez-Lombard, J. Ortiz, C. Pout, Energ. Buildings, 40, 394-398 (2008).
3. M. M. Alam, M. W. Murad, A. H. M. Noman, I. Ozturk, Ecol. Indic., 70, 466-479 (2016).
4. Y. Jafari, J. Othman, A. H. S. M. Nor, J. Policy Model., 34, 879-889 (2012).
5. J. I. Joubert, C. T. Grein, D. Bienstock, Fuel, 52, 181-185 (1973).
6. M. Svabova, Z. Weishauptova, O. Pribyl, Fuel, 92, 187-196 (2012).
7. U. Lorenz, Z. Grudzinski, Appl. Energ., 74, 271-279 (2003).
8. Y. Hu, L. Zou, X. Huang, X. Lu, Sci. Rep. Uk, 7 (2017).
9. Y. Hongfu, C. Xiaoli, L. Haoran, X. Yupeng, Fuel, 85, 1720-1728 (2006).
10. J. P. Mathews, V. Krishnamoorthy, E. Louw, A. H. N. Tchapda, F. Castro-Marcano, V. Karri, D. A. Alexis, G. D. Mitchell, Fuel Process. Technol., 121, 104-113 (2014).
11. Y. Wang, M. Yang, G. Wei, R. Hu, Z. Luo, G. Li, Sens. Actuat. B: Chem., 193, 723-729 (2014).
12. L. Breiman, Mach. Learn., 45, 5-32 (2001).
13. P. Probst, A. Boulesteix, B. Bischl, J. Mach. Learn. Res., 20 (2019).
14. L. Zou, Q. Huang, A. Li, M. Wang, China Life Sci., 55, 6i8-625 (2012).
15. S. Tamura, M. Tateishi, IEEE Trans. Neural Net., 8, 251-255 (1997).
16. G. B. Huang, IEEE Trans. Neural Net., 14, 274-281 (2003).
17. A. Akusok, K. Bjork, Y. Miche, A. Lendasse, IEEE Access, 3, 1011-1025 (2015).
18. G. Huang, H. Zhou, X. Ding, R. Zhang, IEEE Trans. Syst. Man Cybern. B: Cybern., 42, 513-529 (2012).
19. J. Tang, C. Deng, G. Huang, IEEE T. Neur. Net. Learn., 27, 809-821 (2016).
20. G. Huang, Q. Zhu, C. Siew, Neurocomputing, 70, 489-501 (2006).
21. Lei M, Rao Z, Li M, Yu X, Zou L, Appl. Sci., 9, 1111 (2019).
22. P. L. Bartlett, IEEE T. Inform. Theory, 44, 525-536 (1998).
23. G. Huang, Q. Zhu, C. Siew, Neurocomputing, 70, 489-501 (2006).
24. G. B. Huang, Q. Y. Zhu, C. K. Siew, Neural Networks, 2, 985-990(2004).
25. P. Lancaster, M. Tismenetsky, The Theory of Matrices with Application, Elsevier (1985).
Review
For citations:
Liu W., Peng B., Liu X., Ren F., Zhang L. Intelligent Proximate Analysis of Coal Based on NearInfrared Spectroscopy. Zhurnal Prikladnoii Spektroskopii. 2021;88(3):502(1)-502(8).
Views: 226
Email this article 