Identification of natural gas components is vital for the natural gas measurement and determination of the gas flow. The accurate evaluation of the natural gas composition is particularly vital for thermal methods of measurement. The thermal measurement principle is the focus of the current research and development trend of natural gas control technology. Therefore, in this study, we propose a method based on principal component analysis. To eliminate the partial correlation error between the samples and retain maximum information, the dimensionality reduction and pre-classification methods are performed on the data obtained by analyzing the physical parameters of the target natural gas. To reduce the input into the network and ensure recognition efficiency, the new samples are used as the input for the support vector machine. The method can be applied for providing an accurate classification of the existing types of natural gas and obtaining reliable data for thermal metering methods.
Similar content being viewed by others
References
W. X. Leng, H. L. Zhan, L. N. Ge, W. Wang, Y. Ma, K. Zhao, S. Y. Li, and L. Z. Xiao, “Rapidly determinating the principal components of natural gas distilled from shale with terahertz spectroscopy,” Fuel, 159, 84–88 (2015).
D. Ha, U. Ahmed, H. Pyun, C. J. Lee, K. H. Baek, and C. Han, “Multi-mode operation of principal component analysis with k-nearest neighbor algorithm to monitor compressors for liquefied natural gas mixed refrigerant processes,” Comput. Chem. Eng., 106, 96–105 (2017).
M. Hassan, A. Bermak, and R. Bayesian, “Inference of gas identification in electronic nose applications by using random matrix theory,” IEEE Sens. J., 16, 2036–2045 (2016).
Y. Zhang, Y. Zhai, T. Sun, and Z. Cao, “Practical application of a combination of principal component analysis and cluster analysis to evaluate the parameters of layered heterogeneous formations in Dagang oil field,” Chem. Technol. Fuels Oils, 50(6), 525–532 (2015).
M. A. Akbar, A. A. S. Ali, A. Amira, F. Bensaali, M. Benammar, M. Hassan, and A. Bermak, “An empirical study for PCA and LDA based feature reduction for gas identification,” IEEE Sens. J., 16(14), 5734–5746 (2016).
B. Kamiński, M. Jakubczyk, and P. Szufel, “A framework for sensitivity analysis of decision trees,” Cent. Eur. J. Oper. Res., 26(4), 135–159 (2018).
S. B. Kotsiantis, “Decision trees: a recent overview,” Artif. Intell. Rev., 39, 261–683 (2013).
T. Gao, S. Yin, J. Qiu, H. Gao, and O. Kaynak, “A partial least squares aided intelligent model predictive control approach,” IEEE Trans. Syst. Man Cybern., 48(11), 2013–2021 (2018).
T. Mehmood and B. Ahmed, “The diversity in the applications of partial least squares: an overview,” J. Chemomet., 30(1), 4–17 (2016).
M. Ghavipour, M. Ghavipour, M. Chitsazan, S. H. Najibi, and S. S. Ghidary, “Experimental study of natural gas hydrates and a novel use of neural network to predict hydrate formation conditions,” Chem. Eng. Res. Des., 91(2), 264–273 (2013).
J. Junghwan and K. Jinsoo, “Forecasting natural gas prices using wavelets, time series, and artificial neural networks,” PloS One, 10(11), 1–23 (2015).
M. Mesbah, E. Soroush, and M. Rezakazemi, “Development of a least squares support vector machine model for prediction of natural gas hydrate formation temperature,” Chin. J. Chem. Eng., 25(9), 1238–1248 (2017).
S. Esfahani, S. Baselizadeh, and A. Hemmati-Sarapardeh, “On determination of natural gas density: least square support vector machine modeling approach,” J. Nat. Gas Sci. Eng., 22, 348–358 (2015).
R. S. Lakshmi, A. Sivakumar, G. Rajaram, V. Swaminathan, and K. Kannan, “A novel hypergraph-based feature extraction technique for boiler flue gas components classification using PNN - a computational model for boiler flue gas analysis,” J. Ind. Inform. Integr., 9, 35–44 (2018).
S. Ma, H. Zhang, and G. Yang, “Target threat level assessment based on cloud model under fuzzy and uncertain conditions in air combat simulation,” Aerospace Sci. Technol., 67, 49–53 (2017).
H. Zhang, X. Luo, J. Bi, G. He, and Z. Li, “Multi-component fractal representation of multi-scale structure of natural gas hydrate-bearing sediments,” J. Nat. Gas Sci. Eng., 60, 144–152 (2018).
L. Khoshnevisan, F. Hourfar, F. Alhameli, and A. Elkamel, “Combining design of experiments, machine learning, and principal component analysis for predicting energy consumption and product quality of a natural gas processing plant,” Int. J. Energ. Res., 45, 1–14 (2020).
L. J. Cao, K. S. Chua, W. K. Chong, H. P. Leea, and Q. M. Gu, “A comparison of PCA, KPCA, and ICA for dimensionality reduction in support vector machine,” Neurocomput., 55(1-2), 321–336 (2003).
A. Khamparia and B. Pandey, “SVM and PCA based learning feature classification approaches for E-learning system,” Int. J. Web Based Learn. Teach. Technol., 13(2), 32–45 (2018).
A. Bouzalmat, J. Kharroubi, and A. Zarghili, “Comparative study of PCA, ICA, LDA using SVM classifier,” J. Emerg. Technol. Web Intell., 6(1), 64–68 (2014).
J. A. K. Suykens, T. Van Gestel, J. Vandewalle, and B. D. Moor, “A support vector machine formulation to PCA analysis and its kernel version,” IEEE Trans. Neural Netw., 14(2), 447–450 (2003).
P. Gaspar, J. Carbonell, and J. L. Oliveira, “On the parameter optimization of support vector machines for binary classification,” J. Integr. Bioinform., 9(3), 201 (2012).
M. Chu, X. Liu, R. Gong, and L. Liu, “Multi-class classification method using twin support vector machines with multiinformation for steel surface defects,” Chemometr. Intell. Lab. Syst., 176, 108–118 (2018).
J. Lever, M. Krzywinski, and N. Altman, “Principal component analysis,” Nat. Methods, 14(7), 641–642 (2017).
A. E. Curtis, T. A. Smith, B. A. Ziganshin, and J. A. Elefteriades, “The mystery of the Z-score,” Aorta, 4(4), 124–130 (2016).
I. T. Jolliffe and J. Cadima, “Principal component analysis: a review and recent developments,” Philos. Trans. R. Soc. A, 374, 1–6 (2016).
P. Sarothi Roy, C. Ryu, S. K. Dong, and C. S. Park, “Development of a natural gas Methane Number prediction model,” Fuel, 246, 204–211 (2019).
J. Shlens, “A tutorial on principal component analysis,” Int. J. Rem. Sens., 51(2), 1–12 (2014).
A. Tharwat, “Principal component analysis (PCA): an overview,” Int. J. Appl. Pattern Recogn., 3(3), 197–240 (2016).
M. F. Zhang, Z. S. Ge, T. J. Liu, X. H. Wu, and T. H. Qu, “Modeling of individual HRTFs based on spatial principal component analysis,” IEEE/ACM Trans. Aud. Speech Lang. Proc., 28(1), 1–3 (2020).
L. F. Cai, N. F. Thornhill, S. Kuenzel, and B. C. Pal, “Wide-area monitoring of power systems using principal component analysis and k-nearest neighbor analysis,” IEEE Trans. Power Syst., 33(5), 4913–4923 (2018).
S. Xiao, Z. Lu, and L. Xu, “Multivariate sensitivity analysis based on the direction of eigenspace through principal component analysis,” Reliab. Eng. Syst. Saf., 165(9), 1–10 (2017).
B. M. Sherin and M. H. Supriya, “Selection and parameter optimization of SVM kernel function for underwater target classification,” IEEE Underwater Technol. (UT), 5, 1–5 (2015).
M. Javid and J. Hamidzadeh, “An active multi-class classification using privileged information and belief function,” Int. J. Mach. Learn. Cybern., 11(3), 511–524 (2020).
L. Demidova, E. Nikulchev, and Y. Sokolova, “The SVM classifier based on the modified particle swarm optimization,” Int. J. Adv. Comput. Sci. Appl., 7(2), 16–24 (2016).
X. Zhou, P. Jiang, and X. Wang, “Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function,” J. Intell. Manuf., 29, 51–67 (2018).
B. S. Ahmed, D. Rabah, and A. Aissa, “Performance of different kernel functions for LS-SVM-Grey Wolf Optimiser to estimate flashover voltage of polluted insulators,” IET Sci. Meas. Technol., 12(6), 739–745 (2018).
Acknowledgments
This research work was financially supported by the Chongqing Research Program of Basic Research and Frontier Technology (cstc2018jcyjAX0519), Artificial Intelligence Key Laboratory of Sichuan Province (2020RYY01), and Sichuan Provincial Key Lab of Process Equipment and Control (GK201801).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated from Khimiya i Tekhnologiya Topliv i Masel, No. 4, pp. 109–115, July–August, 2021.
Rights and permissions
About this article
Cite this article
Huang, B., Peng, T., Xia, C. et al. Identification of Natural Gas Components Using the Support Vector Machine Model. Chem Technol Fuels Oils 57, 713–723 (2021). https://doi.org/10.1007/s10553-021-01297-w
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10553-021-01297-w