Coal and gas outburst prediction model based on principal component analysis and improved support vector machine

Abstract

In order to predict the coal outburst risk quickly and accurately, a PCA-FA-SVM based coal and gas outburst risk prediction model was designed. Principal component analysis (PCA) was used to pre-process the original data samples, extract the principal components of the samples, use firefly algorithm (FA) to improve the support vector machine model, and compare and analyze the prediction results of PCA-FA-SVM model with BP model, FA-SVM model, FA-BP model and SVM model. Accuracy rate, recall rate, Macro-F1 and model prediction time were used as evaluation indexes. The results show that: Principal component analysis improves the prediction efficiency and accuracy of FA-SVM model. The accuracy rate of PCA-FA-SVM model predicting coal and gas outburst risk is 0.962, recall rate is 0.955, Macro-F1 is 0.957, and model prediction time is 0.312s. Compared with other models, The comprehensive performance of PCA-FA-SVM model is better.

Keywords

Coal and gas outburst / Risk prediction / Principal component analysis (PCA) / Firefly algorithm (FA) / Support vector machine (SVM)

References

[1] X. Wu, Y. Peng, J. Xu, Experimental study on evolution law for particle breakage during coal and gas outburst, Int J Coal Sci Techn 7 ( 2020) 97-106.

[2] S. Li, M. You, D. Li,Identifying coal mine safety production risk factors by employing text mining and Bayesian network techniques, Process Saf Environ 162 ( 2022) 1067-1081. monitoring, PLoS One 14 (5) ( 2019).

[3] C.L. Zhang, E.Y. Wang, Y.B. Wang, Spatial and temporal distribution of coal and gas outburst accidents in China in recent 20 years and prevention and control suggestions, Coal Geol. Explor. 49 (4) ( 2021) 134-141.

[4] B. Li, K. Wang, J.P. Wei, T. Tian, P. Li, Study on basic characteristics and occurrence rules of coal and gas outburst accidents in China from 2001 to 2012, J. Saf. Environ. 13 (3) ( 2013) 274-278.

[5] J. Mou, H. Liu, Y. Zou, A new method to determine the sensitivity of coal and gas outburst prediction index, Arabian J. Geosci. 13 ( 2020) 1-9.

[6] H. Liu, Y. Dong, F. Wang, Gas outburst prediction model using improved entropy weight grey correlation analysis and IPSO-LSSVM, Math. Probl Eng. 2020 ( 2020)1-10.

[7] A. Wang, D. Song, X. He, Investigation of coal and gas outburst risk by microseismic monitoring, PLoS One 14 (5) ( 2019).

[8] W. Wang, H. Wang, B. Zhang, Coal and gas outburst prediction model based on extension theory and its application, Process Saf Environ 154 ( 2021) 329-337.

[9] B. Li, E. Wang, Z. Shang, Deep learning approach to coal and gas outburst recognition employing modified AE and EMR signal from empirical mode decomposition and time-frequency analysis, J. Nat. Gas Sci. Eng. 90 ( 2021) 103942.

[10] S. Li, H.Y. Hu, Coal and gas outburst risk identification based on KPCA and improved Extreme Learning machine, Appl. Res. Comput. 35 (1) ( 2018) 172-176.

[11] E.Y. Wang, Z.H. Li, X.Q. He, Chen Liang, Electromagnetic radiation warning technology and application of coal and gas outburst, Int J Coal Sci Techn 42 (6) ( 2014) 53-57þ91.

[12] H. Ma, A. Ren, K. Gao, Gas emission prediction model based on random search optimization XGBoost, Journal of Safety Science and Technology 18 (5) ( 2022) 129-134.

[13] H.W. Jin, Z.Y. Yang, G. Xu, Risk assessment of coal and gas outburst based on improved AHP-GRA evaluation model, Mining Safety & Environmental Protection 47 ( 5) ( 2020) 113-118þ126.

[14] J. Wang, S. Lu, S.H. Wang, et al., A review on extreme learning machine, Multimed.Tool. Appl. 81 (29) ( 2022) 41611-41660.

[15] J. Wu, Y.G. Wang, K. Burrage, An improved firefly algorithm for global continuous optimization problems, Expert Syst. Appl. 149 ( 2020) 113340.

[16] L. Shi, X. Ding, M. Li, Research on the capability maturity evaluation of intelligent manufacturing based on firefly algorithm, sparrow search algorithm, and BP neural network, Complexity 2021 ( 2021) 1-26.

[17] J. Zhu, L. Yang, X. Wang, Risk assessment of deep coal and gas outbursts based on IQPSO-SVM, Int. J. Environ. Res. Publ. Health 19 (19) ( 2022) 12869.

[18] S.S. Zhou, Research on compound fault diagnosis method of rotor-rolling bearing in rotating machinery, China University of Mining and Technology, 2017.

[19] T. Liu, B. Lin, X. Fu, Mechanical criterion for coal and gas outburst: a perspective from multiphysics coupling, Int J Coal Sci Techn 8 ( 2021) 1423-1435.

[20] C.J. Fan, L. Yang, H. Sun, M.K. Luo, L.J. Zhou, Z.H. Yang, S. Li, Recent advances and perspectives of CO2-enhanced coalbed methane experimental, Modeling, and Technological Development, Energ Fuel ( 2023).

[21] L. Yang, C.J. Fan, H.O. Wen, M.K. Luo, H. Sun, C. Jia, An improved gas-liquid-solid coupling model with plastic failure for hydraulic flushing in gassy coal seam and application in borehole arrangement, Phys. Fluids 35 ( 2023) 036603.

[22] A. Bcw, B. Cxl, X. Ac, Study on factors influencing and the critical value of the drilling cuttings weight: an index for outburst risk prediction - Science Direct, Process Saf Environ 140 ( 2020) 356-366.

[23] C.J. Fan, L.J. Xu, D. Elsworth, M.K. Luo, T. Liu, Sheng Li, L.J. Zhou, W.W. Su, Spatial-temporal evolution and countermeasures for coal and gas outbursts represented as a dynamic system, Rock Mech. Rock Eng. ( 2023).

[24] S. G, S. Liu, Carbonate caprock-brine-carbon dioxide interaction: alteration of hydromechanical properties and implications on carbon dioxide leakage, SPE J. 26 (5) ( 2021) 2780-2792.

[25] H.Z. Wang, Application of improved ant colony clustering algorithm in coal and gas outburst prediction, Taiyuan University of Technology, 2012.