Education, Science, Technology, Innovation and Life
Open Access
Sign In

Study on prediction method of coal seam gas content based on principal component multiple regression

Download as PDF

DOI: 10.23977/ijogse.2020.020101 | Downloads: 29 | Views: 3326

Author(s)

Jufeng Zhang 1,2, Yadong Xie 3, Fengfeng Yang 1, Guanglei Liu 4, Jianjiang Zhang 3, Zaiquan Miao 3, Deqi Ma 1

Affiliation(s)

1 School of Energy Engineering, Longdong University, Qingyang 745000, China
2 School of Resource & Environment and Safety Engineering, Hunan University of Science and Technology, Xiangtan 411201, China
3 Weijiadi coal mine of Jingyuan Coal Power Co., Ltd., Baiyin 730943, China
4 College of physics and Engineering Technology, Xingyi Normal University for Nationality, Xingyi Guizhou, 562400, China

Corresponding Author

Jufeng Zhang

ABSTRACT

The gas content of coal seam is the basis of gas disaster control in coal mine. The accurate prediction of gas content of coal seam is directly related to the effect of gas precise control in coal mine. Weijiadi coal mine is a high gas mine in Gansu Province, the gas content of NO.1 coal seam is related to five factors, including burial depth, elevation of coal seam floor, vertical depth, thickness of coal seam and total thickness of coal seam. In order to avoid the problem that only one factor is taken into account in the statistical analysis and study of coal seam gas occurrence law and the one-dimensional linear model is not accurate in prediction, this paper determines the gas content of NO.1 coal seam through principal component analysis, the thickness and buried depth of coal seam are the main control factors of gas content in coal seam. The predicted value of gas content in coal seam is obtained by multiple linear regression analysis, and compared with the measured value, the predicted value is basically consistent with the measured value, which is of great significance for the prevention and control of gas disaster in coal mine.

KEYWORDS

principal component analysis, gas occurrence, geological factors, multiple linear regression, gas content

CITE THIS PAPER

Jufeng Zhang, Yadong Xie, Fengfeng Yang, Guanglei Liu, Jianjiang Zhang, Zaiquan Miao, Deqi Ma. Study on prediction method of coal seam gas content based on principal component multiple regression. International Journal of Oil and Gas Science and Engineering (2020) Vol. 2: 1-7. DOI: http://dx.doi.org/10.23977/ijogse.2020.020101.

REFERENCES

[1] LU Ping, WANG Zhenping, XIAO Junfeng. Analysis on gas emission characteristics and influence factors at a fully mechanized heading face within high gas coal-seam [J]. Journal of Liaoning Technical University(Natural Science),2012, 31(5) :590-594.
[2] Fu Hua, Xie Sen, Xu Yaosong, et al. Gas emission dynamic prediction model of coal mine based on ACC-ENN algorithm[J]. Journal of China Coal Society, 2014, 39(7) :1296-1301.
[3] ZHANG Ju-feng, YU Lan, YANG Ri-li,et al. Integration Technology of Gas Drainage and Water Injection and Dust Prevention in High Gas Coal Seam[J]. Coal Technology, 2018, 37(04) : 159-160.
[4] ZHANG Jufeng, MA Zhipeng, YANG Fengfeng, et al. Study on Numerical Simulation of Gas Distribution in Goaf of Low Permeability and Extra Thick Coal Seam[J]. Journal of Longdong University, 2019,30(05):35-39.
[5]LI zhen-Xing, WANG Xiao-yan. Gas emission prediction of coal mining face based on BP neurral network[J]. Coal Engineering, 2016, 48(3) : 98-102. 
[6] SHI Shi-liang LI Run-qiu LUO Wen-ke. Method for predicting coal mine gas emission based on EMD-PSO-SVM and its application[J]. China Safety Science Journal, 2014, 24(7) : 43-49.
[7] WANG Xiao-lu, LIU Jian, LU Jian-jun. Gas emission quantity forecasting based on virtual state variables and Kalman filter[J]. Journal of China Coal Society, 2011, 36(1) :80-85.
[8] FU Hua,YU Xiang,LU Wanjie. Prediction of Gas Emission Based on Hybrid Algorithm of Ant  Colony Particle Swarm Optimization and LS-SVM [J]. CHINESE JOURNAL OF SENSORS AND ACTUATORS, 2016, 29(3) : 373-377.
[9] FU Hua,WANG Xirui,YANG Benchen, et al. The Prediction of Mine-Gas Emission Based on MPSO-CWLS-SVM[J]. CHINESE JOURNAL OF SENSORS AND ACTUATRS, 2014, 27(11) : 1568-1572.
[10] LV Fu, LIANG Bing, SUN Weiji, et al. Gas emission quantity prediction of working face based on principal component regression analysis method[J]. Journal of China Coal Society, 2012, 31(7) : 113-116.
[11] CUI Jian-bin, ZHANG Jufeng, YU Lan, et al. Study on multi factor regression prediction of influencing gas content in coal seam [J].Coal,2016,25(09):7-9+17+77.

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.