Research on the coal thickness prediction method based on VMD and SVM

Authors

ZENG Aiping, Engineering Laboratory for Deep Mine Rockburst Disaster Assessment, Jinan 250104, China; Geophysical Prospecting and Surveying Team of Shandong Bureau of Coal Geology, Jinan 250104, China
ZHANG Jiawei, School of Resources and Geosciences, China University of Mining and Technology, Xuzhou 221116, ChinaFollow
REN Enming, Engineering Laboratory for Deep Mine Rockburst Disaster Assessment, Jinan 250104, China; Geophysical Prospecting and Surveying Team of Shandong Bureau of Coal Geology, Jinan 250104, China
LIU Tao, Engineering Laboratory for Deep Mine Rockburst Disaster Assessment, Jinan 250104, China; Geophysical Prospecting and Surveying Team of Shandong Bureau of Coal Geology, Jinan 250104, China
JIANG Fei, Engineering Laboratory for Deep Mine Rockburst Disaster Assessment, Jinan 250104, China; Geophysical Prospecting and Surveying Team of Shandong Bureau of Coal Geology, Jinan 250104, China
LIU Xingjin, Engineering Laboratory for Deep Mine Rockburst Disaster Assessment, Jinan 250104, China; Geophysical Prospecting and Surveying Team of Shandong Bureau of Coal Geology, Jinan 250104, China
SU Huairui, Engineering Laboratory for Deep Mine Rockburst Disaster Assessment, Jinan 250104, China; Shandong Coal Field Geological Survey and Research Institute, Jinan 250104, China

Abstract

Changes in coal thickness have an important impact on safe and efficient coal mining. In order to solve the problem of large errors in coal thickness prediction results when the 3D seismic data contains noise, a method in which variable modal decomposition(VMD) and support vector machine(SVM) methods are combined for coal thickness prediction is proposed. Firstly, a coal-thickness wedge model is constructed and seismic forward modeling is performed on it. Based on the condition of thin coal seam thickness, the amplitude attribute and bandwidth attribute have a good positive correlation with the coal thickness, while the instantaneous frequency attribute has a good negative correlation with the coal thickness. With noise applied to forward seismic records, the experimental results show that noise has a greater impact on coal thickness prediction by using seismic attributes. After VMD denoising, based on SVM, the prediction results of actual seismic data are basically consistent with the coal seam information revealed through existing boreholes. The minimum absolute error is only 0.02 m and the maximum absolute error is 0.52 m, showing the feasibility and effectiveness of the coal thickness prediction method. It provides reference for coal thickness inversion in the low SNR area.

Keywords

variable modal decomposition, support vector machine, coal thickness, seismic attribute

DOI

10.3969/j.issn.1001-1986.2021.06.029

Recommended Citation

ZENG Aiping, ZHANG Jiawei, REN Enming, et al. (2021) "Research on the coal thickness prediction method based on VMD and SVM," Coal Geology & Exploration: Vol. 49: Iss. 6, Article 30.
DOI: 10.3969/j.issn.1001-1986.2021.06.029
Available at: https://cge.researchcommons.org/journal/vol49/iss6/30

Reference

[1] ZHANG Mingjian, LI Feng, YANG Liu. Research on the determination of reasonable mining ratio in fully mechanized caving mining with large thickness variation coefficient[J/OL]. Coal Science and Technology, 2020: 1-10 (2020-11-16). http://kns.cnki.net/kcms/detail/11.2402.td.20201116.1432.004.html. 张明建, 李锋, 杨柳. 厚度变异系数大煤层综放开采合理采放比确定研究[J/OL]. 煤炭科学技术, 2020: 1-10 (2020-11-16). http://kns.cnki.net/kcms/detail/11.2402.td.20201116.1432.004.html.

[2] ZHONG Qitao. Research and application of coal seam thickness inversion method[D]. Xuzhou: China University of Mining and Technology, 2001. 仲其涛. 煤层厚度反演方法研究与应用[D]. 徐州: 中国矿业大学, 2001.

[3] LI Qinghai, ZHANG Cunzhi, LI Kaixin, et al. Analysis of the influence of different parameters of mining under super-thick loose layer on surface subsidence[J/OL]. Coal Science and Technology, 2020. http://kns.cnki.net/kcms/detail/11.2402.TD.20200622.0918.008.html. 李青海, 张存智, 李开鑫, 等. 巨厚松散层下开采地表下沉的影响因素分析[J]. 煤炭科学技术, 2020. http://kns.cnki.net/kcms/detail/11.2402.TD.20200622.0918.008.html.

[4] SHANG Xiuquan, YANG Haoyu, AI Guo, et al. Mining-induced stress changes and rock burst effect in thickness variation of a coal seam[J]. China Mining Magazine, 2020, 29(7): 148–151. 尚秀全, 杨浩宇, 艾国, 等. 煤厚变化区采动应力演化及其冲击影响研究[J]. 中国矿业, 2020, 29(7): 148–151.

[5] SUN Yuan, ZHANG Liang, ZHU Jun, et al. Application of seismic attribute parameters in forecasting coal seam thickness[J]. Coal Geology & Exploration, 2008, 36(2): 58–60. 孙渊, 张良, 朱军, 等. 地震属性参数在煤层厚度预测中的应用[J]. 煤田地质与勘探, 2008, 36(2): 58–60.

[6] GUO Yinjing, JU Yuanyuan, FAN Xiaojing, et al. Progress in research of in–seam seismic exploration[J]. Coal Geology & Exploration, 2020, 48: 216–227. 郭银景, 巨媛媛, 范晓静, 等. 槽波地震勘探研究进展[J]. 煤田地质与勘探, 2020, 48(2): 216–227.

[7] LIU Zuiliang, WANG Ji. Periods of refracted P-waves in coal seams and their applications in coal thickness estimations[J]. Acta Geophysica, 2020, 68(6): 1753–1762.

[8] ZHAO Kai. Application of seismic channel wave exploration in coal thickness exploration[J]. Energy Technology and Management, 2020, 45(5): 164–165. 赵凯. 地震槽波勘探在煤厚探查中的应用[J]. 能源技术与管理, 2020, 45(5): 164–165.

[9] YANG Wenqiang. Seismic facies analysis and seam thickness prediction of middle coal seam in Suntuan mine[D]. Xuzhou: China University of Mining and Technology, 2019. 杨文强. 孙疃矿中组煤层地震相分析与煤厚预测[D]. 徐州: 中国矿业大学, 2019.

[10] ZHANG Xianxu. Model–driven energy attenuation method for coal seam strong reflection[J]. Coal Geology & Exploration, 2020, 48(3): 188–194. 张宪旭. 基于模型驱动的煤层强反射能量衰减方法[J]. 煤田地质与勘探, 2020, 48(3): 188–194.

[11] DU Wenfeng, PENG Suping. Coalseam thickness prediction with geostatistics[J]. Chinese Journal of Rock Mechanics and Engineering, 2010, 29(Sup. 1): 2762–2767. 杜文凤, 彭苏萍. 利用地质统计学预测煤层厚度[J]. 岩石力学与工程学报, 2010, 29(增刊1): 2762–2767.

[12] CHENG Yan. Geological statistical coal thickness prediction method and application analysis[J]. China Mining Magazine, 2019, 28(Sup. 2): 245–249. 程彦. 地质统计煤厚预测方法及应用分析[J]. 中国矿业, 2019, 28(增刊2): 245–249.

[13] SUN Yuan, YANG Feng, ZHENG Jing, et al. Research on microseismic signal denoising based on variational mode decomposition and wavelet energy entropy[J]. Journal of Mining Science and Technology, 2019, 4(6): 469–479. 孙远, 杨峰, 郑晶, 等. 基于变分模态分解和小波能量熵的微震信号降噪[J]. 矿业科学学报, 2019, 4(6): 469–479.

[14] ZHANG Xingli, LU Xinming, JIA Ruisheng, et al. Micro-seismic signal denoising method based on variational mode decomposition and energy entropy[J]. Journal of China Coal Society, 2018, 43(2): 356–363. 张杏莉, 卢新明, 贾瑞生, 等. 基于变分模态分解及能量熵的微震信号降噪方法[J]. 煤炭学报, 2018, 43(2): 356–363.

[15] LI Jin, ZHANG Xian, CAI Jin. Suppression of strong interference for AMT using VMD and MP[J]. Chinese Journal of Geophysics(in Chinese), 2019, 62(10): 3866–3884. 李晋, 张贤, 蔡锦. 利用变分模态分解(VMD)和匹配追踪(MP)联合压制音频大地电磁(AMT)强干扰[J]. 地球物理学报, 2019, 62(10): 3866–3884.

[16] CORTES C, VAPNIK V. Support-vector networks[J]. Mach Learn, 1995, 20: 273–297. https://doi.org/10.1007/BF00994018

[17] YUAN Zhiming, LI Peihong, LIU Xiaosheng. Study on the application of improved PSO-SVM model considering neighbor–point in the settlement prediction of foundation pit[J]. Journal of Geodesy and Geodynamics, 2021, 41(3): 313–318. 袁志明, 李沛鸿, 刘小生. 顾及邻近点的改进PSO-SVM模型在基坑沉降预测的应用研究[J]. 大地测量与地球动力学, 2021, 41(3): 313–318.

[18] LIU Wei, CAO Siyuan, WANG Zhiming. Application of variational mode decomposition to seismic random noise reduction[J]. Journal of Geophysics and Engineering, 2017, 14(4): 888–898.

[19] MAO Zhiyong, HUANG Chunjuan, LU Shichang, et al. Model of gas-bearing coal permeability prediction based on APSO-WLS-SVM[J]. Coal Geology & Exploration, 2019, 47(2): 66–71. 毛志勇, 黄春娟, 路世昌, 等. 基于APSO-WLS-SVM的含瓦斯煤渗透率预测模型[J]. 煤田地质与勘探, 2019, 47(2): 66–71.