Comparison of models for predicting the floor failure depths of coal seams with moderate thicknesses and above under fully mechanized mining

Authors

XU Bin, Hebei State Key Laboratory of Mine Disaster Prevention, University of Emergency Management, Langfang 065201, China; CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, ChinaFollow
ZHONG Cen, Hebei State Key Laboratory of Mine Disaster Prevention, University of Emergency Management, Langfang 065201, China
DONG Shuning, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, ChinaFollow
YIN Shangxian, Hebei State Key Laboratory of Mine Disaster Prevention, University of Emergency Management, Langfang 065201, China
WANG Hao, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, China
LI Shuxia, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
DU Yongwei, Inner Mongolia Yitai Jingyue Suancigou Mining Co, Ltd., Ordos 010300, China
ZHANG Kebin, Inner Mongolia Yitai Jingyue Suancigou Mining Co, Ltd., Ordos 010300, China

Abstract

Objective The failure depth of a coal seam floor represents a critical parameter for assessing the risk of floor water inrushes. With the widespread application of fully mechanized mining with a large mining height, existing empirical equations suffer from insufficient accuracy when used to calculate the mining-induced floor failure depths of coal seams with moderate thicknesses and above.Methods Based on the compressive strength of coal seam floors (i.e., hard, moderately hard, and weak floors), 107 sets of data samples of the measured floor failure depths of coal seams with moderate thicknesses and above under fully mechanized mining were classified. Subsequently, models for predicting the floor failure depth were established while considering four factors: mining height, the length of the mining face along its dip direction, coal seam dip angle, and mining depth. The resulting four theoretical models consisted of three linear models (i.e., the quasi-classical empirical equation, the linear support vector regression (SVR) model, and the log-linear mixed model) and one nonlinear model (i.e., the backpropagation (BP) neural network model). Then, the reliability of the four models was compared and verified using two evaluation metrics, i.e., goodness of fit (R²) and mean absolute percentage error (E_MAP), as well as measured data from nine mines.Results and Conclusions For coal seam floors with three lithologies, the R² values of the four models decreased in the order of the BP neural network model, the log-linear mixed model, the linear SVR model, and the quasi-classical empirical equation model sequentially, suggesting inferior goodness of fit of the latter two models. The log-linear mixed model, the linear SVR model, and the quasi-classical empirical equation model yielded E_MAP values greater than the ideal threshold of 20%. However, the three models showed remarkable improvements compared to the classical empirical equation, which is no longer suited to guiding the prediction of the floor failure depths of coal seams with moderate thicknesses and above under fully mechanized mining due to discrepancies between calculated values and actual data. In contrast, the BP neural network model yielded average relative errors of less than 10%, significantly outperforming other models. By systematically comparing the prediction accuracy of the four theoretical models, this study provides a valuable reference for selecting an appropriate method for calculating the floor failure depths of coal seams with moderate thicknesses and above.

Keywords

coal seam subjected to fully mechanized mining, coal seam with a moderate thickness and above, coal seam floor failure depth, model comparison, backpropagation (BP) neural network

DOI

10.12363/issn.1001-1986.25.09.0697

Recommended Citation

XU Bin, ZHONG Cen, DONG Shuning, et al. (2026) "Comparison of models for predicting the floor failure depths of coal seams with moderate thicknesses and above under fully mechanized mining," Coal Geology & Exploration: Vol. 54: Iss. 3, Article 14.
DOI: 10.12363/issn.1001-1986.25.09.0697
Available at: https://cge.researchcommons.org/journal/vol54/iss3/14

Reference

[1] 康红普. 《采矿与岩层控制工程学报》创刊词[J]. 采矿与岩层控制工程学报,2019,1(2):3−4

[2] 张培森,许大强,付翔,等. 基于断层封闭性研究评价其导水性[J]. 采矿与岩层控制工程学报,2022,4(2):023033

ZHANG Peisen,XU Daqiang,FU Xiang,et al. Evaluation of hydraulic conductivity based on fault confinement studies[J]. Journal of Mining and Strata Control Engineering,2022,4(2):023033

[3] 谢和平,王金华,王国法,等. 煤炭革命新理念与煤炭科技发展构想[J]. 煤炭学报,2018,43(5):1187−1197

XIE Heping,WANG Jinhua,WANG Guofa,et al. New ideas of coal revolution and layout of coal science and technology development[J]. Journal of China Coal Society,2018,43(5):1187−1197

[4] 王朋朋,赵毅鑫,姜耀东,等. 邢东矿深部带压开采底板突水特征及控制技术[J]. 煤炭学报,2020,45(7):2444−2454

WANG Pengpeng,ZHAO Yixin,JIANG Yaodong,et al. Characteristics and control technology of water inrush from deep coal seam floor above confined aquifer in Xingdong coal mine[J]. Journal of China Coal Society,2020,45(7):2444−2454

[5] 郭国强. 综放开采特厚煤层采场底板破坏规律研究[J]. 煤田地质与勘探,2022,50(8):107−115

GUO Guoqiang. Floor failure law of extra–thick coal seam in fully mechanized caving mining[J]. Coal Geology & Exploration,2022,50(8):107−115

[6] 孔皖军,郑根源,国伟,等. 采动条件下底板岩层破坏深度动态测试研究及应用[J]. 煤炭工程,2018,50(10):96−100

KONG Wanjun,ZHENG Genyuan,GUO Wei,et al. Research and application of dynamic testing technology for floor rock damage depth under mining condition[J]. Coal Engineering,2018,50(10):96−100

[7] 李江华,许延春,谢小锋,等. 采高对煤层底板破坏深度的影响[J]. 煤炭学报,2015,40(增刊2):303−310

LI Jianghua,XU Yanchun,XIE Xiaofeng,et al. Influence of mining height on coal seam floor failure depth[J]. Journal of China Coal Society,2015,40(Sup.2):303−310

[8] 刘伟韬,穆殿瑞,谢祥祥,等. 倾斜煤层底板采动应力分布规律及破坏特征[J]. 采矿与安全工程学报,2018,35(4):756−764

LIU Weitao,MU Dianrui,XIE Xiangxiang,et al. Rules of stress distributions and failure characteristics in inclined coal seam floor due to mining[J]. Journal of Mining and Safety Engineering,2018,35(4):756−764

[9] 刘伟韬,宋文成,穆殿瑞,等. 底板采动破坏带分段观测系统与应用[J]. 中南大学学报(自然科学版),2017,48(10):2808−2816

LIU Weitao,SONG Wencheng,MU Dianrui,et al. Section observation system on floor mining damage zone and its application[J]. Journal of Central South University (Science and Technology),2017,48(10):2808−2816

[10] CHEN Yang,ZHU Shuyun,WANG Zhenguang,et al. Deformation and failure of floor in mine with soft coal,soft floor,hard roof and varying thicknesses of coal seam[J]. Engineering Failure Analysis,2020,115:104653.

[11] 张培森,许大强,张晓乐,等. 煤层底板破坏深度多因素影响指标分析与深度预测[J]. 采矿与岩层控制工程学报,2023,5(3):033037

ZHANG Peisen,XU Daqiang,ZHANG Xiaole,et al. Multi–factor influence index analysis and prediction of failure depth of coal seam floor[J]. Journal of Mining and Strata Control Engineering,2023,5(3):033037

[12] 高延法. 底板突水规律与突水优势面[M]. 徐州：中国矿业大学出版社，1999.

[13] 段宏飞,姜振泉,朱术云,等. 综采薄煤层采动底板变形破坏规律实测分析[J]. 采矿与安全工程学报,2011,28(3):407−414

DUAN Hongfei,JIANG Zhenquan,ZHU Shuyun,et al. Measurement of mining–induced floor failure regularity for thin coal seams using fully mechanized coal caving[J]. Journal of Mining & Safety Engineering,2011,28(3):407−414

[14] 中华人民共和国住房和城乡建设部，中华人民共和国国家质量监督检验检疫总局. 煤炭矿井防治水设计规范：GB 51070—2014[S]. 武汉：中煤科工集团武汉设计研究院有限公司，2014.

[15] 董书宁,王皓,张文忠. 华北型煤田奥灰顶部利用与改造判别准则及底板破坏深度[J]. 煤炭学报,2019,44(7):2216−2226

DONG Shuning,WANG Hao,ZHANG Wenzhong. Judgement criteria with utilization and grouting reconstruction of top Ordovician limestone and floor damage depth in North China coal field[J]. Journal of China Coal Society,2019,44(7):2216−2226

[16] 刘树才. 煤矿底板突水机理及破坏裂隙带演化动态探测技术[D]. 徐州：中国矿业大学，2008.

LIU Shucai. Mechanism of water inrush from coal seam floor and continuous survey of fractured zones in coal seam floor[D]. Xuzhou：China University of Mining and Technology，2008.

[17] 施龙青,张荣遨,韩进,等. 基于GWO改进的PCA–BP神经网络煤层底板破坏深度预测模型[J]. 矿业研究与开发,2020,40(2):88−93

SHI Longqing,ZHANG Rongao,HAN Jin,et al. Prediction model of failure depth of coal seam floor based on PCA–BP neural network improved by GWO[J]. Mining Research and Development,2020,40(2):88−93

[18] 邢晁瑞,李磊,王立彬,等. 华北型煤田底板破坏深度BP神经网络预测模型研究[J]. 矿业科学学报,2023,8(5):688−694

XING Chaorui,LI Lei,WANG Libin,et al. BP neural network prediction model of floor failure depth in North China coalfield[J]. Journal of Mining Science and Technology,2023,8(5):688−694

[19] WANG Haoze，LI Xiang，LI Shi. A transfer learning–based approach for rockburst prediction in deep underground engineering using small sample data[J]. Tunnelling and Underground Space Technology，2022，130.

[20] 李刚,赵艺鸣,杨庆贺,等. 基于SA–PSO–BP神经网络的煤层底板破坏深度预测[J]. 地下空间与工程学报,2025,21(1):293−299

LI Gang,ZHAO Yiming,YANG Qinghe,et al. Failure depth prediction of coal seam floor based on SA–PSO–BP neural network[J]. Chinese Journal of Underground Space and Engineering,2025,21(1):293−299

[21] 许延春,杨扬. 大埋深煤层底板破坏深度统计公式及适用性分析[J]. 煤炭科学技术,2013,41(9):129−132

XU Yanchun,YANG Yang. Applicability analysis on statistical formula for failure depth of coal seam floor in deep mine[J]. Coal Science and Technology,2013,41(9):129−132

[22] 陈从磊,姚多喜,赵魁,等. 基于灰色神经网络预测青东矿10煤层底板破坏深度[J]. 煤炭技术,2012,31(11):49−51

CHEN Conglei,YAO Duoxi,ZHAO Kui,et al. Floor 10 damage depth of green east coal mine based on grey neural network[J]. Coal Technology,2012,31(11):49−51

[23] 钱鸣高，石平五，许家林. 矿山压力与岩层控制[M]. 徐州：中国矿业大学出版社，2003.

[24] 国家安全监管总局，国家煤矿安监局，国家能源局，等. 建筑物、水体、铁路及主要井巷煤柱留设与压煤开采规范[M]. 北京：煤炭工业出版社，2017.

[25] 陈洋. 大同矿区特厚煤层采动底板变形及破坏深度研究[D]. 徐州：中国矿业大学，2021.

CHEN Yang. Study on deformation and failure depth of mining floor in extra–thick coal seam of Datong mining area[D]. Xuzhou：China University of Mining and Technology，2021.

[26] 李昂,牟谦,刘朝阳,等. 渭北煤田多因素影响下底板扰动破坏深度研究[J]. 煤炭工程,2020,52(5):138−143

LI Ang,MU Qian,LIU Chaoyang,et al. Fitting analysis and verification of floor disturbance failure depth under the influence of multiple factors in Weibei coalfield[J]. Coal Engineering,2020,52(5):138−143

[27] 张风达,申宝宏. 深部煤层底板破坏特征分析[J]. 采矿与安全工程学报,2019,36(1):44−50

ZHANG Fengda,SHEN Baohong. Failure characteristics analysis of deep coal seam floor[J]. Journal of Mining and Safety Engineering,2019,36(1):44−50

[28] 张文泉,赵凯,张贵彬,等. 基于灰色关联度分析理论的底板破坏深度预测[J]. 煤炭学报,2015,40(增刊1):53−59

ZHANG Wenquan,ZHAO Kai,ZHANG Guibin,et al. Prediction of floor failure depth based on grey correlation analysis theory[J]. Journal of China Coal Society,2015,40(Sup.1):53−59

[29] 李志强. 基于五图–双系数法与脆弱性指数法的煤矿底板突水预测研究[D]. 焦作：河南理工大学，2017.

LI Zhiqiang. Study on water bursting prediction of coal mine floor based on five graph–double coefficient method and vulnerability index method[D]. Jiaozuo：Henan Polytechnic University，2017.

[30] 徐维. 龙王沟煤矿底板突水危险性评价[D]. 廊坊：华北科技学院，2020.

XU Wei. Risk assessment of water inrush from Longwanggou coal mine floor[D]. Langfang：North China Institute of Science and Technology，2020.

[31] JIANG Yulong,CAI Tingting,ZHANG Xiaoqiang. A multifactor coupling prediction model for the failure depth of floor rocks in fully mechanized caving mining:A numerical and in situ study[J]. Royal Society Open Science,2019,6(8):190528.

[32] WU Shaomin,AKBAROV A. Support vector regression for warranty claim forecasting[J]. European Journal of Operational Research,2011,213(1):196−204.

[33] GU Shuancheng，LI Ang，WANG Jianhuan. Theoretical analysis and numerical simulation study on failure depth of coal seams floor caused by mining under pressure[C]//2011 International Conference on Multimedia Technology. Hangzhou：IEEE，2011：1367–1372.

[34] JIANG Hongyan,YUE Rongxian. D–optimal population designs in linear mixed effects models for multiple longitudinal data[J]. Statistical Theory and Related Fields,2021,5(2):88−94.

[35] 秦晋,智荣腾. BP神经网络在软件质量评价中的应用研究[J]. 软件导刊,2016,15(9):1−3

[36] 曾一凡,武强,赵苏启,等. 我国煤矿水害事故特征、致因与防治对策[J]. 煤炭科学技术,2023,51(7):1−14

ZENG Yifan,WU Qiang,ZHAO Suqi,et al. Characteristics,causes,and prevention measures of coal mine water hazard accidents in China[J]. Coal Science and Technology,2023,51(7):1−14

[37] LI Shunfeng. Prediction for damage depth of coal seam floor based on the BP neural network[C]//2015 International Conference on Material Science and Applications. Suzhou：ICMSA，2015.

[38] GABRIEL G，MARSHALL T. Hma dynamic modulus predictive models (a review)[R]. Civil Engineering Studies Illinois Center for Transportation，2007.

[39] LIU Qiang,YANG Chunyan,LIN Li. Deformation prediction of a deep foundation pit based on the combination model of wavelet transform and gray BP neural network[J]. Mathematical Problems in Engineering,2021,2021(1):2161254.

[40] BORGULYA I. A ranking method for multiple–criteria decision–making[J]. International Journal of Systems Science,1997,28(9):905−912.