Transformer-driven intelligent prediction for the time-series features of mine pressure in fully mechanized mining face

Authors

DU Feng, School of Energy Science and Engineering, Henan Polytechnic University, Jiaozuo 454003, China; Collaborative Innovation Center for Coal Safety Production and Clean and Efficient Utilization, Jiaozuo 454003, China; Engineering Technology Research Center of Mine Water Disaster Control and Water Resources Utilization, Henan Polytechnic University, Jiaozuo 454003, China; Zhengzhou Institute for Advanced Research of Henan Polytechnic University, Zhengzhou 451464, ChinaFollow
CHEN Bo, School of Energy Science and Engineering, Henan Polytechnic University, Jiaozuo 454003, China
WANG Wenqiang, School of Energy Science and Engineering, Henan Polytechnic University, Jiaozuo 454003, ChinaFollow
PU Hai, Nation Key Laboratory of Intelligent Construction and Healthy Operation & Maintenance for Deep Earth Engineering, China University of Mining & Technology, Xuzhou 221116, China
DU Xueming, Yellow River Laboratory, Zheng zhou University, Zhengzhou 450000, China
LI Guodong, Jiaozuo Coal Industry Group, Jiaozuo 454002, China
QIAO Rui, Jiaozuo Coal Industry Group, Jiaozuo 454002, China; Shenlong Hydrogeological Engineering Limited Corporation, Jiaozuo 454100, China
LI Xinlei, Jiaozuo Coal Industry Group, Jiaozuo 454002, China
XU Jie, School of Energy Science and Engineering, Henan Polytechnic University, Jiaozuo 454003, China
CAO Yu, Anhui Huichi Geological Safety Research Institute Co., Ltd., Hefei 231200, China

Abstract

Objective Mine pressure prediction represents an important means for early warning and management of disasters in coal seam roofs, serving as the prerequisite and foundation for safe production in intelligent mines. However, the complex and variable conditions of fully mechanized mining face lead to significant variations in the distribution of support pressure data acquired using electro-hydraulic control systems, complicating mine pressure prediction. Methods This study developed a Transformer-based mine pressure prediction model. Specifically, missing mine pressure data were filled using linear interpolation, and the data structure of mine pressure was adjusted using a sliding window algorithm. Based on the time-series features of mine pressure data, an input sequence incorporating these features was constructed. The dynamic weight computation of the model was performed using the multi-head attention mechanism, while adaptive focus on critical time steps was achieved based on the data itself. Consequently, complex nonlinear time-series dependencies can be effectively captured, thus significantly enhancing feature representation and prediction performance. Finally, the support resistance prediction for the upper, middle, and lower sections of the mining face was conducted using the transfer learning method, and a big-data-driven intelligent platform for mine pressure analysis and prediction was established. Results and Conclusions By capturing global features of mine pressure data using a multi-head attention mechanism rather than neural networks, the Transformer model demonstrated stronger long-sequence dependencies and feature learning capabilities compared to the recurrent neural network (RNN) and long short-term memory (LSTM). Therefore, this model effectively reduced loss and was more suitable for mine pressure prediction, with a mean squared error (MSE) of 0.34% and a mean absolute error (MAE) of 2.57% on the test set. Furthermore, the Transformer model exhibited robust generalization performance. This model exhibited effectively reduced loss after fine-tuning with transfer learning and yielded superior generalization performance when transferred to adjacent supports within the same mining face. These findings further validated the applicability and feasibility of this model in mine pressure prediction. The visualization system of the intelligent platform presented the precise analysis results of key parameters before and after prediction, including roof weighting frequency, advancing distance of the mining face, weighting criterion, and mine pressure contour maps. The results of this study provide a new philosophy for the early warning of disasters, including those in coal seam roofs, while also laying a solid foundation for safe, efficient mining and intelligent construction of mines.

Keywords

fully mechanized coal mining face, deep learning, transformer model, time series, mine pressure behavior, mine pressure prediction

DOI

10.12363/issn.1001-1986.25.10.0749

Recommended Citation

DU Feng, CHEN Bo, WANG Wenqiang, et al. (2026) "Transformer-driven intelligent prediction for the time-series features of mine pressure in fully mechanized mining face," Coal Geology & Exploration: Vol. 54: Iss. 2, Article 2.
DOI: 10.12363/issn.1001-1986.25.10.0749
Available at: https://cge.researchcommons.org/journal/vol54/iss2/2

Reference

[1] 徐刚,黄志增,范志忠,等. 工作面顶板灾害类型、监测与防治技术体系[J]. 煤炭科学技术,2021,49(2):1−11

XU Gang,HUANG Zhizeng,FAN Zhizhong,et al. Types,monitoring and prevention technology system of roof disasters in mining face[J]. Coal Science and Technology,2021,49(2):1−11

[2] 于斌,杨敬轩,刘长友,等. 大空间采场覆岩结构特征及其矿压作用机理[J]. 煤炭学报,2019,44(11):3295−3307

YU Bin,YANG Jingxuan,LIU Changyou,et al. Overburden structure and mechanism of rock pressure in large space stope[J]. Journal of China Coal Society,2019,44(11):3295−3307

[3] 郑凯歌,张俭,孙四清,等. 煤层顶板多种灾害发生机理与协同防治技术[J]. 煤田地质与勘探,2025,53(5):24−35

ZHENG Kaige,ZHANG Jian,SUN Siqing,et al. Mechanisms and collaborative prevention and control techniques for various disasters in coal seam roofs[J]. Coal Geology & Exploration,2025,53(5):24−35

[4] 王巍,王文,张广杰. 神东矿区浅埋大采高工作面支架–围岩耦合关系及支架适用性研究[J]. 河南理工大学学报(自然科学版),2025,44(2):32−41

WANG Wei,WANG Wen,ZHANG Guangjie. Study on the coupling relationship between support and surrounding rock and the applicability of support in shallow buried high mining faces of the Shendong Mining Area[J]. Journal of Henan Polytechnic University (Natural Science),2025,44(2):32−41

[5] PAN Chao,XIA Binwei,ZUO Yujun,et al. Mechanism and control technology of strong ground pressure behaviour induced by high–position hard roofs in extra–thick coal seam mining[J]. International Journal of Mining Science and Technology,2022,32(3):499−511.

[6] 徐刚,范志忠,张春会,等. 宏观顶板活动支架增阻类型与预测模型[J]. 煤炭学报,2021,46(11):3397−3407

XU Gang,FAN Zhizhong,ZHANG Chunhui,et al. Support increasing resistance forms of macroscopic roof support and its prediction model[J]. Journal of China Coal Society,2021,46(11):3397−3407

[7] 许慧聪,来兴平,单鹏飞,等. 沟谷区浅埋煤层矿压显现时空特征辨识及预测方法研究[J]. 岩石力学与工程学报,2025,44(6):1450−1465

XU Huicong,LAI Xingping,SHAN Pengfei,et al. Research on spatiotemporal characteristics perception and prediction methods of shallow buried coal seam mining pressure in valley areas[J]. Chinese Journal of Rock Mechanics and Engineering,2025,44(6):1450−1465

[8] 钱鸣高，石平五，许家林. 矿山压力与岩层控制(第2版)[M]. 徐州：中国矿业大学出版社，2010.

[9] 宋振骐,郝建,石永奎,等. “实用矿山压力控制理论”的内涵及发展综述[J]. 山东科技大学学报(自然科学版),2019,38(1):1−15

SONG Zhenqi,HAO Jian,SHI Yongkui,et al. An overview of connotation and development of practical ground pressure control theory[J]. Journal of Shandong University of Science and Technology (Natural Science),2019,38(1):1−15

[10] 王家臣,宋正阳. 综放开采散体顶煤初始煤岩分界面特征及控制方法[J]. 煤炭工程,2015,47(7):1−4

WANG Jiachen,SONG Zhengyang. Characteristic and control method of initial interface between coal and rock under fully mechanized loose top coal caving[J]. Coal Engineering,2015,47(7):1−4

[11] 王国法,杜毅博,陈晓晶,等. 从煤矿机械化到自动化和智能化的发展与创新实践:纪念《工矿自动化》创刊50周年[J]. 工矿自动化,2023,49(6):1−18

WANG Guofa,DU Yibo,CHEN Xiaojing,et al. Development and innovative practice from coal mine mechanization to automation and intelligence:Commemorating the 50th anniversary of the founding of Journal of Mine Automation[J]. Journal of Mine Automation,2023,49(6):1−18

[12] 来兴平,万培烽,单鹏飞,等. 基于免疫粒子群混合算法优化BP网络的矿压预测方法[J]. 西安科技大学学报,2023,43(1):1−8

LAI Xingping,WAN Peifeng,SHAN Pengfei,et al. Mine pressure prediction method based on immune algorithm–particle swarm optimization BP network[J]. Journal of Xi’an University of Science and Technology,2023,43(1):1−8

[13] 王国法,赵国瑞,任怀伟. 智慧煤矿与智能化开采关键核心技术分析[J]. 煤炭学报,2019,44(1):34−41

WANG Guofa,ZHAO Guorui,REN Huaiwei. Analysis on key technologies of intelligent coal mine and intelligent mining[J]. Journal of China Coal Society,2019,44(1):34−41

[14] 董书宁,刘再斌,程建远,等. 煤炭智能开采地质保障技术及展望[J]. 煤田地质与勘探,2021,49(1):21−31

DONG Shuning,LIU Zaibin,CHENG Jianyuan,et al. Technologies and prospect of geological guarantee for intelligent coal mining[J]. Coal Geology & Exploration,2021,49(1):21−31

[15] 王国法,张建中,薛国华,等. 煤矿回采工作面智能地质保障技术进展与思考[J]. 煤田地质与勘探,2023,51(2):12−26

WANG Guofa,ZHANG Jianzhong,XUE Guohua,et al. Progress and reflection of intelligent geological guarantee technology in coal mining face[J]. Coal Geology & Exploration,2023,51(2):12−26

[16] 闫吉太,梁广锋,安满林,等. “孤岛”综采放顶煤工作面矿压预测预报[J]. 中国矿业大学学报,1996,25(4):98−103

YAN Jitai,LIANG Guangfeng,AN Manlin,et al. Forecast of underground pressure for a fully–mechanized sublevel caving face with four mined boundaries[J]. Journal of China University of Mining & Technology,1996,25(4):98−103

[17] 冯夏庭,王泳嘉,姚建国. 煤矿顶板矿压显现实时预报的自适应神经网络方法[J]. 煤炭学报,1995,20(5):455−460

FENG Xiating,WANG Yongjia,YAO Jianguo. An adaptive neural network for real–time prediction of rock behaviour in coal mines[J]. Journal of China Coal Society,1995,20(5):455−460

[18] 尹希文,徐刚,刘前进,等. 基于支架载荷的矿压双周期分析预测方法[J]. 煤炭学报,2021,46(10):3116−3126

YIN Xiwen,XU Gang,LIU Qianjin,et al. Method of double–cycle analysis and prediction for rock pressure based on the support load[J]. Journal of China Coal Society,2021,46(10):3116−3126

[19] VERMA A K,KISHORE K,CHATTERJEE S. Prediction model of longwall powered support capacity using field monitored data of a longwall panel and uncertainty–based neural network[J]. Geotechnical and Geological Engineering,2016,34(6):2033−2052.

[20] 任艳芳. 综采工作面液压支架支护能力的分析与评价方法[J]. 采矿与岩层控制工程学报,2020,2(3):036012

REN Yanfang. Analysis and evaluation method for supporting ability of supports in coalmine working face[J]. Journal of Mining and Strata Control Engineering,2020,2(3):036012

[21] 许永祥,曾明胜,蔡逢华,等. 特厚坚硬煤层两柱掩护式超大采高综放液压支架适应性研究[J]. 采矿与安全工程学报,2025,42(2):252−263

XU Yongxiang,ZENG Mingsheng,CAI Fenghua,et al. Investigation on adaptability of two–leg shielded LTCC hydraulic supports for ultra–thick and hard coal seam with super–large cutting height[J]. Journal of Mining & Safety Engineering,2025,42(2):252−263

[22] 伍永平,胡博胜,解盘石,等. 基于支架–围岩耦合原理的模拟试验液压支架及测控系统研制与应用[J]. 岩石力学与工程学报,2018,37(2):374−382

WU Yongping,HU Bosheng,XIE Panshi,et al. Development and application of support and control system for simulating test based on the coupling principle of support–surrounding rocks[J]. Chinese Journal of Rock Mechanics and Engineering,2018,37(2):374−382

[23] 刘前进,徐刚,卢振龙,等. 液压支架工况综合评价与预警模型研究及应用[J]. 煤炭科学技术,2022,50(10):198−206

LIU Qianjin,XU Gang,LU Zhenlong,et al. Research and application of comprehensive evaluation and early warning model of hydraulic support working condition based on working resistance analysis[J]. Coal Science and Technology,2022,50(10):198−206

[24] 赵毅鑫,杨志良,马斌杰,等. 基于深度学习的大采高工作面矿压预测分析及模型泛化[J]. 煤炭学报,2020,45(1):54−65

ZHAO Yixin,YANG Zhiliang,MA Binjie,et al. Deep learning prediction and model generalization of ground pressure for deep longwall face with large mining height[J]. Journal of China Coal Society,2020,45(1):54−65

[25] 曾庆田,吕珍珍,石永奎,等. 基于Prophet+LSTM模型的煤矿井下工作面矿压预测研究[J]. 煤炭科学技术,2021,49(7):16−23

ZENG Qingtian,LYU Zhenzhen,SHI Yongkui,et al. Research on prediction of underground coal mining face pressure based on Prophet+LSTM model[J]. Coal Science and Technology,2021,49(7):16−23

[26] 柴敬,张锐新,欧阳一博,等. 基于贝叶斯算法优化的CatBoost矿压显现预测[J]. 工矿自动化,2023,49(7):83−91

CHAI Jing,ZHANG Ruixin,OUYANG Yibo,et al. CatBoost mine pressure appearance prediction based on Bayesian algorithm optimization[J]. Journal of Mine Automation,2023,49(7):83−91

[27] 李振华,徐杰,王文强,等. 基于Optuna–LSTM的矿压预测方法研究[J]. 矿业研究与开发,2023,43(3):98−102

LI Zhenhua,XU Jie,WANG Wenqiang,et al. Research on prediction method of mine pressure based on Optuna–LSTM[J]. Mining Research and Development,2023,43(3):98−102

[28] 巩师鑫,任怀伟,杜毅博,等. 基于MRDA–FLPEM集成算法的综采工作面矿压迁移预测[J]. 煤炭学报,2021,46(增刊1):529−538

GONG Shixin,REN Huaiwei,DU Yibo,et al. Transfer prediction of underground pressure for fully mechanized mining face based on MRDA–FLPEM integrated algorithm[J]. Journal of China Coal Society,2021,46(Sup.1):529−538

[29] CHEN Yiqi,LIU Changyou,ZHANG Ningbo,et al. Research on pressure exertion prediction in coal mine working faces based on data–driven approaches[J]. Applied Sciences,2025,15(8):4192.

[30] 冀汶莉,刘艺欣,柴敬,等. 基于随机森林的矿压预测方法[J]. 采矿与岩层控制工程学报,2021,3(3):033525

JI Wenli,LIU Yixin,CHAI Jing,et al. Mine pressure prediction method based on random forest[J]. Journal of Mining and Strata Control Engineering,2021,3(3):033525

[31] 何志铧,熊祖强. 基于Informer神经网络的工作面矿压预测研究[J]. 矿业研究与开发,2024,44(7):142−148

HE Zhihua,XIONG Zuqiang. Research on mining pressure prediction of working face based on Informer neural network[J]. Mining Research and Development,2024,44(7):142−148

[32] 贾澎涛,苗云风. 基于堆叠LSTM的多源矿压预测模型分析[J]. 矿业研究与开发,2021,41(8):79−82

JIA Pengtao,MIAO Yunfeng. Multi–source mine pressure prediction model analysis based on stacked–LSTM[J]. Mining Research and Development,2021,41(8):79−82

[33] 徐刚,张震,张春会,等. 我国煤矿开采工作面顶板灾害及防治技术研究现状[J]. 采矿与岩层控制工程学报,2024,6(5):053028

XU Gang,ZHANG Zhen,ZHANG Chunhui,et al. Review on roof disaster and prevention technology for coal mining face in China[J]. Journal of Mining and Strata Control Engineering,2024,6(5):053028

[34] VASWANI A，SHAZEER N，PARMAR N，et al. Attention is all you need[C]//31st Conference on Neural Information Processing Systems (NIPS 2017). Long Beach，2017：1–11.