Coal Geology & Exploration


In the process of coal mining, the loss of people and property caused by mine water inrush is extremely serious. To prevent the occurrence of water inrush accidents and grasp the law of change of water inrush, the water inrush prediction and forecasting, especially the accurate estimation of mine water inrush, is very important, which is also an important task in the prevention and control of mine water damage. To increase the prediction accuracy of mine water inrush, an efficient time series prediction model combining Variational Mode Decomposition (VMD) and Deep Belief Network (DBN) was proposed for the series of water inrush with no obvious change with time. Firstly, the original data were initially denoised by VMD to break up the original mine water inrush time series into multiple Intrinsic Mode Function (IMF) components, so that each IMF component has the statistical characteristic quantity of the original time series at different time scales, which reduces the strong oscillation and instability of the original time series. Secondly, DBN model was established separately to each IMF component for training and learning, and then the corresponding prediction network model was built. Finally, the predicted values of each component were fused as a result. The results show that the EMA, EMAP, ERMS and R2 of VMD-DBN are 9.23, 0.76%, 11.55 and 0.97 respectively, which are compared with the predicted values of GA-BP, LSTM, VMD-LSTM, RBM, VMD-RBM, and DBN models, finding that the mine water inrush prediction with VMD-DBN model has a higher accuracy. Therefore, the VMD-DBN model has relatively obvious advantages under the conditions that the water inrush has no obvious change law over time but with strong oscillation and instability, thus enriching the mine water inrush prediction methods, providing a new technical means for the intelligent mine safety monitoring, with some theoretical value and practical significance.


mine water inrush prediction, Variational Mode Decomposition (VMD), deep learning, Deep Belief Network (DBN), time series




[1] 虎维岳,闫丽. 对矿井涌水量预测问题的分析与思考[J]. 煤炭科学技术,2016,44(1):13−18.

HU Weiyue,YAN Li. Analysis and consideration on prediction problems of mine water inflow volume[J]. Coal Science and Technology,2016,44(1):13−18.

[2] 范立民,孙魁,李成,等. 榆神矿区煤矿防治水的几点思考[J]. 煤田地质与勘探,2021,49(1):182−188.

FAN Limin,SUN Kui,LI Cheng,et al. Thoughts on mine water control and treatment in Yushen mining area[J]. Coal Geology & Exploration,2021,49(1):182−188.

[3] 虎维岳. 浅埋煤层回采中顶板含水层涌水量的时空动态预测技术[J]. 煤田地质与勘探,2016,44(5):91−96.

HU Weiyue. Water inflows prediction technique of water inflow from roof aquifer during extraction of shallow seam[J]. Coal Geology & Exploration,2016,44(5):91−96.

[4] 杨建,王皓,梁向阳,等. 鄂尔多斯盆地北部深埋煤层工作面涌水量预测方法[J]. 煤田地质与勘探,2021,49(4):185−191.

YANG Jian,WANG Hao,LIANG Xiangyang,et al. Water inflow forecasting method of deep buried coal working face in northern Ordos Basin,China[J]. Coal Geology & Exploration,2021,49(4):185−191.

[5] 陈酩知,刘树才,杨国勇. 矿井涌水量预测方法的发展[J]. 工程地球物理学报,2009,6(1):68−72.

CHEN Mingzhi,LIU Shucai,YANG Guoyong. The development of mining water inflow predict method[J]. Chinese Journal of Engineering Geophysics,2009,6(1):68−72.

[6] 马青山,骆祖江. 解析法和数值法在矿井涌水量预测中的比较[J]. 矿业安全与环保,2015,42(4):63−66.

MA Qingshan,LUO Zujiang. Comparison of analytical method and numerical method in mine water inflow prediction[J]. Mining Safety & Environmental Protection,2015,42(4):63−66.

[7] 戴岩柯,崔世新,张坤. 水均衡法和数值模拟法在矿坑深部涌水量预测中的比较:以西石门铁矿为例[J]. 地下水,2010,32(1):24−26.

DAI Yanke,CUI Shixin,ZHANG Kun. Comparisons water balance to value simulation in the forecast of from the depth inflow of the mine pit:Take an iron–ore in Xishimen as an example[J]. Groundwater,2010,32(1):24−26.

[8] 张子祥. 甘肃核桃峪煤矿矿井涌水量的计算与分析[J]. 中国煤炭地质,2015,27(2):32−36.

ZHANG Zixiang. Estimation and analysis of mine water inflow in Hetaoyu Coal Mine,Gansu[J]. Coal Geology of China,2015,27(2):32−36.

[9] 王家乐,王施智,黄倩. 基于相关分析法的煤矿涌水量预测[J]. 陕西煤炭,2021,40(2):99−102.

WANG Jiale,WANG Shizhi,HUANG Qian. Prediction of coal mine water inflow based on correlation analysis method[J]. Shaanxi Coal,2021,40(2):99−102.

[10] 苏培东,赵熠,邱鹏,等. 花岗岩蚀变带隧道涌水量预测研究[J]. 地下空间与工程学报,2023,19(1):291−301.

SU Peidong,ZHAO Yi,QIU Peng,et al. Prediction of tunnel water inrush volume in granite alteration zone[J]. Chinese Journal of Underground Space and Engineering,2023,19(1):291−301.

[11] 邢金莎. 基于深度学习的矿井水文参数分析与预测[D]. 西安:西安科技大学,2021.

XING Jinsha. Mine hydrological parameter analysis and prediction based on deep learning[D]. Xi’an:Xi’an University of Science and Technology,2021.

[12] 齐晓峰,邵良杉,邢雨艳. 基于EMD的矿井涌水量ARMA预测模型[J]. 辽宁工程技术大学学报(自然科学版),2020,39(6):509−513.

QI Xiaofeng,SHAO Liangshan,XING Yuyan. ARMA prediction model of mine water inflow based on EMD[J]. Journal of Liaoning Technical University (Natural Science),2020,39(6):509−513.

[13] 安欣,贾进章. 矿井涌水量时间序列ARIMA预测模型[J]. 辽宁工程技术大学学报(自然科学版),2015,34(7):785−790.

AN Xin,JIA Jinzhang. Time series prediction of mine water inflow of ARIMA model[J]. Journal of Liaoning Technical University (Natural Science),2015,34(7):785−790.

[14] 孟璐. 基于人工神经网络的矿井涌水量预测[J]. 煤炭与化工,2020,43(4):65−68.

MENG Lu. Mine water volume prediction based on artificial neural networks[J]. Coal and Chemical Industry,2020,43(4):65−68.

[15] 乔美英,程鹏飞,刘震震. 基于GA–SVM的矿井涌水量预测[J]. 煤田地质与勘探,2017,45(6):117−122.

QIAO Meiying,CHENG Pengfei,LIU Zhenzhen. Mine water inflow prediction based on GA–SVM[J]. Coal Geology & Exploration,2017,45(6):117−122.

[16] 黄永刚,李龙. 基于随机森林算法的矿井涌水量预测[J]. 煤炭技术,2017,36(1):220−221.

HUANG Yonggang,LI Long. Mine water inflow forecasting based on random forest algorithm[J]. Coal Technology,2017,36(1):220−221.

[17] LI Zhanli,GAO Tianyu,GUO Cheng,et al. A gated recurrent unit network model for predicting open channel flow in coal mines based on attention mechanisms[J]. IEEE Access,2020,8:119819−119828.

[18] 罗奕,向新,王勇. 矿井明渠流量测定方法[J]. 煤田地质与勘探,2006,34(1):56−57.

LUO Yi,XIANG Xin,WANG Yong. Technological method to measure the canal sewage discharge in coal mine[J]. Coal Geology & Exploration,2006,34(1):56−57.

[19] 降海荣,赵宝峰,康艳旗,等. 基于深度置信网络的矿井涌水量预测研究[J]. 矿业研究与开发,2023,43(2):143−148.

JIANG Hairong,ZHAO Baofeng,KANG Yanqi,et al. Prediction of mine water inflow based on deep belief network[J]. Mining Research and Development,2023,43(2):143−148.

[20] HUANG N E,SHEN Zheng,LONG S R,et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non–stationary time series analysis[J]. Proceedings:Mathematical,Physical and Engineering Sciences,1998,454(1971):903−995.

[21] DRAGOMIRETSKIY K,ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing,2014,62(3):531−544.

[22] KUREMOTO T,KIMURA S,KOBAYASHI K,et al. Time series forecasting using a deep belief network with restricted Boltzmann machines[J]. Neurocomputing,2014,137:47−56.

[23] CHENG Yong,ZHOU Xiangyu,WAN Shaohua,et al. Deep belief network for meteorological time series prediction in the Internet of things[J]. IEEE Internet of Things Journal,2019,6(3):4369−4376.

[24] 侍建国,张亦飞. 拉依达准则在处理区域水文数据异常值中的应用[J]. 海河水利,2016(5):49−51.

SHI Jianguo,ZHANG Yifei. Application of Lajda’s criterion in dealing with regional hydrological data outliers[J]. Haihe Water Resources,2016(5):49−51.

[25] 李秉晨,于惠钧,丁华轩,等. 基于CEEMD和LSTM–ARIMA的短期风速预测[J]. 中国测试,2022,48(2):163−168.

LI Bingchen,YU Huijun,DING Huaxuan,et al. Short–term wind speed prediction based on CEEMD and LSTM−ARIMA[J]. China Measurement & Test,2022,48(2):163−168.

[26] IM K S,PESARAN M H,SHIN Y. Testing for unit roots in heterogeneous panels[J]. Journal of Econometrics,2003,115(1):53−74.

[27] 靳德武,李超峰,刘英锋,等. 黄陇煤田煤层顶板水害特征及其防控技术[J]. 煤田地质与勘探,2023,51(1):205−213.

JIN Dewu,LI Chaofeng,LIU Yingfeng,et al. Characteristics of roof water hazard of coal seam in Huanglong Coalfield and key technologies for prevention and control[J]. Coal Geology & Exploration,2023,51(1):205−213.

[28] 施龙青,王雅茹,邱梅,等. 时间序列模型在工作面涌水量预测中的应用[J]. 煤田地质与勘探,2020,48(3):108−115.

SHI Longqing,WANG Yaru,QIU Mei,et al. Application of time series model in water inflow prediction of working face[J]. Coal Geology & Exploration,2020,48(3):108−115.

[29] VANITHA V,SOPHIA J G,RESMI R,et al. Artificial intelligence–based wind forecasting using variational mode decomposition[J]. Computational Intelligence,2020,37(3):1034−1046.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.