Coal mine water inrush prediction based on LSTM neural network

Authors

DONG Lili, School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China
FEI Cheng, School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China
ZHANG Xiang, School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China
CAO Chaofan, School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China

Abstract

According to the prediction of water inrush from coal seam floor, based on the summarization of existing water inrush prediction methods and theories, the feature selection experiment shows that water pressure, distance from the working surface, sandstone section thickness, coal thickness, coal seam inclination, fault throw, fissure zone, mining area, mining height and strike length are the main factors affecting the occurrence of water inrush. These factors are complex and non-linear. A water inrush prediction model based on long short-term memory(LSTM) neural network was proposed. The data of the coal mine water inrush case was used as sample data to train the model. Finally, the LSTM neural network model is compared with the genetic algorithm-back propagation(GA-BP) neural network model and back propagation(BP) neural network model. The experimental results show that the LSTM neural network model has higher prediction accuracy, better stability, and is more suitable for coal seam floor water inrush prediction.

Keywords

long short-term memory, feature selection, prediction of water inrush from coal seam floor

DOI

10.3969/j.issn.1001-1986.2019.02.021

Recommended Citation

DONG Lili, FEI Cheng, ZHANG Xiang, et al. (2019) "Coal mine water inrush prediction based on LSTM neural network," Coal Geology & Exploration: Vol. 47: Iss. 2, Article 22.
DOI: 10.3969/j.issn.1001-1986.2019.02.021
Available at: https://cge.researchcommons.org/journal/vol47/iss2/22

Reference

[1] 孙继平. 煤矿自动化与信息化技术回顾与展望[J]. 工矿自动化,2010,36(6):26-30. SUN Jiping. Review and prospect of technologies of automation and informatization of coal mine[J]. Industry and Mine Automation,2010,36(6):26-30.

[2] 宋国娟. 基于极限学习机的煤矿突水预测及避险路线优化研究[D]. 徐州:中国矿业大学,2016.

[3] 乔育锋. 遗传算法和BP神经网络在煤矿突水预测中的应用研究[D]. 西安:西安建筑科技大学,2011.

[4] 杜春蕾,张雪英,李凤莲. 改进的CART算法在煤层底板突水预测中的应用[J]. 工矿自动化,2014,40(12):52-56. DU Chunlei,ZHANG Xueying,LI Fenglian. Application of improved CART algorithm in prediction of water inrush from coal seam floor[J]. Industry and Mine Automation,2014,40(12):52-56.

[5] 刘伟韬,廖尚辉,刘士亮,等. 主成分logistic回归分析在底板突水预测中的应用[J]. 辽宁工程技术大学学报(自然科学版),2015,34(8):905-909. LIU Weitao,LIAO Shanghui,LIU Shiliang,et al. Principal component logistic regression analysis in application of water outbursts from coal seam floor[J]. Journal of Liaoning Technical University,2015,34(8):905-909.

[6] 刘再斌,靳德武,刘其声. 基于二项logistic回归模型与CART树的煤层底板突水预测[J]. 煤田地质与勘探,2009,37(1):56-61. LIU Zaibin,JIN Dewu,LIU Qisheng. Prediction of water inrush from seam floor based on binomial logistic regression model and CART tree[J]. Coal Geology & Exploration,2009,37(1):56-61.

[7] LIU Zaibin,JIN Dewu,LIU Qisheng. Prediction of water inrush through coal floors based on data mining classification technique[J]. Procedia Earth & Planetary Science,2011,3:166-174.

[8] LI Fengjun,ZHENG Jidong. The prediction and forecast of coal floor water-inrush based on GIS:A case study on the I-1 mining district in the 5# coal mine in Pingdingshan ar-ea[C]//International Conference on Environmental Science and Information Application Technology. IEEE,2010:663-666.

[9] 李培. 基于PCA-ELM的预测模型在煤矿突水预测中的应用[D]. 徐州:中国矿业大学,2014.

[10] ZHAO Zuopeng,HU Mengke. Multi-level forecasting model of coal mine water inrush based on self-adaptive evolutionary extreme learning machine[J]. Applied Mathematics & Information Sciences Letters,2014,2(3):103-110.

[11] ZHAO Z,LI P,XU X. Forecasting model of coal mine water inrush based on extreme learning machine[J]. Applied Mathematics & Information Sciences,2013,7(3):1243-1250.

[12] 闫志刚,白海波,张海荣. 一种新型的矿井突水分析与预测的支持向量机模型[J]. 中国安全科学学报,2008,18(7):166-170. YAN Zhigang,BAI Haibo,ZHANG Hairong. A novel SVM model for the analysis and prediction of water inrush from coal mine[J]. Journal of Chinese Security Science,2008,18(7):166-170.

[13] 张晓亮. 熵权耦合层次分析赋权在煤层底板突水评价中的应用[J]. 煤田地质与勘探,2017,45(3):91-95. ZHANG Xiaoliang. Application of entropy weight method and analytic hierarchy process in evaluation of water inrush from coal seam floor[J]. Coal Geology & Exploration,2017,45(3):91-95.

[14] 代革联,薛小渊,许珂,等. 基于脆弱性指数法的韩城矿区11号煤层底板突水危险性评价[J]. 煤田地质与勘探,2017,45(4):112-117. DAI Gelian,XUE Xiaoyuan,XU Ke,et al. Risk assessment of water inrush of No.11 coal seam floor in Hancheng mining area on the basis of vulnerability index method[J]. Coal Geology & Exploration,2017,45(4):112-117.

[15] JIN Dewu,ZHENG Gang,LIU Zaibin,et al. Real-Time Monitoring and early warning techniques of water inrush through coal floor[J]. Procedia Earth & Planetary Science,2011,3:37-46.

[16] 施龙青. 突水系数由来及其适用性分析[J]. 山东科技大学学报(自然科学版),2012,31(6):6-9. SHI Longqing. Analysis of water inrush coefficient and its applicability[J]. Journal of Shandong University of Science and Technology,2012,31(6):6-9.

[17] 黄浩,王经明. 煤层底板隐伏断层突水的物理实验研究[J]. 华北科技学院学报,2015,12(1):11-16. HUANG Hao,WANG Jingming. Research on water inrush from the blind fault of coal floor by physical experiment[J]. Journal of North China Institute of Science and Technology (Natural Science),2015,12(1):11-16.

[18] 尹立明. 深部煤层开采底板突水机理基础实验研究[D]. 青岛:山东科技大学,2011.

[19] 张玉军. 煤层底板综合隔水性能及突水危险性预测研究[D]. 北京:煤炭科学研究总院,2012.

[20] 段宏飞. 煤矿底板采动变形及带压开采突水评判方法研究[D]. 徐州:中国矿业大学,2012.

[21] MALHOTRA P,VISHNU T V,RAMAKRISHNAN A,et al. Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder[J]. arXiv Preprint arXiv:1608.06154,2016.

[22] 孙瑞奇. 基于LSTM神经网络的美股股指价格趋势预测模型的研究[D]. 北京:首都经济贸易大学,2016.

[23] GERHARDT L. Pattern recognition and machine learning[M]. Cambridge:Academic Press,1992.

[24] HARRIS D M,HARRIS S L. Digital design and computer architecture[M]. Massachusetts:Morgan Kaufmann,2012.

[25] 姚旭,王晓丹,张玉玺,等. 特征选择方法综述[J]. 控制与决策,2012,27(2):161-166. YAO Xu,WANG Xiaodan,ZHANG Yuxi,et al. Review of feature selection methods[J]. Control and Decision,2012,27(2):161-166.

[26] 杨柳,王钰. 泛化误差的各种交叉验证估计方法综述[J]. 计算机应用研究,2015,32(5):1287-1290. YANG Liu,WANG Yu. Survey for various cross-validation estimators of generalization error[J]. Application Research of Computers,2015,32(5):1287-1290.

[27] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. Delving deep into rectifiers:Surpassing human-level performance on Image Net classification[C]//IEEE International Conference on Computer Vision. IEEE,2015:1026-1034.

[28] NAIR V,HINTON G E. Rectified linear units improve re-stricted boltzmann machines[C]//International Conference on International Conference on Machine Learning. Omnipress,2010:807-814.

[29] RUDER S. An overview of gradient descent optimization algorithms[J]. arXiv Preprint arXiv:1609.04747,2016.

[30] HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science,2012,3(4):212-223.