考虑覆岩结构影响的近松散层开采导水裂隙带发育高度预测模型研究——以淮北煤田为例

陈陆望 王迎新 欧庆华 彭智宏 陈逸飞 李蕊瑞

陈陆望, 王迎新, 欧庆华, 等. 2021. 考虑覆岩结构影响的近松散层开采导水裂隙带发育高度预测模型研究——以淮北煤田为例[J]. 工程地质学报, 29(4): 1048-1056. doi: 10.13544/j.cnki.jeg.2021-0319
引用本文: 陈陆望, 王迎新, 欧庆华, 等. 2021. 考虑覆岩结构影响的近松散层开采导水裂隙带发育高度预测模型研究——以淮北煤田为例[J]. 工程地质学报, 29(4): 1048-1056. doi: 10.13544/j.cnki.jeg.2021-0319
Chen Luwang, Wang Yingxin, Ou Qinghua, et al. 2021. Prediction model for development height of water-conducting fractured zone during mining near loose stratum considering influence of overburden structure:A case study of Huaibei coalfield[J]. Journal of Engineering Geology, 29(4): 1048-1056. doi: 10.13544/j.cnki.jeg.2021-0319
Citation: Chen Luwang, Wang Yingxin, Ou Qinghua, et al. 2021. Prediction model for development height of water-conducting fractured zone during mining near loose stratum considering influence of overburden structure:A case study of Huaibei coalfield[J]. Journal of Engineering Geology, 29(4): 1048-1056. doi: 10.13544/j.cnki.jeg.2021-0319

考虑覆岩结构影响的近松散层开采导水裂隙带发育高度预测模型研究——以淮北煤田为例

doi: 10.13544/j.cnki.jeg.2021-0319
基金项目: 

国家自然科学基金 41972256

详细信息
    作者简介:

    陈陆望(1973-),男,博士,教授,博士生导师,主要从事煤矿防治水研究工作. E-mail: luwangchen8888@163.com

  • 中图分类号: TD12

PREDICTION MODEL FOR DEVELOPMENT HEIGHT OF WATER-CONDUCTING FRACTURED ZONE DURING MINING NEAR LOOSE STRATUM CONSIDERING INFLUENCE OF OVERBURDEN STRUCTURE: A CASE STUDY OF HUAIBEI COALFIELD

Funds: 

the National Natural Science Foundation of China 41972256

  • 摘要: 近松散层开采覆岩导水裂隙带沟通上覆含水层导致了顶板水害事故的发生。在其他开采因素相似时,工作面顶板覆岩结构的不同会致使导水裂隙带发育高度出现较大差异。为此,通过收集淮北煤田17例近松散层开采覆岩导水裂隙带发育高度实测数据作为训练样本,利用一行两列向量对近松散层工作面顶板覆岩结构进行量化,并联合煤层采厚、煤层倾角、工作面斜长、开采深度、松散层厚度共计6个影响因素作为输入数据,实测导水裂隙带发育高度作为输出数据,依据径向基函数神经网络建立了考虑覆岩结构影响的近松散层开采导水裂隙带发育高度预测模型。并将该预测模型应用于淮北煤田中的青东煤矿,经钻孔冲洗液漏失量与钻孔彩色电视观测验证,获得预测结果相对误差为3.3%,低于《“三下”开采规范》中经验公式计算误差19.2%。该方法为近松散层开采导水裂隙带发育高度的合理确定提供了理论支持。
  • 图  1  淮北煤田区域地质图

    Figure  1.  Regional geological map of Huaibei coalfield

    图  2  径向基函数神经网络结构示意图

    Figure  2.  Structure diagram of neural network with radial basis function

    图  3  径向基函数神经网络工作流程图

    Figure  3.  Working flow diagram of neural network with radial basis function

    图  4  祁东煤矿7130工作面典型钻孔顶板覆岩示意图

    Figure  4.  Roof overburden diagram of typical boreholes in the panel 7130 of the Qidong coal mine

    图  5  训练误差图

    Figure  5.  Training error diagram

    图  6  青东煤矿839工作面平面布置

    Figure  6.  Plane layout of the panel 839 of the Qingdong coal mine

    图  7  青东煤矿839工作面2018-水2钻孔柱状及覆岩导水裂隙带观测

    Figure  7.  Histogram of 2018-shui2 borehole in the panel 839 of the Qingdong coal mine and observation of water-conducting fractured zone in overburden

    表  1  近松散层开采导水裂隙带实测高度及其影响因素数据

    Table  1.   Measured heights of water-conducting fractured zone and its influencing factors in mining near loose layer

    工作面名称 采厚/m 倾角/(°) 工作面斜长/m 采深/m 松散层厚度/m 覆岩结构 实测高度/m
    祁东3222 2.4 12 153.4 -437.5 375.1 [1 12.7],[2 36.0],[1 12.0],
    [2 16.5],[1 10.2],[1 12.0]
    65.0
    祁东3224 2.7 12 181.0 -457.2 380.0 [1 12.4],[2 36.0],[1 16.2],
    [2 16.5],[1 12.8],[1 12.9]
    72.0
    祁东3241 2.3 12 184.0 -493.1 370.0 [3 3.3],[2 27.8],[3 10.2],
    [2 31.5],[1 6.6],[2 25.1]
    59.0
    祁东6130 3.0 13 125.2 -410.5 352.5 [1 8.8],[2 7.6],[1 4.8],
    [2 5.9],[1 4.8],[2 20.3]
    37.3
    祁东6131 1.7 13 182.7 -422.3 356.6 [3 5.4],[2 20.6],[3 5.7],
    [2 10.3],[1 8.5],[2 25.0]
    39.0
    祁东7112 1.9 10 173.8 -441.7 351.9 [1 26.1],[2 24.4],[1 9.8],
    [2 51.9],[1 9.0],[3 27.0]
    45.0
    祁东7121 2.6 11 127.3 -428.9 383.2 [1 6.2],[2 29.3],[1 4.9],
    [2 26.1],[3 21.8],[1 17.6]
    67.0
    祁东7122 2.7 12 56.3 -441.8 351.8 [3 14.6],[2 12.0],[3 15.4],
    [1 33.8],[2 4.6],[1 15.6]
    54.9
    祁东7130 2.9 12 168.7 -384.9 342.0 [2 5.2],[1 6.5],[3 7.2],
    [2 24.8],[1 8.4],[3 6.5]
    48.6
    五沟1016 3.2 10 182.8 -335.0 250.6 [2 7.6],[1 7.9],[2 17.2],
    [1 25.8],[3 14.0],[1 22.1]
    41.0
    五沟1033 3.1 11 137.5 -226.2 206.5 [2 24.8],[3 11.0],[1 11.5],
    [2 11.4],[1 33.9],[3 5.0]
    44.3
    桃园1062 3.0 28 158.6 -336.1 256.2 [3 7.7],[1 21.1],[2 5.9],
    [1 58.3],[2 13.6],[1 0]
    53.4
    祁南313 2.8 12 173.8 -310.5 242.8 [2 31.5],[1 6.2],[3 8.8],
    [1 0],[1 0],[1 0]
    32.0
    祁南6141 1.3 14 195.8 -357.3 280.5 [1 6.2],[3 17.3],[1 6.2],
    [2 7.6],[3 7.2],[1 8.8]
    27.0
    孙疃72111 2.2 18 192.4 -341.5 245.3 [1 16.1],[2 18.2],[3 7.8],
    [2 15.6],[1 8.9],[2 19.6]
    34.0
    袁二7232 4.1 17 201.8 -300.8 208.9 [2 12.6],[1 21.3],[3 11.6],
    [2 6.9],[1 8.9],[3 21.9]
    45.1
    袁二7218 3.5 15 144.9 -401.2 290.6 [1 16.3],[2 21.0],[3 10.6],
    [2 19.4],[1 11.4],[3 11.9]
    43.0
    下载: 导出CSV

    表  2  误差分析

    Table  2.   Error analysis

    方法 结果/m 相对误差
    现场实测 91.6
    模型预测 88.5 3.3%
    经验公式 74.0 19.2%
    下载: 导出CSV
  • Broomhead D, Lowe D. 1988. Multivariable functional interpolation and networks[J]. Complex System, 2 (3): 321-355. http://www.ams.org/mathscinet-getitem?mr=955557
    Cao Z B, Wang Q T. 2020. Development characteristics of water conducted fracture zone based on overburden structural effect[J]. Coal Geology & Exploration, 48 (3): 145-151.
    Chai H B, Zhang J P, Yan C. 2018. Prediction of water-flowing height in fractured zone of overburden strata based on GA- SVR[J]. Journal of Mining & Safety Engineering, 35 (2): 359-365.
    Du X, Sun Y F, Song Y P, et al. 2020. Multilayer perception neural network for assessment and prediction of earthquake-induced sand liquefaction[J]. Journal of Engineering Geology, 28(6): : 1425-1432.
    Guo C, Zhang H W, Song W H, et al. 2014. Application of entropy weight attribute measure theory for predicting the height of water flowing fractured zone[J]. Journal of Safety Science and Technology, 10 (12): 87-91. http://en.cnki.com.cn/Article_en/CJFDTOTAL-LDBK201412021.htm
    Hao B C. 2019. Intrusion detection system based on radial basis neural network[D]. Ningxia: North Minzu University.
    Hu X J, Li W P, Cao D T, et al. 2012. Index of multiple factors and expected height of fully mechanized water flowing fractured zone[J]. Journal of China Coal Society, 37 (4): 613-620. http://www.ingentaconnect.com/content/jccs/jccs/2012/00000037/00000004/art00014
    Li Y K. 2020. Research on trajectory control of excavator working device base on RBF neural network[D]. Xi'an: Xi'an University of Science and Technology.
    Li Z H, Xu Y C, Li L F, et al. 2015. Forecast of the height of water flowing fractured zone based on BP neural networks[J]. Journal of Mining & Safety Engineering, 32 (6): 905-910. http://www.researchgate.net/publication/288229798_Forecast_of_the_height_of_water_flowing_fractured_zone_based_on_BP_neural_networks
    Mao Z Y, Lai W Z, Huang C J. 2020. Prediction of height of water flowing fractured zone based on APSO-LSSVM model[J]. Journal of Liaoning Technical University(Natural Science Edition), 39 (1): 34-40.
    Park J, Sandberg I W. 1991. Universal approximation using radial-basis-function networks[J]. Neural Computation, 3 (2): 246-257. doi: 10.1162/neco.1991.3.2.246
    Powell M. 1987. Radial basis functions for multivariable interpolation: a review[J]. Algorithms for Approximation, 1 (1): 143-167. http://ci.nii.ac.jp/naid/10020691947
    Pu C Z, He G C, Zhu Z H. 2019. Test and characterization method for shear strength of slate containing weak intercalated layer[J]. Journal of Engineering Geology, 27 (3): 525-531. http://en.cnki.com.cn/Article_en/CJFDTotal-GCDZ201903008.htm
    Shao L S, Zhou Y. 2018. Application of QGA-RFR model in prediction of height of water flowing fractured zone[J]. China Safety Science Journal, 28 (3): 19-24.
    Shi L Q, Wu H B, Li Y L, et al. 2021. Optimization model of PCA-GA-Elman for development height prediction of water-conducting fissure zone[J]. Journal of Henan Polytechnic University(Natural Science), 40 (4): 10-18.
    Sui W H, Wang D D, Sun Y J, et al. 2019. Mine hydrogeological structure and its responses to mining[J]. Journal of Engineering Geology, 27 (1): 21-28. http://en.cnki.com.cn/Article_en/CJFDTotal-GCDZ201901003.htm
    Wang H B, Gao R B, Mao Z M. 2009. Two types of structural patterns of soft overburden and their inhibition to the height of water flowing fracture zone[J]. Energy Technology and Management, (3): 10-12. http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0716-97602009000300007&lng=en&nrm=iso&tlng=en
    Wang J T, Guo G L, Guo Q B. 2016. Application of grey system theory and GA-BP neural network model in control and prediction of water-flowing fractured zone's height[J]. Coal Technology, 35 (8): 126-128. http://en.cnki.com.cn/Article_en/CJFDTOTAL-MTJS201608052.htm
    Wang W, Guo Y, Fang Z N. 2020. Simulation on main controlling factors of development height of fully-mechanized water flowing fracture zone[J]. Mining Research and Development, 40 (10): 51-55.
    Wu Z S, Wang S Q, Peng T, et al. 2019. Numerical simulation on influencing factors of water flowing fractured zone development in Caojiatan coal mine[J]. Science Technology and Engineering, 19 (25): 125-129. http://en.cnki.com.cn/Article_en/CJFDTotal-KXJS201925018.htm
    Xiao C N, Lu W X, Zhao Y, et al. 2016. Optimization method of identification of groundwater pollution sources based on radial basis function model[J]. China Environmental Science, 36 (7): 2067-2072. http://www.researchgate.net/publication/306145619_Optimization_method_of_identification_of_groundwater_pollution_sources_based_on_radial_basis_function_model
    Xu J L, Zhu W B, Wang X Z. 2012. New method to predict the height of fractured water-conducting zone by location of key strata[J]. Journal of China Coal Society, 37 (5): 762-769.
    Xu S Y, Zhang Y B, Shi H, et al. 2018. Advances in the height of fractured water-conducting zone of mining overburden[J]. Science Technology and Engineering, 18 (34): 139-148. http://en.cnki.com.cn/Article_en/CJFDTotal-KXJS201834020.htm
    Xu W, Liu D W, Ying S X, et al. 2019. Study on development law of water-conductive fracture zone in 28806 working face of Dongqu mine[J]. Coal Technology, 38 (9): 118-121. http://en.cnki.com.cn/Article_en/CJFDTotal-MTJS201909040.htm
    Xue J K, Wang H, Zhao C H, et al. 2020. Prediction of the height of water-conducting fracture zone and water-filling model of roof aquifer in Jurassic coalfield in Ordos Basin[J]. Journal of Mining & Safety Engineering, 37 (6): 1222-1230.
    Yang G Y, Chen C, Gao S L, et al. 2015. Study on the height of water flowing fractured zone based on analytic hierarchy process and fuzzy clustering analysis method[J]. Journal of Mining & Safety Engineering, 32 (2): 206-212. http://en.cnki.com.cn/Article_en/CJFDTOTAL-KSYL201502006.htm
    Yang K, Xie G X. 2008. Caving thickness effects on distribution and evolution characteristics of mining induced fracture[J]. Journal of China Coal Society, 33 (10): 1092-1096. http://www.researchgate.net/publication/286877357_Caving_thickness_effects_on_distribution_and_evolution_characteristics_of_mining_induced_fracture
    Yang Y G, Wang J, Yu Y J. 2015. Effects of different coal safe mining sequence under river on height of water flowing fracture zone[J]. Journal of China Coal Society, 40 (S1): 27-32. http://en.cnki.com.cn/Article_en/CJFDTotal-MTXB2015S1005.htm
    Zhang H W, Zhu Z J, Huo B J, et al. 2013. Water flowing fractured zone height prediction based on improved FOA- SVM[J]. China Safety Science Journal, 23 (10): 9-14. http://en.cnki.com.cn/Article_en/CJFDTOTAL-ZAQK201310002.htm
    Zhu C H, Zhang J J, Ma D H, et al. 2020. Comprehensive analysis on risk of landslides in post-earthquake area based on DinSAR-BP neural networks[J]. Journal of Engineering Geology, 28 (3): 530-540.
    曹祖宝, 王庆涛. 2020. 基于覆岩结构效应的导水裂隙带发育特征[J]. 煤田地质与勘探, 48 (3): 145-151. doi: 10.3969/j.issn.1001-1986.2020.03.021
    柴华彬, 张俊鹏, 严超. 2018. 基于GA-SVR的采动覆岩导水裂隙带高度预测[J]. 采矿与安全工程学报, 35 (2): 359-365. https://www.cnki.com.cn/Article/CJFDTOTAL-KSYL201802018.htm
    杜星, 孙永福, 宋玉鹏, 等. 2020. 基于MPL神经网络的地震作用下砂土液化评估及预测[J]. 工程地质学报, 28 (6): 1425-1432. doi: 10.13544/j.cnki.jeg.2019-321
    郭超, 张宏伟, 宋卫华, 等. 2014. 熵权属性测度理论在导水裂隙带高度预测中的应用[J]. 中国安全生产科学技术, 10 (12): 87-91. https://www.cnki.com.cn/Article/CJFDTOTAL-LDBK201412021.htm
    郝博超. 2019. 基于径向基神经网络的入侵检测系统[D]. 宁夏: 北方民族大学.
    胡小娟, 李文平, 曹丁涛, 等. 2012. 综采导水裂隙带多因素影响指标研究与高度预计[J]. 煤炭学报, 37 (4): 613-620. https://www.cnki.com.cn/Article/CJFDTOTAL-MTXB201204016.htm
    李远凯. 2020. 基于RBF神经网络的挖掘机工装轨迹控制研究[D]. 西安: 西安科技大学.
    李振华, 许延春, 李龙飞, 等. 2015. 基于BP神经网络的导水裂隙带高度预测[J]. 采矿与安全工程学报, 32 (6): 905-910. https://www.cnki.com.cn/Article/CJFDTOTAL-KSYL201506007.htm
    毛志勇, 赖文哲, 黄春娟. 2020. 基于APSO-LSSVM模型的导水裂隙带高度预测[J]. 辽宁工程技术大学学报(自然科学版), 39 (1): 34-40. https://www.cnki.com.cn/Article/CJFDTOTAL-FXKY202001006.htm
    蒲成志, 贺桂成, 朱忠华. 2019. 含软弱夹层板岩抗剪强度试验及表征方法[J]. 工程地质学报, 27 (3): 525-531. doi: 10.13544/j.cnki.jeg.2018-219
    邵良杉, 周玉. 2018. QGA-RFR模型在导水裂隙带高度预测中的应用[J]. 中国安全科学学报, 28 (3): 19-24. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201803004.htm
    施龙青, 吴洪斌, 李永雷, 等. 2021. 导水裂隙带发育高度预测的PCA-GA-Elman优化模型[J]. 河南理工大学学报(自然科学版), 40 (4): 10-18. https://www.cnki.com.cn/Article/CJFDTOTAL-JGXB202104002.htm
    隋旺华, 王丹丹, 孙亚军, 等. 2019. 矿山水文地质结构及其采动响应[J]. 工程地质学报, 27 (1): 21-28. doi: 10.13544/j.cnki.jeg.2019-072
    王惠兵, 高荣斌, 毛增民. 2009. 软弱覆岩的两类结构模式及对导水裂缝带高度的抑制性[J]. 能源技术与管理, (3): 10-12. doi: 10.3969/j.issn.1672-9943.2009.03.004
    王金涛, 郭广礼, 郭庆彪. 2016. 灰色系统理论与GA-BP网络模型在导高控制和预测中的应用[J]. 煤炭技术, 35 (8): 126-128. https://www.cnki.com.cn/Article/CJFDTOTAL-MTJS201608052.htm
    王玮, 郭玉, 方忠年. 2020. 综采导水裂隙带发育高度主控因素模拟研究[J]. 矿业研究与开发, 40 (10): 51-55. https://www.cnki.com.cn/Article/CJFDTOTAL-KYYK202010010.htm
    武忠山, 王生全, 彭涛, 等. 2019. 曹家滩煤矿导水裂隙带发育规律影响因素数值模拟[J]. 科学技术与工程, 19 (25): 125-129. doi: 10.3969/j.issn.1671-1815.2019.25.018
    肖传宁, 卢文喜, 赵莹, 等. 2016. 基于径向基函数模型的优化方法在地下水污染源识别中的应用[J]. 中国环境科学, 36 (7): 2067-2072. doi: 10.3969/j.issn.1000-6923.2016.07.023
    徐树媛, 张永波, 时红, 等. 2018. 采动覆岩导水裂隙带发育高度研究进展[J]. 科学技术与工程, 18 (34): 139-148. doi: 10.3969/j.issn.1671-1815.2018.34.020
    徐维, 刘德旺, 尹尚先, 等. 2019. 东曲矿28806工作面导水裂隙带发育规律研究[J]. 煤炭技术, 38 (9): 118-121. https://www.cnki.com.cn/Article/CJFDTOTAL-MTJS201909040.htm
    许家林, 朱卫兵, 王晓振. 2012. 基于关键层位置的导水裂隙带高度预计方法[J]. 煤炭学报, 37 (5): 762-769. https://www.cnki.com.cn/Article/CJFDTOTAL-MTXB201205011.htm
    薛建坤, 王皓, 赵春虎, 等. 2020. 鄂尔多斯盆地侏罗系煤田导水裂隙带高度预测及顶板充水模式[J]. 采矿与安全工程学报, 37 (6): 1222-1230. https://www.cnki.com.cn/Article/CJFDTOTAL-KSYL202006018.htm
    杨国勇, 陈超, 高树林, 等. 2015. 基于层次分析-模糊聚类分析法的导水裂隙带发育高度研究[J]. 采矿与安全工程学报, 32 (2): 206-212. https://www.cnki.com.cn/Article/CJFDTOTAL-KSYL201502006.htm
    杨科, 谢广祥. 2008. 采动裂隙分布及其演化特征的采厚效应[J]. 煤炭学报, 33 (10): 1092-1096. doi: 10.3321/j.issn:0253-9993.2008.10.003
    杨艳国, 王军, 于永江. 2015. 河下多煤层安全开采顺序对导水裂隙带高度的影响[J]. 煤炭学报, 40 (S1): 27-32. https://www.cnki.com.cn/Article/CJFDTOTAL-MTXB2015S1005.htm
    张宏伟, 朱志洁, 霍丙杰, 等. 2013. 基于改进的FOA-SVM导水裂隙带高度预测研究[J]. 中国安全科学学报, 23 (10): 9-14. doi: 10.3969/j.issn.1003-3033.2013.10.002
    朱崇浩, 张建经, 马东华, 等. 2020. 基于DinSAR-BP神经网络的震后区域滑坡危险性综合评价研究[J]. 工程地质学报, 28 (3): 530-540. doi: 10.13544/j.cnki.jeg.2019-132
  • 加载中
图(7) / 表(2)
计量
  • 文章访问数:  56
  • HTML全文浏览量:  47
  • PDF下载量:  35
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-06-08
  • 修回日期:  2021-07-13
  • 网络出版日期:  2021-09-03
  • 刊出日期:  2021-09-03

目录

    /

    返回文章
    返回