Direct current resistivity method for the advance prediction of water Hazards in coal mines based on an artificial neural network
-
摘要:
矿井直流电阻率法具有施工效率高、成本低的特点，广泛应用于煤矿掘进工作面水害超前探测。随着应用的不断深入，对矿井直流电阻率法超前探测信号处理方法提出了更高的要求。基于有限元方法和数据重构所得响应信息库，采用Levenberg-Marquardt人工神经网络方法实现了矿井直流电阻率法超前预测。首先采用非结构网格剖分和BiCGSTAB迭代有限元法建立了直流电阻率法超前探测模型，基于EMD方法实现数值计算响应与实测响应匹配，并提出了基于异常体超前距离与其异常率的预测机制，得到3 000组23维重构响应；然后，采用L-M算法构建了人工神经网络模型；最后，基于训练好的网络对数值计算响应和实测数据进行预测分析。研究表明：针对数值模拟响应，基于L-M人工神经网络的矿井直流电阻率法超前预测方法可有效预测100 m范围内的水害异常，预测网络均方误差为0.002 47，测试样本显示最大距离误差小于0.6 m；针对实测数据发现，该神经网络在全区段预测准确率为67%，当预测异常位置在15~80 m时预测准确率超过85%，基于L-M算法的人工神经网络可应用于直流电阻率法超前预测。研究成果对煤矿井下掘进工作面直流电阻率法超前探测方法的完善与推广应用有重要意义。
Abstract:The mine Direct Current (DC) resistivity method has the characteristics of high construction efficiency and low cost, which is widely used in the advanced detection of water hazards in coal mine heading face.With the continuous deepening of applications, higher requirements have been put forward for the advanced detection signal processing method of mine DC resistivity method. Based on the response information database obtained by finite element method and data reconstruction, the Levenberg-Marquardt (L-M) artificial neural network method is used to realize the advanced prediction of mine DC resistivity method. First, this study established an advanced prediction model of the DC resistivity method using unstructured mesh and iterative finite element method BiCGSTAB; matched the numerically simulated responses with the measured responses using the empirical mode decomposition (EMD) method; and proposed the prediction mechanism based on the advance detection distance and anomaly rate. As a result, 3 000 sets of 23-dimensional reconstructed responses were obtained. Subsequently, the artificial neural network model is constructed by L-M algorithm. Finally, using the trained artificial neural network, this study predicted the water hazards at the heading face based on the measured data and numerically simulated responses. The results of this study are as follows: (1) For the numerically simulated responses, the mine DC resistivity method based on the L-M artificial neural network can effectively detect the water hazard anomalies within the advance detection distance of 100 m. The mean square error in the detection was 0.002 47, and test samples exhibited that the maximum error of the advance detection distance was less than 0.6 m; (2) As shown by the measured data, the accuracy rate of the detection was 67% in the whole study and was higher than 85% for water hazard anomalies at the advance detection distance of 15-80 m. Therefore, the L-M artificial neural network can be applied to the advance prediction of water disasters based on the mine DC resistivity method. The research results are of great significance for the improvement and wide applications of the mine DC resistivity method-based advance detection of water hazards at the heading face of coal mines.
-
-
![]()
图 1 直流电阻率超前探测几何示意
Fig. 1 Geometric of the advanced detection using the DC resistivity method
![]()
图 2 有限元直流电阻率超前探测模型网格剖分
Fig. 2 Finite element mesh generation for the DC resistivity method-based advance detection model
-
[1] 程久龙,李飞,彭苏萍,等. 矿井巷道地球物理方法超前探测研究进展与展望[J]. 煤炭学报,2014,39(8):1742−1750. CHENG Jiulong,LI Fei,PENG Suping,et al. Research progress and development direction on advanced detection in mine roadway working face using geophysical methods[J]. Journal of China Coal Society,2014,39(8):1742−1750.
[2] 韩德品,李丹,程久龙,等. 超前探测灾害性含导水地质构造的直流电法[J]. 煤炭学报,2010,35(4):635−639. HAN Depin,LI Dan,CHENG Jiulong,et al. DC method of advanced detecting disastrous water–conducting or water–bearing geological structures along same layer[J]. Journal of China Coal Society,2010,35(4):635−639.
[3] 程建远,聂爱兰,张鹏. 煤炭物探技术的主要进展及发展趋势[J]. 煤田地质与勘探,2016,44(6):136−141. CHENG Jianyuan,NIE Ailan,ZHANG Peng. Outstanding progress and development trend of coal geophysics[J]. Coal Geology & Exploration,2016,44(6):136−141.
[4] 于景邨,刘振庆,廖俊杰,等. 全空间瞬变电磁法在煤矿防治水中的应用[J]. 煤炭科学技术,2011,39(9):110−113. YU Jingcun,LIU Zhenqing,LIAO Junjie,et al. Application of full space transient electromagnetic method to mine water prevention and control[J]. Coal Science and Technology,2011,39(9):110−113.
[5] 刘青雯. 井下电法超前探测方法及其应用[J]. 煤田地质与勘探,2001,29(5):60−62. LIU Qingwen. Underground electrical lead survey method and its application[J]. Coal Geology & Exploration,2001,29(5):60−62.
[6] 韩德品,石学锋,石显新,等. 煤矿老窑积水巷道直流电法超前探测异常特征研究[J]. 煤炭科学技术,2019,47(4):157−161. HAN Depin,SHI Xuefeng,SHI Xianxin,et al. Study on anomaly characteristics of in−advance DC electric detection of water–accumulated roadway in abandoned coal mines[J]. Coal Science and Technology,2019,47(4):157−161.
[7] 张萍芳,高建中,徐少华. 焦作矿区电法探测导、含水构造的效果[J]. 煤田地质与勘探,1997,25(5):40−43. ZHANG Pingfang,GAO Jianzhong,XU Shaohua. The effect of DC method used to detect water–transmitting and water–bearing structure in Jiaozuo mining area[J]. Coal Geology & Exploration,1997,25(5):40−43.
[8] 程久龙,王玉和,于师建,等. 巷道掘进中电阻率法超前探测原理与应用[J]. 煤田地质与勘探,2000,28(4):60−62. CHENG Jiulong,WANG Yuhe,YU Shijian,et al. The principle and application of advance surveying in roadway excavation by resistivity method[J]. Coal Geology & Exploration,2000,28(4):60−62.
[9] 高致宏,王信文,何继宾,等. 电法超前探测技术与矿井含水构造精细探测[J]. 煤矿安全,2006,37(9):29−31. GAO Zhihong,WANG Xinwen,HE Jibin,et al. DC method detection technology and application in detailed detection[J]. Safety in Coal Mines,2006,37(9):29−31.
[10] 黄俊革,王家林,阮百尧. 坑道直流电阻率法超前探测研究[J]. 地球物理学报,2006,49(5):1529−1538. HUANG Junge,WANG Jialin,RUAN Baiyao. A study on advanced detection using DC resistivity method in tunnel[J]. Chinese Journal of Geophysics,2006,49(5):1529−1538.
[11] 李飞,程久龙,谭强,等. 巷道掘进中电阻率法超前探测研究[J]. 煤矿安全,2012,43(7):30−34. LI Fei,CHENG Jiulong,TAN Qiang,et al. Study on advanced detection by resistivity method in roadway excavation[J]. Safety in Coal Mines,2012,43(7):30−34.
[12] 张平松,李永盛,胡雄武. 巷道掘进直流电阻率法超前探测技术应用探讨[J]. 地下空间与工程学报,2013,9(1):135−140. ZHANG Pingsong,LI Yongsheng,HU Xiongwu. Application and discussion of the advanced detection technology with DC resistivity method in tunnel[J]. Chinese Journal of Underground Space and Engineering,2013,9(1):135−140.
[13] 强建科,阮百尧,周俊杰,等. 煤矿巷道直流三极法超前探测的可行性[J]. 地球物理学进展,2011,26(1):320−326. QIANG Jianke,RUAN Baiyao,ZHOU Junjie,et al. The feasibility of advanced detection using DC three−electrode method in coal−mine tunnel[J]. Progress in Geophysics,2011,26(1):320−326.
[14] 罗国平. 直流电阻率三极超前探测的有效性[J]. 中国煤炭地质,2017,29(3):72−75. LUO Guoping. Effectiveness of DC resistivity trielectrode advanced prospecting[J]. Coal Geology of China,2017,29(3):72−75.
[15] 李飞,张永超,连会青,等. 掘进工作面直流电法超前探测技术问题探讨[J]. 煤炭科学技术,2020,48(12):250−256. LI Fei,ZHANG Yongchao,LIAN Huiqing,et al. Discussion on problems of direct current advance detection method in roadway driving face[J]. Coal Science and Technology,2020,48(12):250−256.
[16] 王鹏,鲁晶津,王信文. 再论巷道直流电法超前探测技术的有效性[J]. 煤炭科学技术,2020,48(12):257−263. WANG Peng,LU Jingjin,WANG Xinwen. Restudy on effectivity of direct current advance detection method in roadway[J]. Coal Science and Technology,2020,48(12):257−263.
[17] NEYAMADPOUR A,ABDULLAH W A T W,TAIB S,et al. 3D inversion of DC data using artificial neural networks[J]. Studia Geophysica et Geodaetica,2010,54(3):465−485. DOI: 10.1007/s11200-010-0027-5
[18] 高明亮,于生宝,郑建波,等. 基于IGA算法的电阻率神经网络反演成像研究[J]. 地球物理学报,2016,59(11):4372−4382. DOI: 10.6038/cjg20161136 GAO Mingliang,YU Shengbao,ZHENG Jianbo,et al. Research of resistivity imaging using neural network based on immune genetic algorithm[J]. Chinese Journal of Geophysics,2016,59(11):4372−4382. DOI: 10.6038/cjg20161136
[19] JIANG Feibo,DONG Li,DAI Qianwei. Electrical resistivity imaging inversion:An ISFLA trained kernel principal component wavelet neural network approach[J]. Neural Networks,2018(104):114−123.
[20] 吴易智,范宜仁,巫振观,等. 基于卷积神经网络和MPGA–LM算法的阵列侧向测井快速反演方法[J]. 地球物理学报,2021,64(9):3410−3425. WU Yizhi,FAN Yiren,WU Zhenguan,et al. A fast inversion method for array laterolog based on convolutional neural network and hybrid MPGA−LM algorithm[J]. Chinese Journal of Geophysics,2021,64(9):3410−3425.
[21] RUCKER C,GUNTHER T,SPITZER K. Three–dimensional modelling and inversion of dc resistivity data incorporating topography–I. Modelling[J]. Geophysical Journal International,2006,166:495−505. DOI: 10.1111/j.1365-246X.2006.03010.x
[22] 任政勇,汤井田. 基于局部加密非结构化网格的三维电阻率法有限元数值模拟[J]. 地球物理学报,2009,52(10):2627−2634. REN Zhengyong,TANG Jingtian. Finite element modeling of 3–D DC resistivity using locally refined unstructured meshes[J]. Chinese Journal of Geophysics,2009,52(10):2627−2634.
[23] 刘洋. 基于非结构网格的电阻率三维正反演及其应用研究[D]. 合肥: 中国科学技术大学, 2016. LIU Yang. Study of 3D resistivity modeling and inversion using unstructured grids and their applications[D]. Hefei: University of Science and Technology of China, 2016.
[24] VORST H A V D. Bi–CGSTAB:A fast and smoothly converging variant of Bi–CG for the solution of nonsymmetric linear systems[J]. SIAM Journal on Scientific and Statistical Computing,1992,13(2):631−644. DOI: 10.1137/0913035
[25] 李金铭. 地电场与电法勘探[M]. 北京: 地质出版社, 2005. [26] 王婷. EMD算法研究及其在信号去噪中的应用[D]. 哈尔滨: 哈尔滨工程大学, 2010. WANG Ting. Research on EMD algorithm and its application in signal denoising[D]. Harbin: Harbin Engineering University, 2010.
[27] 张峤,邓贵仕. Levenberg–Marquardt神经网络在煤矿作业人员人因可靠性评价中应用研究[J]. 大连理工大学学报,2015,55(4):424−430. ZHANG Qiao,DENG Guishi. Investigation on application of Levenberg–Marquardt neural networks to human reliability evaluation of coalmine workers[J]. Journal of Dalian University of Technology,2015,55(4):424−430.
[28] 彭星煜,刘力升,吕娜,等. 基于BP神经网络的油气长输管道失效概率预测[J]. 全面腐蚀控制,2009,23(5):12−16. PENG Xingyu,LIU Lisheng,LYU Na,et al. Long−distance oil/gas pipeline failure rate prediction using BP artificial neural network model[J]. Total Corrosion Control,2009,23(5):12−16.
[29] 闫滨,高真伟,强丽峰. 基于L–M算法的BP神经网络在大坝安全监控预报中的应用[J]. 沈阳农业大学学报,2009,40(4):506−509. YAN Bin,GAO Zhenwei,QIANG Lifeng. Application of BP neural network based on Levenberg–Marquardt algorithm in prediction of dam safety monitoring[J]. Journal of Shenyang Agricultural University,2009,40(4):506−509.
[30] 赵弘,周瑞祥,林廷圻. 基于Levenberg–Marquardt算法的神经网络监督控制[J]. 西安交通大学学报,2002,36(5):523−527. ZHAO Hong,ZHOU Ruixiang,LIN Tingqi. Neural network supervised control based on Levenberg–Marquardt algorithm[J]. Journal of Xi’an Jiaotong University,2002,36(5):523−527.
-
期刊类型引用(17)
1. 李昊，李叶繁，魏长婧，王磊杰，康利军，姜川. 基于SBAS-InSAR技术的登封市潜在地质灾害识别研究. 河南科学. 2024(08): 1170-1178 . 
百度学术
2. 汪晨星，史凌亚，李瑞东. 基于Stacking-InSAR的煤矿沉降监测与综采面参数反演. 陕西煤炭. 2024(10): 14-20 . 百度学术
3. 张学辉，崔振东，张中俭，赵磊磊，魏涛，刘东旭，王龙灿. 基于SBAS-InSAR技术的新疆某煤矿长时序地表形变监测与分析. 新疆地质. 2024(03): 459-465 . 百度学术
4. 姜川，王磊杰，樊高强，李昊，李叶繁，苑雨，张曦. 基于SBAS-InSAR的郑州煤炭矿区地表沉降监测及演化规律分析. 中国煤炭. 2024(10): 158-165 . 百度学术
5. 任瑶瑶，刘国林，牛冲，韩宇，周一鸣. 基于MSBAS InSAR技术的沧州市地表形变监测与分析. 地球物理学进展. 2023(02): 588-599 . 百度学术
6. 孙晓云. 基于InSAR和微震技术矿区非法开采事件监测技术探讨和应用. 内蒙古煤炭经济. 2023(03): 113-117 . 百度学术
7. 于冰，胡云亮，刘国祥，罗小军，胡金龙. 时序InSAR反演唐山市二维地表形变时间序列. 测绘科学. 2023(06): 82-94+230 . 百度学术
8. 孙军，张锦. 基于SBAS-InSAR和偏移追踪技术的露天煤矿地面形变监测. 煤矿安全. 2022(03): 162-169 . 百度学术
9. 陈宗玥. 基于图像识别的大型建筑钢结构形变监测研究. 测绘技术装备. 2022(01): 17-21 . 百度学术
10. 高宏伟，史先琳，陈晨，尹勇，戴可人. 云南漾濞地震地表二维形变提取. 昆明理工大学学报(自然科学版). 2022(02): 57-64 . 百度学术
11. 王凤云，陶秋香，陈洋，韩宇，郭在洁. 基于InSAR的煤矿采空区地表形变监测与预警. 煤矿安全. 2022(06): 195-203 . 百度学术
12. 贺黎明，裴攀科，吴立新，张香凝. 基于时序InSAR的矿区滑坡前地表运动特征分析. 东北大学学报(自然科学版). 2022(09): 1314-1321+1368 . 百度学术
13. 胡华宗. 基于无人机遥感技术的矿井地面塌陷综合监测. 能源与环保. 2022(09): 85-89 . 百度学术
14. 刘健，周皓，张恩正. 基于机器学习的煤矿开采沉陷自动化监测系统. 信息技术. 2022(11): 143-148+154 . 百度学术
15. 白洁. 基于机器视觉的测绘工程地面位移形变测量方法. 经纬天地. 2021(02): 93-97 . 百度学术
16. 姚鑫，吴付英. 基于GIS技术的矿区开采沉陷形变监测系统设计. 矿产与地质. 2021(03): 549-553+573 . 百度学术
17. 高文，王华，侯凌志. 矿山地质灾害监测方法与自动化监测预警系统应用. 西部资源. 2020(06): 66-68 . 百度学术
其他类型引用(3)
下载:
计量
- 文章访问数: 191
- HTML全文浏览量: 19
- PDF下载量: 32
- 被引次数: 20
