煤矿防治水智能化技术与装备研究现状及展望
|
摘要
为了解决煤矿充水条件的精准探测、有效预测、动态监测和水害的可靠治理问题,人工智能和信息化技术在我国煤矿水害防治技术和装备中获得广泛应用并取得重要进展。依据智能感知、智能判断和智能执行等智能化技术三要素,将煤矿防治水智能化定义为水害致灾因素的有效筛选、自动识别和精准控制的过程。从5个方面系统地总结了煤矿防治水智能化技术现状:即探测装备的智能化芯片应用及数据处理智能算法、含水层富水性分区的信息融合法及煤层底板突水预测的统计学习法、基于智能化传感器及智能算法的矿井水情(害)实时监测预警系统、水害治理工程的信息化设计及智能控制注浆系统、紧急避灾最优路径搜索及突水水源快速识别。结果表明:水害探测装备及解释方法的智能化提高了装备的抗干扰能力,实现了探测数据的快速准确处理;煤层底板突水预测的统计学习法使突水预测精度由82%提高到91%;网络并行电法监测仪在五沟煤矿提前2 d成功预报了工作面底板突水;智能化注浆系统形成了高度定制化的制浆-注浆数字化解决方案,实现全自动造浆30 m3/h;避灾抢险智能化为矿井灾害情景下的井下人员合理疏散和应急救援提供了辅助决策支持平台。提出随着智慧矿山、透明矿井技术的不断发展与完善,多源时空智能化探(监)测、玻璃水文地质、水害监测大数据挖掘、井下救援机器人等将会成为热点研究方向,并最终形成煤矿防治水智能化技术体系。
In order to solve mine water filling problems including accurate detection,effective prediction,dynamic monitoring and reliable management of water hazard,artificial intelligence and information technology have been widely applied in coal mine water controlling technology and equipment in China and great progress has been made.Based on the three elements of artificial intelligence technology,namely intelligent perception,intelligent judgment and intelligent execution,this paper defines the intelligent control of coal mine water as the process of effective screening,automatic identification and precise control of water hazard factors.Then the current intelligent coal mine water control technology is summarized from the following five aspects: detection equipment of intelligent chips and intelligent data processing algorithms,information fusion method of water-rich aquifer partition and statistical learning-based approaches of coal floor water inrush prediction,mine water situation real-time monitoring and warning system based on intelligent sensor and arithmetic,informationalized design and intelligent control grouting system of water hazard control engineering,searching for the optimal path for emergency avoidance and rapid identification of water inrush sources.The results show that the intelligentalization of water hazard detection equipment and interpretation methods have greatly improved the equipment anti-interference abilities and the calculation of parameters detected has been accelerated.The application of statistical learning methods in coal seam floor water inrush prediction improves the water inrush prediction accuracy from 82% to 91%.In Wugou Coal Mine,the network parallel electrical monitoring instrument successfully predicted the water inrush from working face floor two days in advance.In addition,the intelligent grouting system has formed a highly customized digital pulping-grouting solution scheme and realized automatic pulping 30 m3/h.Disaster prevention and rescue intelligentalization provides an auxiliary decisionmaking support platform for reasonable evacuation and emergency rescue of underground personnel under the mine disaster scenario.With the development of intelligent coal mine and transparent coal mine technologies,multi-source spatial-temporal intelligent monitoring,glass hydro-geology,big data mining for groundwater hazard situation monitoring,and underground rescue robots will become hotspsrt research fields in the future,and an intelligent technology system of coal mine water control will finally come into shape.
In order to solve mine water filling problems including accurate detection,effective prediction,dynamic monitoring and reliable management of water hazard,artificial intelligence and information technology have been widely applied in coal mine water controlling technology and equipment in China and great progress has been made.Based on the three elements of artificial intelligence technology,namely intelligent perception,intelligent judgment and intelligent execution,this paper defines the intelligent control of coal mine water as the process of effective screening,automatic identification and precise control of water hazard factors.Then the current intelligent coal mine water control technology is summarized from the following five aspects: detection equipment of intelligent chips and intelligent data processing algorithms,information fusion method of water-rich aquifer partition and statistical learning-based approaches of coal floor water inrush prediction,mine water situation real-time monitoring and warning system based on intelligent sensor and arithmetic,informationalized design and intelligent control grouting system of water hazard control engineering,searching for the optimal path for emergency avoidance and rapid identification of water inrush sources.The results show that the intelligentalization of water hazard detection equipment and interpretation methods have greatly improved the equipment anti-interference abilities and the calculation of parameters detected has been accelerated.The application of statistical learning methods in coal seam floor water inrush prediction improves the water inrush prediction accuracy from 82% to 91%.In Wugou Coal Mine,the network parallel electrical monitoring instrument successfully predicted the water inrush from working face floor two days in advance.In addition,the intelligent grouting system has formed a highly customized digital pulping-grouting solution scheme and realized automatic pulping 30 m3/h.Disaster prevention and rescue intelligentalization provides an auxiliary decisionmaking support platform for reasonable evacuation and emergency rescue of underground personnel under the mine disaster scenario.With the development of intelligent coal mine and transparent coal mine technologies,multi-source spatial-temporal intelligent monitoring,glass hydro-geology,big data mining for groundwater hazard situation monitoring,and underground rescue robots will become hotspsrt research fields in the future,and an intelligent technology system of coal mine water control will finally come into shape.
引文
[1]靳德武.我国煤矿水害防治技术新进展及其方法论思考[J].煤炭科学技术,2017,45(5):141-147.JIN Dewu. New development of water disaster prevention and control technology in China coal mine and consideration on methodology[J].Coal Science and Technology,2017,45(5):141-147.
[2]陈晓晶,何敏.智慧矿山建设架构体系及其关键技术[J].煤炭科学技术,2018,46(2):208-212,236.CHEN Xiaojing,HE Min.Framework system and key technology of intelligent mine construction[J]. Coal Science and Technology,2018,46(2):208-212,236.
[3]韩茜.智慧矿山信息化标准化系统关键问题研究[D].北京:中国矿业大学(北京),2016.
[4] RANDEN T,PEDERSEN S I,SONNELAND L.Automatic extraction of fault surfaces from three-dimensional seismic data[C].7lst Annual lnternational Meeting,SEG,expanded Abstracs,2001(1):550-554.
[5] DORM G A,JAMES H E.Automatic Fault Extraction(AFE)of faults and a salt body in a 3-D survey from the Eugene Island Area,Gulf of Mexico[J].Search&Discovery,2005(4):96-108.
[6] TINGDAHL K M,ROOIJ M.Semi-automatic detection of faults in3D seismic data[J].Geophysical Prospecting,2005,53:533-542.
[7]谢林涛,付志红,谢品芳,等.基于神经网络的视电阻率快速算法[J].地球物理学进展,2009,24(4):1527-1532.XIE Lintao,FU Zhihong,XIE Pinfang,et al.A fast algorithm of apparent resistivity based on neural networks[J]. Progress in Geophys,2009,24(4):1527-1532.
[8]马斌,祃艳双,王永会,等.基于BP神经网络的高密度电阻率数据反演方法[J].沈阳建筑大学学报:自然科学版,2010,26(3):599-603.MA Bin,MA Yanshuaug,WANG Youghui,et al. High-density resistivity data inversion method based on BP neural network[J].Journal of Shenyang architecture University:Natural Science,2010,26(3):599-603.
[9]张凌云,刘鸿福.ABP法在高密度电阻率法反演中的应用[J].地球物理学报,2011,54(1):227-233.ZHANG Lingyun,LIU Hongfu. The application of ABP method in high-density resistivity method inversion[J]. Chinese Journal of Geophysics,2011,54(1):227-233.
[10]戴前伟,江沸菠.基于混沌振荡PSO-BP算法的电阻率层析成像非线性反演[J].中国有色金属学报,2013(10):2897-2904.DAI Qianwei,JIANG Feibo.Nonlinear inversion for electrical resistivity tomography based chaotic oscillation PSO-BP algorithm[J].The Chinese Journal of Nonferrous Metals,2013(10):2897-2904.
[11]戴前伟,江沸菠,董莉.基于汉南-奎因信息准则的电阻率层析成像径向基神经网络反演[J].地球物理学报,2014,57(4):1335-1344.DAI Qianwei,JIANG Feibo,DONG Li.RBFNN inversion for electrical resistivity tomography based on Hannan-Quinn criterion[J].Chinese Journal of Geophysics,2014,57(4):1335-1344.
[12]武强,樊振丽,刘守强,等.基于GIS的信息融合型含水层富水性评价方法:富水性指数法[J].煤炭学报,2011,36(7):1124-1128.WU Qiang,FAN Zhenli,LIU Shouqiang,et al. Water-richness evaluation method of water-filled aquifer based on the principle of information fusion with GIS:water richness index method[J].Journal of China Coal Society,2011,36(7):1124-1128.
[13]赵宝峰.基于AHP-模糊综合评判法的矿井水害威胁程度研究[J].安全与环境学报,2013,13(3):231-234.ZHAO Baofeng. On the AHP-fuzzy comprehensive evaluation of threatening degree caused by mining water floods[J]. Journal of Safety and Environment,2013,13(3):231-234.
[14]靳德武.华北型煤田煤层底板突水预测信息分析理论、方法及应用[J].中国岩溶,2003,22(1):41-46.JIN Dewu,Theory,method and application in analyzing the forecasting information of water inrush from the bottom coal layer in northern China coalfield[J]. Carsologica Sinica,2003,22(1):41-46.
[15]刘再斌.基于数据挖掘分类技术的煤层底板突水预测[D].北京:煤炭科学研究总院,2008.
[16]李颖.基于支持向量机的煤层底板突水预测方法研究[D].北京:煤炭科学研究总院,2007.
[17]周民都,张元生,张树勋.遗传算法在地震定位中的应用[J].地震工程学报,1999,19(2):167-171.ZHOU Mindou,ZHANG Yuansheng,ZHANG Shuxun.Application of the genetic algorithm to seismic location[J].China Earthquake Engineering Journal,1999,19(2):167-171.
[18]刘盛东,王勃,周冠群,等.基于地下水渗流中地电场响应的矿井水害预警试验研究[J].岩石力学与工程学报,2009,28(2):267-272.LIU Shengdong,WANG Bo,ZHOU Guanqun,et al. Experimental research on mine floor water hazard early warning based on response of geoelectric field in groundwater seepage[J]. Chinese Journal of Rock Mechanics and Engineering,2009,28(2):267-272.
[19]王传盈,朱海锋.网络并行电法技术在受水威胁工作面注浆改造前后中的应用[J].山东工业技术,2016(15):140-140.WANG Chuanying,ZHU Haifeng. Application of network parallel electric method in water hazard threaten face before and after grouting[J]. Shandong Industrial Technology,2016(15):140-140.
[20]吴超凡,刘盛东,邱占林,等.矿井采空区积水网络并行电法探测技术[J].煤炭科学技术,2013,41(4):93-95.WU Chaofan,LIU Shendong,QIU Zhanlin,et al. Technology of network parallel electric method applied to detection of water ponding in mining goaf[J]. Coal Science and Technology,2013,41(4):93-95.
[21]靳德武,刘英锋,冯宏,等.煤层底板突水监测预警系统的开发及应用[J].煤炭科学技术,2011,39(11):14-17.JIN Dewu,LIU Yingfeng,FENG Hong,et al.Development and application of monitoring and early warning system to seam floor water inrush[J]. Coal Science and Technology,2011,39(11):14-17.
[22]周明瑞,仲淑姮,徐忠忠.基于JME的工作面底板注浆三维模拟评价系统[J].煤矿安全,2015,46(11):97-103.ZHOU Mingrui,ZHONG Shuheng,XU Zhongzhong.Three-dimensional simulation evaluation system for floor grouting based on Java Monkey Engine[J]. Safety in Coal Mines,2015,46(11):97-103.
[23]赵作鹏,宋国娟,宗元元,等.基于D-K算法的煤矿水灾多最优路径研究[J].煤炭学报,2015,40(2):397-402.ZHAO Zuopeng,SONG Guojuan,ZONG Yuanyuan,et al.Research on the multi-optimal paths of coal mine floods based on the D-K algorithm[J]. Journal of China Coal Society,2015,40(2):397-402.
[24]王玉琨,吴锋.矿井应急救援中最佳避灾路线的Dijkstra算法的改进实现[J].工矿自动化,2008,34(5):13-15.WANG Yukun,WU feng.Implementation of improved Dijkstra algorithm for choosing the best escape route in mine’s emergency rescue[J].Industry and Mine Automation,2008,34(5):13-15.
[25]武强,徐华,杜沅泽,等.矿山突(透)水灾害应急疏散模拟系统与工程应用[J].煤炭学报,2017,42(10):2491-2497.WU Qiang,XU Hua,DU Yuanze,et al. Emergency evacuation simulation for water bursting disaster in mine[J]. Journal of China Coal Society,2017,42(10):2491-2497.
[26]乔伟.基于蚁群算法的煤矿水害避灾路径研究[J].西部探矿工程,2017(8):126-128.QIAO Wei. Research on route for escaping coal mine water disaster based on ant colony algorithm[J].West-China Exploration Engineering,2017(8):126-128.
[27]李彩惠,牛相锋,任素珍,等.水质快速分析及水源快速判别系统[J].煤田地质与勘探,1998(3):43-46.LI Caihui,NIU Xiangfeng,REN Suzhen,et al. A System for fast water quality analysis and fast water source discrimination[J].Coal Geology&Exploration,1998(3):26-28.
[28]孙亚军,杨国勇,郑琳.基于GIS的矿井突水水源判别系统研究[J].煤田地质与勘探,2007,35(2):34-37.SUN Yajun,YANG Guoyong,ZHENG Lin. Distinguishing system study on resource of mine water inrush based on GIS[J].Coal Geology&Exploration,2007,35(2):34-37.
[2]陈晓晶,何敏.智慧矿山建设架构体系及其关键技术[J].煤炭科学技术,2018,46(2):208-212,236.CHEN Xiaojing,HE Min.Framework system and key technology of intelligent mine construction[J]. Coal Science and Technology,2018,46(2):208-212,236.
[3]韩茜.智慧矿山信息化标准化系统关键问题研究[D].北京:中国矿业大学(北京),2016.
[4] RANDEN T,PEDERSEN S I,SONNELAND L.Automatic extraction of fault surfaces from three-dimensional seismic data[C].7lst Annual lnternational Meeting,SEG,expanded Abstracs,2001(1):550-554.
[5] DORM G A,JAMES H E.Automatic Fault Extraction(AFE)of faults and a salt body in a 3-D survey from the Eugene Island Area,Gulf of Mexico[J].Search&Discovery,2005(4):96-108.
[6] TINGDAHL K M,ROOIJ M.Semi-automatic detection of faults in3D seismic data[J].Geophysical Prospecting,2005,53:533-542.
[7]谢林涛,付志红,谢品芳,等.基于神经网络的视电阻率快速算法[J].地球物理学进展,2009,24(4):1527-1532.XIE Lintao,FU Zhihong,XIE Pinfang,et al.A fast algorithm of apparent resistivity based on neural networks[J]. Progress in Geophys,2009,24(4):1527-1532.
[8]马斌,祃艳双,王永会,等.基于BP神经网络的高密度电阻率数据反演方法[J].沈阳建筑大学学报:自然科学版,2010,26(3):599-603.MA Bin,MA Yanshuaug,WANG Youghui,et al. High-density resistivity data inversion method based on BP neural network[J].Journal of Shenyang architecture University:Natural Science,2010,26(3):599-603.
[9]张凌云,刘鸿福.ABP法在高密度电阻率法反演中的应用[J].地球物理学报,2011,54(1):227-233.ZHANG Lingyun,LIU Hongfu. The application of ABP method in high-density resistivity method inversion[J]. Chinese Journal of Geophysics,2011,54(1):227-233.
[10]戴前伟,江沸菠.基于混沌振荡PSO-BP算法的电阻率层析成像非线性反演[J].中国有色金属学报,2013(10):2897-2904.DAI Qianwei,JIANG Feibo.Nonlinear inversion for electrical resistivity tomography based chaotic oscillation PSO-BP algorithm[J].The Chinese Journal of Nonferrous Metals,2013(10):2897-2904.
[11]戴前伟,江沸菠,董莉.基于汉南-奎因信息准则的电阻率层析成像径向基神经网络反演[J].地球物理学报,2014,57(4):1335-1344.DAI Qianwei,JIANG Feibo,DONG Li.RBFNN inversion for electrical resistivity tomography based on Hannan-Quinn criterion[J].Chinese Journal of Geophysics,2014,57(4):1335-1344.
[12]武强,樊振丽,刘守强,等.基于GIS的信息融合型含水层富水性评价方法:富水性指数法[J].煤炭学报,2011,36(7):1124-1128.WU Qiang,FAN Zhenli,LIU Shouqiang,et al. Water-richness evaluation method of water-filled aquifer based on the principle of information fusion with GIS:water richness index method[J].Journal of China Coal Society,2011,36(7):1124-1128.
[13]赵宝峰.基于AHP-模糊综合评判法的矿井水害威胁程度研究[J].安全与环境学报,2013,13(3):231-234.ZHAO Baofeng. On the AHP-fuzzy comprehensive evaluation of threatening degree caused by mining water floods[J]. Journal of Safety and Environment,2013,13(3):231-234.
[14]靳德武.华北型煤田煤层底板突水预测信息分析理论、方法及应用[J].中国岩溶,2003,22(1):41-46.JIN Dewu,Theory,method and application in analyzing the forecasting information of water inrush from the bottom coal layer in northern China coalfield[J]. Carsologica Sinica,2003,22(1):41-46.
[15]刘再斌.基于数据挖掘分类技术的煤层底板突水预测[D].北京:煤炭科学研究总院,2008.
[16]李颖.基于支持向量机的煤层底板突水预测方法研究[D].北京:煤炭科学研究总院,2007.
[17]周民都,张元生,张树勋.遗传算法在地震定位中的应用[J].地震工程学报,1999,19(2):167-171.ZHOU Mindou,ZHANG Yuansheng,ZHANG Shuxun.Application of the genetic algorithm to seismic location[J].China Earthquake Engineering Journal,1999,19(2):167-171.
[18]刘盛东,王勃,周冠群,等.基于地下水渗流中地电场响应的矿井水害预警试验研究[J].岩石力学与工程学报,2009,28(2):267-272.LIU Shengdong,WANG Bo,ZHOU Guanqun,et al. Experimental research on mine floor water hazard early warning based on response of geoelectric field in groundwater seepage[J]. Chinese Journal of Rock Mechanics and Engineering,2009,28(2):267-272.
[19]王传盈,朱海锋.网络并行电法技术在受水威胁工作面注浆改造前后中的应用[J].山东工业技术,2016(15):140-140.WANG Chuanying,ZHU Haifeng. Application of network parallel electric method in water hazard threaten face before and after grouting[J]. Shandong Industrial Technology,2016(15):140-140.
[20]吴超凡,刘盛东,邱占林,等.矿井采空区积水网络并行电法探测技术[J].煤炭科学技术,2013,41(4):93-95.WU Chaofan,LIU Shendong,QIU Zhanlin,et al. Technology of network parallel electric method applied to detection of water ponding in mining goaf[J]. Coal Science and Technology,2013,41(4):93-95.
[21]靳德武,刘英锋,冯宏,等.煤层底板突水监测预警系统的开发及应用[J].煤炭科学技术,2011,39(11):14-17.JIN Dewu,LIU Yingfeng,FENG Hong,et al.Development and application of monitoring and early warning system to seam floor water inrush[J]. Coal Science and Technology,2011,39(11):14-17.
[22]周明瑞,仲淑姮,徐忠忠.基于JME的工作面底板注浆三维模拟评价系统[J].煤矿安全,2015,46(11):97-103.ZHOU Mingrui,ZHONG Shuheng,XU Zhongzhong.Three-dimensional simulation evaluation system for floor grouting based on Java Monkey Engine[J]. Safety in Coal Mines,2015,46(11):97-103.
[23]赵作鹏,宋国娟,宗元元,等.基于D-K算法的煤矿水灾多最优路径研究[J].煤炭学报,2015,40(2):397-402.ZHAO Zuopeng,SONG Guojuan,ZONG Yuanyuan,et al.Research on the multi-optimal paths of coal mine floods based on the D-K algorithm[J]. Journal of China Coal Society,2015,40(2):397-402.
[24]王玉琨,吴锋.矿井应急救援中最佳避灾路线的Dijkstra算法的改进实现[J].工矿自动化,2008,34(5):13-15.WANG Yukun,WU feng.Implementation of improved Dijkstra algorithm for choosing the best escape route in mine’s emergency rescue[J].Industry and Mine Automation,2008,34(5):13-15.
[25]武强,徐华,杜沅泽,等.矿山突(透)水灾害应急疏散模拟系统与工程应用[J].煤炭学报,2017,42(10):2491-2497.WU Qiang,XU Hua,DU Yuanze,et al. Emergency evacuation simulation for water bursting disaster in mine[J]. Journal of China Coal Society,2017,42(10):2491-2497.
[26]乔伟.基于蚁群算法的煤矿水害避灾路径研究[J].西部探矿工程,2017(8):126-128.QIAO Wei. Research on route for escaping coal mine water disaster based on ant colony algorithm[J].West-China Exploration Engineering,2017(8):126-128.
[27]李彩惠,牛相锋,任素珍,等.水质快速分析及水源快速判别系统[J].煤田地质与勘探,1998(3):43-46.LI Caihui,NIU Xiangfeng,REN Suzhen,et al. A System for fast water quality analysis and fast water source discrimination[J].Coal Geology&Exploration,1998(3):26-28.
[28]孙亚军,杨国勇,郑琳.基于GIS的矿井突水水源判别系统研究[J].煤田地质与勘探,2007,35(2):34-37.SUN Yajun,YANG Guoyong,ZHENG Lin. Distinguishing system study on resource of mine water inrush based on GIS[J].Coal Geology&Exploration,2007,35(2):34-37.