Height prediction of water flowing fractured zones based on BP artificial neural network

Factures caused by deformation and destruction of bedrocks over coal seams can easily lead to water flooding(inrush)in mines,a threat to safety production.Fractures with high hydraulic conductivity are good watercourses as well as passages for inrush in mines and tunnels.An accurate height prediction of water flowing fractured zones is a key issue in today's mine water prevention and control.The theory of leveraging BP artificial neural network in height prediction of water flowing fractured zones is analysed and applied in Qianjiaying Mine as an example in this paper.Per the comparison with traditional calculation results,the BP artificial neural network better reflects the geological conditions of the research mine areas and produces more objective,accurate and reasonable results,which can be applied to predict the height of water flowing fractured zones.

Height Detection and Analysis of Water Flowing Fractured Zone of Coal Face

Taking 91105 working face as the research object, the observation method of water flowing fractured zone and the layout of mining holes were determined by analyzing the field geological structure. It was shown that the fractured zone height and the ratio given by the measured method were 52.33 and 12.46, respectively. By the numerical simulation method with the software of UDEC, the fractured zone height and the ratio were 42.5 and 10.12. By comparison of measured height data and UDEC numerical simulation, there were some differences between the measured height and the calculated results of UDEC numerical simulation method. The method of simulation can be used as the technical basis for the design of waterproof coal pillar in the future.

Predicting the height of water-flow fractured zone during coal mining under the Xiaolangdi Reservoir

It is very important to determine the extent of the fractured zone through which water can flow before coal mining under the water bodies.This paper deals with methods to obtain information about overburden rock failure and the development of the fractured zone while coal mining in Xin'an Coal Mine.The risk of water inrush in this mine is great because 40%of the mining area is under the Xiaolangdi reservoir.Numerical simulations combined with geophysical methods were used in this paper to obtain the development law of the fractured zone under different mining conditions.The comprehensive geophysical method described in this paper has been demonstrated to accurately predict the height of the water-flow fractured zone.Results from the new model, which created from the results of numerical simulations and field measurements,were successfully used for making decisions in the Xin'an Coal Mine when mining under the Xiaolangdi Reservoir.Industrial scale experiments at the number 11201,14141 and 14191 working faces were safely carried out.These achievements provide a successful background for the evaluation and application of coal mining under large reservoirs.

Optimum Calculation of Coal Pillars in Inclined Weathered Oxidation Zone

In the mining process of coal mine,waterproof coal pillars should be set between the weathered oxidation zone and the first mining face.In order to determine the reasonable upper limit of the first mining face of Hongyi Coal Mine,the waterproof coal pillar needs to be wide enough to resist the lateral hydrostatic pressure of the oxidation zone,and to ensure that the top plate aquifer does not run through the water guide crack zone,while also liberating as much stagnant coal as possible.In this paper,the first coal mine face’s waterproof coal pillar was calculated using conventional and optimized calculation methods,taking into account the dip angle of the coal seam,the height of the water-guide crack zone,and the rock shift influence zone,and finally the upper limit of the first face of Hongyi Coal Mine was determined.

Forecasting of destroyed height of overlying rock with the top coal caving based on ANN

Analyzed the rule of the Water Flowing Fractured (WFF) zone's development during the fully mechanized top coal caving.Six influence factors of WFF's height were selected,viz.mining thickness,base rock thickness,dip angle,uniaxial compressing strength of roof,mudstone proportion in overlying rock,and structure of overlying rock. The height-forecasting model of WFF was established based on the Artificial Neural Net-work techniques,and was applied in the first fully mechanized top coal caving face under sea in China.

河流下多煤层开采安全性及保护技术

我国新疆地区干旱缺水,艾维尔沟河作为新疆一条具有重要地理特征和环境影响的河流,其对于流经区域的经济、生态都具有重要意义,因此在艾维尔沟河下进行煤炭开采时,既要保证矿井安全也要保证河流的正常使用。采用理论分析、数值模拟等方法对河流下多煤层开采安全性及河流保护技术进行研究,通过理论计算得到多煤层开采条件下,覆岩导水裂隙带发育高度(11401工作面为41.9 m、1502工作面为110 m、11401工作面为113.8 m)并绘制剖面示意图;同时,采用数值模拟方法对覆岩导水裂缝发育形态及高度进行确定,最终基于导水裂隙带高度(117.8 m)与最小煤层埋藏深度(191.5 m)的相互关系,确定河流下开采是安全的可行的。在保证河流下煤层安全开采的前提下,通过分析离层注浆原理,并结合采动影响特征参数及工程现场,提出了以离层注浆为主,河道防渗及优化开采设计为辅的多手段对采动影响范围内地表特定目标的精准保护技术。根据实际采矿地质条件,采用概率积分法计算试采工作面开采前后河道位置处地表移动变形,计算结果显示:采用离层注浆精准保护技术后,河道的最大水平变形值(2 mm/m)未超出允许坝体的极限变形值(2.5 mm/m),所以采用离层注浆精准保护技术可以实现,井下安全开采的同时,保证河道的正常使用。通过对河流下多煤层开采的安全性及保护技术的分析研究,为矿山绿色开采提供参考和借鉴。

坚硬覆岩预裂弱化改性效应及导水裂缝带控制机理

针对深部煤层开采坚硬覆岩条件下导水裂缝带控制问题,充分借鉴坚硬顶板预裂弱化技术,提出预裂弱化坚硬主控覆岩控制导水裂缝带高度的新方法。综合采用实验室试验、理论分析、数值模拟等方法,研究了坚硬主控覆岩预裂弱化改性效应,详细阐述了不同弱化层位对导水裂缝带的控制机理,并进行了实测验证。研究结果表明:预制裂缝可以使坚硬岩石往强度低的方向进行转变,并将完整岩样的劈裂破坏特征转变为以预制裂缝为主控的张拉剪切破坏,坚硬岩石的破坏程度由剧烈趋于缓和;揭示了预制裂缝对坚硬岩体的弱化改性效应,计算得到应力与裂缝耦合的损伤变量,定性的分析了弱化程度与岩性转变的关系,改性后岩体能量存储能力降低,耗散能力增强;数值模拟了不同弱化层位对导水裂缝带的控制效果,综合对比覆岩破坏形态、裂隙数量及破坏高度动态演化规律,发现“马鞍形”破坏形态随着弱化层位的升高而逐渐减弱,覆岩裂隙数量演化基本呈现“缓增−突增”的演化趋势,未弱化以及中、高位弱化覆岩破坏高度动态演化近似呈现“S”形,而中位弱化呈“半抛形”,综合分析得出低位弱化对导水裂缝带的控制效果最好;在分析高、中、低位坚硬岩层破坏特征的基础上,揭示了不同预裂弱化层位控制导水裂缝带发育机理;钻孔实测孟村矿顶板压裂条件下的“两带”发育高度,对比发现预裂弱化条件下裂采比降低,初步验证了顶板预裂弱化对导水裂缝带发育的抑制性。研究成果将为深部矿区耦合灾害防控、水资源及生态保护等领域提供理论和科学依据。

基于LDA-RBF及综合赋权法的顶板突水危险性评价

为了解决龙凤煤矿9号煤层开采过程中顶板突水危险性问题,采用线性判别分析法(LDA)构建1种LDA-RBF神经网络导水裂隙带发育高度预测模型,并基于改进CRITIC评价法结合层次分析法(AHP)建立了CRITIC-AHP综合赋权法,分别评价矿区顶板采裂危险性及含水层富水性等级;通过ArcGis地理信息处理技术,将采裂危险性分区与富水性分区叠加,得到9号煤层顶板突水危险性综合分区图。结果表明:LDA-RBF神经网络预测模型结构简单且拟合精度更高,9号煤层导水裂隙带发育预测高度为50.4 m,已超过区域内大部分含水层底界标高,表明大部分区域存在较高的采裂危险性;而改进后的综合赋权法避免了评价结果主客观性过强的问题,其富水性分区结果与钻孔实际涌水量相符;突水危险区主要在矿区中北部呈条状分布,这是该区域含水层富水性较强和采裂危险性较高共同作用的结果,因此,在实际开采中应对以上区域予以重视。

高家堡井田二盘区导水裂隙带高度实测研究

为了查明煤层顶板导水裂隙发育规律,采用地面钻孔分段注水测试和钻孔窥视方法实测了高家堡井田204工作面和205工作面煤层顶板导水裂隙带发育高度。研究结果表明:(1)205工作面DT1钻孔位置煤层顶板导水裂隙带发育高度为327.75 m,裂采比25.81。(2)204工作面DT2钻孔位置煤层顶板导水裂隙带发育高度为197.85 m,裂采比35.33。(3)高家堡井田二盘区导水裂隙带实测结果丰富了黄陇煤田综放采煤覆岩破坏规律。

缓倾斜煤层综采工作面覆岩“两带”高度研究

随着矿井开采向深部发展,矿井水害风险逐渐增加,准确掌握工作面采空区覆岩“两带”即垮落带、导水裂隙带发育高度,对矿井顶板水害防治、合理留设防隔水煤(岩)柱意义较大。本文采用理论计算、UDEC数值模拟、压水测试3种方法,对青云煤矿020202综采工作面覆岩“两带”发育高度进行了研究,3种方法相互验证,最终得出该工作面垮落带最大高度为10.3 m,冒采比为4.12;导水裂隙带最大高度为41.6 m,裂采比为16.64,该结果可以为矿井的安全生产提供科学指导。

地质构造带大巷顶板淋水注浆封堵技术

以中六运输大巷断层影响范围内顶板淋水防治为工程背景,提出采用RSS化学浆液对顶板淋水区进行快速封堵,同时采用U型钢架棚+聚氨酯浆液强化围岩支护强度,避免围岩变形产生新的导水裂隙。结合现场条件,对具体采用的顶板淋水注浆封堵技术方案进行设计,并进行工程应用。现场应用后,中六运输大巷顶板淋水问题得到较好解决,巷道围岩变形控制在安全范围内,采用的技术方案可满足中六运输大巷后续安全使用需要。

综采一次采全高工作面导水裂隙带发育高度研究

本文以东坡矿东部区为工程背景,对工作面导水裂隙带发育高度进行研究分析。优化经验公式参数,建立导水裂缝带高度预测模型,通过搜集多个矿井数据,对工作面导水裂隙带影响因素进行PAST软件相关性统计分析,确定影响因素及其比值由重到轻分别为:采深(0.93)、关键层间距(0.82)、工作面斜长(0.68)和采高(0.35),并建立导水裂隙带解析式。通过与实测数据对比,确定预测模型绝对误差保持在4.40%以内,符合误差要求。

Forecasting water disaster for a coal mine under the Xiaolangdi reservoir

Xin’an coal mine, Henan Province, faces the risk of water inrush because 40% of the area of the coal mine is under the surface water of the Xiaolangdi reservoir. To forecast water disaster, an effective aquifuge and a limit of water infiltration were determined by rock-phase analysis and long term observations of surface water and groundwater. By field monitoring, as well as physical and numerical simulation experiments, we obtained data reflecting different heights of a water flow fractured zone (WFFZ) under different mining conditions, derived a formula to calculate this height and built a forecasting model with the aid of GIS. On the basis of these activities, the coal mine area was classified into three sub-areas with different potential of water inrush. In the end, our research results have been applied in and verified by industrial mining experiments at three working faces and we were able to present a successful example of coal mining under a large reservoir.

榆神矿区导水裂隙带高度多因素影响规律及保水采煤分区

通过融合数理统计、多元回归与空间分析方法,分析了导水裂隙带发育高度受多种因素影响规律,构建了综采导水裂隙带高度与煤层采高、采深、开采推进速度多因素之间的非线性统计关系式;基于导水裂隙带经验公式及保水采煤阈值,将榆神矿区划分为五类,工况一条件下矿区内基于水资源保护的安全开采区域(WRSE)面积为4.24×10^(9)m^(2),占比为82%;基于水资源保护的非安全开采区域(Non-WRSE)的面积为920 835 911.3 m2,占比为18%;工况二条件下矿区内WRSE的面积为3.87×10^(9)m^(2),占比为77%;Non-WRSE的面积为1.14×10^(9)m^(2),占比为23%;工况三条件下矿区内WRSE的面积为3.78×10^(9)m^(2),占比为73%;Non-WRSE的面积为1.38×10^(9)m^(2),占比为27%;对比研究3种工况预测的保水采煤分区数据,以保水采煤分区结果确定了规划矿井的保水等级,确定了重点保护矿井。项目研究成果可为矿区合理地开采规划和设计提供宏观决策依据,进一步完善保水开采理论与技术体系。

侏罗系弱胶结顶板采动破坏规律与发育高度预测

煤层采动后形成的顶板导水裂隙带是沟通顶板充水含水层的主要通道之一,同时也是顶板水害防治需要重点研究的关键问题。近年来,西部矿区已成为我国煤炭资源主要开采区,其主采侏罗系含煤地层与东部石炭-二叠系有着明显差异,并具有典型的孔隙度高、胶结程度差等特征,顶板采动导水裂隙的演化特征也与东部矿区具有较大差异,相关的研究尚未形成普适性成果。因此,本文选取典型的弱胶结地区——新疆哈密大南湖矿区为例,采用UDEC数值模拟、现场三维钻孔电视成像等方法,并结合“S-R”稳定理论,以垮落带高度为自变量,建立砌体梁承载强度与垮落带高度关系式,全面揭示该区煤层开采过程中顶板的采动破坏过程与演化特征,并以此为依据确定顶板导水裂隙带的发育高度。在此基础上,通过收集侏罗系同类型煤矿导水裂隙带高度的实测数据,采用回归分析方法,拟合并修正现有经验公式。研究表明:研究区顶板导水裂隙带发育高度的范围是60.07~62m,裂采比为17.67~18.24,整体形态呈“梯台”型特征,结合邻矿现场实测对比证实了此次实测结果的可靠性;开采范围内导水裂隙带发育高度受垮落带高度增量、岩块回转角变化的影响呈现:“快速增加-缓慢增加-逐渐稳定”的发展与演化规律;验证计算结果表明,论文提出的回归公式预测精度一般在10.30%~17.25%之间,相较于传统经验公式平均误差降低了51.84%,显著提高了导水裂隙带高度的预测精度。论文的相关研究成果可为新疆地区相似开采条件下顶板导水裂隙带发育高度计算提供理论依据。

基于微震监测技术的煤矿顶板水害预测

以亭南煤矿307工作面为工程背景,通过模拟分析导水断裂隙带高度来验证微震监测数据实时监测导水断裂带高度的可靠性,并利用数理统计方法分析了微震事件与顶板涌水量的关系。研究结果表明:307工作面在不同推进距离条件下,微震事件集中分布于覆岩破坏严重区,能够反映覆岩破坏情况及导水裂隙带发育高度;工作面回采数值模拟结果与微震监测事件变化规律基本一致,导水裂隙带高度发育特点为“前期增长快,中期增长慢,后期达到平衡”;307工作面微震监测数据事件数与同时间段内的涌水量相关性显著,涌水事件和微震事件的发生具有特定的滞后效应,采用合适的滞后微震数据做预测能更好地提高涌水量预测准确度。

鹰骏三号井田2煤层顶板“两带”高度数值模拟研究

本文针对鹰骏三号井田范围内2号煤层顶板导水裂隙带研究较为薄弱的现状,通过FLAC3D数值模拟揭示了11201工作面上覆岩层移动和破坏规律,预测了2号煤层开采后上覆岩层内“冒落带”和“导水裂隙带”的发育高度,并采用经验公式对其覆岩“两带”高度进行计算分析。研究结果表明,FLAC3D数值模拟计算结果与经验公式结果基本一致,为煤矿防治水及安全开采技术措施制定提供可靠参数。

矿井涌水量预测及防治水建议

含水层、老窖水以及采空区积水等水源极易发生透水事故,为煤矿安全生产带来巨大隐患。以某煤矿14152综放工作面为例,观测冒落带与导水裂隙带发育高度,利用富水系数比拟法准确预测矿井涌水量,并针对该煤矿实际情况合理提出防治水措施,对安全生产,提高经济效益具有重要意义。

综采工作条件下覆岩导水裂隙带高度预测模型优化

准确预测导水裂隙带高度是煤炭防治水中的重要问题,也是保障煤矿安全生产的前提。目前,导水裂隙带高度预测模型存在预测准确性差等问题。在广泛收集各地不同煤矿区综采导水裂隙带发育高度实测数据的基础上,总结前人研究成果,选取采厚、工作面斜长、倾角、采深和硬岩比例系数5个因素建立导水裂隙带高度预测模型。同时,采用因素分析法分析了影响因素的权重,确定主控因素,并建立多元线性回归模型、多元非线性回归模型及BP神经网络预测模型,并对预测模型计算导水裂隙带高度进行准确性检验。以西山矿区实测导水裂隙带高度为例,选出最优模型,对最优预测模型BP神经网络模型进行检验分析,并与“三下”规范经验公式、多元线性回归模型和多元非线性回归模型计算结果进行对比。结果表明,“三下”规范经验公式与实际数据存在失真,已不能指导综采条件下导水裂隙带高度预测,而BP神经网络预测模型误差在10%以内,且绝对误差和相对误差较为稳定,同时该模型降低了因素之间的相关性,提高了预测准确性。因此,BP神经网络预测模型在预测导水裂隙带高度方面具有较好的准确性和应用性。研究成果可为指导矿井现场防治水害的工作提供参考建议。

PCA-WNN模型在导水裂隙带高度预测中的应用研究

导水裂隙带是煤层顶板水害的主要通道,准确预计导水裂隙带高度是预测和防治煤层顶板水害的首要任务。基于导水裂隙带发育的复杂性及其影响因素之间的相关性,结合煤矿生产实际和工程地质理论,选取采高、工作面斜长、硬岩岩性比例系数、采深和煤层倾角作为主控因素,利用线性回归拟合及灰色关联分析法分析各主控因素与导水裂隙带发育高度的相关性。将主成分分析(principal component analysis,PCA)与小波神经网络(wavelet neural network,WNN)相结合,通过PCA消除各主控因素间的相关性及冗余信息,构造无相关性的主成分作为WNN的输入因素,建立导水裂隙带高度预测的PCA-WNN模型。结果表明:PCA-WNN模型能有效消除因素间的相关性,预测相对误差为-6.66%~6.13%,平均4.46%,较单纯的WNN模型预测精度高且稳定。将该模型应用于山东新巨龙煤矿1302N工作面,得到了较为准确的预测结果,为导水裂隙带高度预测提供了新方法。