Construction of multi-factor identification model for real-time monitoring and early warning of mine water inrush

As a new technical means that can detect abnormal signs of water inrush in advance and give an early warning,the automatic monitoring and early warning of water inrush in mines has been widely valued in recent years.Due to the many factors affecting water inrush and the complicated water inrush mechanism,many factors close to water inrush may have precursory abnormal changes.At present,the existing monitoring and early warning system mainly uses a few monitoring indicators such as groundwater level,water influx,and temperature,and performs water inrush early warning through the abnormal change of a single factor.However,there are relatively few multi-factor comprehensive early warning identification models.Based on the analysis of the abnormal changes of precursor factors in multiple water inrush cases,11 measurable and effective indicators including groundwater flow field,hydrochemical field and temperature field are proposed.Finally,taking Hengyuan coal mine as an example,6 indicators with long-term monitoring data sequences were selected to establish a single-index hierarchical early-warning recognition model,a multi-factor linear recognition model,and a comprehensive intelligent early-warning recognition model.The results show that the correct rate of early warning can reach 95.2%.

Identification of Mine Water Inrush Source Based on PCA-BP Neural Network

It is of great significance to analyze the chemical indexes of mine water and develop a rapid identification system of water source, which can quickly and accurately distinguish the causes of water inrush and identify the source of water inrush, so as to reduce casualties and economic losses and prevent and control water inrush disasters. Taking Ca2+, Mg2+, Na+ + K+, , , Cl-, pH value and TDS as discriminant indexes, the principal component analysis method was used to reduce the dimension of data, and the identification model of mine water inrush source based on PCA-BP neural network was established. 96 sets of data of different aquifers in Panxie mining area were selected for prediction analysis, and 20 sets of randomly selected data were tested, with an accuracy rate of 95%. The model can effectively reduce data redundancy, has a high recognition rate, and can accurately and quickly identify the water source of mine water inrush.

基于水化学指标的淮南煤田潘谢矿区矿井水源识别研究

快速分析突水成因和准确判别突水水源是矿井突水灾害治理的关键,应用深度神经网络理论,结合矿井含水层的水化学分析资料,选取8种特征离子作为矿井突水水源识别的判别因子,构成深度神经网络的输入状态空间,选取水源类别作为分标签,构成深度神经网络的输出状态空间,从而构建矿井突水水源识别的深度神经网络模型。以2734组采样的水源样品作为学习样本对该模型进行训练,在训练集上可达到95%以上的识别准确率。利用文中方法对淮南矿区的水源进行了识别,结果表明,深度神经网络模型分类性能良好,预测精度高。

Application of HEMS cooling technology in deep mine heat hazard control

This paper mainly deals with the present situation, characteristics, and countermeasures of cooling in deep mines.Given existing problems in coal mines, a HEMS cooling technology is proposed and has been successfully applied in some mines.Because of long-term exploitation, shallow buried coal seams have become exhausted and most coal mines have had to exploit deep buried coal seams.With the increase in mining depth, the temperature of the surrounding rock also increases, resulting in ever increasing risks of heat hazard during mining operations.At present, coal mines in China can be divided into three groups, i.e., normal temperature mines, middle-to-high temperature mines and high temperature mines, based on our investigation into high temperature coal mines in four provinces and on in-situ studies of several typical mines.The principle of HEMS is to extract cold energy from mine water inrush.Based on the characteristics of strata temperature field and on differences in the amounts of mine water inrush in the Xuzhou mining area, we proposed three models for controlling heat hazard in deep mines:1) the Jiahe model with a moderate source of cold energy;2) the Sanhejian model with a shortage of source of cold energy and a geothermal anomaly and 3) the Zhangshuanglou model with plenty of source of cold energy.The cooling process of HEMS applied in deep coal mine are as follows:1) extract cold energy from mine water inrush to cool working faces;2) use the heat extracted by HEMS to supply heat to buildings and bath water to replace the use of a boiler, a useful energy saving and environmental protection measure.HEMS has been applied in the Jiahe and Sanhejian coal mines in Xuzhou, which enabled the temperature and humidity at the working faces to be well controlled.

Principles and technology for stepwise utilization of resources for mitigating deep mine heat hazards

As is well known, deep mines are hot. As mining depth increases, the temperature of the surrounding rock also increases. This seriously affects mine safety and production and has restricted the exploitation of deep coal resources. Therefore, reducing the working face temperature to improve working conditions by controlling these heat hazards is an urgent problem. Considering problems in cooling deep mines both domestically and abroad along with the actual conditions of the Zhangshuanglou coal mine, we propose a HEMS technology that uses heat resources from deep mines in a stepwise manner. HEMS means a high temperature ex-change machinery system. Mine inrush-water is used as a source of cooling. Twice the energy is extracted from the mine inrush water. Heat is used for building heating in the winter and cold water is used for cooling buildings in the summer. This opens a new technology for stepwise utilization of heat energy in deep mines. Energy conservation and reduced pollution, an improved environment and sustainable economic development are realized by this technique. The economic and social effects are obvious and illustrate a good prospect for the application and extension of the method.

综放开采下煤层底板采动破坏深度预测

以淮南顾北煤矿12121工作面为工程研究背景,收集了22个综放工作面地质资料和底板破坏深度实测值,通过线性回归分析建立新的预测模型,得出了底板采动破坏深度的拟合公式,准确计算出底板采动破坏的深度,并将计算值及3个传统统计公式计算结果与现场实测值进行对比分析,得出新预测模型拟合公式比传统统计公式预测精度更高、误差更小,更接近实测值,基本可以满足现场需要。研究成果对淮南矿区煤层综放开采水害防治具有较高的实用价值,为类似工作面的水害防治提供更为科学的依据。

凤凰山矿关井后矿井水对周边矿井影响研究

凤凰山矿停采关井后矿井排水、直排井系统均停止排水,水位上升威胁周边生产矿井的安全生产。鉴于此,晋煤集团在综合分析晋城某矿区井下涌水的充水水源、充水通道、涌水流场、补径排关系的基础上,研究分析了凤凰山矿关井后矿井水对周边矿井的影响程度。研究结果表明,凤凰山矿关井后采空区水不会对晋普山煤矿、朝阳煤矿造成威胁,但会使昌都煤矿产生一定风险,昌都煤矿需留设保护煤柱以防止凤凰山矿关井后水位上升引发透水事故。

基于水化学特征及演化过程的灰岩突水模式研究

矿井突水过程中的水化学特征及其演化规律,对于准确识别矿井突水源具有重要意义。为阐述水化学特征及演化过程与灰岩突水模式的内在联系,采集了孙家沟煤矿灰岩水和突水水样,并通过对水样的对比分析,揭示了底板开裂-灰岩突水过程中主要离子浓度的变化特征及水化学演化机制。结果表明,灰岩水类型为Cl-Ca型,突水类型均为Cl-Na型;地下水阳离子交换程度为突水>灰岩水,平均阳离子交换含量△C_((K++Na+)C)分别为30.85 mmol/kg和8.10 mmol/kg。基于阳离子交换对地下水离子浓度的影响,认为研究区灰岩水和突水样品具有相同的来源。

瞬变电磁探测技术在煤矿防水工作中的应用研究

文章深入研究了瞬变电磁探测技术在煤矿防水工作中的应用情况,通过高精度瞬变电磁仪,成功探测了煤矿工作面的含水异常区,并运用比拟法对涌水量进行了准确计算。在实验分析中,利用MATLAB模拟软件验证了该方法的可行性。研究结果表明,有10个探测点的突水系数均不符合安全标准;结合超前探测钻孔技术,有效疏排约1.8×10^(4)m^(3)积水,显著增强了巷道掘进的安全性,瞬变电磁探测技术为煤矿防水工作提供了有力支持。

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.

基于综合对抗解释结构模型的煤矿透水事故致因分析

为了更加科学高效地对煤矿透水事故致因进行辨识和分类管理,以2021年丰源煤矿“4·10”重大透水事故为例,运用24Model法对事故致因进行分类提取,采用综合对抗解释结构模型(简称TAISM),对致因进行层级结构划分和因果关系分析。通过计算得到了该起事故致因的1组7层对抗型有向拓扑层级图。研究结果表明:监督机构监督检查不力、当地政府安全发展意识不强是造成此次事故发生的最根本原因。此外,在事故致因层级图中出现了2个回路,而同一个回路中的不同事故致因存在较强的关联性,应对其进行一体化控制,最大限度减少煤矿安全事故的发生。为今后煤矿事故致因分析提供了新的思路。

基于非线性渗流理论的破裂岩体突水危险性量化方法

破裂岩体是主要的突水通道之一,突水发生时地下水在破裂岩体中表现出非线性渗流特征,但由于破裂岩体内部结构的复杂性,对其突水危险性的研究以定性分析为主,难以量化评价。为了能够找到一种破裂岩体突水危险性量化方法,开展了破裂岩体非线性渗流实验,研究了破裂岩体的内部结构参数和水在破裂岩体内的非线性渗流参数的变化规律,基于多孔介质非线性渗流理论和分形理论,推导了非线性渗流数学模型,确定了破裂岩体的结构特征参数、非线性渗流特征参数与破裂岩体的突水危险性分级三者之间的关系,建立了基于非线性临界压力梯度的突水危险性判据,结果表明:非线性临界压力梯度可以作为评价破裂区域突水危险性的量化指标,该量化指标同时考虑了破裂岩体内部结构参数和地下水的非线性流动状态参数;相较于传统的突水危险性确定方法只考虑完整岩层的阻水能力,建立的非线性临界压力梯度突水危险性判据考虑了破裂区域岩层和完整岩层在内的所有岩层能够承受的总的临界水压值,反映了所有岩层的阻水能力。建立的非线性临界压力梯度突水危险性判据创新性地尝试了将非线性渗流状态参数应用到突水危险性量化方法研究当中,是一种将破裂岩体的内部结构参数和地下水的流动状态参数耦合的突水危险性量化方法。

基于改进的SSA-BP神经网络的矿井突水水源识别模型研究

机器学习与寻优算法的结合在矿井突水水源识别上得到广泛应用,但突水水样数据具有随机性且寻优算法易陷入局部最优,提高模型泛化能力和跳出局部最优需进一步研究。针对上述问题,提出了一种改进的麻雀搜索算法(SSA)优化BP神经网络模型,用于对矿井突水水源进行定量辨识。以鲁能煤电股份有限公司阳城煤矿为研究对象,通过常规离子浓度分析、Piper三线图对该煤矿水样的水化学特征进行分析,初步判断矿井水来源于奥灰含水层和三灰含水层,并确定Na^(+)+K^(+)浓度、Ca^(2+)浓度、Mg^(2+)浓度、HCO_(3)^(-)浓度、SO_(4)^(2-)浓度、Cl^(-)浓度、矿化度、总硬度、pH值作为突水水源识别指标;建立基于改进SSA-BP神经网络的矿井突水水源识别模型:首先进行SSA参数设置,引入Sine混沌映射使麻雀种群均匀分布,然后通过计算适应度值进行麻雀种群的更新,引入随机游走策略扰动当前最优个体,如果满足终止条件,则获得最优BP神经网络权重和阈值,最后基于构建的BP神经网络,输出识别结果。研究结果表明:①改进的SSA-BP模型在训练集上的识别准确率达95.6%,在测试集上的识别准确率达100%。②改进的SSA-BP神经网络模型与BP神经网络模型、SSA-BP神经网络模型对比结果:BP神经网络模型误判率为5/18,SSA-BP神经网络模型的误判率为2/18,改进的SSA-BP神经网络模型误判率为0,迭代10次后趋于稳定,且与设定的目标误差相差最小,初始适应度值最优,识别结果可信度高。③将阳城煤矿5组矿井水水样数据作为输入层数据输入到训练好的模型中,矿井水水样的主要来源为奥灰含水层、三灰含水层和山西组含水层,模型识别结果与水化学特征分析的结论相互印证,实现了精准区分。

陕西省煤矿典型水灾隐患特征及治理技术

陕西省煤炭资源丰富,2022年煤炭产量达7.46亿t,是我国主要产煤省份之一。由于全省煤矿区地质及水文地质条件差异明显,煤矿水灾类型多样,随着近年煤炭开采强度的增大,水灾事故时有发生,防治水形势较为严峻。以煤炭赋存条件为基础,系统总结区域水文地质结构特征,界定典型水灾类型及各类水灾影响区域分布,论述典型水灾的形成机理及特征,并提出了相应的防控技术。研究表明:(1)陕西省主要煤炭产区分为陕北、黄陇、渭北三大区,陕北侏罗纪煤田主要有顶板松散沙层水灾隐患、厚层砂岩水灾隐患、溃水溃沙灾害,局部区域分布有烧变岩对煤矿造成水灾隐患;黄陇煤田主要受顶板巨厚砂岩水灾隐患、离层溃水隐患、泥砂溃涌灾害隐患威胁;陕北石炭—二叠纪煤田和渭北煤田,主要受到煤层底板奥陶系灰岩水灾隐患威胁。(2)陕北侏罗系煤田顶板水灾隐患主要为顶板含水层受开采导水裂隙带扰动形成,导水裂隙波及砂岩含水层或松散沙层可形成持续大流量涌水,部分区域充水强度较大,在短时间水量较大超过排水系统能力时造成顶板水灾,在薄基岩区域垮落带直接导通松散沙层时可转变为溃水溃沙灾害,导水裂隙带影响到烧变岩富水区域时可形成瞬时水量大且持续的烧变岩水灾;黄陇煤田顶板巨厚砂岩含水层受采动导水裂隙带波及形成高强度持续涌水并可能形成顶板水灾,当含水层下部隔水层厚度较大时,可能形成离层溃水灾害,当近煤层顶板岩层松软遇水易崩解时可转变为泥砂溃涌灾害;陕北石炭—二叠纪煤田和渭北煤田,煤层开采底板扰动破坏带或断层等构造导通奥陶系灰岩含水层时,会引发极为严重的底板突水灾害,该类灾害具突发性强、瞬时水量大的特征。(3)各区域的顶板水灾隐患治理技术主要包括钻孔疏泄、注浆治理、开采参数控制等,底板水灾隐患治理技术主要包括区域注浆加固及封堵等;烧变岩水灾隐患主要采取帷幕注浆与钻孔探放有机结合的防治技术。

机器学习方法在矿井水防治理论体系研究中的应用思考

致灾机理、危险性评价、灾变预测共同构成矿井水防治理论体系基本内容,其在过去20多年里快速发展,目标是理解矿井水行为特征,预测演化趋势,服务矿区水害防治工作。机器学习是大数据时代进行数据分析和挖掘的有力工具。将机器学习应用于矿井水防治理论体系研究,已得到相对广泛的关注。针对理论体系的3项基本内容,重点讨论了机器学习在各内容建设中的具体应用,主要包括:根据不同水害类型分类简述致灾机理研究现状,指出机器学习应用暂为空白的原因为其不具备做出假设的能力。认为未来致灾机理研究方法依然以传统方法(理论分析、数值模拟、相似模拟等)为主,机器学习促进地质数据获取与处理,对机理研究作出贡献;分析方法优势,指出机器学习作用于危险性评价的主要方式为非结构化数据的处理及丰富评价方法;分析基于物理和基于数据的单一预测模式弊端,论述物理模型与数据驱动相结合的必要性,相应给出“模型-数据”双驱动预测模式的3种实现形式,并讨论了基于图像的灾变预测方法可行性。随着生产数据及地质数据的丰富,机器学习方法可推动理论体系研究快速发展,并为矿井水防治学科系统方法论研究作出贡献。

基于微震监测技术的煤矿底板突水预警研究

煤矿底板突水是矿山生产中的主要灾害之一,其破坏性极大,因此,研究有效的突水预警技术具有重要意义。以董家河煤矿22517工作面为例,构建了微震监测系统,并对底板进行突水预警。监测数据显示,该煤矿的底板微震事件总共有191个,其中能量超过1000 J的微震事件仅为18个,占全部微震事件的9.63%,同时,该系统检测到的底板破坏深度约为11.01 m,与底板钻孔声波仪测试计算的数据仅相差0.22 m。这些数据可以说明研究所提出的微震监测技术能够有效预测煤矿底板的突水事故,起到了良好的预警作用,为煤矿开采作业的水害风险防范提供了可靠的技术支持。

煤矿采动覆岩离层水害致灾因素勘查与预测评价

采动覆岩离层突水在我国各地矿区均较为常见且危害性较大,现有的规范中鲜有针对离层水害的具体工程地质和水文地质勘查方法。探索煤矿离层水害工程地质水文地质勘查与评价方法,能够推动我国矿井水害防治水平进一步提升。首先从煤矿采动覆岩高位离层水害孕灾机制出发,分析了离层水害从孕灾到致灾的工程地质条件,将我国现有的离层水害归纳为3种典型类型:离层动力突水、离层静水压涌突水和离层携泥砂突水。然后,确定了“水源”“通道”“力源”和“物源”为控制离层水害类型与强度的关键隐蔽致灾因素,将位于传统导水裂隙带以上,可发生离层突水的复合层位称为采动覆岩“突水离层带”,并提出了煤矿采动覆岩“突水离层带”的判别流程,划分勘查阶段,指明勘查要点。煤矿离层水害采前勘查应包括2个阶段:①开展覆岩基本工程地质和水文地质条件勘探,评估勘探区离层水害的可能性并确定潜在“突水离层带”的层位;②将“突水离层带”和“物源”层作为勘查目标层,开展离层水害致灾因素专项勘查,评定离层水害类型和强度。回采期间对水动力条件和覆岩裂隙演化进行探查。最后,基于离层水害致灾因素互馈演化致灾机制,建立了适用于采动覆岩离层水害的矿井区域预测综合评价模型,提出了全矿井/采区尺度的区域危险性分区、采前工作面突水位置判定及涌水量预计的煤矿采动覆岩离层水害预测评价方法。

新集矿区深部1煤层底板奥灰岩溶突水危险性评价

奥灰岩溶裂隙含水层是影响华北型煤矿深部开采的重要水害,在水-岩相互作用下奥灰含水层易导致煤层底板突水。为进一步认识奥灰岩溶突水问题,文章以新集矿区深部1煤层开采为例,利用矿区近些年最新积累的奥灰钻孔资料,选取断层强度指数、断层交叉点与尖灭点、含水层水压、富水性、隔水层等效厚度、脆塑比7个因素作为奥灰岩溶突水的主控因素,并结合层次分析法(analytic hierarchy process,AHP)确定各主控因素影响权重。运用地理信息系统(geographic information system,GIS)空间分析功能建立各主控因素专题图,通过对专题栅格图归一化处理,将各主控因素按照权重进行空间复合叠加,最终获得1煤层底板奥灰岩溶突水危险性评价分区结果。将评价结果与突水系数法计算结果对比分析可知,基于GIS的煤层底板突水危险性评价方法更符合矿区实际地质情况,可以为矿区深部煤层开采与水害防治工作提供参考依据。

煤岩体突水通道骨料灌注运移堆积机制试验

为揭示突水通道中骨料运移堆积的演化规律,开展了动水条件下骨料灌注试验,得到了骨料的初始沉积位置、堆积体形成方向以及堆积体极限堆积高度与水流速、骨料灌注速度等影响因素的内在关联。结果表明:在1.0 m/s高流速动水环境中,骨料堆积体形成方向为先逆水流方向生长至投料孔底后转为顺水流方向生长;在0.3 m/s低流速条件下,采用口径36 mm漏斗投料同口径18 mm相比,骨料灌注总量相同时,其堆积体的极限高度提升了41%。基于数值力学模型——计算流体动力学-离散元方法(computational fluid dynamics and distinct element method,CFD-DEM),研究了骨料灌注期间突水通道内流场的时空分布特征以及骨料堆积体的过水阻力作用对突水通道内静水压力的影响机制。

大采深高承压水条件下煤层底板突水问题及解决对策

在当前煤矿普遍面临大采深、底板高承压水、高地应力等采掘条件下,正确评价煤层底板承压水突水危险是做好防治水工作的基础。以河南省受底板灰岩承压水突水威胁的大水矿井为例,就底板破坏深度计算、突水系数计算及临界值、脆弱性指数法、不同水文地质单元的“双层水位”效应等问题进行了剖析。分析表明:在大采深和高地应力开采条件下,底板破坏深度较现有用经验公式计算得到的值偏大,一些矿井突水系数虽小于全国临界值,但回采过程中却发生了突水,脆弱性指数法有待于规范化。此外,井田范围内水文地质条件存在着时空变化,甚至会出现“双层水位”等现象。鉴于此,提出了建立大采深和高地应力开采条件下的底板破坏深度计算模型、确定矿区或矿井范围的临界突水系数值、规范脆弱性指数评价方法、查明水文地质条件的时空变化和不同单元的水动力参数、制定同各单元水文地质条件相适应的防治水措施等各项对策。