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 app-lied 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 condi-tions 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.     

基于PSO-BP神经网络的导水裂隙带高度预测

导水裂隙带高度是西部矿区保水采煤的理论依据和关键参数。近年来,BP神经网络广泛应用于导水裂隙带高度预测,但BP神经网络存在收敛速度慢、易陷入局部极小等问题。为提高导水裂隙带高度预测的准确性,利用粒子群优化算法(PSO)对BP神经网络的权值和阈值进行优化,建立基于PSO-BP神经网络的导水裂隙带高度预测模型。选择开采厚度、开采深度、工作面倾斜长度、煤层倾角、覆岩结构特征为导水裂隙带高度主要影响因素,选取22例导水裂隙带高度实测数据对PSO-BP神经网络进行训练,将训练后的PSO-BP神经网络对2例测试样本的预测结果与实际值进行对比,并与BP神经网络预测模型及经验公式预测结果进行对比。结果表明:PSO-BP神经网络预测模型的平均相对误差为1.55%;BP神经网络预测模型的平均相对误差为4.8%,经验公式的最小相对误差为9.4%,PSO-BP神经网络预测精度明显优于BP神经网络和经验公式,且绝对误差和相对误差变化较稳定,可以有效预测导水裂隙带高度。      

基于BP神经网络方法的矿井涌水量预测

鉴于矿井涌水威胁煤矿安全生产及其影响因素的复杂性,提出基于BP神经网络的矿井涌水量预测方法.在充分分析新安煤矿＋25m开采水平的涌水影响因素的基础上,选取大气降水、采空区面积和底板构造断裂和采动裂隙三个影响因子,建立了非线性人工神经网络预测模型,对＋25m开采水平的正常涌水量进行了预计.其结果和实际观测数据能够较好地相吻合,表明采用人工神经网络预计矿井涌水量是可行的.     

基于BP神经网络的孔隙充水矿井涌水量预测

文章分析了孔隙充水矿井的充水水源和通道,利用非线性的BP人工神经网络建立了徐州韩桥煤矿涌水量短期预测模型,选取每天的降水量作为影响因子,用已有的涌水量资料训练得到权值和阈值来表示充水通道,并对-200m水平、-270m水平、-330m水平和全矿井涌水量进行了预测。结果显示,涌水量的预测值与实测值吻合得较好,说明该模型具有一定实用性。     

基于LSTM神经网络的煤矿突水预测

针对煤层底板突水预测问题,在总结现有突水预测方法和理论的基础上,通过特征选择实验得出水压、距工作面距离、砂岩段厚度、煤层厚度、煤层倾角、断层落差、裂隙带、开采面积、采高、走向长度是影响突水发生的主要因素,这些因素具有复杂、非线性的特点。提出基于长短时记忆（LSTM）神经网络构建的突水预测模型,将煤矿突水实例的数据作为样本数据对模型进行训练。最后,将LSTM神经网络模型与遗传算法-反向传播（GA-BP）神经网络模型和反向传播（BP）神经网络模型进行对比实验。实验结果表明,LSTM神经网络模型在测试集上的预测正确率更高,稳定性更好,更适用于煤层底板突水预测。      

基于GA-SVM的矿井涌水量预测

矿井涌水量的准确预测对预防矿山透水事故的发生至关重要,提出利用GA优化的SVM模型（GA-SVM）来实现矿井涌水量的短期准确预测。该方法利用GA的自动寻优功能寻找SVM的最佳参数,提高了预测的准确率。首先,利用微熵率法求矿井涌水量时间序列的最佳嵌入维数和延迟时间,进行相空间重构。其次,采集义煤集团千秋煤矿2011—2015年实际涌水量的时间序列,利用GA-SVM模型对最后12组数据进行预测,其预测平均绝对百分比误差仅为0.92%,最大相对误差为2.62%。最后,与PSO-SVM和BP神经网络预测进行对比,结果表明GA-SVM优化模型适用于矿井涌水量的预测并且预测精度较高。      

基于BP神经网络的降雨充水矿井涌水量预测

长沟峪煤矿矿井涌水量受降雨影响显著,曾经因降雨造成淹井事故。文章分析了长沟峪煤矿矿井充水因素及其影响程度,建立了矿井涌水量预测的BP网络模型,通过对2006年和2007年＋141水平和＋20水平矿井最大涌水量预测验证了该模型的可行性,并据此对不同降雨条件下的矿井涌水量进行了预测。     

深埋土岩接触带下导水裂隙带发育规律

为了探寻深埋土岩界面下压架突水事故的机理,在分析高水压裂隙岩体赋存特征的基础上,基于导水裂隙带高度实测值及钻孔简易水文观测资料,采用理论及主控因素影响分析研究了深埋砂土砂岩界面下导水裂隙带的发育规律,研究结果表明:近深埋土岩界面带煤层开采,裂采比与防水煤岩柱高度符合Boxlucas1指数函数模型;当煤层顶板岩层大部分位于风化带深度范围时,风化带岩性的存在对导水裂隙带的高度发育起到了一定的抑制作用;风化带厚度对导水裂隙带的高度起到一定的抑制作用;而砂土砂岩界面下,由于下渗带的存在,水对岩体强度的影响,使得处于下渗带内岩层实际对导水裂隙带高度抑制作用相应的增大。     

基于SSA优化的GA-BP神经网络煤层底板突水预测模型与应用

随煤层开采深度的不断增加,煤矿生产过程中面临着复杂的突水机理和多变的突水主控因素,且各因素间相互联系的不确定性,使底板突水预测的难度不断增加。为准确预测底板突水危险性,针对底板突水的小样本、非线性问题,首先利用遗传算法(Genetic Algorithm,GA)将网络随机赋值的初始权值和阈值初次优化,再选取搜索能力强、稳定性较好的麻雀搜索算法(Sparrow Search Algorithm,SSA)对权值和阈值进行二次寻优,从而建立SSA-GA-BP神经网络底板突水预测模型。分析整理山东省滨湖煤矿地质及水文地质资料,选取含水层水压、含水层厚度、隔水层厚度、断层密度、断层分维值、渗透系数、单位涌水量、底板破坏深度共8个因素,作为预测底板突水的主控因素,绘制各主控因素3D映射投影曲面图;利用Surfer软件中的克里金插值法提取50个数据点作为模型的输入样本(分为训练集40个,测试集10个),对模型进行训练学习,训练误差精度达到要求后,对滨湖煤矿3个未开采工作面的12个数据点进行突水危险性预测。为了验证所建模型的准确性,利用BP、GA-BP、SSA-GA-BP这3种模型对测试集进行预测;为避免模型仅与BP网络预测对比的片面性,同时选取以熵权法确定权重的模糊综合评判法对测试集进行预测;将各网络模型及方法的预测结果与实际值进行对比分析。结果表明:基于SSA优化的GA-BP神经网络模型突水预测误差较小,预测结果准确率更高,为矿井水害预测预报提供了科学的评价方法和理论依据。      

Prediction of groundwater inrush into coal mines from aquifers underlying the coal seams in China: application of vulnerability index method to Zhangcun Coal Mine,China

Groundwater inrush is a geohazard that can significantly impact safe operations of the coal mines in China. Its occurrence is controlled by many factors and processes are often not amenable to mathematical expressions. To evaluate the water inrush risk, Professor Wu and his colleagues have proposed the vulnerability index approach by coupling the artificial neural network (ANN) and geographic information system (GIS). The detailed procedures of using this innovative approach are shown in a case study. Firstly, the powerful spatial data analysis functions of GIS was used to establish the thematic layer of each of the main factors that control the water inrush, and then to choose the training sample on the thematic layer with the ANN-BP Arithmetic. Secondly, the ANN evaluation model of the water inrush was established to determine the threshold value for each risk level with a histogram of the water inrush vulnerability index. As a result, the mine area was divided into four regions with different vulnerability levels and they served as the general guidelines for the mine operations.     

小庄矿井采煤对地下水的影响及保水采煤措施

针对煤炭开采易造成地表塌陷及含水层破坏等问题,采用类比法计算了彬长矿区规划新建的矿井——小庄矿井开采导水裂缝带高度,在此基础上分析了采煤对地下水的影响,并提出保水采煤的措施。经计算,采用分层开采时产生的导水裂隙带最大高度为147.84 m,在三盘区将导通安定组隔水层,造成宜君组、洛河组承压含水层破坏,导通区域面积为0.773 6 km2。因此,在可能导通的区域应进行保水采煤以保证安定组隔水层的稳定,从而达到保护具有供水意义的含水层和保障矿井生产安全的双重目的。      

灵新煤矿导水裂隙带发育高度数值模拟研究

煤矿的开采利用给国民经济发展带来巨大的收益,但也引发了许多环境地质问题,特别在煤层开采过程中,煤层上覆基岩变形破坏形成的裂隙通道极易发生矿井涌（突）水事故,时刻威胁着井下工人的生命安全。本文以灵新煤矿051505工作面为研究对象,利用Flac3D数值模拟软件,对14号主采煤层上覆基岩导水裂隙带高度进行了模拟研究。模拟结果表明：当煤层开采厚度为2.5 m时,导水裂隙带发育最大高度为59.5 m。同时选取经验公式法对导水裂隙带高度进行了计算。最终通过钻孔实测法得到的结果与前两种方法对比分析,数值模拟结果与钻孔实测结果基本吻合,认为数值模拟方法能够高效、简单、合理达到预测导水裂隙带高度的目的,也为同类矿井安全、绿色生产提供一定的借鉴。     

The Hazard Analysis of Water Inrush of Mining of Thick Coal Seam Under Reservoir Based on Entropy Weight Evaluation Method

The water inrush of roof induced by mining was related to the height of water flowing fractured zone under large-scale water bodies. Based on the drilling revealed stratum, the thickness of different overlying layers was obtained within the scope of Santaizi reservoir. The height of water flowing fractured zone of different workface on the outside of reservoir under the condition of fully mechanized level mining area was the prediction sample, the generalized analysis of sensitive factors that affected the development of water flowing fractured zone was carried on. The mining depth, dip angle of coal seam, mudstone ratio, compressive strength, mining thickness and the inclined length of the goaf were selected as the influence factors to predict the height of water flowing fractured zone. The height of water flowing fractured zone of unmined working face within the scope of Santaizi reservoir was obtained by objective entropy method. The index weight value of each influence factor was determined. The thickness of the different overlying rock layers above water flowing fractured zone was obtained. And the safety evaluation of water-inrush of unmined working face within the scope of Santaizi reservoir was studied. The important parameter and technical support were provided for the rational design and mining of the working faces under the reservoir.     

基于量纲分析的非充分采动导水裂缝带高度预测

为准确预测非充分采动导水裂缝带高度,选取开采厚度M、煤层埋深H、工作面倾斜长度L、煤层倾角α、覆岩力学性质R、覆岩结构特征S为非充分采动导水裂缝带高度主要影响因素。采用量纲分析建立了导水裂缝带高度与M,H,L,α,S间的无量纲关系式。结合30组实测数据,采用多元回归得到无量纲关系式的最优函数关系式。选取2个非充分采动工作面导水裂缝带现场实例对预测模型进行了工程验证,预测模型预测结果与实测结果吻合良好,其相对误差分别为3.64%和2.93%,预测模型的预测精度可以满足煤矿安全生产现场需要。      

Prediction of groundwater inrush into coal mines from aquifers underlying the coal seams in China: vulnerability index method and its construction

Groundwater inrushes often occur in the coal mines of China. One of the water sources is the aquifers underlying the coal seams. Because such a water hazard is affected by many factors, data collected from various sources need to be evaluated to predict its occurrence. This paper introduces an innovative approach in which the water inrush risk is represented by the vulnerability index. This method combines the geographic information system and the artificial neural network. The artificial neural network is used to estimate the weight of each factor. Unlike the traditional prediction method in which two controlling factors are often evaluated without regard to their relative importance, this new approach incorporates multi-factors and describes the non-linear dynamical processes.     

大采高综放开采覆岩破坏特征和裂隙演化规律

工作面回采过程中,覆岩破坏特征对于煤矿水灾害和瓦斯防治具有重要意义,为了进一步研究综放开采覆岩破坏特征。以山西某矿5.82m大采高工作面为试验面,采用分段注水、钻孔电视、地质雷达、微震监测探测覆岩破坏高度,对破坏过程进行了数值模拟研究,并对裂隙演化进行了相似模拟试验,同时对传统经验公式进行了修正,研究结果表明:综放开采垮落带发育高度为43.1m,断裂带发育高度为86.7m;垮落带、断裂带、导水断裂带各测试方法之间相差分别小于4.5%、7.1%、9.0%;工作面采动前,裂隙发育度低,而采动后,裂隙数量明显增多,发育度增加;近煤壁区域为裂隙聚集区,密度曲线呈“蛇”型分布;得到新的适合该矿地质条件下的覆岩导水断裂带发育高度经验公式。     

综采一次采全高顶板导水裂缝带发育高度的计算公式及适用性分析

确定煤层顶板导水裂缝带高度可为顶板防治水、采掘工程布置、防水煤柱留设以及瓦斯抽采设计提供依据。采用井下仰孔注水测渗漏法,实测山西西山煤田镇城底矿8煤导水裂缝带高度为57.98 m,其中冒落带高度16.72 m,裂隙带高度41.26 m。依据实测结果并收集了8个矿综采一次采全高中硬覆岩下导水裂缝带高度数据,利用数理统计回归分析的方法,得出了适用于综采一次采全高中硬覆岩下导水裂缝带高度计算的经验公式,并与《煤矿安全规程》中相应经验公式进行对比分析,结果表明,该公式适用性好,而《煤矿安全规程》中有关公式应用于中厚煤层综采一次采全高开采条件预测,其误差较大。      

Numerical Simulation of the Lagging Water Inrush Process from Insidious Fault in Coal Seam Floor

Because of insidious fault’s concealing performance and lagging nature, water inrush from insidious faults in coal seam floor can cause great threads to the mine safety. Based on analyzing the engineering geology conceptual model, this paper simulated the insidious fault lagging water inrush process and showed the lift height of the confined water in the insidious fault fractured zone (LHCWIFFZ) and the formation of water inrush channel. Then the concept of the potential water inrush channel with time effect was put forward. In order to further illustrate the time effect of the lagging water inrush from insidious fault, theoretical analysis was made from two aspects of the time effect of the plastic zone development height in the insidious fault fractured zone (PZDHIFFZ) based on the differential flow deformation theory and the time effect of water inrush channel in the upper part of the insidious fault (WICUPIF) based on the subcritical crack propagation theory. Simulation results showed that the results are basically consistent with mining practice.     

On prevention and mechanism of bed separation water inrush for thick coal seams: a case study in China

Bed separation can occur in overlying strata, especially in hard and soft interbedded roof strata. If these strata prone to form bed separation are rich aquifers, water can accumulate into bed separation and maybe cause a serious water hazard under the condition of water inflow passages existence. Therefore, studying these types of roof water inrush mechanisms, forecasting roof water inrush, and formulating preventive and control measures in advance are extremely important to a mine. In this paper, we takes the typical case of water inrush in the workface number 1121 at Hongliu coal mine as an example, and study the mechanism of water inrush in detail. Primarily, field drilling with water leakage and color TV observations showed that the maximum height of the water conducting fractured zone was 12.50 times the thickness of the coal seams, which spread to the overlying coarse-grained sandstone aquifer. Secondly, the numerical simulation indicated that bed separation storage space was prone to form under the combination of coarse-grained sandstone and mudstone geological structure. The detection using UWTEM revealed that the groundwater accumulated in this bed separation and formed a water bag (bed separation water). When the water bag reached a certain degree, water bursting happened with the main roof collapsing. Finally, prevention, effective drainage methods, and successful experiences with bed separation water have been summarized, and it will have a major significance to coal mines suffering from bed separation water inrush.     

断层破裂带附近采场采动效应的流固耦合分析

矿井底板突水是一个复杂的多物理场耦合问题,结合含断层破裂带条件下采场开采的工程背景,通过离散元流固耦合分析,研究了采场工作面推进过程中断层带的变形与受力情况以及底板支承压力、渗流矢量和渗流速度的动态发展规律和分布特征。相关模拟结果表明,采场中煤层的开采与断层破裂带之间是相互影响的,以支承压力为代表的采动应力是底板破坏形成导水裂隙带及断层“活化”突水的一个主要诱因,而断层的存在也使得工作面与断层带范围内的围岩应力更加集中,增大了底板破坏突水的危险性。采动过程中,底板破坏所形成的导水裂隙带主要集中在工作面前方及下方围岩中,这些区域渗流速度较大,是形成突水的主要通道。