Waste-filling in fully-mechanized coal mining and its application

A fully-mechanized coal mining (FMCM) technology capable of filling up the goaf with wastes (including solid wastes) is described. Industrial tests have proved that by using this technology not only can waste be re-used but also coal resources can be exploited with a higher recovery rate without removing buildings located over the working faces. Two special devices, a hydraulic support and a scraper conveyor, run side-by-side on the same working face to simultaneously realize mining and filling. These are described in detail. The tests allow analysis of rock pressure and ground subsidence when backfilling techniques are employed. These values are compared to those from mining without using backfilling techniques, under the same geological conditions. The concept of equivalent mining height is proposed based on theoretical analysis of rock pressure and ground subsidence. The upper limits of the rock pressure and ground subsidence can be estimated in backfilling mining using this concept along with traditional engineering formulae.

Use of machine learning algorithms to assess the state of rockburst hazard in underground coal mine openings

The risk of rockbursts is one of the main threats in hard coal mines. Compared to other underground mines, the number of factors contributing to the rockburst at underground coal mines is much greater.Factors such as the coal seam tendency to rockbursts, the thickness of the coal seam, and the stress level in the seam have to be considered, but also the entire coal seam-surrounding rock system has to be evaluated when trying to predict the rockbursts. However, in hard coal mines, there are stroke or stress-stroke rockbursts in which the fracture of a thick layer of sandstone plays an essential role in predicting rockbursts. The occurrence of rockbursts in coal mines is complex, and their prediction is even more difficult than in other mines. In recent years, the interest in machine learning algorithms for solving complex nonlinear problems has increased, which also applies to geosciences. This study attempts to use machine learning algorithms, i.e. neural network, decision tree, random forest, gradient boosting, and extreme gradient boosting(XGB), to assess the rockburst hazard of an active hard coal mine in the Upper Silesian Coal Basin. The rock mass bursting tendency index WTGthat describes the tendency of the seam-surrounding rock system to rockbursts and the anomaly of the vertical stress component were applied for this purpose. Especially, the decision tree and neural network models were proved to be effective in correctly distinguishing rockbursts from tremors, after which the excavation was not damaged. On average, these models correctly classified about 80% of the rockbursts in the testing datasets.

Microstructure & performance of laser cladding on pick surface of coal mining machine

Laser cladding of 316 L steel powders on pick substrate of coal mining machine was conducted, and microstructure of laser cladding coating was analyzed. The micro-hardness of laser cladding coating was examined. The results show that microstructure of laser cladding zone is exiguous dentrite, and there are hard spots dispersible distribution in the laser cladding zone. Performances of erode-resistant, surface micro-hardness and wear-resistant are improved obviously.

Study on safe thickness of overlying thin bedrock in fully-mechanized top-coal caving face with thick coal seam

To prevent support crush, the overlying strata safe thickness and its influential elements were studied by the adoption of theoretical analysis, numerical simulation and in-situ measurement. According to the production and geological condition of first face in Sima coal mine, the results indicate that the clay contains large permissible bearing ability and has better arching force. After mining destruction, stable structure is formed in bedrock to ensure face safety. The clay thickness ＆ bedrock thickness are the key influential elements to stable structure. The minimal bedrock thickness is about 40 m to ensure safe mining under loose surface soil condition. When surface soil contains mainly thick clay, it forms steady structure with the composition of thin bedrock, so that it can reduce minimal thickness of bedrock and to ensure safe mining. When clay thickness is 40 m, minimal bedrock thickness is 20 m. When clay thickness is 30 m, minimal bedrock thickness is 30 m. Bearing pressure peak ranges from 5 to 15 m in the front face under thin bedrock condition. The bearing pressure distribution range is 15 m. Main roof break distance is small, and initial weighting of main roof is not distinctive, while first periodic weighting of main roof is quite distinctive.

Fluidized mining and in-situ transformation of deep underground coal resources: a novel approach to ensuring safe, environmentally friendly, low-carbon, and clean utilisation

Traditional coal mining and utilisation patterns are severely detrimental to natural resources and environments and significantly impede safe, low-carbon, clean, and sustainable utilisation of coal resources. Based on the idea of in situ fluidized coal mining that aims to transform solid coal into liquid or gas and transports the fluidized resources to the ground to ensure safe mining and low-carbon and clean utilisation, in this study, we report on a novel in situ unmanned automatic mining method. This includes a flexible, earthworm-like unmanned automatic mining machine (UAMM) and a coal mine layout for in situ fluidized coal mining suitable for the UAMM. The technological and economic advantages and the carbon emission reduction of the UAMM-based in situ fluidized mining in contrast to traditional mining technologies are evaluated as well. The development trends and possible challenges to this design are also discussed. It is estimated that the proposed method costs approximately 49% of traditional coal mining costs. The UAMM-based in situ fluidized mining and transformation method will reduce CO2 emissions by at least 94.9% compared to traditional coal mining and utilisation methods. The proposed approach is expected to achieve safe and environmentally friendly coal mining as well as lowcarbon and clean utilisation of coal.

Feasibility analysis of gob-side entry retaining on a working face in a steep coal seam

Based on the decline in exploitation of coal resources, steep coal seam mining and mining face tensions continue to explore the feasibility analysis of steeply inclined faces in the gob. One of the key factors in utilizing the technology of gob-side entry retaining in steep coal seams is to safely and effectively prevent caving rock blocks from rushing into the gob-side entry by sliding downwards along levels. Using theoretical analysis and field methods, we numerically simulated the mining process on a fully-mechanized face in a steep coal seam. The stress and deformation process of roof strata has been analyzed, and the difficulty of utilizing the technology is considered and combined with practice in a steep working face in Lvshuidong mine. The feasibility of utilizing the technology of gob-side entry retaining in a steep coal seam has been recognised. We propose that roadways along the left lane offshoot body use a speciallymade reinforced steel dense net to build a dense rock face at the lower head. The results show that the lane offshoot branch creates effective roof control, safe conditions for roadway construction workers, and practical application of steeply inclined gob.

HSP超前探测技术在煤矿TBM掘进巷道中的应用研究

随着全断面掘进机TBM(Tunnel Boring Machine)逐渐应用于煤矿岩巷掘进,对不良地质构造进行超前准确快速预测的需求日益迫切。通过对主动源地震波超前探测方法的特点和TBM破岩震源超前探测技术的适用性进行分析,结合煤矿巷道地质和生产条件,提出了适用于煤矿巷道TBM掘进的HSP超前探测方法。以河南平顶山首山一矿TBM掘进底板瓦斯治理巷道为工程背景,选用防爆硬件一体化设计的探测仪器在煤矿巷道中进行应用。构建了空间型观测方式对煤矿巷道近水平煤线进行探测,优化了双护盾TBM掘进巷道狭小空间检波器阵列式布置参数;基于时频分析、互相关干涉处理、反射与散射联合反演等方法处理原始信号并进行探测结果成像。研究表明:采用空间型观测方式可实现与巷道小角度斜交煤线的识别,设计震源与首检波器间距离为15 m时最优。通过时频分析提取有效信号,利用互相关干涉法获取虚拟震源道和反射特征曲线,并结合反射与散射联合反演成像得到探测区域地层反射能量分布图,能够较准确地推测得到围岩存在的不良地质构造。通过比较现场开挖揭露情况与探测结果发现两者吻合度较高,表明HSP超前探测方法可实现掘进工作面前方100 m范围内超前无损地质预测,有助于提高煤矿岩巷TBM掘进速度。

智能煤矿综采控制系统双人协同作业情境意识研究

目的探究智能煤矿综采控制系统双人协同作业中个体在不同协同条件下的情境意识(SA)的构建情况,为智能煤矿中人员协同操作模式提供管理的相关依据。方法利用E-prime软件模拟智能煤矿综采控制系统中的采煤机运行状态监控任务,实验模拟四种不同协同场景(单独作业、操作协同、工作交流协同、非工作内容交流协同),利用全局情境意识技术测度被试总体情境意识以及感知、理解、预测三阶段情境意识得分,并验证不同协同条件下双人协同作业模式中个体的情境意识影响差异。结果双人操作协同与工作内容交流协同显著提升个体情境意识水平,并取得较高的工作绩效;在情境意识感知阶段,非工作内容交流协同与其他三组对比情境意识得分显著下降;在理解阶段,工作内容交流组与其他三组均呈现情境意识得分上的显著性差异,且工作内容交流组得分最高;在预测阶段单独作业组与操作协同组和工作内容交流协同组在SA得分上存在显著性差异,单独作业在预测阶段的得分显著低于有协同组。结论相较于单独作业,操作协同、有关工作内容的交流协同能够有效维持个体情境意识和提高绩效水平,但非工作内容的交流协同反而会降低个体情境意识。

基于模型迁移和SVM的煤矿电网单相接地电容电流预测方法

针对智慧化矿山背景下煤矿电网单相接地电容电流预测精度低和智能预测实现困难的问题,提出了一种单相接地电容电流智能预测方法。采用模型迁移思想扩充矿用橡套软电缆的电容电流样本数据,以解决智能预测中电容电流数据不完备的问题;基于Sobol’敏感性方法分析了影响单相接地电容电流的关键因素及其各因素的交互关系,确定智能预测模型输入特征量;在此基础上,通过基于稀疏技术的支持向量机建立煤矿电网单相接地电容电流智能预测模型,并引入鲸鱼算法优化预测模型超参数,克服了电容电流数据样本容量小的不足。采用厂家测试数据及多家煤矿电网现场实测数据进行试验,结果表明:电缆绝缘层外径和绝缘层内径是影响单相接地电容电流的关键因素;所提方法预测煤矿电网单相接地电容电流的平均误差为2.26%,相较于现有预测方法,误差分别下降了34.19%,24.91%和7.40%。该方法实现了煤矿电网单相接地电容电流的准确预测,并为其智能化预测提供了新思路。

采煤机滚筒齿座焊接定位机器人系统的设计

针对目前采煤机螺旋滚筒齿座焊接定位精度和工作效率较低等问题,提出采用机器人系统进行齿座焊接定位,该系统主要由四台机器人、一台变位机和一套智能控制系统等组成,利用PQArt仿真软件编写齿座焊接定位工作程序,使机器人和变位机协同工作,从而完成齿座焊接定位的智能化作业,并进行了工业性试验,试验结果表明:该系统提高了齿座焊接定位的智能化程度,提高了齿座焊接定位的精度和工作效率,经济和社会效益显著。

基于多传感器融合的模糊PID采煤机截割路径自适应控制方法

截割路径自适应控制是提高采煤机生产效率和质量的重要手段,但现行方法控制精度较低,在实际中,截割路径RMSE、MAE均比较高。针对现行方法存在的不足和缺陷,提出基于多传感器融合的模糊PID采煤机截割路径自适应控制方法。采用多传感器融合技术感知采煤机截割运动学模型中位置及状态信息,并对多传感器数据融合处理,根据采煤机截割运动学规律得到采煤机截割路径,模糊化截割路径偏差,利用PID控制器调控比例、积分、微分3个参数,修正采煤机截割路径偏差,实现基于多传感器融合的模糊PID采煤机截割路径自适应控制。实验证明,设计方法应用下的采煤机截割路径RMSE和MAE得到了明显降低,为采煤机截割路径自适应控制提供了一定参考。

基于工业互联网架构的煤矿瓦斯智能抽采管控系统设计

目前煤矿瓦斯智能抽采管控系统存在以下问题:①系统功能局限于某一段流程管控,导致瓦斯抽采业务管理覆盖不全、措施落实不到位。②基于传统的“烟囱式”IT架构,导致子系统分散、数据利用率低、协同能力差,后期子系统融合代价大、系统扩展不便。③瓦斯抽采过程仍存在较多的人工环节,系统智能化、自动化能力还有待进一步提升。针对上述问题,设计了一种基于工业互联网架构的煤矿瓦斯智能抽采管控系统。基于发布/订阅模式开发了瓦斯抽采多源异构数据采集流程,促进了数据的解耦和共享,降低了系统复杂度,实现了瓦斯抽采管网数据、钻孔作业及轨迹数据、设备工况数据、达标评判数据等多源异构数据的统一采集。基于数字孪生技术,构建了三维抽采系统模型,达到了井上下抽采系统的立体化展示。基于规则引擎技术,根据订阅的Topic对经过消息中心处理后的传感器数据进行判断,可进行告警消息的推送,并将处理后的传感器数据存入数据库中,以实现瓦斯抽采达标评判的自动化、流程化运行。利用机器视觉视频分析技术识别钻杆根数,从而实现钻孔过程的钻杆根数(钻孔深度)的自动计数和钻孔工程的信息化管理,结合钻孔测量仪器,实现了钻孔轨迹左右、上下偏差分析及可视化。现场应用结果表明:瓦斯抽采相关管理人员通过查看瓦斯智能抽采管控系统软件,可实时快速地了解各抽采面抽采情况、抽采评判情况、钻孔工程施工情况、系统故障情况,提高了瓦斯抽采信息化和智能化管理水平。

煤炭工业发展关键技术突破与超级煤矿建设

为了发展煤炭领域先进生产力,助力煤炭工业高质量发展,研究了近年来我国采场围岩控制技术发展历程,分析了采动应力演化规律及围岩断裂失稳过程,创新提出了超大采高工作面围岩断裂失稳力学模型、控制准则及液压支架合理工作阻力计算方法。系统阐述了我国综采技术装备发展历程,研发了最大采高10 m的超大采高综采成套装备,以及最大支护高度7.0 m的超大采高综放成套装备,解决了西部矿区浅埋深、坚硬、厚及特厚煤层安全高效开采技术难题。系统分析了我国主要煤炭产区煤矿智能化建设现状、关键技术、取得的建设成效及存在的主要问题,提出了智能化超级煤矿的定义、特征及内涵,研究了典型超级煤矿建设成效与经验,并从标准体系、数据体系、技术体系、管理体系、生态体系建设等方面阐述了未来煤炭工业主要发展方向。

煤质煤量全面在线检测技术发展现状及应用进展

当前,煤矿智能化正在向着中高级阶段迈进,煤炭工业数智化转型迫切需要实时掌握煤质煤量全面信息,因此,开展了煤质煤量全面在线检测技术发展现状及应用进展综述研究。在分析煤质煤量检测技术工业应用需求的基础上,重点阐述以激光诱导击穿光谱法(LIBS)及其与其他光谱联合的多光谱联用技术为代表的光谱学技术的基本原理、优缺点、研究进展与工业应用情况和以图像分析为代表的人工智能煤质煤量检测方法。然后,基于不同技术的工业应用情况进行问题梳理,分析实时煤质煤量在线检测技术在工业应用中的技术局限性,包括:基于技术原理的探测精度问题;由复杂环境因素引用的设备稳定性问题;基于大量数据处理的算法分析问题;煤炭全产业链应用的技术适用与灵活性问题。最后,对未来煤质煤量全面分析及在线检测技术提出4点发展建议:结合地质条件的煤质在线检测技术研究;工业化多光谱联用技术研究;光谱学与图像分析技术联用煤质煤量全面分析技术研究;智能化在煤质煤量实时检测的深入应用研究。智能化煤质煤量全面分析及在线检测装备研发需多学科共同努力,基于煤岩学、光谱学、仪器仪表工程、数据处理和模式识别、人工智能和机器学习等多学科科学技术,建立工业应用场景-煤质煤量参数-实际应用指导数据库,是实现智能化煤质煤量在线检测,掌握和预测全面煤质煤量信息的重要发展方向。

煤矿采煤机智能化技术研究

随着我国社会经济水平的日渐提高,同时也给煤炭开采加大了工作量,因此需要煤矿开采技术向集约化、精细化转变,智能化技术是当今科技发展的热点,智能化也代表着更加先进的生产力,同时也需要更加全面和高端的复合型人才投入到煤矿开采智能化的进程中去。通过对采煤机智能化进行分析和研究,对其使用的关键技术进行了剖析,并对煤矿开采智能化的未来进行了探讨和展望,为后续研究提供了参考经验。

基于随机森林算法的煤巷顶板位移预测与应用

煤巷围岩稳定控制是保障煤矿安全高效开采的关键,煤巷顶板位移量是反应煤巷围岩稳定性的关键指标,本研究提出机器学习方法对煤巷顶板位移进行超前预测研究。确定了煤巷顶板位移的8个重要影响指标,建立了煤巷顶板位移预测数据库并对数据进行了指标相关性和重要性分析。基于RF、GA-SVM和GA-ANN分别建立了三种煤巷顶板位移预测模型,选用RMSE、MAE和R2三个指标来评价模型的性能。结果显示,RF模型测试性能最佳,R2=0.909,RMSE=20.475,MAE=16.790,GA-ANN模型的性能最差。采用十折交叉方法对RF模型和GA-ANN模型进行可靠性验证,结果显示RF模型的稳定性更高,平均R2为0.891。将RF模型应用到干河煤矿2-1121巷,预测值与实际值的绝对误差为19 mm,相对误差为11.18%,说明了RF模型对煤巷顶板位移预测的准确性与可靠性,研究结果对煤巷顶板位移预测提供了一种新途径。

采煤机自动化与智能化控制技术的改进研究

山西晋城某煤矿薄煤层工作面采用MG300/700-WDK型采煤机,该采煤机自动化和智能化程度不高,为实现该煤矿9103工作面智能化建设,对该采煤机进行自动化与智能化控制技术改进。实践应用表明,改进后采煤机可实现自动记忆截割功能、降低设备故障率、实现了少人作业,提高了生产效率的优点,安全经济效益显著。

智采工作面三机数字孪生驱动控制架构

为了进一步提高煤矿综采设备智能控制水平,实现智采工作面常态化运行,提出基于数字孪生智采工作面驱动控制的相关概念和系统架构。智采工作面数字孪生系统由物理设备、虚拟孪生体、虚实交互模型组成,通过数字化方法建立与实体设备相映射的虚拟模型,来达到综采设备在作业过程中虚实交互、智能决策、精准控制和动态演化的目的。阐述智采工作面常态化运行要求和采煤机、液压支架和刮板输送机的相关控制难点。提出了智采工作面单机数字孪生驱动控制架构,包括机理模型、控制模型、孪生数据模型和数字孪生模型同步与演化等要素;研究数字孪生虚实交互方法,利用信息物理系统来保障信息交互能力,采用知识模型来解决数据拥堵问题,为智采工作面数字孪生控制系统的虚实交互提供实时性。提出智采工作面数字孪生驱动的三机协同控制方法,包括三机关联关系、智能采煤控制、智能支护控制与智能运输控制。最后以矿山数字孪生实际应用为例,通过建立相关模型和设计相关实验方案,对数字孪生智能控制进行验证。通过展开数字孪生智能控制架构、模式等理论研究,旨在解决目前综采工作面存在的环境感知程度低、设备预测精度差和人工干预强度大等问题,实现在复杂环境条件下设备的自适应控制与人机交互,为煤矿智能化建设提供借鉴意义。

薄煤层工作面“三机”设备选型及布置

为进一步提升煤矿极近距离煤层的开采效率和安全性,降低煤炭开采成本,以某14号煤层为研究对象,结合相关理论计算公式对液压支架、采煤机以及刮板输送机的核心指标进行核算并完成设备的确定;对所选型的综采设备在现场进行布置并对工程实践应用效果进行评估。

基于信息量-机器学习耦合模型的采煤沉陷区滑坡敏感性评价

【目的】采煤沉陷区由于其特殊的地质条件和采煤背景,极易引发地面裂缝和地面塌陷,进而导致滑坡等地质灾害,选择适用的影响因子和训练模型在该地区开展滑坡敏感性评价十分必要。【方法】以北京西山煤矿区为例,采用斜坡单元与数学统计模型和机器学习模型耦合方法,开展采煤沉陷区的滑坡敏感性评价。在地理信息系统环境中,选取坡度、坡向、地表湿润度等地形地貌因子,并加入地质背景的地层岩性和与断层距离因子,采煤背景的与采煤巷道距离和与井口距离等共10个因子作为评价指标,通过相关性分析优化滑坡敏感性评价体系。同时以水文分析法划分的地形斜坡单元为评价基础,分别应用信息量模型(I)信息量-随机森林(I-RF)、信息量-多层感知机(I-MLP)耦合模型对滑坡敏感性进行空间预测。【结果和结论】结果表明,耦合模型(I-RF、I-MLP)的精度均高于独立模型(I),3种模型的AUC值分别为0.861、0.845、0.761,I-RF模型具有更强的预测能力和精度。此外地质和采煤背景因子的加入,优化了滑坡敏感性的评估效果。为了验证滑坡敏感性分区结果的实用性,以北京市“23·7”强降雨事件为时间节点,利用大比例尺航空摄影测量、时序InSAR技术等手段对滑坡敏感性评估结果进行佐证。结果表明,基于斜坡单元和耦合模型的滑坡敏感性评估结果与诱导事件后的滑坡灾害发育情况,有很大程度的吻合性。滑坡敏感性评价结果在一定程度上可以反映各斜坡的滑坡发生概率,对于采煤沉陷区滑坡灾害的预测和防治工作的开展有一定的参考性。