Fuzzy inference system using genetic algorithm and pattern search for predicting roof fall rate in underground coal mines

One of the most dangerous safety hazard in underground coal mines is roof falls during retreat mining.Roof falls may cause life-threatening and non-fatal injuries to miners and impede mining and transportation operations.As a result,a reliable roof fall prediction model is essential to tackle such challenges.Different parameters that substantially impact roof falls are ill-defined and intangible,making this an uncertain and challenging research issue.The National Institute for Occupational Safety and Health assembled a national database of roof performance from 37 coal mines to explore the factors contributing to roof falls.Data acquired for 37 mines is limited due to several restrictions,which increased the likelihood of incompleteness.Fuzzy logic is a technique for coping with ambiguity,incompleteness,and uncertainty.Therefore,In this paper,the fuzzy inference method is presented,which employs a genetic algorithm to create fuzzy rules based on 109 records of roof fall data and pattern search to refine the membership functions of parameters.The performance of the deployed model is evaluated using statistical measures such as the Root-Mean-Square Error,Mean-Absolute-Error,and coefficient of determination(R_(2)).Based on these criteria,the suggested model outperforms the existing models to precisely predict roof fall rates using fewer fuzzy rules.

Interpretable deep learning for roof fall hazard detection in underground mines

Roof falls due to geological conditions are major hazards in the mining industry,causing work time loss,injuries,and fatalities.There are roof fall problems caused by high horizontal stress in several largeopening limestone mines in the eastern and midwestern United States.The typical hazard management approach for this type of roof fall hazards relies heavily on visual inspections and expert knowledge.In this context,we proposed a deep learning system for detection of the roof fall hazards caused by high horizontal stress.We used images depicting hazardous and non-hazardous roof conditions to develop a convolutional neural network(CNN)for autonomous detection of hazardous roof conditions.To compensate for limited input data,we utilized a transfer learning approach.In the transfer learning approach,an already-trained network is used as a starting point for classification in a similar domain.Results show that this approach works well for classifying roof conditions as hazardous or safe,achieving a statistical accuracy of 86.4%.This result is also compared with a random forest classifier,and the deep learning approach is more successful at classification of roof conditions.However,accuracy alone is not enough to ensure a reliable hazard management system.System constraints and reliability are improved when the features used by the network are understood.Therefore,we used a deep learning interpretation technique called integrated gradients to identify the important geological features in each image for prediction.The analysis of integrated gradients shows that the system uses the same roof features as the experts do on roof fall hazards detection.The system developed in this paper demonstrates the potential of deep learning in geotechnical hazard management to complement human experts,and likely to become an essential part of autonomous operations in cases where hazard identification heavily depends on expert knowledge.Moreover,deep learning-based systems reduce expert exposure to hazardous conditions.

Analysis of mechanism of shock bump due to roof fall

According to the characteristics of the shock bump due to roof fall, a simple mechanics model has been established by applying the catastrophic theory and the law of energy conservation. The author suggests that the shock bump may be induced by the sudden energy release in the roof falling after underground mineral extractions, and through the systematic analysis of actual examples on site, the empirical formulae for the roof falling and energy release are derived, which would provide a new way for the study of the origin and mechanism of mine tremor due to fallen-in roof structure. It is of a great importance to enrich the shock bump theory and production safety in mine.

Integrated real-time roof monitoring

CSIRO has recently developed a real-time roof monitoring system for under-groundcoal mines and successfully tried the system in gate roads at Ulan Mine.The systemintegrated displacement monitoring,stress monitoring and seismic monitoring in onepackage.It included GEL multianchor extensometers,vibrating wire uniaxial stress meters,ESG seismic monitoring system with microseismic sensors and high-frequency AE sensors.The monitoring system automated and the data can be automatically collected by acentral computer located in an underground nonhazardous area.The data are then transferredto the surface via an optical fiber cable.The real-time data were accessed at anylocation with an Internet connection.The trials of the system in two tailgates at Ulan Minedemonstrate that the system is effective for monitoring the behavior and stability of roadwaysduring Iongwall mining.The continuous roof displacement/stress data show clearprecursors of roof falls.The seismic data (event count and locations) provide insights intothe roof failure process during roof fall.

Stress state and caving danger of the roof in bolt supporting roadway

The start point of this text is the bottleneck problem of bolt supporting coal entrythat is security problem of bolt supporting roof,we divide one entry into some sections withdifferent stress,simulate stress field of wall rock and rockbolt solidified at different sectionsused umbrella disperse soft UDEC(universal distinct element code),we educe that thestress level of wallrock and bolt solidified is higher in roof fall risk section,and roof rockboltload can reflect this rule clearly,that offer an important guideline in monitoring entry rooffall risk.

急倾斜煤层综采工作面开切眼钻扩施工技术研究

为解决急倾斜煤层开切眼施工难度大,冒顶、飞矸伤人事故频繁发生的问题,以绿水洞煤矿3212综采工作面开切眼为研究对象,提出了采用钻机由下向上施工钻孔形成下煤通道,再由上向下刷大至设计断面的急倾斜煤层开切眼施工方案,在分析了施工技术难点的基础上,提出了下煤通道钻孔、扩孔、护孔、防堵、疏通以及开切眼扩刷、支护等技术措施,工业性试验结果表明:采用钻机沿急倾斜煤层由下向上施工钻孔方式能够代替人工爆破小断面形成下煤通道,有效杜绝煤层随时冒顶给人员带来的安全威胁,同时该方案避免了对开切眼围岩的二次破坏,围岩变形量明显减小,确保急倾斜煤层条件开切眼的施工安全,保证了矿井安全生产。

工作面煤岩互层复合顶板深浅孔注浆加固技术研究

为了解决工作面煤岩互层复合顶板出现破碎松散、离层脱落、整体漏矸严重甚至大面积冒顶等难题,以新元煤矿9104工作面为工程背景,采用现场调研、理论分析及数值模拟方法,研究了工作面煤岩互层复合顶板失稳破坏机理,划分了长度分别为3、25、23 m的基础治理区域、关键治理区域及重要治理区域,确定了工作面复合顶板分区、分重点加固的治理思路。基于此,提出了在回风巷进行"两深孔、一浅孔、两材料、三区域"的分区复合超前预注浆协同加固技术的方案,并依据现场工程实践、工程类比及理论计算公式确定了注浆材料及注浆关键参数。现场工程应用表明,该技术可有效解决工作面煤岩互层复合顶板破碎松软导致的大面积漏矸、冒顶及开采受阻等问题,确保工作面能以正常速度安全回采。

顶板冒顶隐患分区预测模型及应用实践

为解决井下大断面巷道的支护安全问题,参考行业内学者对巷道冒顶机理和顶板稳定性影响因素研究理论,将数学分析和实测考察相结合,通过层次分析法、加权平均法处理不同因素对顶板稳定影响权重;建立指标量化准确、考察简便、层次清晰的顶板稳定性评价体系和冒顶隐患分区预测模型;经过锦界矿开切眼应用实践,该方法预测分级准确,可对薄弱危险区域支护进行针对性的补强完善。

Prediction of upper limit position of bedding separation overlying a coal roadway within an extra-thick coal seam

Failure of the surrounding rock around a roadway induced by roof separation is one major type of underground roof-fall accidents.This failure can especially be commonly-seen in a bottom-driven roadway within an extra-thick coal seam("bottom-driven roadway"is used throughout for ease of reference),containing weak partings in their roof coal seams.To determine the upper limit position of the roof interlayer separation is the primary premise for roof control.In this study,a mechanical model for predicting the interlayer separation overlying a bottom-driven roadway within an extra-thick coal seam was established and used to deduce the vertical stress,and length,of the elastic,and plastic zones in the rock strata above the wall of the roadway as well as the formulae for calculating the deflection in different regions of rock strata under bearing stress.Also,an approach was proposed,calculating the stratum load,deflection,and limiting span of the upper limit position of the interlayer separation in a thick coal seam.Based on the key strata control theory and its influence of bedding separation,a set of methods judging the upper limit position of the roof interlayer separation were constructed.In addition,the theoretical prediction and field monitoring for the upper limit position of interlayer separation were conducted in a typical roadway.The results obtained by these two methods are consistent,indicating that the methods proposed are conducive to improving roof control in a thick coal seam.

深埋大断面开切眼大厚度泥岩顶板冒顶机理及其梯次支护技术研究

针对深埋大断面开切眼大厚度泥岩顶板易发生冒顶的问题,以张家洼煤矿9 m宽的大断面开切眼为研究对象,采用室内试验、现场实测、理论分析及数值模拟等研究了该类巷道的围岩变形破坏特征与应力场分布特征,揭示了冒顶机理,并提出了锚网梁+长短锚索的梯次主动支护与单体柱+木垛的联合被动支护相组合的协同控制技术。结果表明:发生冒顶的内在原因是直接顶的大厚度泥岩强度低,外在原因是水对泥岩的崩解破坏、单体柱反复加卸载的疲劳损伤以及深部高应力,主要原因是支护参数不合理。通过梯次支护中9.3 m的短锚索与锚网梁将顶板中下部的软岩有效组合在一起,形成一个具有承载作用的锚固体,且受力均匀;通过梯次支护中12.3 m的长锚索将该锚固体悬吊于深部稳定岩层。再配合该联合被动支护的有效支撑与信号作用,协同实现该条件下巷道围岩的有效控制。采用梯次支护技术后,1305开切眼围岩稳定性显著提高。

Roof bolting and underground roof falls

Roof bolting has been used in underground entry(roadway)support in U.S.coal mines since the Coal Mine Health and Safety Act of 1969(US Congress,1977)recognized roof bolting as the only means of underground entry(roadway)support.For U.S.underground coal mines,roof bolting pattern is fixed at 4
4 ft(1.2
1.2 m),except in the Pittsburgh Seam where longwall mining is practiced,with occasional 3.6
4 ft(1.1
1.2 m)pattern.However,roof falls or roof failure often occurs in roof-bolted entries in U.S.coal mines.Roof falls can roughly be divided into four types:skin falls,large falls,cutter roofs,and massive falls.Based on this situation,the roof is initially strengthened by bolt based on suspension and friction mechanism.By comparing roof bolting patterns in different coal producing countries,bolt density in all other countries is much higher(except South Africa)than that used in the U.S.In spite of its long history of successful application with hundreds of millions of units installed,roof bolting design is still the lack of a commonly accepted method.

煤矿安全管理问题分析及措施研究

煤矿安全问题严重制约煤炭的开采,威胁工人的人身安全,制订合理、科学的安全管理措施尤为必要。列举了煤矿安全事故中常见的几种,包括瓦斯问题、顶板问题、防治水问题,分析了发生的主要原因,提出了相应的应对措施,为提高煤炭开采工作的安全性提供保障。

李家壕矿切眼顶板冒顶危险区预测技术研究

为解决李家壕矿11208工作面切眼由于断面尺寸大而容易发生冒顶的问题,采用现场测试、理论分析、现场试验等研究方法,对大断面切眼顶板冒顶危险区预测方法进行了研究,建立了以顶板离层变形、岩层结构、支护质量为预测指标的冒顶危险区预测模型,将顶板按冒顶危险程度分为五个等级,并对11208工作面切眼顶板冒顶危险区进行了预测。结果显示超过50%面积的切眼顶板存在冒顶危险,据此对危险区域进行了补强支护设计,补强支护后的顶板离层量从最初的几百毫米降到现在的十几毫米,下沉位移速度放缓,且逐渐趋于稳定。