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.

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.

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.

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.

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.

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.