Hazards In Coal Mines Research Articles

Hybrid CNN-LSTM and IoT-based coal mine hazards monitoring and prediction system

IoT-enabled sensor devices and machine learning methods have played an essential role in monitoring and forecasting mine hazards. In this paper, a prediction model has been proposed for improving the safety and productivity of underground coal mines using a hybrid CNN-LSTM model and IoT-enabled sensors. The hybrid CNN-LSTM model can extract spatial and temporal features from mine data and efficiently predict different mine hazards. The proposed model also improves the flexibility, scalability, and coverage area of a mine monitoring system to an underground mine's remote locations to minimize the loss of miners' lives. The proposed model efficiently predicts miner's health quality index (MHQI) for working faces and gases in goaf areas of mines. The experimental results demonstrated that the predicted mean square error of the proposed model is less than 0.0009 and 0.0025 for MHQI; 0.0011 and 0.0033 for CH4 in comparison with CNN and LSTM models, respectively. The less means square error indicates the better prediction accuracy of the trained. Similarly, the correlation coefficient (R2) value of the proposed model is found greater than 0.005 and 0.001 for MHQI; 0.007 and 0.001 for CH4 compared to CNN and LSTM models, respectively. Thus, the proposed CNN-LSTM model performed better than the two existing models.

PERSEPSI KARYAWAN TERHADAP SISTEM PELAPORAN KECELAKAAN KERJA DAN POTENSI BAHAYA DI PERTAMBANGAN BATUBARA PT. PUTRA KAJANG KALIMANTAN TIMUR

Work accidents in coal mining still occur frequently, so an accident reporting system is needed as an effort to prevent work accidents. This study aims to explain the perceptions of coal mining employees on the reporting system for work accidents and potential hazards. The research design was descriptive with a sample size of 55 people. Data collection was carried out using a questionnaire. Data were analyzed descriptively. As many as 67.3 % of employees have positive perceptions and 32.7 % of employees have negative perceptions of the work accident reporting system and potential hazards. There are 72.7% of employees consider it important to report accidents and potential hazards. It was found that 30.9 % of employees had experienced work accidents and only 5.4 % of them reported accidents. Employees consider a good accident reporting system, among others, digitally 84.6 % and manually 9.1 %. As many as 90.9 % of employees agree and 81.8 % of employees are willing to report accidents and potential hazards if the company implements a digital-based reporting system. There are still employees who have negative perceptions of the work accident reporting system and potential hazards in coal mining. Therefore, efforts are needed to increase employee perceptions from negative to positive perceptions of the work accident reporting system and potential hazards in coal mining companies.

Analysis and Assessment of Parameters Shaping Methane Hazard in Longwall Areas

Increasing coal production concentration and mining in coal seams of high methane content contribute to its growing emission to longwall areas. In this paper, analysis of survey data concerning the assessment of parameters that influence the level of methane hazard in mining areas is presented. The survey was conducted with experts on ventilation and methane hazard in coal mines. The parameters which influence methane hazard in longwall areas were assigned specific weights (numerical values). The summary will show which of the assessed parameters have a strong, or weak, influence on methane hazard in longwall areas close to coal seams of high methane content.

Hazard identification methodology for underground coal mine risk management - Root-State Hazard Identification

Hazard identification is the basis and premise of underlying risk management in underground coal mines. Although a large amount of research has been conducted on hazard identification methods applied to underground coal mines, additional improvements are possible. The traditional hazard identification methods apply to a specific incident or event or are based on experience and therefore lack a systematic and comprehensive identification framework. In this paper, the Root-State Hazard Identification (RSHI) method is proposed to solve the above issues and identify the hazards in underground coal mine risk management. Firstly, the paper categorizes the underground coal mine hazards into root hazards and state hazards and then differentiates their internal relationships. Secondly, the paper explores the relationships among the hazards, risks and accidents in detail. Thirdly, the framework of the RSHI method is proposed based on the hazard classification and relationships among the hazards, risks and accidents. Finally, the proposed RSHI method is applied to identify hazards associated with the risk management of six mines that belong to the Yima Coal Industry Group in China. The results indicate that the RSHI method is capable of comprehensively identifying root hazards and state hazards associated with the underground coal mine risk management. Moreover, its application procedure is simple and convenient and reduces the need for the joint identification and coordination of various types of workers.

Coupling Relation between the Location of Cross-Cut Negative Pressure and Injecting Nitrogen into Coal Mine Goaf.

Injecting nitrogen into goaf has been widely adopted for preventing fire hazards in coal mines. In this paper, the coupling relation between different locations of negative pressure of cross-cut drainage and nitrogen injection was investigated. The minefield data collection was carried out by an in situ beam tube system on the intake airway and return airway of the mine goaf. The validated Computational Fluid Dynamics (CFD) model that was secondarily modified by on-site collected data was applied for further research. It is demonstrated that the area of the spontaneous combustion zone generally shows a sharp decline first, then tends to stabilize, and finally has a slight drop and rise with the increasing nitrogen injection time. It is obvious that the location of the negative pressure of cross-cut exerts a significant influence on the optimal nitrogen injection location and time. When the cross-cut is located in the center of the air leakage zone, spontaneous combustion zone, and asphyxiation zone of goaf, the optimal nitrogen injection location and time correspond to the P2 (25 m, 1200 min), P3 (30 m, 120 min), and P4 (35m, 1800 min), respectively. According to the simulation result, the specific relation between the optimal nitrogen injection point N(x) and the distance from the working distance of the cross-cut (x) by Newton interpolation polynomial analysis was figured out and verified that N(x) = 24.70808 + 0.293356x – 0.001436x2. It is hoped that the result can provide scientific guidance for coal mine fire prevention and control with nitrogen injection.

Model-based Seismic Imaging and Analysis of Karst Water Hazards in Coal Mining

Accurate detection of karst water is the premise of karst water disaster control in coal mines. It is difficult to identify karst geological characteristics based on seismic data, so to solve this problem, a digital model including the coal measure strata and complete karst system was established based on the karst status of a coal mine in the Huaibei area of China. The entire process of seismic acquisition, processing, and interpretation was simulated and then the model was restored according to the seismic interpretation. Based on the results, karst identification and water inrush risk prediction were tried. The results allowed the overall karst geological framework, karst cave system, and stratum contact relationships to be restored more truly. Thus, seismic data can provide accurate geological information for large-scale hydrogeological mine exploration.

On the issue of determining the main factors of gas hazard in coal mines of Ukraine

The main sources of methane emission are located in the undermined coal-bearing strata, which is not taken into account by the requirements of regulatory documents when determining the category hazard of coal mines. Gas emission from each undermined source is not equally dependent on the tons of coal mined. The relative gas emission changes during the cleaning work and cannot be a criterion for assessing the gas hazard of the entire mine. The volatility of the gas emission index per unit area of the underworked space, which was formed because of monthly movements of the working faces, was established. In essence, this indicator repeats the dependence of the relative gas content per ton of coal mined, since the area of the underworked space is functionally related to the amount of coal mined for a certain period. Without coal mining, the rate of movement of the working face is equal to zero, and gas emission from a unit area continues for several months. As a result, the considered indicators do not have their specific meaning and, due to their inconstancy, they cannot reliably reflect the gas hazard of mines.

Experimental Investigation on Mechanics and Seepage Characteristics of Tectonic and Intact Coal Containing Gas

Coalbed methane is a double-edged sword with two attributes of energy and hazard in coal mines. Gas drainage is the most direct and effective measure for gas recovery and disaster prevention in coal mines, which is seriously affected by the mechanics and seepage characteristics of coal. In this work, we experimentally simulated the triaxial compression and gas depletion processes using both tectonic coal and intact coal. The mechanics and seepage characteristics of tectonic and intact coal under the coupling effect of stress and gas pressure were analyzed and compared. The results show that during the triaxial compression, the damage stress and peak stress of tectonic coal is only half that of intact coal, while their compaction stress or residual stress are almost the same. Meanwhile, the permeability recovery value after tectonic coal failure is very limited, even smaller than that of intact coal, although its primary permeability is much larger than that of intact coal. On the contrary, the permeability recovery value after intact coal failure is more than twice of its primary permeability. During the gas depletion, the rebound gas pressure of tectonic coal is smaller than that of intact coal, and the permeability of tectonic coal is one order of magnitude larger than that of intact coal before the gas pressure drops to 2 MPa. The broken of tectonic coal and the low permeability of intact coal may be the two principal reasons. Therefore, in the tectonic coal area, the gas extraction time at high gas pressure stage should be stabilized, while in the intact coal area, the gas extraction time at low gas pressure stage should be increased, and the coal permeability enhancement measures should be combined to achieve the goal of high and stable production of coalbed methane.

Investigation of Groundwater In-rush Zone using Petrophysical Logs and Short-offset Transient Electromagnetic (SOTEM) Data

The water burst from the Ordovician limestone underlain by the Permo-Carboniferous coal seams have potential to trigger coalmine hazards in Northern China. Therefore, it is crucial to identify and accurately map the water enrichment zones and delineate coal seams using an integrated approach based on surface TEM and subsurface wireline log information to avoid water-inrush hazard and ensure safe production of coal. We inverted surface based TEM data using 1-D Occam inversion to identify the conductive anomaly and then further quantified the zone of interest by gamma and resistivity logs. 1-D Occam inversion results show conductive zone around 370 m while higher resistivity and lower gamma ray log signatures were observed against coal seams. Groundwater inrush zone falls within the mid-range gamma ray and resistivity interval as shown on the petrophysical logs. The distinct log signatures (low gamma-ray and high resistivity values) clearly indicated coal seams at depth of 410 and 470 m and subsequently the log trends were used to distinguish between coal units and more permeable sands. The magnitude and the variability of these parameters in the borehole are attributed to the subsurface stratigraphic heterogeneity. They can be key clues for interpretation of depositional facies of coal-bearing sequence and may also be used as a constraint in characterization of groundwater enrichment zone.

Mitigation of ancient coal mining hazards to overhead line equipment structures

Subsidence and collapse of structures supporting overhead line equipment (OLE) due to legacy coal mining can be catastrophic during both the construction and operational phases, causing damage to construction plant, injuries and fatalities to the construction and maintenance workforce, failure of the track and disruption to the operational railway. When applied to linear railway schemes spanning considerable distances, industry guidelines for appraising and mitigating these mining hazards are overly conservative with a disproportionate cost. On phase 4 of the North West Electrification Project between Manchester Victoria and Euxton Junction, an innovative risk-based method was devised and implemented to identify and mitigate mining hazards to OLE structures. Formulation of these value-engineering solutions prevented programme drift and led to significant cost savings. Details of this methodology, including a detailed desk study, computational geomechanics, a well-targeted ground investigation, void remediation and real-time foundation monitoring, are discussed in this paper.

Variation of ignition sensitivity characteristics of non-stick coal dust explosions

Abstract The ignition and explosion of coal dust are significant hazards in coal mines. In this study, the minimum ignition temperature and energy of non-stick coal dust were investigated empirically at different working conditions to identify the key factors that influence the sensitivity and characteristics of coal dust explosions. The results showed that for a given particle size, the minimum ignition temperature of the coal dust layer was inversely related to the thickness of the coal dust layer. Meanwhile, when the layer thickness was kept constant, the minimum ignition temperature of the coal dust layer decreased with smaller coal dust particle sizes. Over the range of particle sizes tested (25–75 μm), the minimum ignition temperature of the coal dust cloud gradually increased when larger particles was used. At the same particle size, the minimum ignition temperature of the coal dust layer was much lower than that of the coal dust cloud. Furthermore, the curves of minimum ignition energy all exhibited a minimum value in response to changes to single independent variables of mass concentration, ignition delay time and powder injection pressure. The interactions of these three independent variables were also examined, and the experimental results were fitted to establish a mathematical model of the minimum ignition energy of coal dust. Empirical verification demonstrated the accuracy and practicability of the model. The results of this research can provide an experimental and theoretical basis for preventing dust explosions in coal mines to enhance the safety of production.

Early-warning of rock burst in coal mine by low-frequency electromagnetic radiation

Rock burst is one of the major geological hazards in coal mines and is difficult to prevent. Faced with this problem, the low-frequency electromagnetic radiation (EMR) test experiments of coal and rock were conducted to explore the characteristics of low-frequency EMR (1 kHz) signals induced form fractures. The relation between EMR signals and paroxysmal fractures was analyzed theoretically. Time-series extraction method was put forward to represent coal and rock paroxysmal fractures. The research results showed that deformation and fracture of coal and rock is caused by the accumulation of paroxysmal and discrete fractures in the samples. The time series obtained by moving average method shows rather good correlation with interior coal rock fractures, which has more obvious precursory characteristics of coal rock instability and dynamic disasters. When the coal rocks are damaged under uniaxial compression, low-frequency EMR (1 kHz) signals are more sensitive to local fracture with more abundant precursor information than high-frequency EMR (500 kHz) signals. The paroxysmal and discrete low-frequency EMR (1 kHz) signal is quite sensitive to rock burst, and when the signals representing coal rock fractures show an increasing trend and the high signals last for some time, it can be regarded as the precursor of rock burst disaster in coal mine. The separation technology of EMR representing coal rock fractures provided the key scientific basis for the field monitoring and forewarning of EMR technology, and a new method to identify the precursor of dynamic disasters of coal and rock.

Fire Safety in Indian Coal Mines using Machine Learning Techniques

There are around 493 coal mines in India (300+ underground and around190 opencast mines) engaged in coal production for meeting energy and other requirements of our country. Coal and the process of mining itself creates an environment conducive for self-oxidation leading to build up of heat and subsequently break out of fire. This causes safety hazards, decrease in production, increased in de-settlement of colonies, fire related fatalities and risk to life and property. Occurrence of fires in coal mines has always been an undesirable proposition for the coal mining community worldwide due to its high hazard potential towards loss of human lives and property. However, with advent of AI/ML and deep learning, there emerges a vast scope of leveraging its application towards significantly reducing fire hazards in coal mining. Data capturing from such fiery mines, providing machine learning and predicting it beforehand for similar mining situations would significantly enhance safety standard in coal mining industry. This project proposes to develop an algorithm on getting input data from the past incidences/accidents of fire in coal mines and apply machine learning software to help it learn pattern/features vis a vis the fire outcomes. Once the learning is over and data trained, the programme would process the test data of other active projects and may predict for fire threat during forthcoming mining operation. The algorithm aims to enable mining personnel to assess and evaluate the risk of fire in their workplace and take informed decisions based on the predictions based on Machine learning outputs. Also, active fires can as well be studied and predicted in a similar way. This will help the mining team to decide about the right approach of continuing mining operation in such an affected area.

A Scientometric Analysis of Trends in Coal Mine Water Inrush Prevention and Control for the Period 2000–2019

Water inrush hazards in coal mines pose a great risk to the safety of miners and coal production. We studied journal articles on coal mine water inrush prevention and control from 2000 to March 2019 using data from the Web of Science Core Collection V.5.32 database. We used CiteSpace V.5.3.R11 software to analyse the literature, including countries, institutions, authors, disciplines, journals, hot topics, and research frontiers. A total of 1612 published papers on coal mine water inrush prevention and control research were identified. China and the USA had the highest numbers of publications in this field. The China University of Mining and Technology was the most influential research institution. The journal with the largest number of relevant publications was the International Journal of Coal Geology. Hidden water disasters, quantitative evaluation of aquicludes, and rapid identification of water inrush sources are still unresolved problems. Improvement of electromagnetic methods, intelligent mine water monitoring, and three-dimensional hydrogeological systems were the leading research trends in this field.

Rapid co-extraction of coal and coalbed methane techniques: a case study in Zhangji coal mine, China

Coalbed methane (CBM) is one of elements of coal mine hazards, the high CBM content and low permeability coefficients of coal seams in Huainan coal filed result in high difficulty of coal exploitation and CBM drainage, and the potential risk of gas explosion and combustion. The CBM drainage works are time-consuming and they typically delay the coal mining operations. A set of novel techniques of rapid co-extraction of coal and CBM are proposed in this paper. In the practice of 1413A longwall panel of Zhangji coal mine, a set of overlying and underlying drainage galleries were replaced by two overlying drainage galleries which were excavated by TBM, thereby the stress of excavation works was reduced. The pre-drainage and roadway excavation are conducted simultaneously and the overlying drainage gallery can also be used for post-drainage purposes. The bolter miners and automatic or remote control of longwall mining have also been used in the practice. The 1413A longwall extracted 2.31 million tons of coal and 15.02 m3 of CBM with the extraction rates of 93.5% and 63.8% respectively in 448 days. The speed and efficiency of co-extraction operations were improved significantly.

Research on Occupational Hazard Supervision System of Petroleum Enterprises Based on Cloud Computing

Aiming at the problem that the petroleum industry is a high-occurrence industry with many occupational hazards, in order to comprehensively evaluate the hazards in coal mines, the number of supervisors for petroleum occupational hazards is small, the number of objects to be supervised, the frequency of supervision, and the scope of supervision are large, combined with cloud computing Based on the characteristics of cloud computing, an occupational hazard supervision system for petroleum companies based on cloud computing is proposed. Based on relevant theories, 15 occupational hazard identification indicators such as lifestyle, average working age, cultural level, professional skills, and health level were selected from massive data to establish an occupational hazard evaluation index system. In this paper, the analytic hierarchy process is used to determine the weight of the occupational hazard identification index, and then a BPNN neural network prediction model is established based on the determined weight index system. The qualitative prediction of the input and output of the index is achieved through model solving and model training. The experimental results show that the training error accuracy of BPNN neural network is less than 5%, and the model accuracy meets the requirements. Compared with the error of AHP, the average evaluation error of BPNN is 0.637% lower than that of AHP. The comprehensive evaluation system based on BPNN accords with the actual situation of the enterprise is greater than 97%, so it has certain guiding significance in the evaluation of petroleum occupational diseases.

Investigate Contribution of Multi-Microseismic Data to Rockburst Risk Prediction Using Support Vector Machine With Genetic Algorithm

As a severe hazard in coal mining and rock excavation, the rockburst is usually induced by the high energy tremor. Microseismic (MS) monitoring is suggested to forecast the rockburst risk to reduce its damage. The paper aims to investigate contribution of multi-MS data, including MS raw wave data and MS energy data, to prediction of the high energy tremor, using support vector machine (SVM) together with genetic algorithm (GA). MS monitoring data recorded for more than 400 days at Wudong coal mine of Xinjiang, China, were used in the paper. 132 and 24 features are initially extracted from MS raw wave and energy data in the frequency domain, entropy and time-frequency domain, respectively. GA is not only used to select effective ones among initially extracted features, but also optimize hyperparameters for SVM to classify high energy tremors from general MS events. The performances of the proposed approach based on multi-MS data are evaluated by cross-validation. The results show that the classifier achieves 98% sensitivity, 88% accuracy and 87% specificity using both MS raw wave and energy data, which is better than solely utilizing MS raw wave (98% sensitivity, 84% accuracy and 83% specificity) or energy data (98% sensitivity, 86% accuracy and 85% specificity). These findings suggest that MS raw wave data makes important contribution to rockburst risk prediction as well as MS energy data, and the better performance can be achieved when utilizing two kinds of data simultaneously.

An overview of surface water hazards in China coal mines and disaster-causing mechanism

Surface water is not only an important water supply to mining region but also the cause of severe water burst accidents in coal mines. In China, surface water is categorized as a major water hazard that has inflicted serious property losses and casualties not seen in the rest of the world. Based on the analysis of the distribution and characteristics of 47 major mining accidents caused by surface water in China coal mines, this paper summarizes the disaster-causing mechanism of surface water hazards in coal mines. Main research results are as follows: (1) coal mine accidents caused by surface water mainly occur in spring and summer with large rainfall; particularly in summer when 70% of such coal mine accidents took place, (2) natural water channels include valleys and gullies, surface tension fissures, water-conducting faults, and karst collapse caves in mountain areas; (3) artificial water channels include underground structures in abandoned mines (such as shafts and roadways), water-conducting cracks resulted from mining activities, and illegal mining of water and sand-resistant coal (rock) pillars. Through the analysis of engineering cases, this paper puts forward prevention and control measures of surface water hazards of coal mines. The results of this paper can be of reference to other countries tasked to treat surface water hazard while protecting surface water resources.

Measurement of Electromagnetic Field Component Emissions as a Precursor of Emerging Hazard in Coal Mines

The article presents the results of research concerning electromagnetic (EM) field emitted by rocks during the process of their destruction. The paper describes a measuring stand designed for subjecting rock samples to axial crushing. During the destruction of rock samples, both components of the electromagnetic field emitted by the rock were recorded. The paper presents the results of research on hard coal samples, presenting the obtained time domain waveforms and frequency spectrum of the emitted EM field components. Further potential uses of tests concerned with EM emitted by rocks are determined. Applications registering EM field in mine environments may provide an early mine collapse warnings.

Thermal effect of ionic liquids on coal spontaneous combustion

Coal spontaneous combustion (CSC) is a global, long-standing thermal hazard in coal mining that causes serious environmental damage, particularly in developing countries. Ionic liquids (ILs) are environmentally friendly, green, economical, and a new type of fire-preventing material that inhibits coal oxidation and alleviates thermal production. In this study, 1-butyl-3-methyl imidazole tetrafluoroborate ([BMIM][BF4]) and 1-butyl-3-methyl imidazole ([BMIM][I]) at various mass ratios (0.0, 0.5, 2.0, 5.0, and 10.0 mass%) were used to treat three types of coal (lignite, 1/3 coking coal, and anthracite) for CSC. The combustion-mass loss and thermal release rate of ILs treated relative to untreated coal samples were investigated using a synchronous thermal analyzer, and the optimal addition mass ratio of ILs was predicted. Not only do ILs have the most efficient inhibiting effect, but they also consider the economic benefit. Per thermogravimetric-differential scanning calorimetry, for the content of 5.0 mass% [BMIM][BF4], the inhibiting effect is favorable for universal applications. In addition, coal samples treated with 5.0 mass% [BMIM][BF4] were subjected to programmed-temperature heating experiment testing. The oxygen consumption rate, inhibiting effect, as well as apparent activation energy, were determined. The inhibiting effect at 120.0–150.0 °C was the most obvious, which provided the basis of the application for CSC prevention.