Prediction of coal spontaneous combustion temperature based on improved grey wolf optimizer algorithm and support vector regression

One of the most catastrophic events that can occur during coal mining is a fire triggered by spontaneous combustion of the coal. Due to complex geological conditions, some coal mines in China have the characteristics of shallow burial and small spacing between coal seams. With the increase of mining depth, there will be many cracks in the overlying goaf. Surface water and groundwater flow into the goaf along these fissures. After long-term water immersion, the increase of ground temperature will lead to the spontaneous combustion of coal. A thorough analysis of the impact of water immersion on the spontaneous combustion of coal necessitates a review of the most recent findings in this field. The review will promote the further development of the theory and prevention of spontaneous combustion of water-immersed coal and provide theoretical help for monitoring and preventing spontaneous combustion of water-immersed coal. The creation of water-immersed coal and the reason for spontaneous combustion is investigated, as are the characteristics of the water accumulation in the goaf and their origins. The research status of spontaneous combustion of water-immersed coal is presented and illustrated domestically and internationally. On this basis, the theoretical and experimental research directions, problems, and prospects of spontaneous combustion of water-immersed coal are put forward. This study can provide a theoretical basis for monitoring, preventing, and controlling the spontaneous combustion of water-immersed coal, and provide a reference for reducing energy waste.

A data-driven method approach for prediction of coal seam gas content combining feature selection and machine learning

Characteristics of polycyclic aromatic hydrocarbon release during spontaneous combustion of coal and gangue in the same coal seam

To accurately predict the risk level of spontaneous coal combustion, we introduce an improved grey wolf optimization strategy (IGWO) to optimize the generalized regression neural network (GRNN), thereby establishing the IGWO-GRNN coal spontaneous combustion risk level prediction model. The superiority of the IGWO algorithm over the grey wolf optimization algorithm (GWO), whale optimization algorithm (WOA) and particle swarm optimization algorithm (PSO) was verified. Fifty sets of sample data of spontaneous coal combustion in the mining area were selected as the research object, and the data were randomly divided into the training set and the test set according to the ratio of 8:2. The prediction results of the IGWO-GRNN prediction model were obtained and compared with those of the GWO-GRNN, GRNN, BP (Backpropagation), and GRU (Gated Recurrent Unit) models, and the absolute value of the relative error was introduced as an evaluation index of the model prediction accuracy. The results demonstrate that IGWO outperforms GWO, WOA, and PSO in terms of optimization efficiency, with the IGWO-GRNN prediction model yielding the most accurate results. Specifically, the maximum absolute value of the relative error does not exceed 4.27%, and the average relative error is only 3.29%, indicating a substantial improvement over the other models. Therefore, this study achieves high-precision prediction under small-sample data, which provides an important reference value for the small-sample prediction problem in the mining field.

Wheat protein and fat contents directly affect the flavor and yield of liquor. This study utilized hyperspectral imaging (HSI) technology along with an integrated learning model to rapidly and non-destructively detect protein and fat contents in wheat. The hyperspectral data of the wheat grains was preprocessed using various methods. The competitive adaptive reweighted sampling (CARS) algorithm, the successive projections algorithm (SPA), and the combination of the two algorithms (CARS-SPA) were used to extract the characteristic wavelengths. Three support vector regression (SVR) models were created to forecast wheat protein and fat contents using full-band spectral data and characteristic wavelengths. These models are gray wolf optimized support vector regression (GWO-SVR), particle swarm optimized support vector regression (PSO-SVR), and support vector regression-based integrated learning (AdaBoost-SVR). Comparing the models showed that the AdaBoost-SVR model, utilizing the Eigen wavelengths extracted through the CARS-SPA and CARS algorithms, stood out as the most accurate in predicting wheat protein and fat contents, with Rp 2 values of 0.9789 and 0.9651, respectively. The study findings indicate that combining HSI with AdaBoost-SVR integrated learning modeling enables rapid, non-destructive determination of wheat protein and fat contents with greater accuracy than using a single machine learning (ML) model.

Experimentalstudy on microscopic action of different form moistureon coal spontaneous combustion

Spontaneous combustion of coal is one of the main natural disasters in the process of coal mining, and spontaneous combustion of sulfur-containing coal is an urgent problem to be solved. In order to understand the influence of different sulfur structures and sulfur content on spontaneous combustion tendency of coal, the self-developed synchronous temperature compensation adiabatic oxidation experiment system was used to study the oxidation self-heating performance of a series of sulfur-containing “coal-like materials.” Through the analysis of the heating rate of coal containing specific sulfur structure, it is considered that the time of adiabatic oxidation temperature of different organic sulfur “coal” to rise to 70°C is dimethyl sulfoxide > phenylene sulfide > dibenzothiophene. By analyzing the oxidation temperature rise characteristics of organic sulfur models with different sulfur contents, it is believed that the higher sulfur content, the faster the low temperature oxidation reaction of “coal-like substance,” the faster the temperature rise rate, and the shorter the time to reach the uncontrollable self-heating temperature, so the shorter the spontaneous combustion period. In general, in the stage of low temperature oxidation, active sulfur containing small molecules (dimethyl sulfoxide) promote the oxidation temperature rise, stable structure, larger molecular weight of dibenzothiophene slow down the “coal-like” oxidation temperature rise.

In the process of coal mining, the compaction characteristics of the goaf and its permeability evolution characteristics are critical to the safe and efficient mining of coal mines, which directly affect surface subsidence, air leakage in the goaf and spontaneous combustion of coal. Although the stress and permeability of the goaf are very important, it is difficult to directly measure the stress and permeability of the goaf. Therefore, this paper uses the damaged coal and rock mass seepage test system to carry out the compaction and seepage tests of the broken coal mass under triaxial loading. The experimental shows that: (1) under the same stress, the strain of a single-size coal sample is smaller than the mixed particle size, and the porosity is greater than the mixed particle size. The larger the particle size of a single-size coal sample, the smaller its strain. (2) There are two stages of rapid compaction and slow compaction under the condition of triaxial compression of broken coal samples. The strain and permeability stress sensitivity of the rapid compaction stage are strong, while the slow compaction stage is weak. (3) Under triaxial loading of broken coal, permeability has an exponential relationship with effective stress, and a power function relationship with porosity, which obeys Darcy's law. The research results are of great significance for guiding the goaf gas drainage and preventing surface subsidence and spontaneous combustion of the goaf coal.

To improve the accuracy of ship track prediction, the improved Grey Wolf Optimizer (GWO) and Support Vector Regression (SVR) models are incorporated for ship track prediction. The hunting strategy of dimensional learning was used to optimize the move search process of GWO and balance exploration and exploitation while maintaining population diversity. Selection and updating procedures keep GWO from being stuck in locally optimal solutions. The optimal parameters obtained by modified GWO were substituted into the SVR model to predict ship trajectory. Dimension Learning Grey Wolf Optimizer and Support Vector Regression (DLGWO-SVR), Grey Wolf Optimized Support Vector Regression (GWO-SVR), and Differential Evolution Grey Wolf Optimized Support Vector Regression (DEGWO-SVR) model trajectory prediction simulations were carried out. A comparison of the results shows that the trajectory prediction model based on DLGWO-SVR has higher prediction accuracy and meets the requirements of ship track prediction. The results of ship track prediction can not only improve the efficiency of marine traffic management but also prevent the occurrence of traffic accidents and maintain marine safety.

Preparation and properties of hydrotalcite microcapsules for coal spontaneous combustion prevention

Determining a reasonable barrier pillar along gob-side entry of spontaneous combustion coal seam is of great significance to the prevention of spontaneous combustion. In this paper, considering the actual situation of 4301 and 4302 working faces of II-class spontaneous combustion coal seam in Changheng Mine, the characteristics of rock mass collapse and mining-induced stress redistribution of barrier pillar and adjacent area were analyzed, the cusp catastrophe model of coal pillar instability and the theoretical model of limit width of coal pillar air leakage spontaneous combustion were established, and a measurement scheme of side abutment pressure in 4301 working face was carried out. The theoretical model of the coal pillar along the gob-side entry shows that its instability is related to density of overlying strata, physical and mechanical parameters of coal body, dip angle of coal seam and weak face, and buried depth and mining width of working face. And the coal pillar in 4302 working face will be unstable if the width a ≤ 6.8 m . Field measured data shows that 2-8 m is the stress-relaxation area of side solid coal. Then, the width of coal pillar was determined as 7 m. The maximum displacement of rib-to-rib and roof-to-floor of 4302 tailentry was 520 mm and 280 mm, respectively. The coal spontaneous combustion (CSC) observation monitoring results showed that the carbon monoxide volume fraction was in the normal range during the entire process of mining, and no other signs of gas were found. The research results can provide a reference for the barrier pillar designing in the mines under similar conditions.

The combination effect of coal and oxygen is a major factor in the coal spontaneous combustion and a significant source of CO and CO2 gas emissions. In order to reveal the relationship between oxygen consumption, gas generation mechanism and microscopic groups during coal spontaneous combustion, the reaction path and thermal dynamic characteristics of hydroperoxides and oxygen-containing intermediates produced by coal-oxygen interaction were studied by density functional theory. The results indicate that hydroperoxides and peroxide radicals are initially formed in the coal-oxygen reaction. The breaking of the peroxide bond (O-O) to form ether oxygen radicals (RO·) and hydroxyl radicals (·OH) is the beginning of the decomposition reaction of hydroperoxides. The decomposition of hydroperoxides is an important pathway for the production of oxygen-containing intermediates such as carbonyl and carboxyl groups, which are key functional groups for the continuous generation of CO and CO2 gases. The heat release of the hydroperoxide dehydration reaction is generally higher than 200 kJ/mol. The activation energies for the decomposition of carbonyl free radicals to produce CO and carboxyl free radicals to produce CO2 are 99.769 kJ/mol and 21.004 kJ/mol, respectively. The reaction of decarbonylating of carbonyl-containing compounds to produce CO is an endothermic reaction, whereas the reaction of decarboxylating of carboxyl-containing compounds to produce CO2 is an exothermic reaction, and increasing the temperature has an obvious accelerating effect on reactions with slow gas production rates. The results of the study provide new ideas for the construction of theoretical basis and the prevention and control of coal spontaneous combustion.

Experimental study on the compound system of proanthocyanidin and polyethylene glycol to prevent coal spontaneous combustion

The coal pillar along the goaf of the completely mechanized caving face of “Isolated Island” is severely damaged, with complex air leakage and a high risk of coal spontaneous combustion. In order to research the law of goaf air leakage in “Isolated Island” working face and effectively control the hidden threat of coal spontaneous combustion in goaf, it is necessary to investigate the goaf air leakage law. In this work, the 3302 “Isolated Island” entirely mechanized caving face of Jining No. 2 Coal Mine in Shandong province, China, served as an example. SF6 tracer gas air leakage measurement was utilized to identify the air leaking route in the goaf. In conjunction with the numerical modeling, the air leakage route surrounding the goaf was evaluated to establish the coal spontaneous combustion risk region, and the targeted prevention and controlled ways of coal spontaneous combustion were proposed. The results indicated that the primary source of air leakage was the seepage of air flow through the working face to the rear goaf and the diffusion to the adjacent goaf through the broken coal pillar. The risk area for coal spontaneous combustion was 40–80 m behind the rear goaf and 50 m within the coal pillar of the adjacent goaf. Regarding this region, the comprehensive prevention and control strategies of plugging and oxygen reduction, inerting and cooling, monitoring and forecasting were proposed. In addition, the fire prevention and extinguishing system combining slurry spraying, sodium silicate, and liquid CO2 injection was designed at both ends of the 3302 track and haulage roads. Using field measurements during the working face mining process, the corresponding methods for reducing the CO volume fraction in 3302 return air roadway and air return corner effectively prevented and controlled the hidden danger of coal spontaneous combustion in the goaf and ensured the safety of working face mining. This research developed a new technology for the prevention and management of coal spontaneous combustion in the goaf of the “Isolated Island” working face.

The index gas analysis is an important method of predicting coal spontaneous combustion (CSC). The temperature programmed experiment was used to simulate the CSC process in goaf, and the characteristics of each index gas and coal temperature change were investigated. The corresponding relationship between the target center distance and the coal temperature was determined using the multi-index weighted gray target decision theory. The findings indicate that the selected gases (CO, C2H4, C2H6) and gas combination (format fire coefficient (R), φ(CO)/φ(CO2), φ(C2H4)/φ(CH4), φ(C2H4)/φ(C2H6)) can be used as index gases for CSC prediction. The critical temperature was 70°C and the dry cracking temperature was 110°C. The combined action of coal and oxygen is divided into three stages: slow oxidation (30–70°C), accelerated oxidation (70–110°C), and strong oxidation (after 110°C). The combination of the programmed temperature experiment and the weighted gray target decision theory model determines the relationship between the off-target distance and the coal temperature. The lower the degree of CSC, the better the decision scheme, and the smaller the off-target distance. The results of Xiaobaodang’s experimental analyses are applied to the field, and the actual coal temperature in the goaf is predicted to be between 37–62°C. The risk level of CSC in the goaf is determined more intuitively and precisely, providing a theoretical foundation for improving the mining area’s fire prevention and extinguishing scheme.