As the mechanization of the CBM extraction process advances and geological conditions continuously evolve, the production data from CBM wells is deviating increasingly from linearity, thereby presenting a significant challenge in accurately predicting future gas production from these wells. When it comes to predicting the production of CBM, a single deep-learning model can face several drawbacks such as overfitting, gradient explosion, and gradient disappearance. These issues can ultimately result in insufficient prediction accuracy, making it important to carefully consider the limitations of any given model. It's impressive to see how advanced technology can enhance the prediction accuracy of CBM. In this paper, the use of a CNN model to extract features from CBM well data and combine it with Bi-LSTM and a Multi-Head Attention mechanism to construct a production prediction model for CBM wells-the CNN-BL-MHA model-is fascinating. It is even more exciting that predictions of gas production for experimental wells can be conducted using production data from Wells W1 and W2 as the model's database. We compared and analyzed the prediction results obtained from the CNN-BL-MHA model we constructed with those from single models like ARIMA, LSTM, MLP, and GRU. The results show that the CNN-BL-MHA model proposed in the study has shown promising results in improving the accuracy of gas production prediction for CBM wells. It's also impressive that this model demonstrated super stability, which is essential for reliable predictions. Compared to the single deep learning model used in this study, its prediction accuracy can be improved up to 35%, and the prediction results match the actual yield data with lower error.
Currently, the utilization of coalbed methane resources in the Guizhou region faces challenges such as complex reservoir structure, high gas content, and microporous development. Based on these, the pore structure and adsorption capacity of Guizhou tectonic deformed coals (TDCs) were evaluated using a suite of integrated diagnostic techniques including low-temperature nitrogen adsorption (LT-N2A), mercury intrusion porosimetry (MIP), methane isothermal adsorption. Through the above methods, the pore structure and adsorption characteristics of the samples were characterized; The samples were divided into the range of joint pores by combining the results of MIP and LT-N2A; Using the molecular simulation software, the 2 nm, 4 nm, 10 nm pores affecting the methane endowment state were investigated respectively, and from the perspective of the heat of adsorption and energy, the concept of the three-phase transition of methane was proposed, and explore the change of the pore spacing affecting the endowment state of methane from the solid state pore to the gas state pore. The results provide new ideas for the in-depth study of gas storage in tectonic coal reservoirs in Guizhou Province.
The chemical and pore structures of coal play a crucial role in determining the content of free gas in coal reservoirs. This study focuses on investigating the impact of acidification transformation on the micro-physical and chemical structure characteristics of coal samples collected from Wenjiaba No. 1 Mine in Guizhou. The research involves a semi-quantitative analysis of the chemical structure parameters and crystal structure of coal samples before and after acidification using Fourier Transform infrared spectroscopy (FTIR) and X-ray diffraction (XRD) experiments. Additionally, the evolution characteristics of the pore structure are characterized through high-pressure mercury injection (HP-MIP), low-temperature nitrogen adsorption (LT-N2A), and scanning electron microscopy (SEM). The experimental findings reveal that the acid solution modifies the structural features of coal samples, weakening certain vibrational structures and altering the chemical composition. Specifically, the asymmetric vibration structure of aliphatic CH2, the asymmetric vibration of aliphatic CH3, and the symmetric vibration of CH2 are affected. This leads to a decrease in the contents of -OH and -NH functional groups while increasing aromatic structures. The crystal structure of coal samples primarily dissolves transversely after acidification, affecting intergranular spacing and average height. Acid treatment corrodes mineral particles within coal sample cracks, augmenting porosity, average pore diameter, and the ratio of macro-pores to transitional pores. Moreover, acidification increases fracture width and texture, enhancing the connectivity of the fracture structure in coal samples. These findings provide theoretical insights for optimizing coalbed methane (CBM) extraction and gas control strategies.
Coal , X-Ray Diffraction , Coal/analysis , Porosity , Spectroscopy, Fourier Transform Infrared , Acids/chemistry , Microscopy, Electron, Scanning , Coal Mining
An acid solution improves the pore-plugging problem in hydraulic fracturing, which in turn improves the permeability of the coal seam. The study aimed to investigate the effect of mixed acid on the micronano mechanical properties and permeability of the coal seam. The surface morphology of acidified coal was analyzed from the micronano scale using atomic force microscopy (AFM) and scanning electron microscopy. Additionally, the micronano scale mechanical characteristics of acidified coal were examined using the mechanical mode in an atomic force microscope. Furthermore, the complexity and connectivity of the micronano pores of samples were investigated using the low-temperature nitrogen adsorption and mercury intrusion porosimetry methods and the fractal theory. The results indicated that the surface minerals of acidified coal were dissolved, loosening the coal and increasing the complexity of the pore structure. Mineral deformation and pore deformation weakened the mechanical properties of coal at the micronano scale, and the mean elastic modulus of acidified coal (B# and E#) decreased by 28.78 and 25.66% compared to that of raw coal. The acid solution effectively enlarged the pore diameter, transitioning from micropores to mesopores and macropores, and the total pore volume of acidified coal increased by 1.88 times and 1.25 times, Kn increased from 0.064 to 0.581 and 0.37, respectively. The type of methane diffusion in the diffusion pores changed from Knudsen diffusion to transition-type diffusion. The tortuosity of the pore structure of acidified coal decreased, the fractal dimension of the tortuosity of the pore structure decreased, and the permeability increased by nearly three times. The research results indicate that the mechanical properties of coal decrease after acidification and that the microstructural changes can promote methane migration (diffusion-seepage), which can provide theoretical guidance for coalbed methane extraction in low-permeability coal reservoirs.
The gas content and permeability of coal reservoirs are the main factors affecting the productivity of coalbed methane. To explore the law of gas content and permeability of coal reservoirs in the Zhijin area of Guizhou, taking No.16, No.27 and No.30 coal seams in Wenjiaba mining area of Guizhou as the engineering background, based on the relevant data of coalbed methane exploration in Wenjiaba block, the geological structure, coal seam thickness, coal quality characteristics,coal seam gas content and permeability of the area were studied utilizing geological exploration, analysis of coal components and methane adsorption test. The results show that the average thickness of coal seams in this area is between 1.32 and 1.85 m; the average buried depth of the coal seam is in the range of 301.3-384.2 m; the gas content of No.16 and No.27 coal seams is higher in the syncline core. The gas content of the No.30 coal seam forms a gas-rich center in the south of the mining area. The buried depth and gas content of coal seams in the study area show a strong positive correlation. Under the same pressure conditions, the adsorption capacity of dry ash-free basis is significantly higher than that of air-dried coal. The permeability decreases exponentially with the horizontal maximum principal stress and the horizontal minimum principal stress. The horizontal maximum primary stress and the flat minimum prominent stress increase with the increase of the buried depth of the coal seam. The permeability and coal seam burial depth decrease exponentially. This work can provide engineering reference and theoretical support for selecting high-yield target areas for CBM enrichment in the block.
Experiments on corrosion reactions of pulverized coal with monomeric and polymeric (mixed) acid solutions reveal that monomeric acids are listed in a descending order as HF, HCl, and CH3COOH according to their corrosion effects on tectonic coal collected in Faer Coal Mine (Liupanshui City, Guizhou Province, China). In addition, the optimal mixing ratio of mixed acids is 6% HCl + 6% HF + 3% CH3COOH + 2% KCl. The mineral grains filled in pores in coal samples treated with mixed acid solutions are dissolved, so the porosity increases. The volumes of transition pores and mesopores are obviously affected by acidization, and some transition pores are transformed into mesopores and macropores to form dissolved pores. At the same time, inkbottle-shaped pores reduce, while slit pores or open pores increase. The coal samples after acidization show a higher aromatization degree and an increased relative content of oxygen-containing functional groups, with a generally lower hydroxyl content, so the methane (CH4) adsorption capacity of coal declines, which promotes CH4 desorption. The control effect of pore structures after acidization reactions on CH4 desorption was revealed from perspectives of the diffusion coefficient (Kn), adsorption volume (ω), average pore-throat ratio (PT), and average sinuosity (τav). That is, CH4 molecules in tectonic coal after acidization turn from Knudsen diffusion to transitional diffusion, the adsorption volume of CH4 molecules shrinks, the average pore-throat ratio decreases, and the average sinuosity reduces, which promotes CH4 desorption from tectonic coal.
The evolution of fissures and permeability associated with mining of the upper protective layer of the coal seam is crucial for pressure relief gas drainage of the underlying seam. To understand the influence of mining the upper protective layer on gas drainage within the underlying coal seam, this study utilized the M16 and M18 seams in the Qinglong Coal Mine in Guizhou. Theoretical analysis, discrete element numerical simulation, and field tests were used to characterize the evolution of fractures associated with mining of the upper protective layer and the effects of pressure relief gas drainage within the protected coal seam. The results show that mining-related stress changes controlled the development of fractures, altering the permeability values of coals. An analysis of the crack development in the coal mass caused by mining of the upper protective layer shows that during the initial stage of mining, the produced cracks exhibited a butterfly shape network. Yet, with further development of the mining, these cracks and the stress changes gradually produced an inverted butterfly shape network. According to simulations, the areas of maximum deformation via expansion in the protected coal seam were located near the open cut and the mining end line of the working face. The maximum deformation values were 29.06 and 26.68 mm, respectively, and the corresponding deformation rates were 9.37 and 8.61, which are greater than the required 3. The findings of this study provide a new reference for gas control in pressure relief coal seams under similar working conditions.
