It is of great significance to study the porosity and permeability properties of medium and low-rank coal. The porosity and permeability in confining stress experiments were used to simulate the porosity and permeability variations of coal samples under different depth conditions. The pore structure of Baoqing coal samples is greatly affected by the confining pressure, and the pores and micro cracks are more easily compressed. Based on the experimental data of mercury intrusion porosimetry (MIP) and nitrogen adsorption (NA), the pore size distributions (PSDs) of medium and low-rank coals were studied. High mercury intrusion pressure would lead to coal matrix compression. Therefore, the pore volume calculated by MIP data was corrected by NA data. The PSDs characteristics of Jixi (JX) coal and Baoqing (BQ) coal samples are obtained from the revised pore volume, and the dominant pores of medium and low-rank coals are obtained. The results show that JX coal has higher spatial heterogeneity, connectivity and pore autocorrelation. Micro fractures have an influence on the autocorrelation and heterogeneity of coal samples, especially for BQ coal samples.

No abstract

Fluid flow modeling of coalbed methane (CBM) wells is effective in predicting gas production and designing appropriate depressurization schemes. Moreover, hydraulic fracturing is an important measure for improving the permeability of CBM reservoirs. In this work, we assumed the hydraulic fracture area near the main fracture to be rectangular. We developed a gas–water two-phase flow model considering the difference in stress sensitivity between the hydraulic fracturing area and the original coal reservoir. The numerical simulation results indicate that our model can accurately predict the production of CBM wells. In the early stage of CBM extraction, gas production increased with the increase of gas relative permeability. When the water saturation was below 0.7, the relative permeability of the gas phase was difficult to increase. At this time, the absolute permeability of the hydraulic fracturing area continued to decrease, leading to a decrease in gas production. Thus, if the difference of permeability evolution between the two areas is not considered, the production of CBM wells will be overestimated. In the process of CBM extraction, both reservoir pressure and water saturation decreased, but the distribution was inconsistent. The variation in reservoir pressure was mainly affected by absolute permeability and gas desorption, while the variation of water saturation was further affected by the distribution of relative permeability and initial water saturation. Therefore, the evolution of water saturation is generally more complex than that of reservoir pressure. In the hydraulic fracturing area, the effect of fracture compressibility on gas production was greater than the initial permeability. In the original coal reservoir, the larger initial permeability was more beneficial than the fracture compressibility for improving the production of CBM wells.

No abstract

It is of great significance to evaluate and predict coalbed methane (CBM) production for the exploitation and exploration of CBM. The flow characteristics of gas and water are very complicated and important in the process of CBM exploitation. In recent years, machine learning has been introduced to analyze CBM well production and its influence based on the historical production data. However, there are some problems with the determination of hyperparameters in machine learning algorithms. Some previous random forests (RF) models of CBM production prediction were suitable for individual CBM wells, but for different types of CBM wells, a large amount of time is needed to adjust the hyperparameters. Therefore, a genetic algorithm (GA) was applied to optimize RF, and a hybrid GA–RF algorithm was presented to solve this problem, which can automatically adjust two important hyperparameters, n tree and m try , and adapt different types of CBM wells. Meanwhile, the Pearson method and RF were carried out in this work to analyze the data of CBM well production to avoid multicollinearity caused by the improper selection of the model’s independent variables. The importance and correlation analysis of drainage control parameters, including casing pressure ( P c ), bottom-hole pressure ( P b ), stroke frequency ( f s ), liquid column depth ( D L ), daily decline of bottom-hole pressure ( P bd ), and daily decline of casing pressure ( P cd ) were obtained. It was found that the casing pressure, bottom-hole pressure, and stroke frequency had more effects on the gas production of CBM wells than other drainage control parameters. Furthermore, the correlation and importance order of the influencing factors were: P c > P b > f s > P bd > P cd > D L and P c > P b > f s > D L > P bd > P cd , respectively. A CBM production model based on the GA–RF algorithm was constructed to study and predict the gas production of CBM wells in Qinshui Basin, China. Compared with the production model based on RF, this model can automatically optimize its hyperparameters to adapt to different types of CBM wells, and the mean-square-error of the GA–RF algorithm can be reduced by 40–60% than that of RF. 93% of the training errors were less than 5%, and 89% of the prediction errors were less than 10%. The GA–RF model can spot promptly the ma...