Coal seam with low permeability is widely distributed in China. Injection of flue gas (N2:CO2 = 0.85:0.15) is an effective approach to improve coal seam gas drainage efficiency. This process relates complex responses among ternary gases (CH4, CO2, and N2) competitive sorption on coals, gas diffusion, gas‐water migration by means of two‐phase flow, and coal deformation. In this paper, an improved hydraulic‐mechanical model coupling above interactions is established for flue gas injection enhanced gas drainage. This model is used to simulate flue gas enhanced drainage by finite element method. The sensitivity analyses of key factors are made to recovery a better understanding on the processes controlling flue gas enhanced drainage. Results show that the flue gas enhanced drainage can indeed improve the efficiency of gas extraction and reduce the gas pressure to the required value in a shorter duration. Due to the competitive adsorption and gas sweeping effect of injected flue gas, CH4 is driven toward drainage borehole, and CH4 pressure and content near the injection borehole decrease faster than that near the drainage borehole. The peak CH4 pressure laterally moves from the injection borehole to the drainage borehole. Higher injection pressure, initial permeability, and smaller sorption affinity ratios may lead to greater CH4 production rate at early drainage stage, but smaller CH4 production rate at late stage. The factors controlling the behavior of flue gas enhanced drainage are initial permeability, injection pressure, and sorption affinity ratios in order. This work offers useful framework to investigate important technical challenges associated with enhanced mine gas drainage, as well as unconventional gas development.
Precise ionospheric total electron content (TEC) is critical for many aerospace applications, and forecasting ionospheric TEC is of great significance to it. Besides, short-term prediction of TEC values fills the gap between the TEC product latency and the precision. The machine learning-based approaches are promising in solving the non-linear prediction issues, particularly suitable for short-term GPS TEC forecasting due to its complex temporal and spatial variation. In this paper, four different machine learning models, i.e., Artificial Neural Network (ANN), Long Short-Term Memory (LSTM) networks, Adaptive Neuro-Fuzzy Inference System based on Subtractive Clustering (ANFIS-SC), and Gradient Boosting Decision Tree (GBDT) are applied for forecasting ionospheric TEC in three IGS GNSS monitoring stations at the low-latitude region (16°S to 10°S). The performance of these approaches in extreme conditions is investigated, including the high solar activity and magnetic storm, which are the most challenging scenario for TEC prediction. The results show that the machine learning algorithms outperform the Global Ionospheric Map (GIM) prediction model. The prediction accuracy during the high solar activity period was improved from 37.93% to 49.28%. During the magnetic storm period, the prediction accuracy was improved from 28.16% to 67.39% . Among the machine learning algorithms, the GBDT model outperforms the rest three algorithms in ionosphere prediction scenarios, which improves the prediction accuracy by 5.6% and 12.7% than the rest three approaches on average during high solar activity (2012-2015) and magnetic storm periods respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.