The factors affecting permeability change under repeated mining of coal seams are important study aspects that need to be explored. This study combined various stress variation characteristics of protective seam mining and simplified the stress path of repeated mining in protective seam mines. Based on the results from the bespoke gas flow and displacement testing apparatus, seepage tests for simulated repetitive mining were carried out. The results simulated the actual behavior very well. With any drastic increase in the mining influence, the axial deviation stress in the stress path increased, and the greater the difference in coal permeability during the unloading and stress recovery stage, the more substantial the increase in permeability. The change in coal permeability was significantly influenced by the severity of simulated repeated mining cycles. When the mining stress exceeded a critical value, the permeability of the coal sample increased with the increase in the number of loading and unloading cycles, but the reverse was true when the mining stress was lower than the critical value. The effective sensitivity of seepage to the applied stress decreased with an increase in the number of stress cycles. With a decrease in the deviation stress, that is, with lower severity of mining influence, the effective sensitivity of coal seepage to stress gradually decreased.
ABSTRACTThe spatio-temporal residual network (ST-ResNet) leverages the power of deep learning (DL) for predicting the volume of citywide spatio-temporal flows. However, this model, neglects the dynamic dependency of the input flows in the temporal dimension, which affects what spatio-temporal features may be captured in the result. This study introduces a long short-term memory (LSTM) neural network into the ST-ResNet to form a hybrid integrated-DL model to predict the volumes of citywide spatio-temporal flows (called HIDLST). The new model can dynamically learn the temporal dependency among flows via the feedback connection in the LSTM to improve accurate captures of spatio-temporal features in the flows. We test the HIDLST model by predicting the volumes of citywide taxi flows in Beijing, China. We tune the hyperparameters of the HIDLST model to optimize the prediction accuracy. A comparative study shows that the proposed model consistently outperforms ST-ResNet and several other typical DL-based models on prediction accuracy. Furthermore, we discuss the distribution of prediction errors and the contributions of the different spatio-temporal patterns. 相似文献
Natural Resources Research - High-volatile bituminous coal samples were reacted in deionized water with supercritical CO2 (ScCO2–water) under simulated in situ pressure and temperature... 相似文献
Journal of Geographical Sciences - The dramatic land use changes that occur in rapidly urbanized areas are important inducement to changes in the eco-environmental quality. Investigating urban land... 相似文献