Microseismic(MS)monitoring is an effective technique to detect mining-induced rock fractures.However,recognizing grouting-induced signals is challenging due to complex geological conditions in deep rock plates.Therefo...Microseismic(MS)monitoring is an effective technique to detect mining-induced rock fractures.However,recognizing grouting-induced signals is challenging due to complex geological conditions in deep rock plates.Therefore,a hybrid model(WM-ResNet50)integrating data enhancement,a deep convolutional neural network(CNN),and convolutional block attention modules(CBAM)was proposed.Firstly,an MS system was established at the Xieqiao coal mine in Anhui Province,China.MS waveforms and injection parameters were acquired during grouting.Secondly,signals were categorized based on time-frequency characteristics to build a dataset,which was divided into training,validation,and test sets at a ratio of 4:1:1.Subsequently,the performance of WM-ResNet50 was evaluated based on indices such as individual precision,total accuracy,recall,and loss function.The results indicated that WMResNet50 achieved an average recognition accuracy of 94.38%,surpassing that of a simple CNN(90.04%),ResNet18(91.72%),and ResNet50(92.48%).Finally,WM-ResNet50 was applied to monitor the whole process at laboratory tests and field cases.Both results affirmed the feasibility and effectiveness of MS inversion in predicting actual slurry diffusion ranges within deep rock layers.By comparison,it was revealed that the MS sources classified by WM-ResNet50 matched grouting records well.A solution to address insufficient diffusion under long-borehole grouting has been proposed.WM-ResNet50′s accuracy was validated through in-situ coring and XRD analysis for cement-based hydration products.This study provides a beneficial reference for similar rock signal processing and in-field grouting practices.展开更多
The numerical simulation program of PFC2D(Particle Flow Code in 2 Dimension)particle flow based on the flow-solid coupling principle and,on its built-in FISHTANK function library and FISH language,defines the flow equ...The numerical simulation program of PFC2D(Particle Flow Code in 2 Dimension)particle flow based on the flow-solid coupling principle and,on its built-in FISHTANK function library and FISH language,defines the flow equation and pressure equation of fluid domain respectively,and carries out numerical simulation calculations on the diffusion process and,on the morphology and particle displacement of slurry during the slurry injection process.By adjusting the parameters of hist,n_bond,s_bond and measure in the PFC command flow,the tracking of granular body displacement changes is achieved,and the mesoscopic mechanism such as the diffusion law of soil slurry at different depths and the change of formation porosity is revealed.The numerical calculations show that:the grouting pressure has a significant effect on the alteration and destruction of the formation structure,and the fracturing effect becomes gradually worse with increasing adhesive strength,while the porosity increases significantly with increasing grouting pressure.Based on the elastic-plastic theory of the Mohr-Colomb criterion to theoretically derive the stress field of the soil around the borehole,it is pointed out that the mechanical mechanism of annular tension and radial compression is the fundamental reason for the appearance of fracturing grouting action mode.The increase of slurry viscosity is beneficial to improve the grouting effect of fracturing-compacting grouting,while the increase of friction coefficient has little effect on the grouting effect.The comparative analysis of the laboratory tests shows that the PFC2D simulation of the grouting process is feasible.展开更多
基金financial support from the National Natural Science Foundation of China(Nos.52204089,52374082)the Young Elite Scientists Sponsorship Program(No.2023QNRC001)by China Association for Science and Technology(CAST).
文摘Microseismic(MS)monitoring is an effective technique to detect mining-induced rock fractures.However,recognizing grouting-induced signals is challenging due to complex geological conditions in deep rock plates.Therefore,a hybrid model(WM-ResNet50)integrating data enhancement,a deep convolutional neural network(CNN),and convolutional block attention modules(CBAM)was proposed.Firstly,an MS system was established at the Xieqiao coal mine in Anhui Province,China.MS waveforms and injection parameters were acquired during grouting.Secondly,signals were categorized based on time-frequency characteristics to build a dataset,which was divided into training,validation,and test sets at a ratio of 4:1:1.Subsequently,the performance of WM-ResNet50 was evaluated based on indices such as individual precision,total accuracy,recall,and loss function.The results indicated that WMResNet50 achieved an average recognition accuracy of 94.38%,surpassing that of a simple CNN(90.04%),ResNet18(91.72%),and ResNet50(92.48%).Finally,WM-ResNet50 was applied to monitor the whole process at laboratory tests and field cases.Both results affirmed the feasibility and effectiveness of MS inversion in predicting actual slurry diffusion ranges within deep rock layers.By comparison,it was revealed that the MS sources classified by WM-ResNet50 matched grouting records well.A solution to address insufficient diffusion under long-borehole grouting has been proposed.WM-ResNet50′s accuracy was validated through in-situ coring and XRD analysis for cement-based hydration products.This study provides a beneficial reference for similar rock signal processing and in-field grouting practices.
文摘The numerical simulation program of PFC2D(Particle Flow Code in 2 Dimension)particle flow based on the flow-solid coupling principle and,on its built-in FISHTANK function library and FISH language,defines the flow equation and pressure equation of fluid domain respectively,and carries out numerical simulation calculations on the diffusion process and,on the morphology and particle displacement of slurry during the slurry injection process.By adjusting the parameters of hist,n_bond,s_bond and measure in the PFC command flow,the tracking of granular body displacement changes is achieved,and the mesoscopic mechanism such as the diffusion law of soil slurry at different depths and the change of formation porosity is revealed.The numerical calculations show that:the grouting pressure has a significant effect on the alteration and destruction of the formation structure,and the fracturing effect becomes gradually worse with increasing adhesive strength,while the porosity increases significantly with increasing grouting pressure.Based on the elastic-plastic theory of the Mohr-Colomb criterion to theoretically derive the stress field of the soil around the borehole,it is pointed out that the mechanical mechanism of annular tension and radial compression is the fundamental reason for the appearance of fracturing grouting action mode.The increase of slurry viscosity is beneficial to improve the grouting effect of fracturing-compacting grouting,while the increase of friction coefficient has little effect on the grouting effect.The comparative analysis of the laboratory tests shows that the PFC2D simulation of the grouting process is feasible.
