In order to ensure the construction safety of the 38.5 m deep excavation for the gravity anchorage foundation of Fuma Yangtze River Bridge, an intelligent feedback analysis was applied to this excavation project. Firs...In order to ensure the construction safety of the 38.5 m deep excavation for the gravity anchorage foundation of Fuma Yangtze River Bridge, an intelligent feedback analysis was applied to this excavation project. First, a three-dimensional numerical model that simulating the construction process of the excavation was built,and the deformations of the supporting structures were calculated by the finite difference program FLAC3 D. Then,the non-linear mapping relationship between the geomechanical parameters and the excavation-induced displacements was established by the back-propagation neural network(BPNN). Last,the geomechanical parameters were optimized intelligently by the genetic algorithm(GA) based on the developed BPNN model and the measured displacements,and the deformations during the subsequent excavation stages were predicted based on the back-calculated parameters. The research results showed that:the back-calculated values of E1,μ1,c1,and φ1 of the completely weathered stratum,and E2 of the heavily weathered stratum were greater than the initial values,while the inversion value of E3 of the moderately weathered stratum was smaller than the initial value. The magnitudes and the variation tendencies of the predicted displacements were in good accordance with the measured displacements. At the end of the excavation,the retaining piles and the top beams had a maximum displacement of 15–20 mm,exhibiting a quite small magnitude as comparing with other case histories. Local concentration of shear stress mainly occurred at the soil-pile interface and at the toe of the excavation slope,and the plastic zones mainly appeared in the completely weathered stratum. After the completion of the excavation,there were no yielding elements in the model,and the convergence of the numerical computation was achieved,indicating the excavation was in a stable state. This study lays the basis for the subsequent construction and operation of the bridge,and offers a significant reference for the feedback analysis of similar a展开更多
The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characteriz...The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characterized by coupling the artificial fracture model and the natural fracture model.Based on an assisted history matching(AHM)using multiple-proxy-based Markov chain Monte Carlo algorithm(MCMC),an embedded discrete fracture modeling(EDFM)incorporated with reservoir simulator was used to predict productivity of shale gas well.When using the natural fracture generation method,the distribution of natural fracture network can be controlled by fractal parameters,and the natural fracture network generated coupling with artificial fractures can characterize the complex system of different-scale fractures in shale after fracturing.The EDFM,with fewer grids and less computation time consumption,can characterize the attributes of natural fractures and artificial fractures flexibly,and simulate the details of mass transfer between matrix cells and fractures while reducing computation significantly.The combination of AMH and EDFM can lower the uncertainty of reservoir and fracture parameters,and realize effective inversion of key reservoir and fracture parameters and the productivity forecast of shale gas wells.Application demonstrates the results from the proposed productivity prediction model integrating FDFN,EDFM and AHM have high credibility.展开更多
文摘In order to ensure the construction safety of the 38.5 m deep excavation for the gravity anchorage foundation of Fuma Yangtze River Bridge, an intelligent feedback analysis was applied to this excavation project. First, a three-dimensional numerical model that simulating the construction process of the excavation was built,and the deformations of the supporting structures were calculated by the finite difference program FLAC3 D. Then,the non-linear mapping relationship between the geomechanical parameters and the excavation-induced displacements was established by the back-propagation neural network(BPNN). Last,the geomechanical parameters were optimized intelligently by the genetic algorithm(GA) based on the developed BPNN model and the measured displacements,and the deformations during the subsequent excavation stages were predicted based on the back-calculated parameters. The research results showed that:the back-calculated values of E1,μ1,c1,and φ1 of the completely weathered stratum,and E2 of the heavily weathered stratum were greater than the initial values,while the inversion value of E3 of the moderately weathered stratum was smaller than the initial value. The magnitudes and the variation tendencies of the predicted displacements were in good accordance with the measured displacements. At the end of the excavation,the retaining piles and the top beams had a maximum displacement of 15–20 mm,exhibiting a quite small magnitude as comparing with other case histories. Local concentration of shear stress mainly occurred at the soil-pile interface and at the toe of the excavation slope,and the plastic zones mainly appeared in the completely weathered stratum. After the completion of the excavation,there were no yielding elements in the model,and the convergence of the numerical computation was achieved,indicating the excavation was in a stable state. This study lays the basis for the subsequent construction and operation of the bridge,and offers a significant reference for the feedback analysis of similar a
基金Supported by the National Science and Technology Major Project(2017ZX05063-005)Science and Technology Development Project of PetroChina Research Institute of Petroleum Exploration and Development(YGJ2019-12-04)。
文摘The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characterized by coupling the artificial fracture model and the natural fracture model.Based on an assisted history matching(AHM)using multiple-proxy-based Markov chain Monte Carlo algorithm(MCMC),an embedded discrete fracture modeling(EDFM)incorporated with reservoir simulator was used to predict productivity of shale gas well.When using the natural fracture generation method,the distribution of natural fracture network can be controlled by fractal parameters,and the natural fracture network generated coupling with artificial fractures can characterize the complex system of different-scale fractures in shale after fracturing.The EDFM,with fewer grids and less computation time consumption,can characterize the attributes of natural fractures and artificial fractures flexibly,and simulate the details of mass transfer between matrix cells and fractures while reducing computation significantly.The combination of AMH and EDFM can lower the uncertainty of reservoir and fracture parameters,and realize effective inversion of key reservoir and fracture parameters and the productivity forecast of shale gas wells.Application demonstrates the results from the proposed productivity prediction model integrating FDFN,EDFM and AHM have high credibility.
