Tight sandstone reservoirs have strong heterogeneity and complex gas-water relationship,causing diffi culty in quantitatively predicting water saturation.Deep learning,combined with rock physics analysis and geostatis...Tight sandstone reservoirs have strong heterogeneity and complex gas-water relationship,causing diffi culty in quantitatively predicting water saturation.Deep learning,combined with rock physics analysis and geostatistics theory,was used to predict water saturation in tight sandstone,focusing on the P_(sh)^(8) in the GFZ area of the Ordos Basin.Results show that:Starting with actual wells where porosity and saturation results are obtained from log interpretations,the relationship between reservoir parameters(porosity and saturation)and elastic properties(P-wave velocity,S-wave velocity,and density)is established through the development of a rock physics model suitable for the region.Under the constraints of geostatistical laws,such as background trends of elastic and reservoir parameters and the vertical variations in logging curves,reservoir conditions(including porosity,saturation,and thickness)are simulated to generate numerous pseudowells and corresponding seismic gathers modeled using the Zoeppritz equation.A convolution neural network is used to train the target curve and predict the target body.The predicted water saturation of the P_(sh)^(8) shows strong agreement with the results from two blind wells,providing a reliable basis for understanding the water saturation(Sw)of tight sandstone.展开更多
This paper presents an overview of experimental investigations conducted at China University of Mining and Technology Beijing(CUMTB) on roadway excavation using large-scale geomechanical model tests.The simulated sedi...This paper presents an overview of experimental investigations conducted at China University of Mining and Technology Beijing(CUMTB) on roadway excavation using large-scale geomechanical model tests.The simulated sedimentary rocks are composed by alternating layers of sandstone, mudstone and coal seam inclined at varied angles with respect to the horizontal including 0°, 45°, 60°, and 90°. During the excavation, infrared thermography was employed to detect the thermal response of the surrounding rocks under excavation. The obtained raw thermograms were processed using denoising algorithm, data reduction procedure and Fourier analysis. The infrared temperature(IRT) characterizes the overall rock response; the processed thermal images represent the structural behavior, and the Fourier spectrum describes damage development in the frequency domain. Deeper understanding was achieved by the comparative analyses of excavation in differently inclined rock masses using the image features of IRTs, thermal images and Fourier spectra.展开更多
基金Supported by:CNPC Major Project "Research on Key Technologies for Enhanced Oil Recovery in Tight Sandstone Gas Reservoirs"(No. 2023ZZ25)Gansu Provincial Science and Technology Major Project"Research and Application of Key Technologies for Geophysical Prediction of Natural Gas Reservoirs in Longdong Area"(No. 23ZDGA004)PetroChina Changqing Oilfield Company'Qingshimao gas field water-bearing gas reservoir 3D seismic fine interpretation and well position support'(No.2023QCPJ33)。
文摘Tight sandstone reservoirs have strong heterogeneity and complex gas-water relationship,causing diffi culty in quantitatively predicting water saturation.Deep learning,combined with rock physics analysis and geostatistics theory,was used to predict water saturation in tight sandstone,focusing on the P_(sh)^(8) in the GFZ area of the Ordos Basin.Results show that:Starting with actual wells where porosity and saturation results are obtained from log interpretations,the relationship between reservoir parameters(porosity and saturation)and elastic properties(P-wave velocity,S-wave velocity,and density)is established through the development of a rock physics model suitable for the region.Under the constraints of geostatistical laws,such as background trends of elastic and reservoir parameters and the vertical variations in logging curves,reservoir conditions(including porosity,saturation,and thickness)are simulated to generate numerous pseudowells and corresponding seismic gathers modeled using the Zoeppritz equation.A convolution neural network is used to train the target curve and predict the target body.The predicted water saturation of the P_(sh)^(8) shows strong agreement with the results from two blind wells,providing a reliable basis for understanding the water saturation(Sw)of tight sandstone.
基金provided by the Special Funds for the Major State Basic Research Project(No.2006CB202200)the Innovative Team Development Project of the state Educational Ministry of China(No.IRT0656)
文摘This paper presents an overview of experimental investigations conducted at China University of Mining and Technology Beijing(CUMTB) on roadway excavation using large-scale geomechanical model tests.The simulated sedimentary rocks are composed by alternating layers of sandstone, mudstone and coal seam inclined at varied angles with respect to the horizontal including 0°, 45°, 60°, and 90°. During the excavation, infrared thermography was employed to detect the thermal response of the surrounding rocks under excavation. The obtained raw thermograms were processed using denoising algorithm, data reduction procedure and Fourier analysis. The infrared temperature(IRT) characterizes the overall rock response; the processed thermal images represent the structural behavior, and the Fourier spectrum describes damage development in the frequency domain. Deeper understanding was achieved by the comparative analyses of excavation in differently inclined rock masses using the image features of IRTs, thermal images and Fourier spectra.
