Yangtze University

A system for intelligently recovering water-flooded layer of oil reservoir based on spiking neural network is provided. The system includes: a data acquiring module, a data preprocessing module, a model training module, a resistivity recovering module, and a water-flooded layer interpreting module. The data acquiring module is configured to acquire multi-modal data such as conventional and electrical well logging curves. The data preprocessing module is configured to perform range normalization and Z-Score standardization on the data. The model training module is configured to construct a resistivity recovering model based on a spiking neural network, and the resistivity recovering model is improved and verified by various manners. The resistivity recovering module is configured to recover an original resistivity. The water-flooded layer interpreting module is configured to calculate correlative parameters based on the original resistivity to determine a water-flooded layer and classify and interpret it.

The present invention discloses a porosity and permeability model method and system for a delta front channel based on a spatial trend constraint. The method includes the following steps: establishing a lateral trend body in a single-stage channel; establishing a pendant trend body in a single-stage channel; setting different weightings for the lateral trend body and the pendant trend body respectively for multiple times to obtain a fusion trend body corresponding to each weighted fusion; and based on porosity data and permeability data in the drilling data, and with all different fusion trend bodies as modeling constraint conditions, obtaining a porosity model and a permeability model of the underwater distributary channel in the study area corresponding to each weighted fusion, respectively. Therefore, internal heterogeneity characteristics of the underwater distributary channel at different positions can be characterized based on a modeling process of multi-directional trend fusion constraints.

This invention presents a projection embedded discrete fracture model integrating a TPFA and MFD hybrid approach, creating a pEDFM framework for various anisotropic two-phase flow situations. It specifies the distribution of extra pressure freedoms on matrix grids for MFD implementation, maintains f-f connections in TPFA through a standard pEDFM workflow, and introduces a low-conductivity fracture treatment for MFD. It also outlines the derivation of numerical flux calculation formulas for effective m-m and m-f connections. The mixed TPFA-MFD design applies to numerical flux estimation across both K-orthogonal and non-K-orthogonal grids, enhancing computational efficiency and facilitating the spatial discretization of continuity equations for matrix and fracture grids under anisotropic permeability conditions. A global equation system is formulated based on the continuity of effective connections, with time discretization via the implicit backward Euler method and pressure and water saturation distributions determined by a Newton-Raphson based nonlinear solver.

A multi-point geostatistical prestack inversion method based on a renewal probability ratio constant theory, comprising the following steps: sorting information, work area gridding and distributing well data, assigning an initial attribute value to a simulation work area, selecting a data template with an appropriate size, inversion and judging iteration termination; the method overcomes the defects that in the prior art, oil and gas exploration and development are more and more difficult, exploration degree is higher and higher, new oil and gas reservoirs are more and more difficult to find, reservoir parameters are inaccurate, and exploration uncertainty is increased, and the method has the advantages that prior information is obtained through a multi-point geostatistics method and then screening is carried out through a minimum objective function such that the complexity of seismic inversion is reduced.

A multi-point geostatistical prestack inversion method based on a renewal probability ratio constant theory, comprising the following steps: sorting information, work area gridding and distributing well data, assigning an initial attribute value to a simulation work area, selecting a data template with an appropriate size, inversion and judging iteration termination; the method overcomes the defects that in the prior art, oil and gas exploration and development are more and more difficult, exploration degree is higher and higher, new oil and gas reservoirs are more and more difficult to find, reservoir parameters are inaccurate, and exploration uncertainty is increased, and the method has the advantages that prior information is obtained through a multi-point geostatistics method and then screening is carried out through a minimum objective function such that the complexity of seismic inversion is reduced.

The invention discloses a dolomite reservoir prediction method and system based on well and seismic combination, and storage medium. The method steps include: obtaining the dolomite index characteristic curve through well log sensitivity analysis, and distinguishing the dolomite and limestone according to the difference in their response range; after the artificial intelligence deep learning is performed on the dolomite index characteristic curve of the drilling area, the dolomite index characteristic curve of the virtual drilling area is obtained; according to the dolomite index characteristic curve of the drilling area and the virtual drilling area, the post-stack seismic data is used for inversion to obtain the distribution and development status of the dolomite reservoir in the test area. The invention effectively distinguishes the dolomite and limestone through the dolomite index characteristic curve, and accurately predicts the distribution and development status of the dolomite reservoir in the test area with less wells.

The invention discloses a dolomite reservoir prediction method and system based on well and seismic combination, and storage medium. The method steps include: obtaining the dolomite index characteristic curve through well log sensitivity analysis, and distinguishing the dolomite and limestone according to the difference in their response range; after the artificial intelligence deep learning is performed on the dolomite index characteristic curve of the drilling area, the dolomite index characteristic curve of the virtual drilling area is obtained; according to the dolomite index characteristic curve of the drilling area and the virtual drilling area, the post-stack seismic data is used for inversion to obtain the distribution and development status of the dolomite reservoir in the test area. The invention effectively distinguishes the dolomite and limestone through the dolomite index characteristic curve, and accurately predicts the distribution and development status of the dolomite reservoir in the test area with less wells.