14 results about "Stratigraphic section" patented technology

A three-dimensional heterogeneous aquifer horizontal equivalent permeability coefficient multi-scale prediction method based on a residual network comprises the steps that a foundation pit dewatering two-dimensional pressure-bearing steady flow model is constructed, the influence of the size of a lenticular body on foundation pit dewatering flow field disturbance is evaluated, and the resolution ratio of a parameter prediction model grid is determined; based on actual drilling data and transition probability / Markov chain T-Progs, according to multiple deposition types formed by a binary deposition structure, a multi-layer aquifer structure, a coarse-grained deposition structure and a fine-grained deposition structure, a three-dimensional stratigraphic random structure model set is constructed, and three-dimensional stratigraphic section random slices are established; obtaining horizontal equivalent permeability coefficients corresponding to stratigraphic sections in various stratigraphic structures based on the underground water flow numerical model FloPy, and establishing a stratigraphic structure-equivalent permeability coefficient training set based on a neural network; a deep learning model is constructed based on the residual network ResNet50; and training, verifying and testing the equivalent permeability coefficient of the stratum section formed by the binary sedimentary structure, the multi-layer aquifer structure, the coarse grain sedimentary structure and the fine grain sedimentary structure.

The application discloses a cobalt-rich crust resource distribution circle division method and system, an electronic device and a storage medium. The method comprises the following steps: obtaining preset geological sedimentary environment data; wherein the preset geological sedimentary environment data comprises oceanic crust age data, sedimentation rate data and preset near-bottom shallow stratigraphic profile data; determining first region data according to the oceanic crust age data and the sedimentation rate data through a preset discrimination model; wherein the preset discrimination model is constructed by the coupling effect of a sedimentation rate parameter and an oceanic crust age parameter; performing topographic constraint correction on the first region data according to a preset topographic constraint parameter to obtain second region data; and performing crust region analysis according to the second region data and the preset near-bottom shallow stratigraphic profile data to obtain a target cobalt-rich crust region. The embodiment of the application can effectively improve the efficiency and accuracy of cobalt-rich crust circle division. The application can be widely applied to the field of resource development.

The present application relates to a method for predicting pre-drilling stratigraphic profile based on multi-algorithm interpolation of well logging curves, comprising: predicting the top / bottom and thickness of each layer of the target well based on stratified data; aligning the normalized depth within the layer; predicting multiple well logging curves by using multi-algorithm (at least IDW and Kriging) interpolation; correcting the proximity and mapping the depth based on the well deviation trajectory; outputting the multi-depth reference predicted curve and the stratigraphic position QC result. Further comprising lithology profile prediction: obtaining the classification probability by using stratified supervised classification, and fusing the spatial prior probability obtained based on the lithology of adjacent wells and distance weight to output the lithology interval of the target well and the profile comparison chart. This method comprehensively utilizes the well logging curves of adjacent drilled wells, stratigraphic position stratified data, well location and well deviation trajectory information, and under the unified depth reference, performs multi-algorithm horizontal interpolation prediction on multiple well logging curves of the target well, and further combines supervised learning and spatial prior to realize lithology profile prediction, and outputs the stratigraphic profile results which can be used for pre-drilling decision and well location deployment.

The present application relates to the technical field of geological modeling, in particular to a deep stratum petrophysical modeling method under complex lithology background, comprising the following steps: well logging data preprocessing, mineral model optimization processing, petrophysical modeling and shear wave prediction, and verification of the accuracy of the petrophysical model in predicting shear wave. The present application adopts four mineral models of quartz-clay model, calcite-clay model, coal and bauxite, respectively, and performs optimal multi-mineral model processing in stratigraphic sections, so as to obtain the petrophysical modeling of deep coal measure stratum complex lithology combination and pore structure under shear wave prediction, and improve the accuracy of shear wave prediction.

The invention relates to the technical field of sea sand automatic identification, in particular to a sea sand automatic identification method based on multi-source geophysical data fusion. The method comprises the following steps: acquiring well drilling data, single-channel seismic data and shallow stratum profile data of a target area, and performing preprocessing to generate a fused data volume; constructing a dual-channel deep learning model based on the fused data body; training a dual-channel deep learning model by using the fused data volume and the lithologic label calibrated in the drilling data; identifying a target area by using the trained dual-channel deep learning model, and verifying an identification result to generate a sea sand distribution result; according to the invention, through sea sand automatic identification, full-process automation from data preprocessing to result output is realized.

The invention relates to the technical field of three-dimensional modeling, and discloses a system and method for exporting a stratum section line file adaptive to MapGIS modeling based on Petrel software, and the method comprises the steps: preparing three-dimensional structure planar graph data of a stratum to be modeled; establishing a vertical fault plane in Petrel software along the trend of a target section, and converting the vertical fault plane into a Surface file; utilizing a Surface operation function to generate a space intersection line between the upright fault plane and each structural plane graph; and exporting the intersecting line data as an SHP format file, and converting the intersecting line data into a line file which can be identified by a MapGIS platform. The system comprises a corresponding data preparation module, an upright fault plane construction module, an intersection line generation module and a data export conversion module. According to the method, efficient and accurate conversion of core structure data from a Petrel platform in the field of oil exploration and development to a MapGIS platform in the field of geological survey is realized, and the problem of cross-department and cross-software data barriers is solved.

The invention relates to an earthquake high-resolution processing method and device based on deep learning and a storage medium, which are applied to the technical field of oil-gas exploration and development, and comprise the following steps: calculating a depth domain reflection coefficient by acquiring longitudinal wave velocity and density data in logging data of each logging; carrying out stratigraphic division on the depth domain reflection coefficient by adopting a dynamic threshold method to obtain a reflection coefficient set of each divided stratigraphic section; the method comprises the following steps: acquiring a depth index of an end position of each stratum section, and calculating the thickness and two-way travel time of each stratum section; the geologic features such as lithologic transverse change, formation thickness heterogeneity and tectonic col are simulated through reflection coefficient strength, formation thickness and depth disturbance, the underground geologic structure outside a well is effectively simulated, the bottleneck that model training samples are insufficient under the condition of few wells is solved, and the method has the advantages of being simple in structure, convenient to operate and high in practicability. Samples and labels required by network model training can be constructed based on a small amount of well data.

The invention belongs to the technical field of oil-gas exploration, and discloses a carbonate rock stratum sequence stratigraphic quantitative division method based on element geochemistry, which comprises the following steps: S1, sampling rocks, and drawing a stratigraphic histogram and sampling point horizon; s2, the obtained samples are screened, and fresh flour of the selected samples is ground into powder for preparation; s3, testing the prepared sample powder to obtain geochemical test data; s4, key indexes for identifying third-level and fourth-level sequence interfaces are determined, and values of the key indexes are projected on the stratigraphic section according to the depth. The method has the advantages that according to the characteristic that the change of the ancient sedimentary environment can cause rising and falling of the sea level, so that stratigraphic records have different geochemical response characteristics; the geochemical elements are innovatively introduced to quantitatively divide the stratigraphic sequence, the problem that only the stratigraphic sequence can be qualitatively divided in the prior art is solved, and the precision and accuracy of carbonate rock stratigraphic sequence recognition are improved.

The application discloses a kind of underwater structure fluid loss intensity evaluation methods based on multi-dimension acoustic scanning, belong to underwater engineering detection technical field.The method is by ROV carrying shallow stratigraphic profiler to the underwater structure is bidirectional scanning in transverse and longitudinal direction, obtains acoustic profile data;From data, identify the silt reflection phenomenon caused by structure gap;Based on the phenomenon identified, extract impact height, impact mouth section to water surface length and structure gap width and other parameters;According to the extracted parameters, calculate impact height coefficient, impact section coefficient and impact compression coefficient, realize multi-dimension quantitative evaluation of fluid loss intensity through the coupling calculation of three coefficients.The application can accurately identify siltation and structure deformation in turbidity water area, realize efficient data acquisition while reducing manual risk, improve the reliability and accuracy of evaluation.

The invention discloses a deposition path process fingerprint decoding method and system based on a complex source-sink system, and relates to the technical field of tectonic sedimentology and data modeling crossing. Target strata geochemical characteristic data of a research area are collected and arranged, and a large deposition geochemical data set of the research area is established; and establishing standard stratum characteristics and sedimentary geochemical characteristics thereof in combination with a typical stratum profile of the basin. According to the method, the multi-source supply and re-cycle contribution proportion on the geologic source-sink system deposition path is quantitatively recovered through establishment of target layer series multi-dimensional scaling analysis, homogenization degree analysis, fingerprint decoding parameter PCA data statistics and the like, the defects that a traditional source-sink analysis method depends on prior end member selection and is easily influenced by personal errors are overcome, and the method is suitable for large-scale analysis of the geologic source-sink system deposition path. The inverse Monte Carlo model is utilized to carry out iterative simulation for multiple times, the simulation effect is gradually optimized, the accuracy and reliability of the deposition path and process description result are ensured, and a more scientific and accurate technical means is provided for geological research and resource exploration.

The application provides a sound velocity and stratigraphic dip estimation method for non-equal layer thickness deposition layers, and belongs to the technical fields of seafloor shallow stratigraphic profile detection and digital signal processing. The method solves the problems of easy divergence and falling into trivial solution in parameter inversion under complex seafloor conditions. The method comprises the following steps: obtaining shallow stratigraphic echo data of multi-direction detection; establishing a multi-direction sound propagation geometric model, and constructing a nonlinear objective function with a physical time residual as a core to form a physical residual barrier against degradation; substituting actual observation echo time differences of each wave beam into the nonlinear objective function to jointly construct an over-determined nonlinear equation set; using a finite difference method to approximately solve a Jacobian matrix of the over-determined nonlinear equation set; performing constraint truncation on the trial updated geosound parameters; adaptively adjusting an algorithm damping factor, and performing cyclic iteration until a convergence condition is met, and finally outputting an estimated value. The method is mainly used for sound velocity and stratigraphic dip estimation of non-equal layer thickness deposition layers.

The embodiment of the invention provides a method and device for establishing a sequence stratum time profile based on sedimentary forward modeling. The method comprises the steps that three-dimensional sedimentary forward modeling numerical simulation is conducted on a stratum in a research area based on a diffusion coefficient equation to obtain a sedimentary simulation result; establishing a deposition forward modeling model according to the deposition simulation result; determining grid points according to the two-dimensional profile position of the research area; according to the deposition simulation result and the deposition forward modeling model, outputting deposition states of the grid points at different times, and obtaining depth domain stratigraphic sections of the grid points at different times; establishing a two-dimensional time domain stratigraphic profile; and comparing the two-dimensional time domain stratigraphic section with the depth domain stratigraphic section at the corresponding position of the grid point to obtain sequence stratigraphic time section features. The method is simple and easy to implement, the sedimentation forward modeling model can be established by considering water flow driving, slope terrain driving and the combined effect of the three influence factors, the accuracy of the sedimentation forward modeling model is improved, and finally the accuracy of obtaining the sequence stratigraphic time profile characteristics of the research area is improved.

The invention relates to a formation section construction method and device, a storage medium and a computer program, and the method comprises the steps that layer position points on tracks of a plurality of reference wells in a preset range of a horizontal well are obtained, and the layer position points on the tracks of the reference wells come from corresponding layers on a formation section of the reference wells and are used for representing the positions of the layers. And traversing each test point, and calculating a distance coefficient between the current test point and the different reference wells. Based on a preset distance coefficient calculation formula, according to the distance between each horizon point on the same reference well and the test point, the distance coefficient between the test point and the reference well is calculated, and the distance coefficients between the same test point and different reference wells are compared; the reference well with the minimum distance coefficient is selected as the interpretation well to which the test point belongs, different interpretation wells have different stratigraphic sections, and the thickness of the same layer in the stratigraphic sections of the different interpretation wells is different.