42 results about "Tectonic stress" patented technology

The invention relates to the technical field of three-dimensional visualization, in particular to a geological exploration three-dimensional visualization analysis system which comprises a spatial discretization construction module, an interface geometric feature extraction module, an attenuation factor calculation module, an internal stress field inversion module and a voxel lighting effect mapping module. According to the method, by constructing a voxelization space system and combining projection coordinates of a top plate and a bottom plate of the stratum, the geometric bending degree and local thickness variation characteristics of the stratum interface are accurately quantified, and a mapping relation between a spatial form and an internal stress field is established by utilizing geometric conduction factors; the method can invert tectonic stress distribution from stratum extrusion deformation and thickness reduction trends, effectively identify a hidden stress concentration area in a geologic body, dynamically adjust optical attributes of regular hexahedron units according to stress intensity, convert abstract mechanical characteristics into visual three-dimensional images, realize spanning from pure geometric display to internal physical mechanism analysis, and improve the analysis accuracy of the geologic body. And the identification precision and the early warning capability of the geological disaster source are obviously improved.

The invention discloses a tectonic stress factor-based landslide risk prediction method suitable for Sichuan-Tibet regions, and belongs to the technical field of geological disaster prevention and control. The method aims at solving the problem that traditional landslide prediction under strong tectonic stress and complex terrain in the Sichuan-Tibet region is insufficient in accuracy, and comprises the steps that data are collected and processed into DEM raster data, the DEM raster data are converted into point Shapefile data, and terrain point plane coordinates and elevation values are extracted to form a terrain dot matrix associated with global coordinates; calculating the slope length and gradient of the topographic point and the landslide center point, the tectonic stress of the topographic point and the topographic stress, and constructing a tectonic stress magnitude risk factor; determining an area stress field direction in a molecular area and obtaining an included angle of topographic points in a near-far fault area, and constructing a tectonic stress direction risk factor; and calculating the landslide risk of each topographic point, dividing extremely high to extremely low danger areas, and outputting a danger map of the calculation area. The method adapts to Sichuan-Tibet geological features, the prediction accuracy is improved, and a scientific basis is provided for Sichuan-Tibet area landslide prevention and control.

The invention discloses a structure-karst-unloading coupling degradation high and steep slope collapse physical model experiment system, and relates to the field of slope collapse risk management, and the system comprises a construction module which is used for constructing a high and steep slope model containing a karst network; the monitoring module is used for synchronously capturing micron-order opening and micro-fracture evolution information of an internal structural surface of the model and stress-seepage field distribution data; according to the method, the model is guaranteed to be highly matched with the actual geological environment through dynamic calibration of the adaptation degree, micron-sized synchronous capture of internal structure evolution, stress distribution and seepage field data of the model is achieved, and the monitoring precision is improved through multi-device collaborative layout and data credibility verification; and cooperatively applying tectonic stress, karst seepage and graded unloading according to a real time sequence, and dynamically adapting to the quasi-steady-state requirements of the stress-seepage field of the model.

The invention relates to the technical field of shale gas geology, in particular to a method for depicting a breaking joint body in a breaking joint body development area, and the method comprises the steps: firstly, generating an initial breaking joint body probability body based on interpretable machine learning fusion seismic attributes, and building a three-dimensional space distribution model containing large and medium faults after manual interactive interpretation and well seismic calibration; on the basis, large and medium-sized faults serve as a deterministic skeleton, a fracture development rule is predicted in combination with paleotectonic stress field simulation and a rock fracture criterion, a three-dimensional discrete fracture network model constrained by geomechanics is constructed and then coupled with a matrix model, and a model set is generated by defining an uncertainty parameter space. And screening out an equivalent model group through historical matching, performing prediction verification and iterative optimization by using recent production data, and finally obtaining a three-dimensional space distribution model of the high-precision breaking joint body. According to the method, closed loop of static identification and dynamic verification is realized, and the depicting precision and the geological reliability are remarkably improved.

The present application relates to a kind of methods for restoring porosity evolution of clastic reservoirs under tectonic extrusion, belonging to the technical field of oil and gas exploration and development.The method comprises the following steps: calculating the total compaction and pore loss of clastic rock samples, selecting samples with similar burial depth, similar rock structure and different maximum paleo-tectonic stress as selected samples, obtaining the lateral compaction and pore loss of the one with larger maximum paleo-tectonic stress by the difference of total compaction and pore loss corresponding to the two selected samples adjacent to the maximum paleo-tectonic stress, and establishing the functional relationship between lateral compaction and pore loss and maximum paleo-tectonic stress;calculating the lateral compaction and pore loss of each lateral extrusion in multiple lateral extrusions;calculating the vertical compaction and pore loss according to the total compaction and pore loss and lateral compaction and pore loss, and establishing the relationship chart between vertical compaction and pore loss and burial depth;using the inverse back stripping method, combining lateral compaction and pore loss and vertical compaction and pore loss, and drawing the porosity evolution curve of clastic reservoirs in geological history under tectonic extrusion.This method solves the problem of being unable to quantitatively calculate lateral and vertical compaction and pore loss in the process of restoring porosity evolution of foreland basin reservoirs.

The application discloses a method for reconstructing a paleo-tectonic stress field based on vertical displacement of vertical fractures, and aims at solving the problem of low accuracy of the prior art in establishing a paleo-tectonic stress field. V V‑MAX V‑MIN V V V‑MAX V‑MIN V V‑MAX V‑MIN H V h H The method avoids the possible large human errors in the identification of typical structures and the matching with the theoretical model, and significantly improves the accuracy.​​​​​​​​​​​​​

The application provides a deep and shallow buried division method and system of underground engineering based on tunnel excavation effect, and belongs to the technical field of computer-aided design. The scheme comprises the following steps: obtaining an initial ground stress field of a tunnel area; sampling the tunnel area, carrying out a conventional triaxial test, and obtaining a full stress-strain curve of surrounding rock; obtaining ground stress information of a given engineering section according to the initial ground stress field of the tunnel area, establishing a three-dimensional numerical model of the tunnel, carrying out numerical simulation by using a constitutive model considering strain softening, and obtaining a stress field after tunnel excavation; and based on the full stress-strain curve and the stress field after tunnel excavation, deep and shallow buried division is carried out. The scheme fully considers that the occurrence of tunnel disasters under strong tectonic stress is significantly affected by true three-dimensional stress, considers the tunnel excavation effect, carries out deep and shallow buried division based on the true three-dimensional stress field, provides clear suggestions for the selection of the constitutive model of surrounding rock in the design process, and provides clear guidance for support design.

This invention relates to the field of oil and gas reservoir geological exploration technology, specifically a method for identifying multiple fracture stages in buried hill oil and gas reservoirs based on tectonic stress field evolution. The method includes the following steps: Tectonic evolution history analysis step: Geological data of the target buried hill oil and gas reservoir area are systematically collected. Based on seismic profiles, stratigraphic contact relationships, tectonic deformation characteristics, and chronological data, a comprehensive analysis is conducted to construct a multi-stage tectonic evolution history of the area from the Paleozoic to the Cenozoic, accurately determining the geological age and tectonic nature of each key tectonic event. Compared to existing technologies, this application establishes a quantitative discrimination model based on mechanical principles through paleostress field numerical simulation and quantitative prediction of theoretical fracture parameters. This standardizes and quantifies the fracture stage identification process, significantly reducing the uncertainty caused by human factors, improving the objectivity and repeatability of the discrimination results, and achieving a leap from qualitative analysis to quantitative discrimination.

The invention provides a maximum horizontal principal stress obtaining method based on a Mohr-Coulomb criterion, and belongs to the technical field of reservoir rock mechanics research. The maximum horizontal principal stress obtaining method comprises the steps that formation pore pressure and rock strength parameters are obtained through comprehensive logging data, and drilling fluid column pressure is calculated through drilling fluid density data; measuring the minimum horizontal principal stress; the well wall caving width is obtained through the dual-hole-diameter logging data; according to a calculation equation, factors such as tectonic stress, drilling working conditions and formation fluid are fully considered in the method, and the well wall caving width is obtained through well logging information; indoor rock core testing is not needed; the calculation precision is high, and a scientific basis is provided for oil reservoir engineering, drilling engineering and yield increase engineering.

The invention provides a metallogenic prediction system based on a knowledge graph, and belongs to the technical field of mines. Comprising a data acquisition module used for constructing a mining area multi-source monitoring data set; the knowledge graph construction module is used for generating a mining area disaster knowledge graph representing the incidence relation between the mining area underground structure state and the disaster induction factors; the risk knowledge portrait construction module is used for constructing a disaster risk knowledge portrait for depicting mining area hidden geological disaster characteristics; the risk assessment module is used for constructing a collapse risk coefficient, a tectonic stress concentration coefficient and an induced earthquake sensitivity coefficient; and the risk response module is used for constructing a comprehensive risk coefficient, presetting a comprehensive risk threshold value, comparing the comprehensive risk coefficient with the comprehensive risk threshold value, triggering an alarm instruction and performing optimization. The characteristics of mining area activities and the like are reflected from multiple dimensions, overall description of mining area hidden geological disaster risks is achieved, judgment is not depended on a single monitoring index, and mining area mining safety is improved.

FIELD: underground mining in rocks.SUBSTANCE: method of mining a working in a rock mass exposed to tectonic stresses includes making a straight cut with the formation of a cutting cavity in the centre of the mine working, determining the direction of the greatest compressive stress in the massif and forming the mine working. If the greatest compressive stress is found in the horizontal transverse direction to the contour of the working, the cutting cavity is expanded by exploding pre-contour and contour blasthole charges in the horizontal transverse direction to the contour of the mine working, whereas as a result of the explosion, a dome-shaped part of the cavity of the mine working is formed due to the natural destruction of the rock.EFFECT: increase in the stability of the workings' boundary rocks.1 cl, 3 dwg

The invention relates to the technical field of petroleum geological exploration and geophysical data processing, and discloses a fault rod extraction method and system based on a morphological erosion algorithm, which can be used for removing noise in low signal-to-noise ratio data and accurately segmenting a fault fracture zone, and carrying out erosion operation based on a directional anisotropic structural element customized by a tectonic stress field. The erosion operation is carried out along the dominant direction of the fault, the fracture zone is compressed towards the core axis of the fault by using the iterative erosion and feedback correction means constrained by the fault trend model, and the artificial limb on the fault rod is eliminated and the missing part on the fault rod is complemented by using the multi-attribute fusion verification and topological optimization method. According to the fault rod extraction method, a fault rod has higher authenticity and spatial continuity, a generated data body is input into a three-dimensional Kriging interpolation gap filling and then is converted through a coordinate system, so that the output fault rod data body can directly meet the precision required by tectonic framework modeling, and the fault rod extraction method suitable for low-signal-to-noise-ratio data is provided.

The invention belongs to the technical field of oil exploration, and discloses a crack propagation path quantitative prediction method based on a double extreme value principle. The method comprises the following steps: obtaining a stress-strain curve and related mechanical parameters through a rock mechanics experiment; constructing a rock fracture criterion based on a double extreme value principle; establishing a quantitative prediction model of the crack propagation angle and length; combining with three-dimensional tectonic stress field simulation to realize spatial prediction of a crack propagation path; and the reliability of the prediction result is verified through measured data. The method disclosed by the invention reveals a crack propagation mechanism from the perspective of energy evolution, has the advantages of solid physical foundation and adaptability to complex geological conditions, remarkably improves the precision of crack length and direction prediction, and provides reliable technical support for evaluation and development optimization of an unconventional reservoir crack system.

This invention provides a method and system for predicting reservoir permeability based on formation tectonic stress. The method includes: acquiring reservoir rock mechanics test data, formation test data, core permeability test data, fracturing operation data, and well logging data; constructing an effective stress model using the formation test data and well logging data to calculate formation pressure; calculating various rock mechanics parameters and performing dynamic-static conversion of Poisson's ratio using the reservoir rock mechanics test data and well logging data; obtaining the horizontal maximum principal stress based on the Huang model, using the fracturing operation data and the obtained rock mechanics parameters; and establishing a fitting relationship between the horizontal maximum principal stress and core permeability to predict permeability. The system can implement the method described above. The advantage of this invention is that the obtained carbonate rock permeability has higher accuracy.

This invention belongs to the field of seismic information processing technology and discloses a method and system for constructing a three-dimensional model of seismogenic faults based on aftershock precision location data. The method includes: acquiring seismic geological data of the study area; establishing a high-resolution three-dimensional crustal velocity model of the study area and determining precise source parameters; obtaining tectonic stress field characteristics through source mechanism solutions and GNSS observation data; and studying the seismogenic mechanism of the study area and obtaining information on potential strong earthquake hazards. This invention combines two grid intervals, 0.2°×0.2° and 0.1°×0.1°, to obtain both the velocity structure of the non-source area with a 0.2°×0.2° grid interval and the velocity structure of the source area with a 0.1°×0.1° grid interval. This is suitable for studying the velocity structure of source areas with a relatively small number of stations.

The invention provides an active fracture cascade dislocation field simulation method and system, and relates to the technical field of geomechanical tests, and the method comprises the steps: building a fracture triggering time sequence prediction model based on a fracture mechanics theory and an energy release principle; constructing an inter-fracture stress transfer function based on the physical information of the fracture zone; predicting fracture triggering time based on the fracture triggering time sequence prediction model, simulating stress transfer between fractures and updating a stress field; calculating mechanical energy generated by the dislocation, constructing a quantitative model for converting the mechanical energy into chemical energy, predicting a chemical product generation condition based on the quantitative model, and updating physical information of the fault zone according to the chemical product generation condition; and performing cascade dislocation simulation based on the updated physical information of the fault zone and the updated stress field to obtain a simulation result. By establishing a complete theoretical framework and mathematical model, high-precision simulation of cascade dislocation of multiple secondary fractures in an active fault zone under the action of strong shock or tectonic stress is realized.

The utility model discloses a kind of composite support structure for the large deformation of soft rock tunnel surrounding rock caused by tectonic stress, including tunnel body, the initial support system and secondary lining system of setting in tunnel body inner wall, the arch waist of the tunnel body has expansion area, and the expansion area is filled with concrete.The utility model provides composite support structure for the large deformation of soft rock tunnel surrounding rock caused by tectonic stress, to solve the problem that initial support is subjected to horizontal direction tectonic stress and generates larger deformation in arch waist part in prior art, realize the purpose of improving the support resistance of horizontal direction tectonic stress, reducing the damage risk of initial support structure, reducing construction risk.

The invention provides a method for calculating the pore reduction amount of sandstones with different preexisting porosities by using compressive tectonic stress. The method comprises the following steps: (1) selecting parallel samples to carry out experimental analysis test; (2) calculating the vertical stress hole reduction amount in the burying process; (3) recovering the pre-stored porosity when the tectonic action occurs; (4) calculating the sandstone pore reduction amount corresponding to the lateral extrusion tectonic stress; (5) building a function relationship between the tectonic stress and the hole reduction quantity in a classified manner; (6) calculating'one-stage multiple-effect 'of compressive structure deformation; (7) calculating a'multi-period cumulative effect 'of compressive structure deformation; and (8) recovering the diagenetic-pore evolution history of the compressive structure. Compared with a traditional porosity prediction method, the calculation method provided by the invention plays an important role in prediction of the pre-drilling porosity of the reservoir of the mountain-front tectonic zone, the prediction result is finer and more accurate, the practicability is higher, and large-scale popularization and application are facilitated.

The invention relates to a model and method for obtaining a multi-factor weight value for evaluating the development potential of a shale gas well. According to the method, the stress intensity, the Anderson coefficient and the slippage risk coefficient are used as geological structure parameters for evaluating the gas production rate of the shale gas well, the problems that in the prior art, parameter selection is single, and complex structure stress field characterization is insufficient are solved, an evaluation index system is made to have physical rationality and engineering pertinence, and the evaluation accuracy is improved. Therefore, a more comprehensive and reliable geologic structure foundation is provided for gas production capacity evaluation of the shale gas well. According to the method, a heterogeneous base learner system composed of the LassoNet, the random forest and the XGBoost is introduced on the model structure, the complementary advantages of different models in the aspects of feature selection, nonlinear relation modeling and anti-noise capability are fully played, and the deviation risk caused by a single model is effectively reduced.

The invention belongs to the technical field of simulation test devices, and particularly relates to a rock mass self-weight-tectonic stress response super-large span cave depot excavation simulation test device, which comprises a frame assembly, a rock mass self-weight-tectonic stress simulation test device and a rock mass self-weight-tectonic stress simulation test device, the loading assembly is arranged in the frame assembly, and the loading assembly is used for applying a load to the sample; the window is formed in the frame assembly and used for simulating cave depot excavation unloading response; the support assembly is movably connected with one end of the frame assembly, and the support assembly is used for supporting the frame assembly; the angle adjusting assembly is fixedly connected with the other end of the frame assembly, and the angle adjusting assembly is used for adjusting the inclination angle of the frame assembly. According to the method, the synergistic effect of the rock mass self-weight-tectonic stress response and the dynamic excavation unloading response can be achieved, the limitation of a traditional test technology is broken through, and a scientific basis is provided for safe construction and long-term operation and maintenance of a super-large-span cave depot.

The present application relates to the technical field of coal resource exploration, and particularly relates to a deep coal resource intelligent exploration method based on tectonic stress field, comprising: arranging a detection drill hole in an exploration target area, synchronously collecting five types of parameters of tectonic stress, ground temperature, ground pressure, fluid migration rate and coal porosity by using a deep integrated detection device, and gathering and constructing a multi-field basic data sample library of each parameter; calculating a tectonic stress intensity index based on the multi-field basic data sample library, dividing the exploration target area into a stress concentration area, a transition area and a stable area according to the index, and determining a regulation coefficient of tectonic stress on porosity and fluid migration. In the present application, a multi-field coupling correction model dominated by tectonic stress is constructed, and then the real formation physical property parameters are restored, so that the traditional exploration which mostly uses single physical field detection is improved. Since the nonlinear regulation of tectonic stress on multi-physical field is ignored, the problem that the tectonic coal and gas enrichment area cannot be accurately identified in the deep stress concentration area is caused.

This invention discloses a landslide hazard prediction method based on tectonic stress factors applicable to the Sichuan-Tibet region, belonging to the field of geological disaster prevention and control technology. It aims to address the insufficient accuracy of traditional landslide prediction methods under strong tectonic stress and complex terrain in the Sichuan-Tibet region. The method includes: collecting data and processing it into DEM raster data; converting the DEM raster data into point-like Shapefile data; extracting the planar coordinates and elevation values ​​of topographic points to form a topographic point matrix with associated global coordinates; calculating the slope length and gradient of the topographic point and the landslide center point, as well as the tectonic stress and topographic stress of the topographic point, to construct a tectonic stress magnitude hazard factor; determining the direction of the regional stress field in molecular regions and the angle between the topographic point and the near-far fault zone, to construct a tectonic stress direction hazard factor; calculating the landslide risk of each topographic point, dividing the area into extremely high to extremely low hazard zones, and outputting a hazard map of the calculated area. This invention is adapted to the geological characteristics of the Sichuan-Tibet region, improves prediction accuracy, and provides a scientific basis for landslide prevention and control in the Sichuan-Tibet region.

The application discloses a kind of determination method and system of roadway surrounding rock stability control parameter.It is determined that method includes: receiving input parameter, including tectonic stress grade identification, overburden average specific gravity, roadway buried depth, surrounding rock lithology information, component span and concrete compressive strength;Determine lateral pressure coefficient based on tectonic stress grade identification and query preset mapping table, calculate basic lateral ground stress;According to surrounding rock lithology information, it is judged whether it belongs to soft rock category, if it is, according to softening degree, another mapping table is inquired to obtain correction coefficient, and the basic stress is softened and expanded to correct, to obtain the modified lateral ground stress value;Using the correction stress value, component span and concrete compressive strength, the design thickness of stress self-balancing precast component is calculated by the formula of built-in comprehensive safety factor;Finally, the modified lateral ground stress value and component design thickness are output, and support scheme early warning can be output when stress value is too high.

This invention relates to a method for predicting natural fractures based on tectonic stress evolution, comprising: S1, construction of a three-dimensional geomechanical parameter field; S2, preliminary calculation of the present-day geostress field; S3, historical stress constraints and past-present stress inversion; S4, past-present forward modeling of tectonic stress and simulation of fault activity; and S5, prediction and output of stress-induced fracture distribution. This application achieves multi-source parameter consistency, present-day geostress field inversion, determination of past-present stress evolution paths, and quantitative characterization of the control effect of fault activation-healing processes on fracture / damage zones within a unified three-dimensional geomechanical framework. This results in verifiable, interpretable, and generalizable predictions of the intensity distribution of natural fracture development, improving the reliability and engineering guidance value of the prediction results.

The invention discloses a quantitative evaluation method and device for different cause overpressure contribution degrees of an oil and gas reservoir, and the method comprises the steps: determining the vertical effective stress of an overpressure point based on the logging data and actually measured pressure data of a research region; respectively determining the maximum horizontal principal stress and the minimum horizontal principal stress of the overpressure point based on the extrusion tectonic stress and the rock Poisson's ratio of the overpressure point and the vertical effective stress; the average stress of the overpressure point is determined based on the overlying stratum pressure, the maximum horizontal principal stress and the minimum horizontal principal stress of the overpressure point; based on the average stress of the overpressure point and the average effective stress of the overpressure point at the equivalent depth point, the tectonic extrusion pressurization amount of the overpressure point is determined; determining an overpressure point sound wave velocity of an overpressure point based on a correlation curve of normal compaction section sound wave velocity-vertical effective stress of the research area; and based on the vertical effective stress of the overpressure point and the sound wave velocity of the overpressure point, the overpressure transmission pressurization amount of the overpressure point is determined, so that overpressure contribution degrees of different causes are determined, and a theoretical basis is provided for oil-gas exploration.

The invention provides a multi-source data fusion three-dimensional crustal stress field dynamic inversion method and system based on an intelligent optimization algorithm, and the method comprises the steps: collecting multi-source geological data containing crustal stress components and rock mass mechanical parameters, and constructing a three-dimensional geomechanical model; setting model boundary gravity and multi-direction tectonic stress load working conditions, calculating single-working-condition stress distribution and extracting stress calculation values of measuring points; constructing an inversion objective function based on the stress calculation value and the measured value; an improved intelligent optimization algorithm is adopted, and an optimal boundary load combination coefficient is inversed by taking a target function as a fitness function; and linearly superposing the optimal coefficient and the corresponding working condition stress distribution to synthesize a global three-dimensional initial crustal stress field. The problems that a traditional method is low in inversion efficiency, prone to falling into local optimum and insufficient in stress component precision under complex geological conditions are solved, and rapid and accurate acquisition of the three-dimensional crustal stress field of the engineering area is achieved.

The invention relates to the technical field of coal resource exploration, in particular to a deep coal resource intelligent exploration method based on a tectonic stress field, which comprises the following steps of: arranging exploration drill holes in an exploration target area, synchronously acquiring five types of parameters including tectonic stress, ground temperature, ground pressure, fluid migration rate and coal porosity by utilizing a deep integrated detection device, and calculating the exploration drill holes; gathering the parameters to construct a multi-field basic data sample library; and calculating a tectonic stress intensity index based on the multi-field basic data sample library, dividing the exploration target area into a stress concentration area, a transition area and a stable area according to the index, and determining a regulation coefficient of the tectonic stress on porosity and fluid migration. According to the method, the multi-field coupling correction model dominated by the tectonic stress is constructed, and then the real physical property parameters of the stratum are restored, so that the problems that the traditional exploration mostly adopts single physical field detection, and non-linear regulation and control of the tectonic stress on multiple physical fields are ignored; and the problem that the tectonic coal and gas enrichment area cannot be accurately identified in the deep stress concentration area is solved.

This invention proposes a method and system for quantifying the uncertainty of surrounding rock pressure in deep rock tunnels. The method includes: acquiring the measured stress components at multiple measuring points along the tunnel, constructing a multivariate linear regression model, and combining numerical simulation of different stress conditions to invert the initial geostress distribution in the tunnel area; constructing a three-dimensional numerical model of the tunnel, applying the initial geostress distribution as a boundary condition to the three-dimensional numerical model of the tunnel, and using it to calculate the maximum unbalanced force ratio of the tunnel contour nodes; identifying the search interval limit value of the surrounding rock pressure corresponding to the critical stability state of the tunnel through the strength reduction method, and solving iteratively through an improved bisection search algorithm to invert and output the final vertical surrounding rock pressure value; this method improves the scientificity, accuracy, and reliability of surrounding rock pressure calculation under deep tunnel geostress environment by inverting the deep strata tectonic stress field, realizing efficient iterative inversion of surrounding rock pressure, and probabilistic expression of horizontal surrounding rock pressure.

The invention discloses a gold mine geological information analysis system and method based on deep learning, and relates to the technical field of geological information intelligent processing, and the method comprises the steps: collecting mining area geological data, and extracting fusion space structure and time sequence evolution characteristics; carrying out feature mapping by utilizing the adversarial network to generate standardized geologic features; dividing the time window into a plurality of time windows, and constructing an evolution sequence in combination with tectonic stress field data; calculating response characteristics of the geologic characteristics to the stress field, and determining correlation strength of the two; and inputting the correlation intensity into a prediction function, calculating the metallogenic probability of each time window by adopting adaptive weight, and constructing a distribution map to realize gold mine prediction. According to the method, multi-source geological data and spatial-temporal characteristics are integrated, and the accuracy and reliability of gold mine prediction are improved.

The application discloses a tunnel hole wall secondary stress recovery test method and device, and relates to the technical field of tunnel construction surveying.The method is that firstly, an integrated combined strain gauge containing strain gauges in 0° direction, 45° direction, 90° direction and-45° direction and the like is pasted on the end surface of a rock core; secondly, initial strain values in each direction are measured and recorded; thirdly, the rock core is placed between upper and lower saddle-shaped cushion blocks, and the rock core is subjected to secondary stress recovery test in each direction; finally, the 0° direction and the 90° direction are divided into a group, the-45° direction and the 45° direction are divided into another group, the stress values recovered by two perpendicular directions in each group are regarded as confining pressures, and the final secondary stress measurement result is corrected in combination with the known mapping relationship between the confining pressures and the confining pressure influence coefficient, so that the measurement precision of the secondary stress of the hole wall surrounding rock can be greatly improved without using regional tectonic stress for estimation.