Intelligent Processing Method, Device and Storage Medium for Geological Exploration Data

Abstract

The present invention relates to the field of geological exploration technology, and particularly to an intelligent processing method, device and storage medium for geological exploration data, including: collecting geological vibration data and hydrothermal vent parameters of a target area in real time, and also collecting sediment physical property data, constructing a pressure compensation model and a temperature correction model, and then correcting the geological vibration data, constructing a first characteristic surface of the target area, and then constructing a second characteristic value of the target area, and strengthening the characteristics of the first characteristic surface with the second characteristic value to generate the geological structure characteristics of the target area, constructing a third-dimensional characteristic of the geological structure characteristics of the target area to update the geological structure characteristics of the target area, constructing an alarm model based on the geological structure characteristics of the target area, and outputting an alarm result. The present invention effectively improves the efficiency of geological exploration data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of geological exploration, and particularly to an intelligent processing method, device and storage medium for geological exploration data. Background Art

[0002] Traditional geological exploration systems are mostly designed for land or shallow sea environments, and their data processing methods have significant limitations in deep sea extreme environments. For example, conventional sensors are prone to signal drift in high-pressure environments, and data such as the activities of deep-sea hydrothermal vents and the propagation characteristics of submarine seismic waves, which are unique to the deep sea, have not been fully integrated and analyzed.

[0003] Chinese Patent Publication No. CN113608271A discloses a geological exploration data processing method and system. Obtain induced polarization instrument parameters, original data and original data files; calculate the corresponding K value and apparent resistivity for each measuring point; update the original data file to obtain an updated original data file; summarize all the original data to obtain an original data summary file; perform quality inspection on the original data according to the quality inspection data to generate a quality inspection data summary file; match the quality inspection data in the quality inspection data summary file with the original data in the original data summary file, and generate a quality inspection summary file; add planar coordinates to obtain a corresponding file with coordinates. It can be seen that this invention does not analyze geological exploration in special environments. Although it realizes automatic data processing, the induced polarization instrument parameters and apparent resistivity calculation it depends on cannot be directly applied in deep sea scenarios, and it does not consider dynamic environment adaptability, resulting in low efficiency in processing geological exploration data. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent processing method, device and storage medium for geological exploration data to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, according to one aspect of the present application, an intelligent processing method for geological exploration data is provided, including:

[0006] Construct a first characteristic surface of the target area based on the corrected geological vibration data, and then combine hydrothermal vent parameters and sediment physical property data to construct a second characteristic value of the target area, and use the second characteristic value to strengthen the characteristics of the first characteristic surface, and then generate the geological structure characteristics of the target area;

[0007] Obtain the regional physical parameters of the target area, and construct a third-dimensional characteristic of the geological structure characteristics of the target area based on the obtained results and hydrothermal vent parameters to update the geological structure characteristics of the target area;

[0008] Construct an alarm model based on the geological structure characteristics of the target area and output an alarm result.

[0009] Optionally, obtain the seabed topographic map of the target area;

[0010] Establish the first characteristic surface of the target area based on the seabed topographic map and the corrected geological vibration data;

[0011] The implementation process of establishing the first characteristic surface of the target area is as follows:

[0012] Construct the vibration spectrum entropy H(x,y) of each plane coordinate point in the seabed topographic map of the target area, and set ; where p[fi(x,y)] represents the power spectral density of the i-th type of frequency at the point with coordinates (x,y) in the target area, and fi(x,y) represents the frequency value of the i-th type of frequency;

[0013] Combine the vibration spectrum entropy of each plane coordinate point in the seabed topographic map of the target area into the first characteristic surface of the target area.

[0014] Optionally, construct the second characteristic value of the target area based on the fusion of hydrothermal vent parameters and sediment physical property data;

[0015] Construct a hydrothermal activity index I with the temperature gradient △T of the hydrothermal vent, the fluid flow velocity in the target area, and the hydrogen sulfide concentration, and set ;

[0016] where v is the fluid flow velocity in the target area, ρ(H 2 S) is the hydrogen sulfide concentration;

[0017] Construct a sediment state index G with the surface porosity φ, surface sand density ρ, and shear wave velocity Vs in the target area, and set ; where k1 is the flow velocity weight, k2 is the soil density weight, k3 is the wave velocity weight, φmax, ρmax, and Vsmax are the maximum values of the surface porosity, surface sand density, and shear wave velocity, respectively;

[0018] Take the value of [0.4×I / 100 + G×0.6] as the second characteristic value of the target area.

[0019] Optionally, use the result of multiplying the second characteristic value by the vibration spectrum entropy of each plane coordinate point in the first characteristic surface as the first characteristic surface after feature enhancement;

[0020] Extract the feature point map with entropy values greater than the preset entropy value from the first characteristic surface after feature enhancement, and use the feature point map as the geological structure feature of the target area; the feature point map contains multiple feature plane coordinate points.

[0021] Optionally, obtain the regional physical parameters of the target area;

[0022] Construct a third - dimension feature based on the obtained regional physical parameters and calorific value nozzle parameters of the target area, and update the generation process of the geological structure feature of the target area according to the third - dimension feature;

[0023] When \(c1\times\mu r + c2\times\sigma\leq I / 100\), do not construct the third - dimension feature; when \(c1\times\mu r + c2\times\sigma>I / 100\), set \(c1\times\mu r + c2\times\sigma\) as the third - dimension feature;

[0024] When there is a third - dimension feature, use the sum of the third - dimension feature and the second eigenvalue as the updated second eigenvalue, and update the generation process of the geological structure feature of the target area based on the updated second eigenvalue;

[0025] Where, \(\mu r\) is the relative magnetic permeability of the target area, \(\sigma\) is the relative conductivity of the geology and seawater in the target area, \(c1\) is the magnetic field weight, \(c2\) is the conductivity weight, and \(c1 + c2 = 1\).

[0026] Optionally, construct the complexity of each plane coordinate point of the target area, integrate based on the complexity of each plane coordinate point to obtain the geological complexity state of the target area, and then iterate the update process of the geological structure feature of the target area;

[0027] Calculate the average value of the complexity of each plane coordinate point, and use the average value of the complexity of each plane coordinate point as the terrain state index \(\gamma\) of the target area. Judge the geological complexity state of the target area by setting the terrain complexity threshold \(Y\): if \(\gamma\leq Y\), do not iterate the update process of the geological structure feature of the target area; if \(\gamma>Y\), use the terrain state index \(\gamma\) as the fourth - dimension feature to iterate the third - dimension feature, and its iteration process is as follows:

[0028] When \(c1\times\mu r + c2\times\sigma>I / 100\times\eta\), set \([c1\times\mu r + c2\times\sigma] / \gamma\) as the highly active third - dimension feature;

[0029] When \(c1\times\mu r + c2\times\sigma\leq I / 100\times\eta\) and \(c1\times\mu r + c2\times\sigma>I / 100\), set \([c1\times\mu r + c2\times\sigma]\) as the low - active third - dimension feature;

[0030] Where, \(\eta\) is the preset offset ratio.

[0031] Optionally, the process of constructing the alarm model is as follows:

[0032] When the value of the \(j\) - th feature plane coordinate point in the feature point map is less than 150% of the preset entropy value, mark this feature plane coordinate point as a mineral resource point;

[0033] When the value of the j-th characteristic plane coordinate point in the characteristic point map is greater than or equal to 150% of the preset entropy value, mark the characteristic plane coordinate point as a geological activity alarm point.

[0034] Optionally, it further includes: real-time collecting geological vibration data and hydrothermal vent parameters of the target area, and also collecting sediment physical property data;

[0035] Obtain the underwater pressure and actual detection water depth when collecting geological vibration data, and construct a pressure compensation model and a temperature correction model, and then correct the geological vibration data based on the pressure compensation model and the temperature correction model;

[0036] Set the nonlinear attenuation coefficient α according to the underwater pressure and water quality density, and then set the compensation range according to the actual detection water depth. When the nonlinear attenuation coefficient α meets the set compensation range, use the nonlinear attenuation coefficient α as the compensation coefficient of the pressure compensation model;

[0037] Set the signal drift correction coefficient β based on the real-time collected hydrothermal vent parameters, and use the signal drift correction coefficient β as the output result of the temperature correction model; the process of setting the signal drift correction coefficient β is the temperature correction model;

[0038] Perform real-time correction on the geological vibration data based on the pressure compensation model and the temperature correction model; the above real-time correction process of the geological vibration data includes correction of the low-frequency seismic wave amplitude, correction of the recording time delay, and correction of the amplitude attenuation rate.

[0039] According to another aspect of the present application, there is provided an intelligent processing device for geological detection data, including:

[0040] A data acquisition module for: real-time collecting geological vibration data and hydrothermal vent parameters of the target area, and also collecting sediment physical property data;

[0041] A data correction module for: obtaining the underwater pressure and actual detection water depth when collecting geological vibration data, and constructing a pressure compensation model and a temperature correction model, and then correcting the geological vibration data based on the pressure compensation model and the temperature correction model;

[0042] A feature extraction module for: constructing a first feature surface of the target area based on the corrected geological vibration data, and then combining the hydrothermal vent parameters and sediment physical property data to construct a second eigenvalue of the target area, and enhancing the features of the first feature surface with the second eigenvalue, and then generating the geological structure features of the target area;

[0043] A geological update module for: obtaining the regional physical parameters of the target area, and constructing a third-dimensional feature of the geological structure features of the target area based on the obtained results and the hydrothermal vent parameters to update the geological structure features of the target area;

[0044] An alarm model construction module, configured to: construct an alarm model based on the geological structure characteristics of a target area and output an alarm result.

[0045] According to another aspect of the present application, there is provided a computer-readable storage medium storing a computer program, wherein the computer program is used to control the device where the computer-readable storage medium is located to execute the intelligent processing method for geological exploration data when running.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: through the pressure compensation and temperature correction models, the problem of sensor data distortion caused by high pressure and large temperature difference in the deep sea is effectively solved, filling the technical gap of traditional land / shallow sea methods; integrating vibration data, hydrothermal parameters, sediment physical properties and regional physical parameters to construct multi-level features and comprehensively depict the geological structure; based on the geological complex state and preset thresholds, realizing dynamic adjustment of model parameters and feature update, improving the analysis accuracy and real-time performance; quickly marking mineral resource points and geologically active areas through the alarm model, taking into account economic benefits and operation safety, and reducing exploration risks; from data collection, calibration to feature extraction and alarm output, the whole process is automatically processed, reducing manual intervention and significantly improving data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a schematic flowchart of the intelligent processing method for geological exploration data in this embodiment.

[0049] Figure 2 It is a schematic flowchart of the geological vibration data correction method in this embodiment.

[0050] Figure 3 It is a schematic flowchart of the geological structure feature generation method in this embodiment.

[0051] Figure 4 It is a schematic flowchart of the third-dimensional feature analysis method in this embodiment.

[0052] Figure 5 It is a schematic structural diagram of a computer-readable storage medium in this embodiment.

[0053] Figure 6 It is a schematic structural diagram of the intelligent processing device for geological exploration data in this embodiment. Specific Embodiments

[0054] To more clearly illustrate the present invention, the present invention will be further described below in conjunction with preferred embodiments and the accompanying drawings. Similar components in the drawings are denoted by the same reference numerals. Those skilled in the art should understand that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the protection scope of the present invention.

[0055] It should be noted that although terms such as first, second, and third may be used in the embodiments of the present application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0056] In the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0057] Specifically, the intelligent processing method for geological exploration data described in this embodiment is applied to the intelligent processing of exploration data in the deep-sea geological environment. The deep-sea geological environment described in this embodiment is specifically an area with frequent deep-sea geological activities, and there are geological activities and hydrothermal vents in this environment; in this environment, the prior art lacks a processing solution for geological exploration data in this extreme environment and cannot meet the task requirements of geological exploration.

[0058] Based on the above application environment, please refer to Figure 1 As shown, it is a schematic flow chart of the intelligent processing method for geological exploration data described in this embodiment, including:

[0059] Step S101, collect geological vibration data, hydrothermal vent parameters, and sediment physical property data of the target area in real time; the geological vibration data includes low-frequency seismic wave amplitude, low-frequency seismic wave frequency, recording time delay, and amplitude attenuation rate; the hydrothermal vent parameters include the temperature gradient of the hydrothermal vent, the coefficient of thermal expansion of the material of the in-situ sensor, the fluid flow rate in the target area, and the hydrogen sulfide concentration; the sediment physical property data includes surface porosity, surface sand density, and shear wave velocity; by simultaneously collecting geological vibration data, hydrothermal vent parameters, and sediment physical property data, the comprehensiveness of the data is ensured, providing multi-dimensional input for subsequent analysis; it is stipulated that the collection interval between sediment data and vibration data does not exceed 1 month to avoid data invalidation problems caused by dynamic changes in the deep-sea environment.

[0060] In this application, the real-time acquisition frequencies of the geological vibration data and hydrothermal vent parameters in the target area are simultaneously acquired at a fixed frequency and time; the acquisition time of the sediment physical property data should not exceed 1 month from the acquisition time of the geological vibration data and hydrothermal vent parameters in the target area to ensure the timeliness of data in the target area with frequent activities.

[0061] Exemplarily, the geological vibration data can be acquired through a distributed hydrophone array; the hydrothermal vent parameters can be acquired in real time through in-situ sensors; the sediment physical property data is acquired with a sampler.

[0062] The intelligent geological exploration data processing system described in this embodiment further includes:

[0063] Step S102: Obtain the underwater pressure and actual detection water depth during the acquisition of geological vibration data, construct a pressure compensation model and a temperature correction model, and then correct the geological vibration data based on the pressure compensation model and the temperature correction model.

[0064] To achieve the correction of geological vibration data for subsequent geological analysis of the target area, the specific analysis process in the above step S102 is Figure 2 The geological vibration data correction method shown includes:

[0065] Step S201: Set the nonlinear attenuation coefficient α according to the underwater pressure and water quality density, and then set the compensation range according to the actual detection water depth. When the nonlinear attenuation coefficient α meets the set compensation range, use the nonlinear attenuation coefficient α as the compensation coefficient of the pressure compensation model.

[0066] Specifically, the process of setting the nonlinear attenuation coefficient α is: Take the opposite of the ratio of the underwater pressure to the reference pressure as the logarithm of the exponential function with the natural logarithm as the base, and use the value of this exponential function as the nonlinear attenuation coefficient α.

[0067] Optionally, the compensation range is set in combination with the actual detection water depth. In an exemplary embodiment, the setting of the compensation range is: Take the range of the nonlinear attenuation coefficient α greater than or equal to ln(actual detection water depth) as the compensation range, and take the range of the nonlinear attenuation coefficient α less than ln(actual detection water depth) as the non-compensation range; Set the nonlinear attenuation coefficient α based on the underwater pressure and detection water depth to correct the low-frequency seismic wave amplitude, recording time delay, etc., and reduce the interference of the high-pressure environment on the sensor data.

[0068] Please continue to refer to Figure 2 As shown, the geological vibration data correction method further includes:

[0069] Step S202: Set the signal drift correction coefficient β based on the hydrothermal vent parameters collected in real time, and use the signal drift correction coefficient β as the output result of the temperature correction model. The process of setting the signal drift correction coefficient β is the temperature correction model.

[0070] Specifically, the process of setting the signal drift correction coefficient β is as follows: Use the product of the temperature gradient △T of the hydrothermal vent and the coefficient of thermal expansion of the material of the in-situ sensor as the main part of the signal drift correction coefficient β, and use 1 plus the corrected main part as the signal drift correction coefficient β. Dynamically adjust the signal drift correction coefficient β through the temperature gradient of the hydrothermal vent to solve the signal drift problem caused by the thermal expansion of the material of the in-situ sensor and improve the data reliability.

[0071] In order to make the temperature correction model more accurate in complex environments, in an optional implementation manner, when implementing the above step S202, preset conditions need to be set, and when the water flow data in the target area meets the preset conditions, add the main part elements of the signal drift correction coefficient. The process of setting the preset conditions is as follows: Use the product of the standard fluid flow rate and the concentration of chemical calorific value components as the judgment threshold of the preset conditions. When the product of the fluid flow rate and the concentration of chemical calorific value components in the target area collected in real time is greater than or equal to the judgment threshold of the preset conditions, it is judged to meet the preset conditions, and use the ratio exceeding the judgment threshold of the preset conditions as the added element of the main part of the signal drift correction coefficient β, and its addition operation is addition.

[0072] It should be noted that the concentration of chemical calorific value components is the concentration of chemical components that affect the water temperature in the target area. For example: H 2 S, Fe 3+ etc.; the concentration of chemical calorific value components can be either a single component or a mixture of multiple components; the standard fluid flow rate is the average fluid flow velocity in the target area during a continuous monitoring process with a duration exceeding 1 month.

[0073] Step S203: Perform real-time correction on the geological vibration data based on the pressure compensation model and the temperature correction model. The above real-time correction process of the geological vibration data includes the correction of the amplitude of low-frequency seismic waves, the correction of the recording time delay, and the correction of the amplitude attenuation rate.

[0074] Specifically, the process of performing real-time correction on the geological vibration data in the step S203 is to correct the corresponding data through mathematical formulas:

[0075] Use the product of the compensation coefficient of the pressure compensation model and the amplitude of the low-frequency seismic wave as the corrected amplitude of the low-frequency seismic wave;

[0076] Use the product of the recording time delay and the signal drift correction coefficient β as the corrected recording time delay;

[0077] Use the product of the amplitude decay rate and the signal drift correction coefficient β as the corrected amplitude decay rate.

[0078] The intelligent geological exploration data processing system described in this embodiment further includes:

[0079] Step S103: Construct the first characteristic surface of the target area based on the corrected geological vibration data, and then generate the geological structure characteristics of the target area by combining the hydrothermal vent parameters and the first characteristic surface.

[0080] To analyze the geological structure characteristics of the target area, the specific analysis process of the above step S103 is Figure 3 The geological structure characteristic generation method shown, this method includes:

[0081] Step S301: Obtain the seabed topographic map of the target area; the above seabed topographic map is obtained by devices such as a multibeam sonar system and a laser altimeter; the seabed topographic map is a three-dimensional space image within the first octant.

[0082] Step S302: Establish the first characteristic surface of the target area based on the seabed topographic map and the corrected geological vibration data; the first characteristic surface is a spatial surface composed of the vibration characteristic values of the target area established based on the geological vibration data, the first characteristic surface is a spatial surface projected on the seabed topographic map of the target area, and is another non-entity, mathematical surface established in three-dimensional space.

[0083] Specifically, the implementation process of establishing the first characteristic surface of the target area is:

[0084] Construct the vibration spectral entropy H(x,y) of each plane coordinate point in the seabed topographic map of the target area, and set ; in the formula, p[fi(x,y)] represents the power spectral density of the i-th type of frequency at the point with coordinates (x,y) in the target area, and fi(x,y) represents the frequency value of the i-th type of frequency;

[0085] Combine the vibration spectral entropy of each plane coordinate point in the seabed topographic map of the target area into the first characteristic surface of the target area; use the vibration spectral entropy H(x,y) to quantify the vibration characteristics of each point in the seabed topographic map, form a spatial surface, and intuitively reflect the distribution law of geological vibrations.

[0086] In this application, taking the point (x,y) as an example, construct the vibration spectral entropy of all points in the seabed topographic map of the target area; at the same time, set the points in the seabed topographic map of the target area as a planar square matrix, and its side length is set by the user himself, and its side length setting depends on the user's accuracy requirements; the plane coordinate points are the coordinate points within the area formed by the projection of the seabed topographic map on the horizontal plane.

[0087] It should be noted that the vibration spectrum entropy of each plane coordinate point described in this application is a numerical analysis of integer points. For plane coordinate points that are not integer points, this application uses a data tool for smoothing processing, and its processing process is a technical solution fully disclosed in the prior art, and this embodiment does not specifically limit it.

[0088] Step S303: Construct a second eigenvalue of the target area based on the fusion of hydrothermal vent parameters and sediment physical property data; the specific explanation of the second eigenvalue is the surface composition eigenvalue of the target area established based on sediment physical property data and hydrothermal vent parameters.

[0089] Specifically, the implementation process of constructing the second eigenvalue of the target area in step S303 is as follows:

[0090] Construct a hydrothermal activity index I with the temperature gradient △T of the hydrothermal vent, the fluid velocity of the target area, and the hydrogen sulfide concentration, and set ;

[0091] In the formula, v is the fluid velocity of the target area, ρ(H 2 S) is the hydrogen sulfide concentration; the purpose of constructing a logarithmic function with the H 2 S concentration is to balance the contributions of high and low concentrations, avoid numerical explosion, and enhance the sensitivity of low concentrations;

[0092] Construct a deposition state index G with the surface porosity φ, surface sand density ρ, and shear wave velocity Vs of the target area, and set ; In the formula, k1 is the flow velocity weight, k2 is the soil density weight, k3 is the wave velocity weight, φmax, ρmax, and Vsmax are the maximum surface porosity, maximum surface sand density, and maximum shear wave velocity, respectively;

[0093] Take the value of [0.4×I / 100 + G×0.6] as the second eigenvalue of the target area; combine the hydrothermal activity index I and the deposition state index G to balance the surface and deep geological characteristics and enhance the comprehensiveness of feature expression.

[0094] It can be understood that the reason for using H 2 S as the construction of the hydrothermal activity index in this application is that H 2 S is a key marker for hydrothermal vent activities, and its concentration is directly related to the formation of metal sulfide deposits (such as copper and zinc mines). High H 2 S usually indicates a potential mineral enrichment area; it should be noted that the unit of △T is ℃ / m, the unit of v is m / s, ρ(H 2The unit of (S) is mg / L; meanwhile, the hydrothermal activity index I is only used as a mathematical value without physical meaning; meanwhile, the specific values of the flow velocity weight k1, the soil density weight k2, and the wave velocity weight k3 are determined by the statistical method of regression analysis in this application to obtain the optimal values. The best value of the flow velocity weight k1 is 0.17, the best value of the soil density weight k2 is 0.53, and the best value of the wave velocity weight k3 is 0.3; the maximum surface porosity, the maximum surface sand density, and the maximum shear wave velocity are set by the user through self-interaction input, which reflect the corresponding data thresholds acceptable to the user in the actual situation.

[0095] Step S304: Based on the first characteristic surface of the target area, use the second eigenvalue to enhance the characteristics of the first characteristic surface, and then generate the geological structure characteristics of the target area; the process of enhancing the characteristics of the first characteristic surface with the second eigenvalue is as follows.

[0096] Specifically, the process of generating the geological structure characteristics of the target area includes:

[0097] Use the result of multiplying the second eigenvalue by the vibration spectral entropy of each plane coordinate point in the first characteristic surface as the first characteristic surface after characteristic enhancement;

[0098] Extract the feature point map with values greater than the preset entropy value from the first characteristic surface after characteristic enhancement, and use the feature point map as the geological structure characteristics of the target area; the feature point map contains multiple feature plane coordinate points; by enhancing the first characteristic surface with the second eigenvalue, extract the significant feature point map, highlight the geological anomaly area, and reduce the interference of redundant data.

[0099] It can be understood that the process of extracting the feature points with values greater than the preset entropy value from the first characteristic surface after characteristic enhancement is to compare the values of each plane coordinate point in the first characteristic surface after characteristic enhancement with the preset entropy value, use the plane coordinate points greater than the preset entropy value as the feature plane coordinate points, and use all the feature points in the target area as the feature point map; the value of each plane coordinate point is the "result of multiplying the second eigenvalue by the vibration spectral entropy of each plane coordinate point in the first characteristic surface".

[0100] Specifically, in this embodiment, no specific limitation is imposed on the value of the preset entropy value, and those skilled in the art can freely set it as long as it meets their value requirements. In this embodiment, the best value of the preset entropy value can be 110% of the mean value of the historical vibration spectral entropy, and those skilled in the art can also construct the best value through a mathematical model.

[0101] The intelligent processing system for geological exploration data described in this embodiment further includes:

[0102] Step S104: Obtain the regional physical parameters of the target area, and construct the third-dimensional features of the geological structure characteristics of the target area based on the obtained results and the hydrothermal vent parameters to update the geological structure characteristics of the target area. The regional physical parameters include the relative magnetic permeability of the target area and the relative electrical conductivity of the geology and seawater in the target area; the third-dimensional features are the features reflecting the deep geological structure of the target area.

[0103] Please refer to Figure 4 as shown, which is a schematic flowchart of the third-dimensional feature analysis method in this embodiment, including:

[0104] Step S401: Obtain the regional physical parameters of the target area; the acquisition of the regional physical parameters of the target area is the same as the acquisition methods of the hydrothermal vent parameters and the geological vibration data, and the acquisition time is the same;

[0105] Step S402: Construct the third-dimensional features based on the obtained regional physical parameters of the target area and the calorific value vent parameters, and update the generation process of the geological structure characteristics of the target area according to the third-dimensional features.

[0106] Specifically, the process of constructing the third-dimensional features and updating the geological structure characteristics of the target area is as follows:

[0107] When c1×μr + c2×σ is less than or equal to I / 100, do not construct the third-dimensional features; when c1×μr + c2×σ is greater than I / 100, set c1×μr + c2×σ as the third-dimensional features;

[0108] When there are third-dimensional features, use the sum of the third-dimensional features and the second eigenvalue as the updated second eigenvalue, and update the generation process of the geological structure characteristics of the target area based on the updated second eigenvalue;

[0109] Among them, μr is the relative magnetic permeability of the target area, σ is the relative electrical conductivity of the geology and seawater in the target area, c1 is the magnetic field weight, c2 is the conductivity weight, and c1 + c2 = 1; construct deep geological features through regional physical parameters (magnetic permeability, conductivity), dynamically update the second eigenvalue, and improve the adaptability of the model to complex geological structures.

[0110] Please continue to refer to Figure 4 as shown, the third-dimensional feature analysis method further includes:

[0111] Step S403: Construct the complexity of each plane coordinate point of the target area, and integrate based on the complexity of each plane coordinate point to obtain the geological complexity state of the target area, and then iterate the update process of the geological structure characteristics of the target area; the geological complexity state is specifically the terrain complexity degree of the target area; Step S403 is a step that runs when there are third-dimensional features.

[0112] Specifically, the calculation process of the complexity of each plane coordinate point in the target area is as follows: Taking the plane coordinate point a as an example, define the z-axis coordinates of all coordinate points surrounding the coordinate point a as the complex data set of the coordinate point a, calculate the coefficient of variation of the complex data set of the coordinate point a, and use the coefficient of variation of the complex data set of the coordinate point a as the complexity of the coordinate point a;

[0113] The process of iterating the update process of the geological structure characteristics of the target area is as follows:

[0114] Calculate the mean value of the complexity of each plane coordinate point, and use the mean value of the complexity of each plane coordinate point as the terrain state index γ of the target area. Judge the geological complexity state of the target area by setting the terrain complexity threshold Y: If γ is less than or equal to Y, do not iterate the update process of the geological structure characteristics of the target area; If γ is greater than Y, use the terrain state index γ as the fourth-dimensional feature to iterate the third-dimensional feature, and its iteration process is as follows:

[0115] When c1×μr + c2×σ is greater than I / 100×η, set [c1×μr + c2×σ] / γ as the highly active third-dimensional feature;

[0116] When c1×μr + c2×σ is less than or equal to I / 100×η and c1×μr + c2×σ is greater than I / 100, set [c1×μr + c2×σ] as the low-active third-dimensional feature;

[0117] Among them, η is a preset offset ratio.

[0118] Specifically, in this application, the value of the preset offset ratio η is 0.05. Those skilled in the art can freely set the preset offset ratio η, as long as it meets the value requirements of the preset offset ratio η; In step S403, adjust the weight of the third-dimensional feature according to the geological complexity state to realize the dynamic iteration of the model parameters and improve the fineness of the analysis.

[0119] Step S105, construct an alarm model based on the geological structure characteristics of the target area and output an alarm result; The process of outputting the alarm result is a publicly available technology and will not be elaborated in this embodiment.

[0120] Specifically, the process of constructing the alarm model is as follows:

[0121] When the value of the j-th feature plane coordinate point in the feature point map is less than 150% of the preset entropy value, mark this feature plane coordinate point as a mineral resource point;

[0122] When the value of the j-th characteristic plane coordinate point in the characteristic point map is greater than or equal to 150% of the preset entropy value, mark the characteristic plane coordinate point as a geological activity alarm point.

[0123] It should be noted that the geological activity alarm point is also a mineral resource point in the actual environment. In this embodiment, safety is given priority, and it is named the geological activity alarm point.

[0124] At the hardware level, for the functional implementation of the geological detection data intelligent processing method in a computer, the present application also provides a computer-readable storage medium. Please refer to Figure 5 as shown, which is set in an electronic device. The electronic device includes:

[0125] A processor 1, a memory 2, a communication interface 3, and a bus 4; wherein, data transmission is carried out between the processor 1 and the memory 2, and between the memory 2 and the communication interface 3 through the bus 4; the processor is used to process data in the memory and generate commands, the memory is used for data storage, the communication interface is used to receive and send data, and the bus is used to realize data transmission between the processor, the memory, and the communication interface.

[0126] In this embodiment, the geological detection data intelligent processing method can be implemented as a runnable computer program. When the computer program is loaded into the processor and when the computer program is loaded into the memory and handed over to the processor for processing through the bus, one or more steps of the geological detection data intelligent processing method can be executed.

[0127] Optionally, the processor in this embodiment can access the computer program through hardware burning or other means to complete the data execution process of the geological detection data intelligent processing method.

[0128] Please refer to Figure 6 as shown, which is a schematic structural diagram of a geological detection data intelligent processing device provided in this embodiment, including:

[0129] A data acquisition module, which is used for: real-time acquisition of geological vibration data and hydrothermal vent parameters of the target area, and also acquisition of sediment physical property data;

[0130] A data correction module, which is used for: obtaining the underwater pressure and the actual detection water depth during the acquisition of geological vibration data, and constructing a pressure compensation model and a temperature correction model, and then correcting the geological vibration data based on the pressure compensation model and the temperature correction model;

[0131] A feature extraction module, configured to: construct a first feature surface of a target area based on the corrected geological vibration data, and then combine hydrothermal vent parameters and sediment physical property data to construct a second eigenvalue of the target area, and use the second eigenvalue to enhance the features of the first feature surface, and then generate the geological structure features of the target area;

[0132] A geological update module, configured to: obtain the regional physical parameters of the target area, and construct a third-dimensional feature of the geological structure features of the target area based on the obtained results and hydrothermal vent parameters to update the geological structure features of the target area;

[0133] An alarm model construction module, configured to: construct an alarm model based on the geological structure features of the target area and output an alarm result.

[0134] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A method for intelligent processing of geological exploration data, characterized in that: include: Based on the corrected geological vibration data, a first characteristic surface of the target area is constructed, and then a second characteristic value of the target area is constructed by combining the hydrothermal vent parameters and the sediment physical property data, and the first characteristic surface is enhanced by the second characteristic value, so as to generate the geological structure characteristics of the target area; Acquire regional physical parameters of the target area, and construct a third dimension feature of the geological structure characteristics of the target area based on the acquisition results and the hydrothermal vent parameters to update the geological structure characteristics of the target area; Construct an alarm model based on the geological structure characteristics of the target area and output the alarm results; The implementation process of establishing the first characteristic surface of the target area is: Construct the vibration spectrum entropy H(x,y) of each plane coordinate point in the seabed topographic map of the target area, and set ; In the formula, p[fi(x,y)] represents the power spectrum density of the i-th frequency at the point with coordinates (x,y) in the target area, and fi(x,y) represents the frequency value of the i-th frequency; Combining the vibration spectrum entropy of each plane coordinate point in the seabed topography of the target area into the first characteristic surface of the target area; The hydrothermal activity index I is constructed based on the temperature gradient △T of the hydrothermal vent, the fluid flow rate and hydrogen sulfide concentration in the target area. ; Where v is the fluid velocity in the target area, and ρ(H2S) is the hydrogen sulfide concentration; The sedimentation state index G is constructed based on the surface porosity φ, surface sand density ρ and shear wave velocity Vs of the target area. ; In the formula, k1 is the flow velocity weight, k2 is the soil density weight, k3 is the wave velocity weight, φmax, ρmax, and Vsmax are the maximum surface porosity, the maximum surface sand density, and the maximum shear wave velocity, respectively; The value of [0.4×I / 100+G×0.6] is taken as the second eigenvalue of the target area.

2. The method for intelligent processing of geological exploration data according to claim 1, characterized in that: The result of multiplying the second eigenvalue by the vibration spectrum entropy of each plane coordinate point in the first characteristic surface is used as the first characteristic surface after feature enhancement; A feature point map having a value greater than a preset entropy value is extracted from the first feature surface after feature enhancement, and the feature point map is used as the geological structure feature of the target area; the feature point map includes a plurality of feature plane coordinate points.

3. The method for intelligent processing of geological exploration data according to claim 2, characterized in that: Obtaining regional physical parameters of the target area; A generation process of constructing a third dimensional feature based on the acquired regional physical parameters and calorific value nozzle parameters of the target area, and updating the geological structure features of the target area according to the third dimensional feature; When c1×μr+c2×σ is less than or equal to I / 100, the third dimension feature is not constructed; when c1×μr+c2×σ is greater than I / 100, c1×μr+c2×σ is set as the third dimension feature; When there is a third dimensional feature, the sum of the third dimensional feature and the second eigenvalue is used as the updated second eigenvalue, and the generation process of the geological structure feature of the target area is updated based on the updated second eigenvalue; Among them, μr is the relative magnetic permeability of the target area, σ is the relative electrical conductivity of the geology and seawater in the target area, c1 is the magnetic field weight, c2 is the conductivity weight, and c1+c2=1.

4. The method for intelligent processing of geological exploration data according to claim 3, characterized in that: Constructing the complexity of each plane coordinate point of the target area, and integrating the complexity of each plane coordinate point to obtain the geological complexity state of the target area, and then iterating the updating process of the geological structure characteristics of the target area; The complexity mean of each plane coordinate point is calculated, and the complexity mean of each plane coordinate point is used as the terrain state index γ of the target area. The geological complexity state of the target area is judged by setting the terrain complexity threshold Y: if γ is less than or equal to Y, the update process of the geological structure characteristics of the target area is not iterated; if γ is greater than Y, the terrain state index γ is used as the fourth dimension feature to iterate the third dimension feature. The iterative process is as follows: When c1×μr+c2×σ is greater than I / 100×η, [c1×μr+c2×σ] / γ is set as a highly active third dimension feature; When c1×μr+c2×σ is less than or equal to I / 100×η and c1×μr+c2×σ is greater than I / 100, [c1×μr+c2×σ] is set as a low-activity third dimension feature; Wherein, η is the preset offset ratio.

5. The method for intelligent processing of geological exploration data according to claim 4, characterized in that: The process of building an alarm model is as follows: When the value of the j-th feature plane coordinate point in the feature point map is less than 150% of the preset entropy value, the feature plane coordinate point is marked as a mineral resource point; When the value of the j-th characteristic plane coordinate point in the characteristic point map is greater than or equal to 150% of the preset entropy value, the characteristic plane coordinate point is marked as a geologically active alarm point.

6. The method for intelligent processing of geological exploration data according to claim 5, characterized in that: Also includes: Real-time collection of geological vibration data and hydrothermal vent parameters in the target area, as well as sediment physical property data; Obtain the underwater pressure and actual detection water depth during geological vibration data collection, and construct a pressure compensation model and a temperature correction model, and then correct the geological vibration data based on the pressure compensation model and the temperature correction model; The nonlinear attenuation coefficient α is set according to the underwater pressure and water density, and then the compensation range is set according to the actual detected water depth. When the nonlinear attenuation coefficient α meets the set compensation range, the nonlinear attenuation coefficient α is used as the compensation coefficient of the pressure compensation model; The signal drift correction coefficient β is set based on the real-time collected hydrothermal vent parameters, and the signal drift correction coefficient β is used as the output result of the temperature correction model; The process of setting the signal drift correction coefficient β is the temperature correction model; The geological vibration data is corrected in real time based on the pressure compensation model and the temperature correction model; the above-mentioned real-time correction process of the geological vibration data includes the correction of the amplitude of the low-frequency seismic wave, the correction of the recording delay, and the correction of the amplitude attenuation rate.

7. A geological exploration data intelligent processing device, characterized in that: include: Data acquisition module, used to: collect geological vibration data and hydrothermal vent parameters of the target area in real time, and also collect sediment physical property data; The data correction module is used to obtain the underwater pressure and the actual detection water depth during the geological vibration data collection, and to construct a pressure compensation model and a temperature correction model, and then to correct the geological vibration data based on the pressure compensation model and the temperature correction model; A feature extraction module is used to: construct a first characteristic surface of the target area based on the corrected geological vibration data, and then construct a second characteristic value of the target area in combination with the hydrothermal vent parameters and the sediment physical property data, and enhance the first characteristic surface with the second characteristic value, so as to generate the geological structure characteristics of the target area; A geological update module, used to: obtain regional physical parameters of the target area, and construct a third dimension feature of the geological structure characteristics of the target area based on the obtained results and the hydrothermal vent parameters to update the geological structure characteristics of the target area; The alarm model building module is used to: build an alarm model based on the geological structure characteristics of the target area and output the alarm result; The realization process of establishing the first characteristic surface of the target area is as follows: construct the vibration spectrum entropy H(x,y) of each plane coordinate point in the seabed topography of the target area, set ; In the formula, p[fi(x,y)] represents the power spectrum density of the i-th frequency at the point with coordinates (x,y) in the target area, and fi(x,y) represents the frequency value of the i-th frequency; Combining the vibration spectrum entropy of each plane coordinate point in the seabed topography of the target area into the first characteristic surface of the target area; The hydrothermal activity index I is constructed based on the temperature gradient △T of the hydrothermal vent, the fluid flow rate and hydrogen sulfide concentration in the target area. ; Where v is the fluid velocity in the target area, and ρ(H2S) is the hydrogen sulfide concentration; The sedimentation state index G is constructed based on the surface porosity φ, surface sand density ρ and shear wave velocity Vs of the target area. ; In the formula, k1 is the flow velocity weight, k2 is the soil density weight, k3 is the wave velocity weight, φmax, ρmax, and Vsmax are the maximum surface porosity, the maximum surface sand density, and the maximum shear wave velocity, respectively; The value of [0.4×I / 100+G×0.6] is taken as the second eigenvalue of the target area.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is used to control the electronic device where the computer-readable storage medium is located to execute the intelligent processing method for geological exploration data according to any one of claims 1 to 6 during operation.

Images