CN117173428B - Geological intelligent cataloging method of rock core - Google Patents
Geological intelligent cataloging method of rock core Download PDFInfo
- Publication number
- CN117173428B CN117173428B CN202311443653.2A CN202311443653A CN117173428B CN 117173428 B CN117173428 B CN 117173428B CN 202311443653 A CN202311443653 A CN 202311443653A CN 117173428 B CN117173428 B CN 117173428B
- Authority
- CN
- China
- Prior art keywords
- core
- hyperspectral
- image
- box
- rock
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000011435 rock Substances 0.000 title claims abstract description 41
- 238000002310 reflectometry Methods 0.000 claims abstract description 32
- 238000005192 partition Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 9
- 229910052500 inorganic mineral Inorganic materials 0.000 claims description 18
- 239000011707 mineral Substances 0.000 claims description 18
- 230000003595 spectral effect Effects 0.000 claims description 10
- 230000004075 alteration Effects 0.000 abstract description 3
- 230000033558 biomineral tissue development Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 11
- 238000001228 spectrum Methods 0.000 description 11
- 238000013507 mapping Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000008602 contraction Effects 0.000 description 3
- 230000004308 accommodation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009411 base construction Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 125000006850 spacer group Chemical group 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application relates to the technical field of geological information cataloging, in particular to an intelligent geological cataloging method of a rock core, which comprises the following steps: processing the hyperspectral image of the core to obtain a hyperspectral reflectivity image; identifying each core box and each partition plate in the hyperspectral reflectivity image; determining the splicing sequence of core columns in each core box based on the identification results of each core box and each partition plate; performing image stitching on the core column according to the stitching sequence to obtain a core reconstruction hyperspectral reflectance image, and converting a coordinate system of the core reconstruction hyperspectral reflectance image into an actual depth coordinate system of the core; and based on the hyperspectral reflectance images of the core column, carrying out information identification on the reconstructed hyperspectral reflectance images of the core under the actual depth coordinate system of the core, thereby forming the intelligent catalogue method of the core geology. According to the method and the device, the coordinate system of the rock core image is converted into the actual depth coordinate system of the rock core, so that mineralization information of the rock core alteration horizon and the corresponding depth can be displayed more intuitively.
Description
Technical Field
The application relates to the technical field of geological information cataloging, in particular to an intelligent geological cataloging method of a rock core.
Background
Cores are cylindrical rock samples taken from the bore using core ring bits and other coring tools, as desired for geological work or engineering. Core is an important physical material for researching and knowing underground geology and mineral conditions. Therefore, the geological logging of the drill core is very important.
In the conventional geological logging of the drilling site, the core is sampled manually, and based on the surface information of the core, the geological elements are visually identified by using tools such as a magnifying glass and the like to be recorded on paper media such as field geological records. The method has the defects of poor precision, low efficiency and the like.
Disclosure of Invention
In view of the above, the present application has been made to provide a method that overcomes or at least partially solves the above-mentioned problems.
The application provides an intelligent geological logging method of a rock core, which comprises the following steps of: processing the hyperspectral image of the core to obtain a hyperspectral reflectance image of the core; identifying each core box and each partition plate in the core hyperspectral reflectivity image; determining the splicing sequence of core columns in each core box based on the identification results of the core box and the partition plate; performing image stitching on the core column according to the stitching sequence to obtain a core reconstruction hyperspectral reflectance image, and converting a coordinate system of the core reconstruction hyperspectral reflectance image into an actual depth coordinate system of the core; based on the hyperspectral reflectance images of the core, the reconstructed hyperspectral reflectance images of the core converted into the actual depth coordinate system of the core are subjected to information identification, so that the core is intelligently recorded.
According to the geological intelligent cataloging method provided by the application, geological information is obtained by utilizing the hyperspectral image of the rock core, and the geological intelligent cataloging method has the advantages of being high in accuracy and efficiency. According to the method and the device, the coordinate system of the rock core image is converted into the actual depth coordinate system of the rock core, and mineralization information of the rock core alteration horizon and the corresponding depth can be displayed more intuitively.
Drawings
FIG. 1 is a flow chart of a method for intelligent cataloging of geology of a core according to an embodiment of the present application;
FIG. 2 is a schematic illustration of core box placement;
fig. 3 is a schematic diagram of core logging.
Reference numerals:
10. a core box; 101. a frame; 102. a partition plate; 11. a first gap; 12. a core column; 13. and a second gap.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. It will be apparent that the described embodiments are one embodiment of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without the benefit of the present disclosure, are intended to be within the scope of the present application based on the described embodiments.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which this application belongs. If, throughout, reference is made to "first," "second," etc., the description of "first," "second," etc., is used merely for distinguishing between similar objects and not for understanding as indicating or implying a relative importance, order, or implicitly indicating the number of technical features indicated, it being understood that the data of "first," "second," etc., may be interchanged where appropriate. If "and/or" is present throughout, it is meant to include three side-by-side schemes, for example, "A and/or B" including the A scheme, or the B scheme, or the scheme where A and B are satisfied simultaneously.
In the related art, hyperspectral imaging technology is utilized to collect and measure hyperspectral images of the core in the wavelength range of 350 nm-2500 nm. By calculating and identifying the different minerals based on the spectral diagnostic features of the hyperspectral image, mineralogical information is ultimately formed. The inventor of the application finds that in the related technology, when geological logging is performed on a core, information of the core corresponding to an underground real position is not logged, so that when geological information of the core is researched, the underground depth of a certain position of the core can be estimated only through the repeated time in the logged information and the rotation hole range, and the estimation is not accurate enough and cannot be intuitively embodied in the logged information.
Aiming at the technical problems, the embodiment of the application provides a geological intelligent cataloging method of a rock core. Referring to fig. 1, the geological intelligent logging method of the core according to the embodiment of the present application includes steps S100 to S600.
S100: and processing the hyperspectral image of the core to obtain a hyperspectral reflectance image of the core.
S200: and identifying each core box and each baffle plate in the core hyperspectral reflectivity image.
S300: and determining the splicing sequence of the core columns in the core box based on the identification results of the core box and the partition plate.
S400: and (3) performing image stitching on the core column according to the stitching sequence to obtain a core reconstruction hyperspectral reflectivity image.
S500: and converting the coordinate system of the reconstructed hyperspectral reflectance image of the core into an actual depth coordinate system of the core.
S600: based on the hyperspectral reflectance image of the core, the information identification is carried out on the reconstructed hyperspectral reflectance image of the core converted into the actual depth coordinate system of the core, so that the geological intelligent catalogue of the core is realized.
According to the geological intelligent cataloging method, the core high-spectral reflectance image is obtained through utilizing the core high-spectral reflectance image, and the geological intelligent cataloging method has the advantages of being high in accuracy and efficiency. According to the embodiment of the application, the coordinate system of the rock core image is converted into the actual depth coordinate system of the rock core, so that the rock core is rebuilt, and mineralization information of the rock core alteration horizon and the corresponding depth can be displayed more intuitively. According to the method provided by the embodiment of the application, the user can directly acquire the related information of the rock core corresponding to the real underground position.
In some embodiments, in step S100, the step of processing the hyperspectral image of the core may include: and carrying out radiation correction and spectrum reconstruction on the hyperspectral image of the core to obtain a hyperspectral reflectance image of the core. The radiation correction can be implemented by a module of the Hyspex imaging spectrometer, and the spectrum reconstruction can be implemented by a method commonly used in the field.
In step S200, each core box and separator in the core hyperspectral reflectance image is identified based on the established core box priori knowledge base. The core box priori knowledge base may be established by: and collecting the existing multiple core box spectrums as priori knowledge samples, forming a priori knowledge base, comparing the priori knowledge samples with the core hyperspectral reflectivity images, determining pixels similar to spectrums corresponding to the core boxes (or partition boards) from the core hyperspectral reflectivity images, and calibrating the pixels as the core boxes (or partition boards), so that the core boxes and the partition boards in the core hyperspectral reflectivity images are identified.
Referring to fig. 2, the core box 10 may include a frame 101. The frame 101 defines an upwardly open receiving cavity, and a bulkhead 102 is disposed within the receiving cavity to divide the receiving cavity into a plurality of core receiving slots, each core receiving slot having a length of core column 12 disposed therein.
It is readily understood that the identification of core box 10 and bulkhead 102 includes the identification of frame 101 and bulkhead 102. Since the frame 101 and the partition 102 are different in material, the spectra in the hyperspectral images corresponding to the two are different, and it is necessary to perform spectral recognition on the frame 101 and the partition 102, respectively.
The image recognition of the core box 10 can be performed by software using corresponding a priori knowledge samples. If the accuracy of the core box 10 identified in step S200 is not sufficient (e.g., because the material of the core box 10 is a new material or other reasons), the core box 10 may be separately subjected to hyperspectral scanning to obtain a corresponding hyperspectral image thereof, and the core box 10 in the hyperspectral image of the core is identified by using the hyperspectral image of the core box 10. The obtained hyperspectral image of the core box 10 can be used for obtaining and expanding samples of the core box priori knowledge base, so that priori knowledge samples of the core box priori knowledge base are continuously increased, and accuracy of identifying the core box 10 by using the core box priori knowledge base is improved.
In step S300, the core box 10 corresponds to the back-order information of the core drilling (it is easy to understand that the back-order information corresponds to the order in which the cores are produced). After each core box 10 in the hyperspectral reflectivity image is identified, the secondary information corresponding to each core box 10 and each core accommodating groove of each core box 10 can be obtained. The splicing order of the core columns 12 in each core box 10 can be determined according to the round information.
In step S400, the cores are sequentially spliced based on the core identification result, so as to form a core reconstructed hyperspectral reflectance image which is composed of core hyperspectral reflectance image data and is consistent with the underground core arrangement. Typically, when acquiring hyperspectral images of a core, the nomenclature of the data corresponding to the hyperspectral images includes the depth range of the core. For example, for cores with a core acquisition depth of 50-80 meters, the data file corresponding to the hyperspectral image may be named 50-80.Bat. When data is imported into the computer for geological logging, the computer can acquire the acquisition depth of the core through the file name, and automatic processing of the data is achieved. For example, after a file with a file name of 50-80.Bat is imported into a computer, the computer can automatically acquire a core with a collection depth of 50-80 meters. The coordinate system of the newly formed core reconstruction hyperspectral reflectance image can be converted into the actual depth coordinate system of the core based on the naming of the data corresponding to the hyperspectral image, and the reconstruction process of the underground core is completed according to the splicing sequence of the core columns in each core box.
In some embodiments, in step S500, the converting the coordinate system of the core reconstructed hyperspectral reflectance image into the actual depth coordinate system of the core specifically includes the following steps: acquiring the ordinate of each pixel of the core reconstructed hyperspectral reflectivity image; acquiring the number of pixels in the longitudinal direction of the core reconstructed hyperspectral reflectivity image; and determining the depth corresponding to each pixel based on the depth range corresponding to the core, so as to convert the ordinate of each pixel into a corresponding depth value.
For example, 10000 pixels a1, a2, … … and a10000 exist in the longitudinal direction of the core reconstruction hyperspectral reflectance image, the ordinate of the pixels a1, a2, … … and z10000 are respectively z1, z2, … … and z10000, the corresponding depth range of the core is 50-80 meters, the distance between two adjacent longitudinal pixels is 0.003 meter, the ordinate z1 and z10000 of the pixels a1 and a10000 at two longitudinal ends respectively correspond to 50 meters and 80 meters, and the ordinate z can be converted into a depth value corresponding to the longitudinal position of the ordinate z of the pixel according to the longitudinal position of the ordinate z of the pixel.
In some embodiments, the geological intelligent cataloging method may further comprise the steps of: based on the identification results of the core box and the partition plate, cutting the reconstructed hyperspectral reflectivity image of the core so as to delete the invalid area of the core column. Cutting the core reconstruction hyperspectral reflectance image, and removing an invalid region of the core reconstruction hyperspectral reflectance image to obtain the core reconstruction hyperspectral reflectance image only containing a core part, so that the data processing amount is reduced, and the interference caused by invalid data in the data processing is avoided.
The external invalid region scanned in the scanning process can be removed, so that the 'tightening' of the space range is realized; further, invalid regions in the spectrum may be removed, achieving "tightening" of the spectral range. Through the space contraction process, the removal of a large-range invalid region outside the core box can be realized, and the subsequent unnecessary spectrum calculation is avoided; through the spectrum contraction process, spectrum bands (such as invalid values corresponding to data of some wavelength bands) which do not need parameter calculation can be removed, and through the 2 processes, effectiveness judgment of the core can be achieved, and images of the effective bands can be formed by cutting.
In some embodiments, the step of cropping the core reconstructed hyperspectral reflectance image may comprise: performing partition plate and core box pixel identification on the reconstructed hyperspectral reflectivity image of the core according to the spectral characteristics of the partition plate 102 and the core box 10; and dividing the effective area of the reconstructed hyperspectral reflectance image of the core according to the abscissa of the partition plate and the pixels of the core box and the number of core columns in the core box, so that the aim of cutting the reconstructed hyperspectral reflectance image of the core is fulfilled.
Cutting the reconstructed hyperspectral reflectance image of the core comprises cutting an area between two adjacent core boxes. In some embodiments, cropping the core reconstructed hyperspectral reflectance image includes cropping the region between the core box 10 and the core column 12 stored in the core box 10.
As shown in fig. 2, the frame 101 includes two first plates parallel to the partition 102, and two second plates perpendicular to the partition 102. For the two core accommodation grooves located at the outermost side, the area between the core box 10 and the core column 12 stored in the core box 10 comprises a gap between the partition plate 102 and the core column 12 and a gap between the first plate body of the frame 101 and the core column 12; for other core-receiving slots, the region between the core box 10 and the core column 12 stored in the core box 10 includes a gap between two spacers 102 and the core column 12, respectively.
The core box 10 and the second gap 13 of the core box 10, and the partition plate 102 and the first gap 11 of the core column 12 can also be cut and removed.
In the imaging process, the periphery of the effective core is provided with a larger black area, the pixels are analyzed by pixels, the values are not 0, but some smaller values, calculation is not needed to be participated in subsequent data processing and analysis, and therefore, the outer area needs to be removed in the step, the principle of the process is that the image is approximated from the periphery to the middle, and the function can be completed by adopting a smaller threshold value, namely the process of 'spatial contraction' corresponding to the previous process.
In some embodiments, prior to cropping the core reconstructed hyperspectral image effective area, rotating the core column 12 to be parallel to the extending direction of the core box 10 and the bulkhead 102 is further included. In some embodiments, before the image is cut, it is further required to determine whether each core column 12 in the core box 10 is placed in a standard, that is, whether the axial direction of the core column 12 is parallel to the extending direction of the bulkhead 102. The two most protruding points at the two axial ends of the core column 12 can be connected, whether the connecting line is parallel to the vertical base line of the image or not can be judged, and whether the axial direction of the core column 12 is parallel to the extending direction of the partition plate 102 or not can be further judged. If it is determined that the connecting line is not parallel to the vertical base line of the image, the image area corresponding to the core column 12 is rotated to a position where the connecting line is parallel to the vertical base line of the image, that is, a position where the axial direction of the core column 12 is parallel to the extending direction of the partition 102. The image area may be an area (corresponding to an image area corresponding to each core accommodation groove) defined by the partition 102 and the frame 101 together.
In some embodiments, in step 600, based on the hyperspectral reflectance image of the core, the step of identifying information about the reconstructed hyperspectral reflectance image of the core converted into the actual depth coordinate system of the core may include: and identifying geological information, mineral information, lithology information and the like of the core based on the hyperspectral reflectivity image of the core. In such an embodiment, the identified geological information, mineral information, lithology information and the like can be added to the reconstructed hyperspectral reflectance image of the core converted into the actual depth coordinate system of the core, so that the geological information, mineral information, lithology information and the like are associated with the depth of the core, and a user can intuitively acquire the geological information, mineral information, lithology information and the like of different depths of the core, thereby being more beneficial to researching the core.
The intelligent geological catalog can be developed through the processes of automatic mapping by an algorithm tool, intelligent mapping prototype system construction, regional geological investigation lithology mapping application demonstration and the like, and through the data fusion, knowledge fusion and algorithm application of the acquired hyperspectral data and lithology knowledge base. And finally, adding affine transformation information of the new image into the rock core converted into the rock core actual depth coordinate system to reconstruct the hyperspectral reflectivity image, and then irradiating corresponding geological information.
In some embodiments, based on the hyperspectral reflectance image of the core, the step of identifying mineral information of the core may include: and carrying out similarity matching on the spectral characteristics of the image pixels of the hyperspectral reflectivity of the rock core based on the mineral priori knowledge base, thereby obtaining mineral information.
And a spectral angle method or other knowledge matching algorithm can be adopted to carry out similarity matching on the spectral characteristics of the image pixels with the hyperspectral reflectivity of the rock core.
In some embodiments, the step of identifying lithology information of the core based on the hyperspectral reflectance images of the core may include: identifying core geological elements of the core based on the core hyperspectral reflectivity image; and carrying out intelligent core geological record according to the core geological elements and the mineral information.
In some embodiments, the core geological elements may include color and granularity. Corresponding models can be established on the basis of past experience, and a relation mapping of rock core colors and granularity and lithology is established, so that lithology information of the rock core is determined according to the color and granularity of the rock core and mineral information.
The step of identifying the color and granularity of the core may include: performing color identification based on R, G, B three primary color values of the image pixels of the hyperspectral reflectivity of the core; and carrying out granularity identification based on gray values of pixels around the image pixels of the hyperspectral reflectivity image of the core.
The step of performing color identification based on R, G, B three primary color values of the image pixels of the hyperspectral reflectance of the core can comprise: and (5) resampling the images of the three wavebands of R, G, B based on the hyperspectral image of the visible light waveband, and comparing the image with a standard colorimetric card according to the value of R, G, B to identify the color of a single pixel.
The step of performing granularity identification based on gray values of pixels around the image pixels of the hyperspectral reflectivity image of the core can comprise the following steps: according to the hyperspectral image in the visible light wave band, edge detection is carried out by utilizing an edge detection operator, a rock mass model is constructed according to the gray level co-occurrence matrix, and granularity identification of a single pixel is carried out.
In some embodiments, the step of determining lithology information of the core may include: and carrying out lithology recognition on the reconstructed hyperspectral reflectance image of the core based on the hyperspectral lithology knowledge base, and confirming lithology information of the core.
Referring to fig. 3, the hyperspectral lithology knowledge base can be constructed through four links of sample acquisition, feature design, sample base construction and knowledge base construction, corresponding samples are managed, and the hyperspectral lithology knowledge base is applied to subsequent calculation. A multi-element multi-dimensional open sample library construction method facing a sample characteristic calculation unit is established, and a multi-element multi-dimensional open hyperspectral lithology sample library is established by researching and developing a sample information automatic extraction technology and combining existing rock mineral spectrum data, rock core hyperspectral scanning data and the like. And then carrying out spectrum matching through certain algorithms, and extracting mineral information.
Based on a hyperspectral lithology sample library and a knowledge expression method, a self-adaptive knowledge learning and reasoning lithology recognition algorithm is developed, geological elements, spectral features and other information are extracted through global sample feature extraction, spatial relationship feature analysis and the like, lithology recognition marks, sample classification rules, lithology classification knowledge patterns and other processes are established, a lithology recognition knowledge library is constructed, a knowledge library service interface is developed, and knowledge services such as mapping marks and the like are provided for hyperspectral lithology mapping.
For the hyperspectral lithology sample library, a convolutional neural network based on an object is designed, the object is taken as a basic unit, and the convolutional neural network is used for analyzing and marking lithology categories of the object. Meanwhile, the introduction of the knowledge base provides rich initial attributes for the object, and the constructed joint model can realize higher lithology recognition accuracy than the single time-space domain attribute. In the agent model analysis part, different lithology distribution modes are automatically separated from a convolution layer of the convolution neural network through an unsupervised method, and an interpretation graph is constructed to reveal a knowledge hierarchy structure inside the convolution neural network. The contribution degree of lithology time-space domain mode to the prediction result can be determined through agent model analysis, and knowledge learned by a huge neural network model is extracted into an interpretable model through a knowledge distillation method. Finally, the physical mechanism of the interpretable model is interpreted, and the knowledge base is updated iteratively.
It should also be noted that, in the embodiments of the present invention, the features of the embodiments of the present invention and the features of the embodiments of the present invention may be combined with each other to obtain new embodiments without conflict. The present invention is not limited to the above embodiments, but the scope of the invention is defined by the claims.
Claims (3)
1. A geological intelligent cataloging method of a rock core comprises the following steps:
processing the hyperspectral image of the core to obtain a hyperspectral reflectance image of the core;
identifying each core box and each partition plate in the core hyperspectral reflectivity image;
determining the splicing sequence of core columns in the core box based on the identification results of the core box and the partition plate;
performing image stitching on the core column according to the stitching sequence to obtain a core reconstruction hyperspectral reflectivity image;
converting the coordinate system of the core reconstructed hyperspectral reflectance image into an actual depth coordinate system of the core;
based on the hyperspectral reflectance image of the core, carrying out information identification on the reconstructed hyperspectral reflectance image of the core converted into the actual depth coordinate system of the core;
the step of identifying each core box and each partition plate in the core hyperspectral reflectivity image comprises the following steps: identifying each core box and each partition plate in the core hyperspectral reflectivity image based on the established core box priori knowledge base;
the method further comprises the steps of: cutting the reconstructed hyperspectral reflectivity image of the rock core based on the identification results of the rock core box and the partition plate so as to delete the invalid region of the rock core column;
cutting the core reconstructed hyperspectral reflectance image comprises the following steps:
performing partition plate and core box pixel identification on the reconstructed hyperspectral reflectance image of the core according to the spectral characteristics of the partition plate and the core box;
dividing the effective area of the reconstructed hyperspectral reflectance image of the rock core according to the abscissa of the partition plate and the pixels of the rock core box and the number of rock core columns in the rock core box;
before cutting the effective area of the reconstructed hyperspectral reflectance image of the rock core, the method further comprises the step of rotating the rock core column to be parallel to the extending direction of the rock core box and the partition plate;
based on the hyperspectral reflectance image of the core, the information identification of the reconstructed hyperspectral reflectance image of the core converted into the actual depth coordinate system of the core comprises the following steps: identifying geological information, mineral information and lithology information of the core based on the hyperspectral reflectivity image of the core;
based on the hyperspectral reflectance image of the core, identifying mineral information of the core comprises: based on a mineral priori knowledge base, carrying out similarity matching on spectral characteristics of the image pixels of the hyperspectral reflectivity of the rock core, thereby obtaining mineral information;
identifying lithology information of the core based on the hyperspectral reflectance image of the core comprises: identifying core geological elements of the core based on the core hyperspectral reflectivity image; and carrying out intelligent cataloging on the core geology according to the core geology elements and the mineral information.
2. The method of claim 1, wherein said converting the coordinate system of the core reconstructed hyperspectral reflectance image to the core actual depth coordinate system comprises:
acquiring the ordinate of each pixel of the core reconstructed hyperspectral reflectivity image;
acquiring the number of pixels in the longitudinal direction of the core reconstructed hyperspectral reflectivity image;
and determining the depth corresponding to each pixel based on the depth range corresponding to the core, so as to convert the ordinate of each pixel into a corresponding depth value.
3. The method of claim 1, wherein the core geological elements comprise color and granularity;
the method further comprises the steps of:
performing color identification based on R, G, B three primary color values of the core hyperspectral reflectance image pixels;
and carrying out granularity identification based on gray values of pixels around the core hyperspectral reflectivity image pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311443653.2A CN117173428B (en) | 2023-11-01 | 2023-11-01 | Geological intelligent cataloging method of rock core |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311443653.2A CN117173428B (en) | 2023-11-01 | 2023-11-01 | Geological intelligent cataloging method of rock core |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117173428A CN117173428A (en) | 2023-12-05 |
| CN117173428B true CN117173428B (en) | 2024-01-30 |
Family
ID=88947136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311443653.2A Active CN117173428B (en) | 2023-11-01 | 2023-11-01 | Geological intelligent cataloging method of rock core |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117173428B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934915A (en) * | 2017-12-18 | 2019-06-25 | 核工业北京地质研究院 | A kind of deep altered mineral three-dimensional modeling method |
| WO2021008528A1 (en) * | 2019-07-15 | 2021-01-21 | 南京大学 | Method for accelerating hyperspectral video reconstruction, and apparatus therefor |
| CN115508303A (en) * | 2022-09-20 | 2022-12-23 | 核工业北京地质研究院 | Rock core box information shielding method in digital record |
| CN115761318A (en) * | 2022-11-09 | 2023-03-07 | 数岩科技股份有限公司 | Method and device for identifying texture layer and storage medium |
-
2023
- 2023-11-01 CN CN202311443653.2A patent/CN117173428B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934915A (en) * | 2017-12-18 | 2019-06-25 | 核工业北京地质研究院 | A kind of deep altered mineral three-dimensional modeling method |
| WO2021008528A1 (en) * | 2019-07-15 | 2021-01-21 | 南京大学 | Method for accelerating hyperspectral video reconstruction, and apparatus therefor |
| CN115508303A (en) * | 2022-09-20 | 2022-12-23 | 核工业北京地质研究院 | Rock core box information shielding method in digital record |
| CN115761318A (en) * | 2022-11-09 | 2023-03-07 | 数岩科技股份有限公司 | Method and device for identifying texture layer and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117173428A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111742329B (en) | Mining typical feature dynamic monitoring method and platform based on multi-source remote sensing data fusion and deep neural network | |
| Rossel et al. | A global spectral library to characterize the world's soil | |
| CN100547438C (en) | A kind of oil-gas exploration method and system | |
| US20200034966A1 (en) | Group sparsity model for image unmixing | |
| US7983885B2 (en) | Method and apparatus for multi-dimensional data analysis to identify rock heterogeneity | |
| CN109934915B (en) | Three-dimensional modeling method for deep alteration minerals | |
| CN107923240A (en) | Method for determining the porosity associated with the organic matter in well or stratum | |
| CN106682377B (en) | A kind of the EO-1 hyperion extraction and quantitative estimation method of drilling core altered mineral | |
| Chabrillat et al. | HYSOMA: An easy-to-use software interface for soil mapping applications of hyperspectral imagery | |
| CN114742272A (en) | Soil cadmium risk prediction method based on space-time interaction relation | |
| CN113436153A (en) | Method for predicting carbon components of undisturbed soil profile based on hyperspectral imaging and support vector machine technology | |
| CN111259771A (en) | High spatial resolution remote sensing image prospecting method based on image feature decomposition | |
| CN117173428B (en) | Geological intelligent cataloging method of rock core | |
| Kruse et al. | Improving multispectral mapping by spectral modeling with hyperspectral signatures | |
| doninck et al. | Multispectral canopy reflectance improves spatial distribution models of Amazonian understory species | |
| CN115330664A (en) | Image recognition-based surrounding rock weathering degree full-automatic recognition method and device | |
| Kokaly | Spectroscopic remote sensing for material identification, vegetation characterization, and mapping | |
| Jia | Classification techniques for hyperspectral remote sensing image data | |
| CN115346141A (en) | Method and system for identifying unfavorable geology through integration of sky, space, ground, tunnel and hole | |
| CN114549899A (en) | Reservoir classification method and device, electronic equipment and computer-readable storage medium | |
| CN114398351A (en) | Drill core hyperspectral logging method combining spectral similarity and spectral parameters | |
| CN114596490A (en) | Hilly land feature line extraction method and hilly land DEM (digital elevation model) fine production method | |
| US20210254457A1 (en) | Systems and Methods for Generating Continuous Grain Size Logs from Petrographic Thin Section Images | |
| Kruse et al. | Expert system for geologic mapping with imaging spectrometers | |
| CN117423013B (en) | Ore potential prediction method based on geological big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |