CN117456118A - Ore finding method based on k-meas method and three-dimensional modeling - Google Patents
Ore finding method based on k-meas method and three-dimensional modeling Download PDFInfo
- Publication number
- CN117456118A CN117456118A CN202311364984.7A CN202311364984A CN117456118A CN 117456118 A CN117456118 A CN 117456118A CN 202311364984 A CN202311364984 A CN 202311364984A CN 117456118 A CN117456118 A CN 117456118A
- Authority
- CN
- China
- Prior art keywords
- data
- modeling
- interpolation
- model
- dimensional
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 112
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 44
- 239000011707 mineral Substances 0.000 claims abstract description 44
- 238000005553 drilling Methods 0.000 claims abstract description 43
- 238000005065 mining Methods 0.000 claims abstract description 33
- 238000012216 screening Methods 0.000 claims abstract description 14
- 239000011435 rock Substances 0.000 claims description 72
- 230000006870 function Effects 0.000 claims description 55
- 238000005070 sampling Methods 0.000 claims description 28
- 239000000126 substance Substances 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000003556 assay Methods 0.000 claims description 12
- 230000008520 organization Effects 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000011835 investigation Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- -1 methyl ethyl propyl butyl Chemical group 0.000 claims description 6
- 238000012946 outsourcing Methods 0.000 claims description 6
- 230000000704 physical effect Effects 0.000 claims description 6
- 238000007639 printing Methods 0.000 claims description 6
- 238000003908 quality control method Methods 0.000 claims description 6
- 239000000523 sample Substances 0.000 claims description 6
- 239000007787 solid Substances 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007670 refining Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 239000002245 particle Substances 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 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
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Abstract
The invention discloses a mineral prospecting method based on a k-meas method and three-dimensional modeling, which comprises the following steps of; s1 survey, S2 screening and S3 modeling, wherein the survey steps are as follows, geological survey is carried out, 10-30 areas to be surveyed are selected, the area of each area is controlled to be 1-60 hectares, 3200-6400 points are randomly selected in each area to be drilled by using a 150-rig, and the drilling depth is controlled to be 150-450 meters. According to the invention, through the k-meas method, the mining areas at a plurality of positions are clustered, screened and clustered repeatedly, so that the data can be more accurate, the principle is simpler, the implementation is easy, the convergence speed is high, the clustering effect is better, the interpretability of the algorithm is stronger, and the parameter which mainly needs to be adjusted is only the cluster number k, thereby accelerating the mining speed and reducing the workload of staff.
Description
Technical Field
The invention relates to the technical field of mineral exploration, in particular to a mineral prospecting method based on a k-meas method and three-dimensional modeling.
Background
The mining is a behavior or process for searching mineral resources, and can be divided into two major links of mining deployment and mining methods. The mining deployment is the selection of mining areas and ore types, and comprises four stages of geological prospecting, mining area prospecting, deposit research and deposit evaluation; the method for searching the ore is characterized in that according to the ore-forming remote scenic spot defined by geological work, various geological means are adopted to investigate and research the ore-forming remote scenic spot by applying various geological theories, and the process of directly searching mineral resources is directly carried out. Meanwhile, the natural ecological environment is protected, and damage to the local natural environment caused by excessive mining is prevented.
The existing defects are as follows:
1. patent document US20040230467A9 discloses a method of passive mining usage information in a location-based service system, "a method and system for providing advertisement effectiveness search capabilities, predictive modeling capabilities, and using mining in a location-based service system. During operation of the location-based service system, usage information for advertising campaigns placed on the location-based service system is stored. Advertisers are provided with the ability to enter search request forms on remote terminals to mine usage information. Then, the search request is sent to an application program of the search use information to generate a response to the search request, but the existing mining method is complicated, and a worker is required to work for a long time in the field, so that the workload of the worker is increased;
2. patent document JP2005078606a discloses a light source position tracking device and a tailing method, "problems to be solved: a light source position tracking device and a tailing method are provided which are capable of moving any kind of light source tailing regardless of where they are disposed. The solution is as follows: the light source position tracking device includes an irradiation surface 2a, a motor, photosensors 5a to 5d, a developing section 6, a main sensor 7, and a controller. The light L from the light source is irradiated on the irradiation surface 2 a. The motor for the vertical/lateral movement tilts the irradiation surface about two axes X and Y forming a rectangular cross on the irradiation surface. The light sensors 5a to 5d output light and dark detection signals, are arranged at equal intervals around the irradiation surface, and are formed into spheres, so that light reception along the spheres is possible. The developing part 6 is arranged on a photosensor in the vicinity of the irradiation surface, and when the irradiation surface does not intersect the optical axis of the light source in a rectangular shape, a shadow b, which is a shadow of one of the photosensors, is formed. The controller controls the vertical/horizontal movement of the driving motor, and compares each detection signal from the photoelectric sensor with a comparison reference signal from the main sensor, but most of the existing mining methods are not accurate enough, so that repeated measurement and determination are needed when mining, the difficulty is high when workers find the mine, and the information needs to be updated in real time;
3. The patent document CN101819169B discloses a method for prospecting earth gas particles, which belongs to the field of geology, and relates to a method for prospecting earth gas particles by deep penetration in the earth. The method improves the test precision, enables the test object to reach the earth gas nanometer level single particles, analyzes the characteristics of mineral components, granularity, shape, ratio among various particles, aggregation and the like of the particles, chemical components (including main elements and microelements), content, structure and mineral formation type, and comprehensively surveys the hidden ore body ", but the existing three-dimensional model of the ore area is not corrected after being established, so that the model is easy to deviate from the actual field, and the accuracy of ore finding is affected;
4. the patent document CN110060173A discloses a deep gold deposit ore-forming and prospecting method, and the invention discloses a deep gold deposit ore-forming and prospecting method, which is characterized in that analysis results comprising indication types, index types, comprehensive characteristic types and the like are rapidly and comprehensively obtained according to actual detection and analysis data by introducing a hierarchical knowledge system, so that the utilization rate of the prior artificial research results is enhanced; meanwhile, when analysis and research of survey data are performed based on a hierarchical knowledge system module, a deep learning method is introduced, the requirements on correlation analysis of the survey data are reduced, and the efficiency of the survey analysis and the mine target area positioning is greatly improved.
Disclosure of Invention
The invention aims to provide a mineral prospecting method based on a k-meas method and three-dimensional modeling, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: a method for finding ore based on k-meas method and three-dimensional modeling comprises the following steps; s1, surveying, S2 screening and S3 modeling, wherein the surveying steps are as follows;
geological investigation, namely selecting 10-30 areas to be surveyed, controlling the area of the areas to be 1-60 hectares, randomly selecting 3200-6400 points in each area, drilling by using a 150 drilling machine, and controlling the drilling depth to be 150-450 meters;
rock sampling, detecting rock drilled out from different areas by using a spectrometer and an electronic probe, detecting chemical components, mineral content and rock physical properties of the rock, setting chemical components of a plurality of rocks as X1, X2 and X3., and setting mineral content of the rocks as C1, C2 and C3..
And (3) labeling, namely printing the position information, the components and the mineral content of the rock into labels and attaching the labels to the corresponding rock.
Preferably, the screening step is as follows;
the data sets are the rock composition X1, X2, X3. respectively, and the mineral content C1, C2, C3. of the rock The two data sets are respectively formed into two 5×5 matrices, thereby obtaining matrices of X and Y as followsThe data set X has a total of n pieces of data, each piece of data has M features, the data set Y has K pieces of data, each piece of data has M features, wherein ci= [ Ci1, ci2, ci 3..cim]，1≤i≤K；
Comparing the distances between each point, namely each piece of data, and K clustering centers, namely classifying the distances into the class with the nearest distance, and classifying the distances into the class randomly if the distances between a certain point and different clustering centers are equal, wherein the clustering centers are iterated, and the distance formula is as follows;
where xi= [ Xi1, xi2, xi 3..xim]；
The data points are classified into categories with the nearest distance by comparing the distances between the data points and each data center, the operations are repeated continuously, and K-type data can be obtained after all the data points are classified;
updating a cluster center, wherein the analysis result is { S1, S2, S3..and SK }, S1 represents a set of all data points of a first class, the cluster center of each class is updated, the cluster center is the average value of all objects in the class in each dimension, and an updating formula is that;
where |Si| represents the number of data points in the i-th class;
the criterion for the termination of the iteration is that the change of the cluster centers is very small, namely the sum of d1+d2+ … +dk is very small, and is smaller than a certain value, and di refers to the distance between the cluster centers before and after updating in the ith class or the number of iterations is reached.
Preferably, the clustering result is analyzed to find out the geological features and rules in each cluster. According to the clustering result, the ore bodies can be divided into different types, the ore body types are divided into four types of methyl ethyl propyl butyl, three subclasses are arranged in each major class, the ore bodies of different types are subdivided, and the ore bodies of different types are respectively modeled.
Preferably, the ore body modeling flow is as follows, a database is built, a solid model is built, the model is reconstructed, and the model is assigned.
Preferably, the drilling coordinates and depth are determined by utilizing the exploration information of the ore body, the exploration information in a digital form is managed and utilized by using a three-dimensional graph form through software, high-precision measurement is realized by using a three-dimensional scanning technology, two or three of three-dimensional modeling software GOCAD, surpac, XModel, DMine are used, and related information data of drilling positions and rocks are formed into a database and imported into the software to start modeling;
modeling, constraint data, interpolation data and modeling parameters, wherein the constraint data is constructed by various constraint rules, the model generates outsourcing, boundary and anisotropic trend, the interpolation data is composed of data directly used for calculating and generating the model, the modeling parameters comprise a plurality of geological rule parameters, and the specific steps of the modeling flow of the implicit modeling method with geometric boundary constraint directly based on drilling data are as follows;
Collecting data such as result data, mining area topography geologic map, exploration line profile map and the like related to a mineral area, arranging the data to meet the data organization requirements of mining area three-dimensional geologic modeling, establishing a geologic database under the support of three-dimensional modeling software, establishing an engineering coordinate table, a inclinometry data table, a lithology data table and an assay data table according to the mineral area engineering, sampling data and the like, inputting the data such as the engineering coordinate table, the inclinometry data table, the lithology data table and the assay data table into the three-dimensional modeling software according to the data organization requirements of the three-dimensional geologic modeling, generating a three-dimensional geologic model, correcting and optimizing the three-dimensional geologic model according to other related data such as industrial indexes, weight, faults, mine phase boundaries and the like, and finally forming the modeling result of the implicit modeling method meeting the requirements.
Preferably, the ore body implicit modeling method uses implicit functions meeting various geological rule constraints to represent an ore body model, converts geological data of corresponding types into various different interpolation constraints according to a certain sampling granularity in a discretization mode, obtains the implicit functions representing the ore body model by solving interpolation equations constructed by the interpolation constraints, and reconstructs the implicit functions representing the ore body model by using an equivalent surface extraction method, wherein the interpolation method comprises a radial basis function interpolation method, and a radial basis interpolation function s (x) has the following form;
Where x= { X1, X2, x3.., xn } is a set of distinct interpolation centers, ωi is a weight coefficient to be determined, Φ (xixj) is a radial basis kernel function, S Φ (X) is a kernel function part, p (X) is a polynomial part, let { p1, p2,., pq } be a set of bases in the corresponding polynomial space, the radial basis interpolation function S (X) is typically used for the interpolation domain constraint, S (xi) = pi, i=1, 2..n;
for the radial basis function interpolation method, constraints of potential field threshold values and potential field direction types are defined through interpolation constraints at any sampling positions, the Hermite radial basis function interpolation HRBF method can consider the situation that constraint point information contains function derivative values, in the HRBF interpolation method, weak off-plane constraints are replaced by strong normal constraints, ambiguous off-plane constraints are prevented from being locally generated, and therefore better geometric constraint features are achieved at places where the off-plane constraints are not easy to express.
Preferably, the model reconstruction is carried out, the contour line of the ore body is automatically or manually edited and modified, then the control on the shape of the ore body is realized by utilizing a method of encrypting the contour line in the middle, branch points are automatically added by calculating the shortest distance between the closed contour lines through projection, the automatic construction of the branches is realized by utilizing plane with holes to limit triangulation, the quality control is introduced aiming at the poor geometric quality of the initially constructed three-dimensional ore body surface model, the reconstruction of the surface model is realized, and the model quality and the subsequent calculation are ensured.
Preferably, corresponding numerical values of drilling sampling are corresponding to data of different rock layers in the model, the three-dimensional model of different ore bodies is optimized and refined, 1-3 ore areas are randomly extracted from each ore area grade for field exploration, and exploration results are recorded, so that the accuracy rate of prospecting is improved.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the k-meas method is used for clustering, screening and repeated clustering of mining areas at a plurality of positions, so that the data can be more accurate, the principle is simpler, the implementation is easy, the convergence speed is high, the clustering effect is better, the interpretability of the algorithm is stronger, and the parameter which mainly needs to be adjusted is only the cluster number k, thereby accelerating the mining speed and reducing the workload of staff;
2. according to the invention, the accuracy of prospecting can be greatly improved by using the k-meas method and the method for carrying out three-dimensional modeling on the mining area, so that the prospecting of the staff is more accurate, and the time of the staff in field work is reduced;
3. according to the invention, the three-dimensional map data are more accurate by reconstructing the three-dimensional model and then assigning the three-dimensional model, under the environment of three-dimensional geological modeling, from the design to modification of a scheme, from the input to confirmation of original data, from on-site investigation to experimental judgment, from judgment of technicians to comprehensive analysis of an expert system, the whole process implements a digital management mode, the accuracy of geological data is greatly improved, comprehensive engineering geological results are provided, and convenience is provided for further application and analysis of the geological data;
4. According to the invention, different screened mining areas are classified, so that the probability of mining at the position of the mining area with higher level is higher through a k-meas method, and the accuracy of mining is improved.
Drawings
FIG. 1 is an overall workflow diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific direction, be configured and operated in the specific direction, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "provided," "connected," and the like are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1 an example provided by the present invention: a method for finding ore based on k-meas method and three-dimensional modeling comprises the following steps; s1, surveying, S2 screening and S3 modeling, wherein the surveying steps are as follows;
geological investigation, namely 10 areas to be surveyed are selected, the area of each area is controlled to be 1 hectare, 3200 points are randomly selected in each area, a 150 drilling machine is used for drilling, and the drilling depth is controlled to be 150 meters;
rock sampling, detecting rock drilled out from different areas by using a spectrometer and an electronic probe, detecting chemical components, mineral content and rock physical properties of the rock, setting chemical components of a plurality of rocks as X1, X2 and X3., and setting mineral content of the rocks as C1, C2 and C3..
And (3) labeling, namely printing the position information, the components and the mineral content of the rock into labels and attaching the labels to the corresponding rock.
The screening steps are as follows;
the data sets were the rock composition X1, X2, X3. respectively, and the rock mineral content C1, C2, C3. respectively, the two data sets were each formed into two 5X 5 matrices, resulting in the matrices X and Y as followsThe data set X has a total of n pieces of data, each piece of data has M features, the data set Y has K pieces of data, each piece of data has M features, wherein ci= [ Ci1, ci2, ci 3..cim]，1≤i≤K；
Comparing the distances between each point, namely each piece of data, and K clustering centers, namely classifying the distances into the class with the nearest distance, and classifying the distances into the class randomly if the distances between a certain point and different clustering centers are equal, wherein the clustering centers are iterated, and the distance formula is as follows;
where xi= [ Xi1, xi2, xi 3..xim]；
The data points are classified into categories with the nearest distance by comparing the distances between the data points and each data center, the operations are repeated continuously, and K-type data can be obtained after all the data points are classified;
updating a cluster center, wherein the analysis result is { S1, S2, S3..and SK }, S1 represents a set of all data points of a first class, the cluster center of each class is updated, the cluster center is the average value of all objects in the class in each dimension, and an updating formula is that;
Where |Si| represents the number of data points in the i-th class;
the criterion for the termination of the iteration is that the change of the cluster centers is very small, namely the sum of d1+d2+ … +dk is very small, and is smaller than a certain value, and di refers to the distance between the cluster centers before and after updating in the ith class or the number of iterations is reached.
And analyzing the clustering result to find out the geological features and rules in each cluster. According to the clustering result, the ore bodies can be divided into different types, the ore body types are divided into four types of methyl ethyl propyl butyl, three subclasses are arranged in each major class, the ore bodies of different types are subdivided, and the ore bodies of different types are respectively modeled.
The ore body modeling flow is as follows, a database is built, a solid model is built, the model is reconstructed, and assignment is carried out on the model.
Determining drilling coordinates and depth by utilizing exploration information of a ore body, managing and utilizing the exploration information in a digital form by using a three-dimensional graph form through software, realizing high-precision measurement by using a three-dimensional scanning technology, forming a database by using two or three of three-dimensional modeling software GOCAD, surpac, XModel, DMine, and importing related information data of drilling positions and rocks into the software to start modeling;
Modeling, constraint data, interpolation data and modeling parameters, wherein the constraint data is constructed by various constraint rules, the model generates outsourcing, boundary and anisotropic trend, the interpolation data is composed of data directly used for calculating and generating the model, the modeling parameters comprise a plurality of geological rule parameters, and the specific steps of the modeling flow of the implicit modeling method with geometric boundary constraint directly based on drilling data are as follows;
collecting data such as result data, mining area topography geologic map, exploration line profile map and the like related to a mineral area, arranging the data to meet the data organization requirements of mining area three-dimensional geologic modeling, establishing a geologic database under the support of three-dimensional modeling software, establishing an engineering coordinate table, a inclinometry data table, a lithology data table and an assay data table according to the mineral area engineering, sampling data and the like, inputting the data such as the engineering coordinate table, the inclinometry data table, the lithology data table and the assay data table into the three-dimensional modeling software according to the data organization requirements of the three-dimensional geologic modeling, generating a three-dimensional geologic model, correcting and optimizing the three-dimensional geologic model according to other related data such as industrial indexes, weight, faults, mine phase boundaries and the like, and finally forming the modeling result of the implicit modeling method meeting the requirements.
The hidden modeling method of the ore body uses hidden functions meeting various geological rule constraints to represent the ore body model, corresponding types of geological data are converted into various different interpolation constraints according to a certain sampling granularity in a discretization mode, then, the hidden functions representing the ore body model are obtained by solving interpolation equations constructed by the interpolation constraints, the hidden functions representing the ore body model are reconstructed by an isosurface extraction method, the interpolation method comprises a radial basis function interpolation method, and a radial basis interpolation function s (x) has the following form;
where x= { X1, X2, x3.., xn } is a set of distinct interpolation centers, ωi is a weight coefficient to be determined, Φ (xixj) is a radial basis kernel function, S Φ (X) is a kernel function part, p (X) is a polynomial part, let { p1, p2,., pq } be a set of bases in the corresponding polynomial space, the radial basis interpolation function S (X) is typically used for the interpolation domain constraint, S (xi) = pi, i=1, 2..n;
for the radial basis function interpolation method, constraints of potential field threshold values and potential field direction types are defined through interpolation constraints at any sampling positions, the Hermite radial basis function interpolation HRBF method can consider the situation that constraint point information contains function derivative values, in the HRBF interpolation method, weak off-plane constraints are replaced by strong normal constraints, ambiguous off-plane constraints are prevented from being locally generated, and therefore better geometric constraint features are achieved at places where the off-plane constraints are not easy to express.
Model reconstruction, namely automatically or manually editing and modifying the contour lines of the ore body, then realizing control on the shape of the ore body by utilizing a method of encrypting the contour lines in the middle, automatically adding branch points by calculating the shortest distance between the closed contour lines through projection, realizing automatic construction of branches by utilizing plane with holes to limit triangulation, introducing quality control aiming at poor geometric quality of the initially constructed three-dimensional ore body surface model, realizing reconstruction of the surface model, and ensuring model quality and subsequent calculation.
And finally, corresponding values of drilling sampling to data of different rock layers in the model, optimizing and refining the three-dimensional model of different ore bodies, randomly extracting 1 ore zone in each ore zone grade for field exploration, recording exploration results, and improving the accuracy rate of prospecting.
Example 2 an example provided by the present invention: a method for finding ore based on k-meas method and three-dimensional modeling comprises the following steps; s1, surveying, S2 screening and S3 modeling, wherein the surveying steps are as follows;
geological investigation, namely selecting 25 areas to be surveyed, controlling the area of the areas to be 55 hectares, randomly selecting 6000 points in each area, drilling by using a 150 drilling machine, and controlling the drilling depth to be 320 meters;
Rock sampling, detecting rock drilled out from different areas by using a spectrometer and an electronic probe, detecting chemical components, mineral content and rock physical properties of the rock, setting chemical components of a plurality of rocks as X1, X2 and X3., and setting mineral content of the rocks as C1, C2 and C3..
And (3) labeling, namely printing the position information, the components and the mineral content of the rock into labels and attaching the labels to the corresponding rock.
The screening steps are as follows;
the data sets were the rock composition X1, X2, X3. respectively, and the rock mineral content C1, C2, C3. respectively, the two data sets were each formed into two 5X 5 matrices, resulting in the matrices X and Y as followsThe data set X has a total of n pieces of data, each piece of data has M features, the data set Y has K pieces of data, each piece of data has M features, wherein ci= [ Ci1, ci2, ci 3..cim]，1≤i≤K；
Comparing the distances between each point, namely each piece of data, and K clustering centers, namely classifying the distances into the class with the nearest distance, and classifying the distances into the class randomly if the distances between a certain point and different clustering centers are equal, wherein the clustering centers are iterated, and the distance formula is as follows;
where xi= [ Xi1, xi2, xi 3..xim ]；
The data points are classified into categories with the nearest distance by comparing the distances between the data points and each data center, the operations are repeated continuously, and K-type data can be obtained after all the data points are classified;
updating a cluster center, wherein the analysis result is { S1, S2, S3..and SK }, S1 represents a set of all data points of a first class, the cluster center of each class is updated, the cluster center is the average value of all objects in the class in each dimension, and an updating formula is that;
where |Si| represents the number of data points in the i-th class;
the criterion for the termination of the iteration is that the change of the cluster centers is very small, namely the sum of d1+d2+ … +dk is very small, and is smaller than a certain value, and di refers to the distance between the cluster centers before and after updating in the ith class or the number of iterations is reached.
And analyzing the clustering result to find out the geological features and rules in each cluster. According to the clustering result, the ore bodies can be divided into different types, the ore body types are divided into four types of methyl ethyl propyl butyl, three subclasses are arranged in each major class, the ore bodies of different types are subdivided, and the ore bodies of different types are respectively modeled.
The ore body modeling flow is as follows, a database is built, a solid model is built, the model is reconstructed, and assignment is carried out on the model.
Determining drilling coordinates and depth by utilizing exploration information of a ore body, managing and utilizing the exploration information in a digital form by using a three-dimensional graph form through software, realizing high-precision measurement by using a three-dimensional scanning technology, forming a database by using two or three of three-dimensional modeling software GOCAD, surpac, XModel, DMine, and importing related information data of drilling positions and rocks into the software to start modeling;
modeling, constraint data, interpolation data and modeling parameters, wherein the constraint data is constructed by various constraint rules, the model generates outsourcing, boundary and anisotropic trend, the interpolation data is composed of data directly used for calculating and generating the model, the modeling parameters comprise a plurality of geological rule parameters, and the specific steps of the modeling flow of the implicit modeling method with geometric boundary constraint directly based on drilling data are as follows;
collecting data such as result data, mining area topography geologic map, exploration line profile map and the like related to a mineral area, arranging the data to meet the data organization requirements of mining area three-dimensional geologic modeling, establishing a geologic database under the support of three-dimensional modeling software, establishing an engineering coordinate table, a inclinometry data table, a lithology data table and an assay data table according to the mineral area engineering, sampling data and the like, inputting the data such as the engineering coordinate table, the inclinometry data table, the lithology data table and the assay data table into the three-dimensional modeling software according to the data organization requirements of the three-dimensional geologic modeling, generating a three-dimensional geologic model, correcting and optimizing the three-dimensional geologic model according to other related data such as industrial indexes, weight, faults, mine phase boundaries and the like, and finally forming the modeling result of the implicit modeling method meeting the requirements.
The hidden modeling method of the ore body uses hidden functions meeting various geological rule constraints to represent the ore body model, corresponding types of geological data are converted into various different interpolation constraints according to a certain sampling granularity in a discretization mode, then, the hidden functions representing the ore body model are obtained by solving interpolation equations constructed by the interpolation constraints, the hidden functions representing the ore body model are reconstructed by an isosurface extraction method, the interpolation method comprises a radial basis function interpolation method, and a radial basis interpolation function s (x) has the following form;
where x= { X1, X2, x3.., xn } is a set of distinct interpolation centers, ωi is a weight coefficient to be determined, Φ (xixj) is a radial basis kernel function, S Φ (X) is a kernel function part, p (X) is a polynomial part, let { p1, p2,., pq } be a set of bases in the corresponding polynomial space, the radial basis interpolation function S (X) is typically used for the interpolation domain constraint, S (xi) = pi, i=1, 2..n;
for the radial basis function interpolation method, constraints of potential field threshold values and potential field direction types are defined through interpolation constraints at any sampling positions, the Hermite radial basis function interpolation HRBF method can consider the situation that constraint point information contains function derivative values, in the HRBF interpolation method, weak off-plane constraints are replaced by strong normal constraints, ambiguous off-plane constraints are prevented from being locally generated, and therefore better geometric constraint features are achieved at places where the off-plane constraints are not easy to express.
Model reconstruction, namely automatically or manually editing and modifying the contour lines of the ore body, then realizing control on the shape of the ore body by utilizing a method of encrypting the contour lines in the middle, automatically adding branch points by calculating the shortest distance between the closed contour lines through projection, realizing automatic construction of branches by utilizing plane with holes to limit triangulation, introducing quality control aiming at poor geometric quality of the initially constructed three-dimensional ore body surface model, realizing reconstruction of the surface model, and ensuring model quality and subsequent calculation.
And finally, corresponding values of drilling sampling to data of different rock layers in the model, optimizing and refining the three-dimensional model of different ore bodies, randomly extracting 2 ore areas in each ore area grade for field exploration, recording exploration results, and improving the accuracy rate of prospecting.
Example 3 an example provided by the present invention: a method for finding ore based on k-meas method and three-dimensional modeling comprises the following steps; s1, surveying, S2 screening and S3 modeling, wherein the surveying steps are as follows;
geological investigation, namely selecting 20 areas to be surveyed, controlling the area of the areas to be 30 hectares, randomly selecting 4200 points in each area, drilling by using 150 drilling machines, and controlling the drilling depth to be 200 meters;
Rock sampling, detecting rock drilled out from different areas by using a spectrometer and an electronic probe, detecting chemical components, mineral content and rock physical properties of the rock, setting chemical components of a plurality of rocks as X1, X2 and X3., and setting mineral content of the rocks as C1, C2 and C3..
And (3) labeling, namely printing the position information, the components and the mineral content of the rock into labels and attaching the labels to the corresponding rock.
The screening steps are as follows;
the data sets were the rock composition X1, X2, X3. respectively, and the rock mineral content C1, C2, C3. respectively, the two data sets were each formed into two 5X 5 matrices, resulting in the matrices X and Y as followsThe data set X has a total of n pieces of data, each piece of data has M features, the data set Y has K pieces of data, each piece of data has M features, wherein ci= [ Ci1, ci2, ci 3..cim]，1≤i≤K；
Comparing the distances between each point, namely each piece of data, and K clustering centers, namely classifying the distances into the class with the nearest distance, and classifying the distances into the class randomly if the distances between a certain point and different clustering centers are equal, wherein the clustering centers are iterated, and the distance formula is as follows;
where xi= [ Xi1, xi2, xi 3..xim ]；
The data points are classified into categories with the nearest distance by comparing the distances between the data points and each data center, the operations are repeated continuously, and K-type data can be obtained after all the data points are classified;
updating a cluster center, wherein the analysis result is { S1, S2, S3..and SK }, S1 represents a set of all data points of a first class, the cluster center of each class is updated, the cluster center is the average value of all objects in the class in each dimension, and an updating formula is that;
where |Si| represents the number of data points in the i-th class;
the criterion for the termination of the iteration is that the change of the cluster centers is very small, namely the sum of d1+d2+ … +dk is very small, and is smaller than a certain value, and di refers to the distance between the cluster centers before and after updating in the ith class or the number of iterations is reached.
And analyzing the clustering result to find out the geological features and rules in each cluster. According to the clustering result, the ore bodies can be divided into different types, the ore body types are divided into four types of methyl ethyl propyl butyl, three subclasses are arranged in each major class, the ore bodies of different types are subdivided, and the ore bodies of different types are respectively modeled.
The ore body modeling flow is as follows, a database is built, a solid model is built, the model is reconstructed, and assignment is carried out on the model.
Determining drilling coordinates and depth by utilizing exploration information of a ore body, managing and utilizing the exploration information in a digital form by using a three-dimensional graph form through software, realizing high-precision measurement by using a three-dimensional scanning technology, forming a database by using two or three of three-dimensional modeling software GOCAD, surpac, XModel, DMine, and importing related information data of drilling positions and rocks into the software to start modeling;
modeling, constraint data, interpolation data and modeling parameters, wherein the constraint data is constructed by various constraint rules, the model generates outsourcing, boundary and anisotropic trend, the interpolation data is composed of data directly used for calculating and generating the model, the modeling parameters comprise a plurality of geological rule parameters, and the specific steps of the modeling flow of the implicit modeling method with geometric boundary constraint directly based on drilling data are as follows;
collecting data such as result data, mining area topography geologic map, exploration line profile map and the like related to a mineral area, arranging the data to meet the data organization requirements of mining area three-dimensional geologic modeling, establishing a geologic database under the support of three-dimensional modeling software, establishing an engineering coordinate table, a inclinometry data table, a lithology data table and an assay data table according to the mineral area engineering, sampling data and the like, inputting the data such as the engineering coordinate table, the inclinometry data table, the lithology data table and the assay data table into the three-dimensional modeling software according to the data organization requirements of the three-dimensional geologic modeling, generating a three-dimensional geologic model, correcting and optimizing the three-dimensional geologic model according to other related data such as industrial indexes, weight, faults, mine phase boundaries and the like, and finally forming the modeling result of the implicit modeling method meeting the requirements.
For the radial basis function interpolation method, constraints of potential field threshold values and potential field direction types are defined through interpolation constraints at any sampling positions, the Hermite radial basis function interpolation HRBF method can consider the situation that constraint point information contains function derivative values, in the HRBF interpolation method, weak off-plane constraints are replaced by strong normal constraints, ambiguous off-plane constraints are prevented from being locally generated, and therefore better geometric constraint features are achieved at places where the off-plane constraints are not easy to express.
Model reconstruction, namely automatically or manually editing and modifying the contour lines of the ore body, then realizing control on the shape of the ore body by utilizing a method of encrypting the contour lines in the middle, automatically adding branch points by calculating the shortest distance between the closed contour lines through projection, realizing automatic construction of branches by utilizing plane with holes to limit triangulation, introducing quality control aiming at poor geometric quality of the initially constructed three-dimensional ore body surface model, realizing reconstruction of the surface model, and ensuring model quality and subsequent calculation.
And finally, corresponding values of drilling sampling to data of different rock layers in the model, optimizing and refining the three-dimensional model of different ore bodies, randomly extracting 3 ore areas in each ore area grade for field exploration, recording exploration results, and improving the accuracy rate of prospecting.
Example 4 an example provided by the present invention: a method for finding ore based on k-meas method and three-dimensional modeling comprises the following steps; s1, surveying, S2 screening and S3 modeling, wherein the surveying steps are as follows;
geological investigation, namely selecting 10 areas to be surveyed, controlling the area of the areas to be 1 hectare, randomly selecting 5000 points in each area, drilling by using 150 drilling machines, and controlling the drilling depth to be 200 meters;
rock sampling, detecting rock drilled out from different areas by using a spectrometer and an electronic probe, detecting chemical components, mineral content and rock physical properties of the rock, setting chemical components of a plurality of rocks as X1, X2 and X3., and setting mineral content of the rocks as C1, C2 and C3..
And (3) labeling, namely printing the position information, the components and the mineral content of the rock into labels and attaching the labels to the corresponding rock.
The screening steps are as follows;
the data sets were the rock composition X1, X2, X3. respectively, and the rock mineral content C1, C2, C3. respectively, the two data sets were each formed into two 5X 5 matrices, resulting in the matrices X and Y as followsThe data set X has a total of n pieces of data, each piece of data has M features, the data set Y has K pieces of data, each piece of data has M features, wherein ci= [ Ci1, ci2, ci 3..cim ]，1≤i≤K；
Comparing the distances between each point, namely each piece of data, and K clustering centers, namely classifying the distances into the class with the nearest distance, and classifying the distances into the class randomly if the distances between a certain point and different clustering centers are equal, wherein the clustering centers are iterated, and the distance formula is as follows;
where xi= [ Xi1, xi2, xi 3..xim]；/>
The data points are classified into categories with the nearest distance by comparing the distances between the data points and each data center, the operations are repeated continuously, and K-type data can be obtained after all the data points are classified;
updating a cluster center, wherein the analysis result is { S1, S2, S3..and SK }, S1 represents a set of all data points of a first class, the cluster center of each class is updated, the cluster center is the average value of all objects in the class in each dimension, and an updating formula is that;
where |Si| represents the number of data points in the i-th class;
the criterion for the termination of the iteration is that the change of the cluster centers is very small, namely the sum of d1+d2+ … +dk is very small, and is smaller than a certain value, and di refers to the distance between the cluster centers before and after updating in the ith class or the number of iterations is reached.
And analyzing the clustering result to find out the geological features and rules in each cluster. According to the clustering result, the ore bodies can be divided into different types, the ore body types are divided into four types of methyl ethyl propyl butyl, three subclasses are arranged in each major class, the ore bodies of different types are subdivided, and the ore bodies of different types are respectively modeled.
The ore body modeling flow is as follows, a database is built, a solid model is built, the model is reconstructed, and assignment is carried out on the model.
Determining drilling coordinates and depth by utilizing exploration information of a ore body, managing and utilizing the exploration information in a digital form by using a three-dimensional graph form through software, realizing high-precision measurement by using a three-dimensional scanning technology, forming a database by using two or three of three-dimensional modeling software GOCAD, surpac, XModel, DMine, and importing related information data of drilling positions and rocks into the software to start modeling;
modeling, constraint data, interpolation data and modeling parameters, wherein the constraint data is constructed by various constraint rules, the model generates outsourcing, boundary and anisotropic trend, the interpolation data is composed of data directly used for calculating and generating the model, the modeling parameters comprise a plurality of geological rule parameters, and the specific steps of the modeling flow of the implicit modeling method with geometric boundary constraint directly based on drilling data are as follows;
collecting data such as result data, mining area topography geologic map, exploration line profile map and the like related to a mineral area, arranging the data to meet the data organization requirements of mining area three-dimensional geologic modeling, establishing a geologic database under the support of three-dimensional modeling software, establishing an engineering coordinate table, a inclinometry data table, a lithology data table and an assay data table according to the mineral area engineering, sampling data and the like, inputting the data such as the engineering coordinate table, the inclinometry data table, the lithology data table and the assay data table into the three-dimensional modeling software according to the data organization requirements of the three-dimensional geologic modeling, generating a three-dimensional geologic model, correcting and optimizing the three-dimensional geologic model according to other related data such as industrial indexes, weight, faults, mine phase boundaries and the like, and finally forming the modeling result of the implicit modeling method meeting the requirements.
The hidden modeling method of the ore body uses hidden functions meeting various geological rule constraints to represent the ore body model, corresponding types of geological data are converted into various different interpolation constraints according to a certain sampling granularity in a discretization mode, then, the hidden functions representing the ore body model are obtained by solving interpolation equations constructed by the interpolation constraints, the hidden functions representing the ore body model are reconstructed by an isosurface extraction method, the interpolation method comprises a radial basis function interpolation method, and a radial basis interpolation function s (x) has the following form;
where x= { X1, X2, x3.., xn } is a set of distinct interpolation centers, ωi is a weight coefficient to be determined, Φ (xixj) is a radial basis kernel function, S Φ (X) is a kernel function part, p (X) is a polynomial part, let { p1, p2,., pq } be a set of bases in the corresponding polynomial space, the radial basis interpolation function S (X) is typically used for the interpolation domain constraint, S (xi) = pi, i=1, 2..n;
model reconstruction, namely automatically or manually editing and modifying the contour lines of the ore body, then realizing control on the shape of the ore body by utilizing a method of encrypting the contour lines in the middle, automatically adding branch points by calculating the shortest distance between the closed contour lines through projection, realizing automatic construction of branches by utilizing plane with holes to limit triangulation, introducing quality control aiming at poor geometric quality of the initially constructed three-dimensional ore body surface model, realizing reconstruction of the surface model, and ensuring model quality and subsequent calculation.
And finally, corresponding values of drilling sampling to data of different rock layers in the model, optimizing and refining the three-dimensional model of different ore bodies, randomly extracting 2 ore areas in each ore area grade for field exploration, recording exploration results, and improving the accuracy rate of prospecting.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (8)
1. A method for finding ore based on a k-meas method and three-dimensional modeling is characterized in that: comprises the following steps of; s1, surveying, S2 screening and S3 modeling, wherein the surveying steps are as follows;
geological investigation, namely selecting 10-30 areas to be surveyed, controlling the area of the areas to be 1-60 hectares, randomly selecting 3200-6400 points in each area, drilling by using a 150 drilling machine, and controlling the drilling depth to be 150-450 meters;
Rock sampling, detecting rock drilled out from different areas by using a spectrometer and an electronic probe, detecting chemical components, mineral content and rock physical properties of the rock, setting chemical components of a plurality of rocks as X1, X2 and X3., and setting mineral content of the rocks as C1, C2 and C3..
And (3) labeling, namely printing the position information, the components and the mineral content of the rock into labels and attaching the labels to the corresponding rock.
2. The method for prospecting based on the k-meas method and three-dimensional modeling according to claim 1, wherein the method comprises the following steps: the screening steps are as follows;
the data sets were the rock composition X1, X2, X3. respectively, and the rock mineral content C1, C2, C3. respectively, the two data sets were each formed into two 5X 5 matrices, resulting in the matrices X and Y as followsThe data set X has a total of n pieces of data, each piece of data has M features, the data set Y has K pieces of data, each piece of data has M features, wherein ci= [ Ci1, ci2, ci 3..cim]，1≤i≤K；
Comparing the distances between each point, namely each piece of data, and K clustering centers, namely classifying the distances into the class with the nearest distance, and classifying the distances into the class randomly if the distances between a certain point and different clustering centers are equal, wherein the clustering centers are iterated, and the distance formula is as follows;
Where xi= [ Xi1, xi2, xi 3..xim]；
The data points are classified into categories with the nearest distance by comparing the distances between the data points and each data center, the operations are repeated continuously, and K-type data can be obtained after all the data points are classified;
updating a cluster center, wherein the analysis result is { S1, S2, S3..and SK }, S1 represents a set of all data points of a first class, the cluster center of each class is updated, the cluster center is the average value of all objects in the class in each dimension, and an updating formula is that;
where |Si| represents the number of data points in the i-th class;
the criterion for the termination of the iteration is that the change of the cluster centers is very small, namely the sum of d1+d2+ … +dk is very small, and is smaller than a certain value, and di refers to the distance between the cluster centers before and after updating in the ith class or the number of iterations is reached.
3. The method for prospecting based on the k-meas method and three-dimensional modeling according to claim 1, wherein the method comprises the following steps: and analyzing the clustering result to find out the geological features and rules in each cluster. According to the clustering result, the ore bodies can be divided into different types, the ore body types are divided into four types of methyl ethyl propyl butyl, three subclasses are arranged in each major class, the ore bodies of different types are subdivided, and the ore bodies of different types are respectively modeled.
4. A method of prospecting based on the k-meas method and three-dimensional modeling according to claim 3, wherein: the ore body modeling flow is as follows, a database is built, a solid model is built, the model is reconstructed, and assignment is carried out on the model.
5. The method for prospecting based on the k-meas method and three-dimensional modeling according to claim 4, wherein the method comprises the following steps: determining drilling coordinates and depth by utilizing exploration information of a ore body, managing and utilizing the exploration information in a digital form by using a three-dimensional graph form through software, realizing high-precision measurement by using a three-dimensional scanning technology, forming a database by using two or three of three-dimensional modeling software GOCAD, surpac, XModel, DMine, and importing related information data of drilling positions and rocks into the software to start modeling;
modeling, constraint data, interpolation data and modeling parameters, wherein the constraint data is constructed by various constraint rules, the model generates outsourcing, boundary and anisotropic trend, the interpolation data is composed of data directly used for calculating and generating the model, the modeling parameters comprise a plurality of geological rule parameters, and the specific steps of the modeling flow of the implicit modeling method with geometric boundary constraint directly based on drilling data are as follows;
Collecting data such as result data, mining area topography geologic map, exploration line profile map and the like related to a mineral area, arranging the data to meet the data organization requirements of mining area three-dimensional geologic modeling, establishing a geologic database under the support of three-dimensional modeling software, establishing an engineering coordinate table, a inclinometry data table, a lithology data table and an assay data table according to the mineral area engineering, sampling data and the like, inputting the data such as the engineering coordinate table, the inclinometry data table, the lithology data table and the assay data table into the three-dimensional modeling software according to the data organization requirements of the three-dimensional geologic modeling, generating a three-dimensional geologic model, correcting and optimizing the three-dimensional geologic model according to other related data such as industrial indexes, weight, faults, mine phase boundaries and the like, and finally forming the modeling result of the implicit modeling method meeting the requirements.
6. The method for prospecting based on the k-meas method and three-dimensional modeling according to claim 5, wherein the method comprises the following steps: the hidden modeling method of the ore body uses hidden functions meeting various geological rule constraints to represent the ore body model, corresponding types of geological data are converted into various different interpolation constraints according to a certain sampling granularity in a discretization mode, then, the hidden functions representing the ore body model are obtained by solving interpolation equations constructed by the interpolation constraints, the hidden functions representing the ore body model are reconstructed by an isosurface extraction method, the interpolation method comprises a radial basis function interpolation method, and a radial basis interpolation function s (x) has the following form;
Where x= { X1, X2, x3.., xn } is a set of distinct interpolation centers, ωi is a weight coefficient to be determined, Φ (xixj) is a radial basis kernel function, S Φ (X) is a kernel function part, p (X) is a polynomial part, let { p1, p2,., pq } be a set of bases in the corresponding polynomial space, the radial basis interpolation function S (X) is typically used for the interpolation domain constraint, S (xi) = pi, i=1, 2..n;
for the radial basis function interpolation method, constraints of potential field threshold values and potential field direction types are defined through interpolation constraints at any sampling positions, the Hermite radial basis function interpolation HRBF method can consider the situation that constraint point information contains function derivative values, in the HRBF interpolation method, weak off-plane constraints are replaced by strong normal constraints, ambiguous off-plane constraints are prevented from being locally generated, and therefore better geometric constraint features are achieved at places where the off-plane constraints are not easy to express.
7. The method for prospecting based on the k-meas method and three-dimensional modeling according to claim 5, wherein the method comprises the following steps: model reconstruction, namely automatically or manually editing and modifying the contour lines of the ore body, then realizing control on the shape of the ore body by utilizing a method of encrypting the contour lines in the middle, automatically adding branch points by calculating the shortest distance between the closed contour lines through projection, realizing automatic construction of branches by utilizing plane with holes to limit triangulation, introducing quality control aiming at poor geometric quality of the initially constructed three-dimensional ore body surface model, realizing reconstruction of the surface model, and ensuring model quality and subsequent calculation.
8. The method for prospecting based on the k-meas method and three-dimensional modeling according to claim 5, wherein the method comprises the following steps: and finally, corresponding values of drilling sampling to data of different rock layers in the model, optimizing and refining the three-dimensional model of different ore bodies, randomly extracting 1-3 ore areas in each ore area grade for field exploration, recording exploration results, and improving the accuracy rate of prospecting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311364984.7A CN117456118A (en) | 2023-10-20 | 2023-10-20 | Ore finding method based on k-meas method and three-dimensional modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311364984.7A CN117456118A (en) | 2023-10-20 | 2023-10-20 | Ore finding method based on k-meas method and three-dimensional modeling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117456118A true CN117456118A (en) | 2024-01-26 |
Family
ID=89580912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311364984.7A Pending CN117456118A (en) | 2023-10-20 | 2023-10-20 | Ore finding method based on k-meas method and three-dimensional modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117456118A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020161627A1 (en) * | 2001-04-27 | 2002-10-31 | Gailey Michael L. | Method for passive mining of usage information in a location-based services system |
| JP3521197B1 (en) * | 2003-09-03 | 2004-04-19 | 株式会社虎門琴平会館ビル | Light source position tracking device and tracking method |
| CN101819169A (en) * | 2010-04-16 | 2010-09-01 | 中山大学 | Method for prospecting by using geo-gas particles |
| CN106780591A (en) * | 2016-11-21 | 2017-05-31 | 北京师范大学 | A kind of craniofacial shape analysis and Facial restoration method based on the dense corresponding points cloud in cranium face |
| CA2915802A1 (en) * | 2015-12-18 | 2017-06-18 | Objectivity.Ca | Explorative sampling of natural mineral resource deposits |
| CN110060173A (en) * | 2019-04-27 | 2019-07-26 | 烟台市牟金矿业有限公司 | A kind of deep gold deposit method of prospecting |
| CN111737867A (en) * | 2020-06-15 | 2020-10-02 | 鞍钢集团矿业有限公司 | Method for rapidly updating three-dimensional entity model of ore body |
| CN113515847A (en) * | 2021-05-12 | 2021-10-19 | 中国矿业大学 | Heterogeneous rock digital core modeling method based on K-means clustering algorithm |
| CN114297929A (en) * | 2021-12-29 | 2022-04-08 | 中国地质大学（武汉） | Machine learning-fused radial basis function curved surface complex ore body modeling method and device |
| CN114547927A (en) * | 2021-12-28 | 2022-05-27 | 核工业北京地质研究院 | Hydrothermal deposit three-dimensional quantitative prediction evaluation method based on numerical simulation |
| WO2022257930A1 (en) * | 2021-06-07 | 2022-12-15 | 中国地质大学（北京） | Method and apparatus for simulating mineralization in mineralization research area |
| CN115879648A (en) * | 2023-02-21 | 2023-03-31 | 中国地质科学院 | Machine learning-based ternary deep mineralization prediction method and system |
-
2023
- 2023-10-20 CN CN202311364984.7A patent/CN117456118A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020161627A1 (en) * | 2001-04-27 | 2002-10-31 | Gailey Michael L. | Method for passive mining of usage information in a location-based services system |
| JP3521197B1 (en) * | 2003-09-03 | 2004-04-19 | 株式会社虎門琴平会館ビル | Light source position tracking device and tracking method |
| CN101819169A (en) * | 2010-04-16 | 2010-09-01 | 中山大学 | Method for prospecting by using geo-gas particles |
| CA2915802A1 (en) * | 2015-12-18 | 2017-06-18 | Objectivity.Ca | Explorative sampling of natural mineral resource deposits |
| CN106780591A (en) * | 2016-11-21 | 2017-05-31 | 北京师范大学 | A kind of craniofacial shape analysis and Facial restoration method based on the dense corresponding points cloud in cranium face |
| CN110060173A (en) * | 2019-04-27 | 2019-07-26 | 烟台市牟金矿业有限公司 | A kind of deep gold deposit method of prospecting |
| CN111737867A (en) * | 2020-06-15 | 2020-10-02 | 鞍钢集团矿业有限公司 | Method for rapidly updating three-dimensional entity model of ore body |
| CN113515847A (en) * | 2021-05-12 | 2021-10-19 | 中国矿业大学 | Heterogeneous rock digital core modeling method based on K-means clustering algorithm |
| WO2022257930A1 (en) * | 2021-06-07 | 2022-12-15 | 中国地质大学（北京） | Method and apparatus for simulating mineralization in mineralization research area |
| CN114547927A (en) * | 2021-12-28 | 2022-05-27 | 核工业北京地质研究院 | Hydrothermal deposit three-dimensional quantitative prediction evaluation method based on numerical simulation |
| CN114297929A (en) * | 2021-12-29 | 2022-04-08 | 中国地质大学（武汉） | Machine learning-fused radial basis function curved surface complex ore body modeling method and device |
| CN115879648A (en) * | 2023-02-21 | 2023-03-31 | 中国地质科学院 | Machine learning-based ternary deep mineralization prediction method and system |
Non-Patent Citations (4)
| Title |
|---|
| YONGLIN MA等: "A data mining model of knowledge discovery based on the deep learning", IEEE, 23 November 2015 (2015-11-23) * |
| 刘岳: "区域地球化学数据分析及成矿信息融合模型研究-以南岭成矿带为例", 中国优秀博硕士学位论文全文数据库, 15 January 2016 (2016-01-15), pages 3 - 5 * |
| 国家统计局: "大数据在统计工作中的应用与实践:案例汇编", 30 November 2020, 中国统计出版社 * |
| 扶金铭等: "Stacking集成策略下的径向基函数曲面复杂矿体三维建模方法", 地球科学, 6 March 2023 (2023-03-06), pages 2 - 3 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Knox‐Robinson et al. | Towards a holistic exploration strategy: using geographic information systems as a tool to enhance exploration | |
| CN110490100A (en) | Ground automatic identification based on deep learning names method and system | |
| CN108931814A (en) | A method of the basement rock FRACTURE PREDICTION based on the fusion of more attributes | |
| CN108415079B (en) | Rock stratum interface delineation method based on rock drilling impact sound identification | |
| CN106780730A (en) | The construction method and device of three-dimensional geological model | |
| CN101221250A (en) | Three-dimensional stratum characteristic decryption method based on geologic information acquisition data | |
| CN105205864A (en) | Multi-source-data-based automatic modeling method and system of three-dimension model of geological structural surface | |
| KR20180055518A (en) | System and method of 3d mineral prospectivity | |
| CN104380143A (en) | Systems and methods for processing geophysical data | |
| WO2020124148A1 (en) | Automated updating of geological model boundaries for improved ore extraction | |
| Zhiliang et al. | Construction of carbonate reservoir knowledge base and its application in fracture-cavity reservoir geological modeling | |
| CN102053981A (en) | Multi-scale expression method for semantic-considered overground-underground integrated model | |
| CN113627657A (en) | Sandstone-type uranium mineralization interest area prediction method using machine learning model | |
| Li et al. | Knowledge-driven based three-dimensional prospectivity modeling of Fe–Cu skarn deposits; a case study of the Fanchang volcanic basin, anhui province, Eastern China | |
| Zhang et al. | Method and application of urban 3D rapid modeling of geology based on CAD borehole logs | |
| CN117456118A (en) | Ore finding method based on k-meas method and three-dimensional modeling | |
| Rabeau et al. | Log-uniform distribution of gold deposits along major Archean fault zones | |
| Pollock et al. | 3D exploratory analysis of descriptive lithology records using regular expressions | |
| CN113420348B (en) | Method for rapidly drawing uranium mine exploration line profile map | |
| CN115100373A (en) | Surface and underground environment three-dimensional integrated representation method, device, medium and equipment | |
| CN114117898A (en) | While-drilling gamma logging forward modeling method based on machine learning algorithm | |
| CN114398696A (en) | Alkaline granite type uranium deposit three-dimensional fine modeling method | |
| CN113075744A (en) | Karst detection system for shield tunnel affected area under building | |
| Niu et al. | Optimization of geological and mineral exploration by integrating remote sensing technology and borehole database | |
| Martin et al. | Discovery from 3D visualization and quantitative modelling |
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 |