A method and system for predicting deep mine resources based on data analysis

Abstract

The present invention relates to the technical field of deep mine resource prediction, and discloses a deep mine resource prediction method and system based on data analysis, including a geological data acquisition module, a geological data analysis module and a resource prediction module, wherein the geological data acquisition module includes an ore grade data acquisition unit, an ore type acquisition unit, a deep mine environment data acquisition unit and a historical mining data storage unit. The system collects ore grade data, altered mineral type data and deep mine environment data of mine samples, obtains ore similarity through comprehensive calculation of ore grade data and altered ore type data, extracts a similarity sequence with the current mining ore from the historical mining process, calculates environmental similarity based on the deep mine environment data, performs secondary screening on the current mining process, and outputs the most similar one from the historical mining process to the current mining process, thereby ensuring accurate prediction of mineral resources in the mine.

Description

Technical Field

[0001] The present invention relates to the technical field of deep mine resource prediction, and in particular to a deep mine resource prediction method and system based on data analysis. Background Art

[0002] Mineral resources are an important material basis for human survival and development. The safe supply of mineral resources depends to a large extent on the development level of mineral exploration technology. With the continuous strengthening of mineral exploration and development, the number of surface mines, shallow mines and easily identifiable mines is decreasing. Mineral exploration is shifting towards finding hidden mines, deep mines and difficult-to-identify mines, and the difficulty of prospecting is increasing. With the increase in prospecting depth and the reduction of exploration projects, the available favorable information on deep mineralization is becoming less and less. With the decreasing number of surface mines, shallow mines and easily identifiable mines, the difficulty of prospecting is increasing and the prospecting effect is decreasing. Since the 1980s, the focus on finding deep hidden mines, new types of mines and new fields of mines has become the prospecting direction that countries around the world are concerned about. How to use limited data to carry out prediction and evaluation of deep minerals is a technical difficulty that we currently need to solve. Summary of the invention

[0003] 1. Technical issues to be resolved

[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for predicting deep mine resources based on data analysis, which has the advantages of predicting deep mine resources and solves the above-mentioned technical problems.

[0005] (II) Technical solution

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a deep mine resource prediction system based on data analysis, comprising a geological data acquisition module, a geological data analysis module and a resource prediction module;

[0007] The geological data acquisition module includes an ore grade data acquisition unit, an ore type acquisition unit, a mine deep environment data acquisition unit and a historical mining data storage unit. The ore grade data acquisition unit is used to collect ore grade data of mine samples, the ore type acquisition unit is used to collect altered mineral type data, and the mine deep environment data acquisition unit is used to collect environmental data in the deep mine: including underground pressure and the number of underground cavities. The historical mining data storage unit stores data in the historical mining process and constructs a historical mine database. The geological data acquisition module sends the collected ore grade data, altered mineral type data and deep mine environment data to the geological data analysis module.

[0008] The geological data analysis module calculates the ore similarity based on the ore grade data and the altered ore type data in combination with the historical mine database, and sends the calculated ore similarity to the resource prediction module. The resource prediction module executes the comparison instruction based on the historical mine database and the environmental data deep in the mine, and outputs the resource prediction result.

[0009] As a preferred technical solution of the present invention, the specific expression of the ore grade data acquisition unit for collecting ore grade data of mine samples is as follows:

[0010] ;

[0011] in, represents the ore grade dataset of the samples, Respectively represent the first type of ore collected from the mine, , No. Kinds of ore, , No. Kind of ore, Respectively represent the first type of ore grade data set, , No. ore grade datasets, , No. ore grade datasets, and Ore grade dataset The expression is as follows:

[0012] ;

[0013] in, Respectively represent The first ore grade in the ore grade data set, , No. Ore grade, , No. Ore grade.

[0014] As a preferred technical solution of the present invention, the expression of the altered mineral type data collected by the ore type collection unit is as follows:

[0015] ;

[0016] in, Indicates the total data index set of alteration mineral types data, Respectively represent the first alteration mineral type data, , No. Alteration mineral type data, , No. Alteration mineral type data, and Alteration mineral type data Includes altered minerals and the frequency of occurrence of altered minerals.

[0017] As a preferred technical solution of the present invention, the specific expression of the deep mine environment data acquisition unit for collecting deep mine environment data is as follows:

[0018] ;

[0019] in, represents the environment dataset, They represent the underground pressure collected at the first sampling point, , No. The underground pressure collected at the sampling points , No. The underground pressure collected at the sampling points is They represent the number of underground cavities collected at the first sampling point, , No. The number of underground cavities collected from the sampling points, , No. The number of underground cavities collected at each sampling point.

[0020] As a preferred technical solution of the present invention, the geological data analysis module obtains a specific expression of ore similarity by comprehensive calculation based on ore grade data and altered ore type data combined with historical mine database as follows:

[0021] ;

[0022] in, Indicates the current mine and the historical mine database Similarity of ores in the secondary mining mines, Indicates The first Ore grade, Indicates the historical mining database The corresponding first The first If the ore grade is in the historical mine database, There is no corresponding The first Ore grade, then , represents the alteration mineral influence function, represents the absolute value, Indicates Ore grade data set After summing up the ore grades, The ore grade data sets are summed.

[0023] As a preferred technical solution of the present invention, the altered mineral influence function The specific expression is as follows:

[0024] ;

[0025] in, represents the absolute value, Indicates The frequency of occurrence of alteration minerals in the alteration mineral type data, Indicates During the mining process, the corresponding The frequency of occurrence of altered minerals in the altered mineral type data is There is no corresponding The alteration minerals in the alteration mineral type data are .

[0026] As a preferred technical solution of the present invention, the resource prediction module executes comparison instructions based on the historical mine database and the environmental data of the deep mine, and outputs the specific steps of resource prediction results as follows:

[0027] Step A1: Store the current mine and the historical mine database in sequence Similarity of ores in the secondary mining mines, ;

[0028] Step A2: Execute the comparison instruction and output the ore similarity stored in step A1. The similarity sequence and number of sequences of the ore. If the number of sequences is lower than the threshold, recursively go to step A2. Indicates the number of times step A2 is executed. If the number of sequences is not less than the threshold, step A3 is executed;

[0029] Step A3: Calculate the environmental similarity based on the environmental data deep in the mine, and select the one with the highest environmental similarity from the ore similarity sequence output in step A2 as the resource prediction result.

[0030] As a preferred technical solution of the present invention, the specific expression for calculating the environment similarity in step A3 is as follows:

[0031] ;

[0032] in, represents the environmental factor, Indicates the corresponding environmental coefficient stored in the historical mine database, environmental coefficient The specific expression is as follows:

[0033] ;

[0034] in, and represents the weight coefficients that sum to 1, Indicates based on The calculated mean is Indicates based on The calculated mean.

[0035] As a preferred technical solution of the present invention, the resource prediction result output in step A3 includes the proportion of all minerals mined during the historical mining process.

[0036] The present invention also provides a method for predicting deep mine resources based on data analysis, based on the above-mentioned system for predicting deep mine resources based on data analysis, comprising the following steps:

[0037] Step 1: Collect ore grade data, altered mineral type data and deep mine environment data of samples collected from the mine: including rock type and geological structure characteristics;

[0038] Step 2: Based on the ore grade data and altered ore type data, the ore similarity is calculated comprehensively;

[0039] Step 3: Execute comparison instructions based on the historical mining database and environmental data deep in the mine, and output resource prediction results.

[0040] Compared with the prior art, the present invention provides a method and system for predicting deep mine resources based on data analysis, which has the following beneficial effects:

[0041] The present invention collects ore grade data, altered mineral type data and environmental data of deep mine samples from mines, and then calculates ore similarity based on the ore grade data and altered ore type data. It also extracts a similarity sequence with the ore mined this time from historical mining processes, and calculates environmental similarity based on environmental data deep in the mine, thereby performing a secondary screening of the current mining process, and outputs the one that is most similar to the current mining process from the historical mining process, thereby ensuring that the mineral resources in the mine can be accurately predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the system framework of the present invention;

[0043] Figure 2 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] See also Figure 1-2 , a deep mine resource prediction system based on data analysis, including a geological data acquisition module, a geological data analysis module and a resource prediction module;

[0046] The geological data acquisition module includes an ore grade data acquisition unit, an ore type acquisition unit, a deep mine environment data acquisition unit and a historical mining data storage unit. The ore grade data acquisition unit is used to collect ore grade data of mine samples, the ore type acquisition unit is used to collect altered mineral type data, and the deep mine environment data acquisition unit is used to collect deep mine environment data: including underground pressure and underground cavity number. The historical mining data storage unit stores the data of historical mining process and builds a historical mine database. The geological data acquisition module sends the collected ore grade data, altered mineral type data and deep mine environment data to the geological data analysis module. The specific expression of the ore grade data acquisition unit collecting ore grade data of mine samples is as follows:

[0047] ;

[0048] in, represents the ore grade dataset of the samples, Respectively represent the first type of ore collected from the mine, , No. Kinds of ore, , No. Kind of ore, Respectively represent the first type of ore grade data set, , No. ore grade datasets, , No. ore grade datasets, and Ore grade dataset The expression is as follows:

[0049] ;

[0050] in, Respectively represent The first ore grade in the ore grade data set, , No. Ore grade, , No. The expression of the altered mineral type data collected by the ore type collection unit is as follows:

[0051] ;

[0052] in, Indicates the total data index set of alteration mineral types data, Respectively represent the first alteration mineral type data, , No. Alteration mineral type data, , No. Alteration mineral type data, and Alteration mineral type data The data include altered minerals and the frequency of occurrence of altered minerals. The specific expression of the deep mine environmental data acquisition unit to collect deep mine environmental data is as follows:

[0053] ;

[0054] in, represents the environment dataset, They represent the underground pressure collected at the first sampling point, , No. The underground pressure collected at the sampling points , No. The underground pressure collected at the sampling points is They represent the number of underground cavities collected at the first sampling point, , No. The number of underground cavities collected from the sampling points, , No. The number of underground cavities collected at each sampling point;

[0055] The geological data analysis module calculates the ore similarity based on the ore grade data and the altered ore type data combined with the historical mine database, and sends the calculated ore similarity to the resource prediction module. The specific expression of the ore similarity calculated by the geological data analysis module based on the ore grade data and the altered ore type data combined with the historical mine database is as follows:

[0056] ;

[0057] in, Indicates the current mine and the historical mine database Similarity of ores from the secondary mining mines, Indicates The first Ore grade, Indicates the historical mining database The corresponding first The first If the ore grade is in the historical mine database, There is no corresponding The first Ore grade, then , represents the alteration mineral influence function, represents the absolute value, Indicates Ore grade data set After summing up the ore grades, Alteration mineral influence function The specific expression is as follows:

[0058] ;

[0059] in, represents the absolute value, Indicates The frequency of occurrence of alteration minerals in the alteration mineral type data, Indicates During the mining process, the corresponding The frequency of occurrence of altered minerals in the altered mineral type data is There is no corresponding The alteration minerals in the alteration mineral type data are , when There is no corresponding When altered minerals are included in the altered mineral type data, it is necessary to ensure To avoid the situation where the data is too large;

[0060] The resource prediction module executes comparison instructions based on the historical mine database and the environmental data in the deep mine, and outputs the resource prediction results. The specific steps of the resource prediction module are as follows:

[0061] Step A1: Store the current mine and the historical mine database in sequence Similarity of ores in the secondary mining mines, ;

[0062] Step A2: Execute the comparison instruction and output the ore similarity stored in step A1. The similarity sequence and number of sequences of the ore. If the number of sequences is lower than the threshold, recursively go to step A2. Indicates the number of times step A2 is executed. If the number of sequences is not less than the threshold, step A3 is executed. By continuously adjusting the search range through step A2, as many ore similarity sequences as possible can be output. For example, in the first recursive process, when there is only one similar mining area in the top 5% similarity sequences of the output step, the calculation of step A3 is meaningless. When there are 20 similarity sequences in the top 5% similarity sequences of the output step in the first recursive process, which exceeds the threshold = 15, it is judged that step A2 is terminated and step A3 is executed;

[0063] Step A3: Calculate the environmental similarity based on the environmental data deep in the mine, and select the one with the highest environmental similarity from the ore similarity sequence output in step A2 as the resource prediction result. The resource prediction result is based on the one that is most similar to the current mining process in the historical mining process as the output, so as to accurately predict the mineral resources in the mine. The resource prediction result includes the proportion of all minerals mined in the historical mining process. The specific expression for calculating the environmental similarity in step A3 is as follows:

[0064] ;

[0065] in, represents the environmental factor, Indicates the corresponding environmental coefficient stored in the historical mine database, environmental coefficient The specific expression is as follows:

[0066] ;

[0067] in, and represents the weight coefficients that sum to 1, Indicates based on The calculated mean is Indicates based on The calculated mean.

[0068] The present invention also provides a method for predicting deep mine resources based on data analysis, based on the above-mentioned system for predicting deep mine resources based on data analysis, comprising the following steps:

[0069] Step 1: Collect ore grade data, altered mineral type data and deep mine environment data of samples collected from the mine: including rock type and geological structure characteristics;

[0070] Step 2: Based on the ore grade data and altered ore type data, the ore similarity is calculated comprehensively;

[0071] Step 3: Execute comparison instructions based on the historical mining database and environmental data deep in the mine, and output resource prediction results.

[0072] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A deep mine resource prediction system based on data analysis, characterized by: It includes geological data acquisition module, geological data analysis module and resource prediction module; The geological data acquisition module includes an ore grade data acquisition unit, an ore type acquisition unit, a mine deep environment data acquisition unit and a historical mining data storage unit. The ore grade data acquisition unit is used to collect ore grade data of mine samples, the ore type acquisition unit is used to collect altered mineral type data, and the mine deep environment data acquisition unit is used to collect environmental data in the deep mine: including underground pressure and the number of underground cavities. The historical mining data storage unit stores data in the historical mining process and constructs a historical mine database. The geological data acquisition module sends the collected ore grade data, altered mineral type data and deep mine environment data to the geological data analysis module. The geological data analysis module calculates the specific expression of ore similarity based on ore grade data and altered ore type data combined with historical mine database as follows: ； in, Indicates the current mine and the historical mine database Similarity of ores in the secondary mining mines, Indicates The first Ore grade, Indicates the historical mining database The corresponding first The first If the ore grade is in the historical mine database, There is no corresponding The first Ore grade, then , represents the alteration mineral influence function, represents the absolute value, Indicates Ore grade data set After summing up the ore grades, The altered minerals affect the function The specific expression is as follows: ； in, represents the absolute value, Indicates The frequency of occurrence of alteration minerals in the alteration mineral type data, Indicates During the mining process, the corresponding The frequency of occurrence of altered minerals in the altered mineral type data is There is no corresponding The alteration minerals in the alteration mineral type data are ; The geological data analysis module calculates the ore similarity based on the ore grade data and the altered ore type data in combination with the historical mine database, and sends the calculated ore similarity to the resource prediction module. The resource prediction module executes the comparison instruction based on the historical mine database and the environmental data deep in the mine, and outputs the resource prediction result.

2. A deep mine resource prediction system based on data analysis according to claim 1, characterized in that: The specific expression of the ore grade data acquisition unit for collecting ore grade data of mine samples is as follows: ； in, represents the ore grade dataset of the samples, Respectively represent the first type of ore collected from the mine, , No. Kinds of ore, , No. Kind of ore, Respectively represent the first type of ore grade data set, , No. ore grade datasets, , No. ore grade datasets, and Ore grade dataset The expression is as follows: ； in, Respectively represent The first ore grade in the ore grade data set, , No. Ore grade, , No. Ore grade.

3. A deep mine resource prediction system based on data analysis according to claim 2, characterized in that: The expression of the altered mineral type data collected by the ore type collection unit is as follows: ； in, Indicates the total data index set of alteration mineral types data, Respectively represent the first alteration mineral type data, , No. Alteration mineral type data, , No. Alteration mineral type data, and Alteration mineral type data Includes altered minerals and the frequency of occurrence of altered minerals.

4. A deep mine resource prediction system based on data analysis according to claim 3, characterized in that: The specific expression of the deep mine environment data acquisition unit for collecting deep mine environment data is as follows: ； in, represents the environment dataset, They represent the underground pressure collected at the first sampling point, , No. The underground pressure collected at the sampling points , No. The underground pressure collected at the sampling points is They represent the number of underground cavities collected at the first sampling point, , No. The number of underground cavities collected from the sampling points, , No. The number of underground cavities collected at each sampling point.

5. A deep mine resource prediction system based on data analysis according to claim 4, characterized in that: The resource prediction module executes comparison instructions based on the historical mine database and the environmental data of the deep mine, and outputs the resource prediction results in the following specific steps: Step A1: Store the current mine and the historical mine database in sequence Similarity of ores in the secondary mining mines, ; Step A2: Execute the comparison instruction and output the ore similarity stored in step A1. The similarity sequence and number of sequences of the ore. If the number of sequences is lower than the threshold, recursively go to step A2. Indicates the number of times step A2 is executed. If the number of sequences is not less than the threshold, step A3 is executed; Step A3: Calculate the environmental similarity based on the environmental data deep in the mine, and select the one with the highest environmental similarity from the ore similarity sequence output in step A2 as the resource prediction result.

6. A deep mine resource prediction system based on data analysis according to claim 5, characterized in that: The specific expression for calculating the environment similarity in step A3 is as follows: ； in, represents the environmental factor, Indicates the corresponding environmental coefficient stored in the historical mine database, environmental coefficient The specific expression is as follows: ； in, and represents the weight coefficients that sum to 1, Indicates based on The calculated mean is Indicates based on The calculated mean.

7. A deep mine resource prediction system based on data analysis according to claim 6, characterized in that: The resource prediction result output in step A3 includes the proportion of all minerals mined during the historical mining process.

8. A method for predicting deep mine resources based on data analysis, based on a system for predicting deep mine resources based on data analysis as claimed in any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Collect ore grade data, altered mineral type data and deep mine environment data of samples collected from the mine: including rock type and geological structure characteristics; Step 2: Based on the ore grade data and altered ore type data, the ore similarity is calculated comprehensively; Step 3: Execute comparison instructions based on the historical mining database and environmental data deep in the mine, and output resource prediction results.

Images