Hidden ore body three-dimensional positioning prediction method and system based on artificial intelligence

Abstract

The invention discloses a hidden ore body three-dimensional positioning prediction method and system based on artificial intelligence, and relates to the technical field of hidden ore body positioning prediction. Geological information variables and three-dimensional data of known ore bodies are collected and preprocessed; dividing the geological space range into a plurality of cubic information units, and obtaining geological information variables in each unit and a space position relation of a known ore body; analyzing the geological information variables by using a neural network algorithm, and calculating to obtain relevance and weight values among the geological information variables; according to the relevance and the weight value, calculating a comprehensive evaluation value of each cubic information unit, and delineating a metallogenic prediction target region; through comparison and verification with actual exploration data, a neural network algorithm model is continuously optimized and adjusted. Based on the artificial intelligence algorithm, the three-dimensional positioning prediction precision and the prospecting effectiveness of the concealed ore body are improved. The invention provides an effective method for objectively determining the weight, and the reliability and the accuracy of a prediction result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of concealed ore body positioning prediction, and in particular to a method and system for three-dimensional positioning prediction of concealed ore bodies based on artificial intelligence. Background Art

[0002] Concealed ore bodies refer to mineral resources that are buried below the surface and are difficult to directly discover through conventional exploration methods. With the increasing reduction of mineral resources and the improvement of environmental protection awareness, the exploration and development of concealed ore bodies have become increasingly important. However, due to the complexity and uncertainty of geological conditions, the exploration of concealed ore bodies still faces many challenges.

[0003] Although traditional exploration methods such as geological mapping, geophysical exploration, and geochemical exploration can reveal the existence of hidden ore bodies to a certain extent, they often have problems such as long exploration cycle, high cost, and low accuracy.

[0004] In recent years, with the rapid development of artificial intelligence technology, its application in the field of geological mineral resource exploration has become increasingly widespread. However, most of the existing artificial intelligence-based hidden ore prediction methods remain at the two-dimensional level and cannot accurately reflect the three-dimensional spatial distribution characteristics of hidden ore bodies. Therefore, how to develop a three-dimensional positioning prediction method and system for hidden ore bodies based on artificial intelligence has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and system for three-dimensional positioning prediction of hidden ore bodies based on artificial intelligence. By collecting geological information variables and three-dimensional data of known ore bodies, the geological information variables are analyzed using artificial intelligence algorithms, and the correlation and weight values ​​between the geological information variables are calculated, thereby realizing the three-dimensional positioning prediction of hidden ore bodies.

[0006] In order to solve the above technical problems, the present invention provides a technical solution: a three-dimensional positioning prediction method for hidden ore bodies based on artificial intelligence, comprising the following steps:

[0007] S1. Collect geological information variables and three-dimensional data of known ore bodies and perform preprocessing;

[0008] S2, dividing the geological space range into a number of cubic information units, and obtaining the spatial position relationship between the geological information variables and the known ore bodies in each unit;

[0009] S3, using a neural network algorithm to analyze the geological information variables, and calculating the correlation and weight values ​​between the geological information variables;

[0010] S4. Calculate the comprehensive evaluation value of each cube information unit according to the correlation and weight value, and delineate the mineralization prediction target area;

[0011] S5. Continuously optimize and adjust the neural network algorithm model by comparing and verifying with actual exploration data.

[0012] Furthermore, the method further comprises step S6: continuously updating and improving the three-dimensional data model according to new exploration data and geological information.

[0013] Furthermore, the geological information variables in step S1 include stratigraphic structure, lithology distribution, and structural characteristics.

[0014] Furthermore, the preprocessing includes data cleaning and format conversion to ensure the accuracy and consistency of the data.

[0015] Furthermore, the specific method of dividing the geological space range into several cubic information units is as follows:

[0016] (1) Determination of geological spatial scope

[0017] Based on the existing geological exploration data and geological maps, clarify the geological spatial scope of the study;

[0018] Determine the boundaries of the study area, including coordinate information of longitude, latitude, and depth;

[0019] (2) Cube Information Unit Division

[0020] According to the size and complexity of the geological space, the study area is divided into several cubic information units using the grid division method;

[0021] The size of each unit must ensure that it can fully reflect the spatial distribution characteristics of the geological information variables.

[0022] Furthermore, each of the cubic information units contains geological information variables and known ore body data; through spatial position matching, the spatial position relationship between the geological information variables and the known ore bodies in each unit is obtained.

[0023] Furthermore, the neural network algorithm includes:

[0024] Input layer: receiving geological information variables and three-dimensional data of known ore bodies;

[0025] Hidden layer: Perform nonlinear transformation on input data through multiple layers of neurons to extract features;

[0026] Output layer: Output the correlation and weight values ​​between geological information variables, as well as the comprehensive evaluation value of each cube information unit.

[0027] Furthermore, according to the evaluation value, the mineralization prediction target area is delineated.

[0028] A three-dimensional positioning prediction system for hidden ore bodies based on artificial intelligence, including

[0029] Data collection and preprocessing module, used to collect geological information variables and three-dimensional data of known ore bodies, and perform preprocessing;

[0030] The cubic information unit processing module is used to divide the geological space range into several cubic information units, and obtain the spatial position relationship between the geological information variables and the known ore bodies in each unit;

[0031] Artificial intelligence algorithm analysis module, used to analyze geological information variables using neural network algorithms, and calculate the correlation and weight values ​​between geological information variables;

[0032] The module for calculating the comprehensive evaluation value and defining the target area is used to calculate the comprehensive evaluation value of each cube information unit according to the correlation and weight value, and define the target area for mineralization prediction;

[0033] The algorithm optimization and verification module is used to continuously optimize and adjust the artificial intelligence algorithm model by comparing and verifying with actual exploration data.

[0034] Furthermore, it also includes a data updating module for continuously updating and improving the three-dimensional data model according to new exploration data and geological information.

[0035] The advantages of the present invention over the prior art are: based on artificial intelligence algorithms, the present invention improves the three-dimensional positioning prediction accuracy of concealed ore bodies and the effectiveness of prospecting. The present invention provides an effective method for objectively determining weights, thereby improving the reliability and accuracy of prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The present invention is a flowchart of a method for three-dimensional positioning prediction of a concealed ore body based on artificial intelligence.

[0037] Figure 2 The present invention is a system block diagram of a three-dimensional positioning prediction system for hidden ore bodies based on artificial intelligence. DETAILED DESCRIPTION

[0038] The following is a further detailed description of a method and system for three-dimensional positioning prediction of a concealed ore body based on artificial intelligence according to the present invention in conjunction with the accompanying drawings.

[0039] Combined with Figure 1-2 The specific implementation process of the method and system for three-dimensional positioning prediction of hidden ore bodies based on artificial intelligence of the present invention is as follows:

[0040] A three-dimensional positioning prediction method for hidden ore bodies based on artificial intelligence includes the following steps:

[0041] Data collection and preprocessing:

[0042] Collect geological information variables (such as stratigraphic structure, lithology distribution, structural characteristics, etc.) and three-dimensional data of known ore bodies, and build a three-dimensional data model based on this. These data can be obtained through geological exploration, geophysical exploration, geochemical exploration, etc. Then, pre-process the data, including data cleaning (removing duplicate and erroneous data) and format conversion (converting data into a format suitable for artificial intelligence algorithm processing) to ensure the accuracy and consistency of the data.

[0043] Cube information unit processing:

[0044] The geological space range is divided into several cubic information units; the size of each unit can be adjusted according to the actual situation to ensure that the spatial distribution characteristics of the geological information variables can be fully reflected. Then, the spatial position relationship between the geological information variables and the known ore bodies in each unit is obtained through spatial position matching. The purpose of this step is to simplify the complex geological space into easy-to-handle cubic information units, which facilitates the subsequent artificial intelligence algorithm analysis.

[0045] The specific method of dividing the geological space range into several cubic information units is as follows:

[0046] (1) Determination of geological spatial scope

[0047] Based on the existing geological exploration data and geological maps, clarify the geological spatial scope of the study;

[0048] Determine the boundaries of the study area, including coordinate information of longitude, latitude, and depth;

[0049] (2) Cube Information Unit Division

[0050] According to the size and complexity of the geological space, the study area is divided into several cubic information units using the grid division method;

[0051] The size of each unit must ensure that it can fully reflect the spatial distribution characteristics of the geological information variables.

[0052] (3) Extraction and assignment of geological information variables

[0053] The extracted geological information variables are assigned to the corresponding cube information units to establish a corresponding relationship between the geological information variables and the cube information units.

[0054] (4) Spatial Position Matching and Relationship Establishment

[0055] By spatially matching the positions, the spatial position relationship between each cube information unit is obtained. This can be achieved through technical means such as geographic information system (GIS) to establish the topological relationship between the cube information units.

[0056] At the same time, it is also necessary to establish the spatial position relationship between the cube information unit and the known ore body for subsequent mineralization prediction.

[0057] (5) Data storage and management

[0058] The divided cube information units and their related geological information variables, spatial position relationships and other data are stored in the database; the database should have good data management capabilities and support data query, update, deletion and other operations.

[0059] At the same time, it is also necessary to establish a data backup and recovery mechanism to ensure the security and reliability of data.

[0060] Artificial Intelligence Algorithm Analysis:

[0061] The geological information variables are analyzed using neural network algorithms.

[0062] Neural network algorithms include:

[0063] Input layer: receiving geological information variables and three-dimensional data of known ore bodies;

[0064] Hidden layer: Perform nonlinear transformation on input data through multiple layers of neurons to extract features;

[0065] Output layer: Output the correlation and weight values ​​between geological information variables, as well as the comprehensive evaluation value of each cube information unit.

[0066] The algorithm can automatically extract the correlation and weight values ​​between geological information variables through training and learning, and improve prediction accuracy and efficiency by continuously adjusting algorithm parameters and model structure.

[0067] Calculation of comprehensive evaluation value and delineation of target area:

[0068] According to the correlation and weight value, the comprehensive evaluation value of each cube information unit is calculated. The purpose of this step is to convert the spatial distribution characteristics of geological information variables into easy-to-understand numerical representations for subsequent target area delineation. Then, according to the evaluation value, the mineralization prediction target area is delineated. The scope of the target area can be adjusted according to the actual situation to ensure that the possible distribution area of ​​the concealed ore body can be fully reflected.

[0069] Algorithm optimization and verification:

[0070] By comparing and verifying with actual exploration data, the neural network algorithm model is continuously optimized and adjusted. The purpose of this step is to ensure the accuracy and reliability of the algorithm model and improve the prediction accuracy. At the same time, based on new exploration data and geological information, the three-dimensional data model is continuously updated and improved to adapt to the continuous development of geological and mineral resource exploration.

[0071] Based on the above method, the present invention also provides a three-dimensional positioning prediction system for hidden ore bodies based on artificial intelligence, the system comprises

[0072] Data collection and preprocessing module, used to collect geological information variables and three-dimensional data of known ore bodies, and perform preprocessing;

[0073] The cubic information unit processing module is used to divide the geological space range into several cubic information units, and obtain the spatial position relationship between the geological information variables and the known ore bodies in each unit;

[0074] Artificial intelligence algorithm analysis module, used to analyze geological information variables using neural network algorithms, and calculate the correlation and weight values ​​between geological information variables;

[0075] The module for calculating the comprehensive evaluation value and defining the target area is used to calculate the comprehensive evaluation value of each cube information unit according to the correlation and weight value, and define the target area for mineralization prediction;

[0076] Algorithm optimization and verification module, used to continuously optimize and adjust the artificial intelligence algorithm model by comparing and verifying with actual exploration data;

[0077] The data update module is used to continuously update and improve the 3D data model based on new exploration data and geological information.

[0078] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A three-dimensional positioning prediction method for hidden ore bodies based on artificial intelligence, characterized in that: The following steps are included: S1. Collect geological information variables and three-dimensional data of known ore bodies and perform preprocessing; S2, dividing the geological space range into a number of cubic information units, and obtaining the spatial position relationship between the geological information variables and the known ore bodies in each unit; S3, using a neural network algorithm to analyze the geological information variables, and calculating the correlation and weight values ​​between the geological information variables; S4. Calculate the comprehensive evaluation value of each cube information unit according to the correlation and weight value, and delineate the mineralization prediction target area; S5. Continuously optimize and adjust the neural network algorithm model by comparing and verifying with actual exploration data.

2. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 1 is characterized in that: The method further includes step S6: continuously updating and improving the three-dimensional data model according to new exploration data and geological information.

3. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 2 is characterized in that: The geological information variables in step S1 include stratum structure, lithology distribution, and structural characteristics.

4. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 3 is characterized in that: The preprocessing includes data cleaning and format conversion to ensure the accuracy and consistency of the data.

5. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 4 is characterized in that: The specific method of dividing the geological space range into several cubic information units is as follows: (1) Determination of geological spatial scope Based on the existing geological exploration data and geological maps, clarify the geological spatial scope of the study; Determine the boundaries of the study area, including coordinate information of longitude, latitude, and depth; (2) Cube Information Unit Division According to the size and complexity of the geological space, the study area is divided into several cubic information units using the grid division method; The size of each unit must ensure that it can fully reflect the spatial distribution characteristics of the geological information variables.

6. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 5 is characterized in that: Each of the cubic information units contains geological information variables and known ore body data; through spatial position matching, the spatial position relationship between the geological information variables and the known ore bodies in each unit is obtained.

7. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 6 is characterized in that: The neural network algorithm includes: Input layer: receiving geological information variables and three-dimensional data of known ore bodies; Hidden layer: Perform nonlinear transformation on input data through multiple layers of neurons to extract features; Output layer: Output the correlation and weight values ​​between geological information variables, as well as the comprehensive evaluation value of each cube information unit.

8. The method for three-dimensional positioning prediction of a hidden ore body based on artificial intelligence according to claim 7 is characterized in that: According to the evaluation value, the mineralization prediction target area is delineated.

9. A three-dimensional positioning prediction system for hidden ore bodies based on artificial intelligence, characterized in that: include Data collection and preprocessing module, used to collect geological information variables and three-dimensional data of known ore bodies, and perform preprocessing; The cubic information unit processing module is used to divide the geological space range into several cubic information units, and obtain the spatial position relationship between the geological information variables and the known ore bodies in each unit; Artificial intelligence algorithm analysis module, used to analyze geological information variables using neural network algorithms, and calculate the correlation and weight values ​​between geological information variables; The module for calculating the comprehensive evaluation value and defining the target area is used to calculate the comprehensive evaluation value of each cube information unit according to the correlation and weight value, and define the target area for mineralization prediction; The algorithm optimization and verification module is used to continuously optimize and adjust the artificial intelligence algorithm model by comparing and verifying with actual exploration data.

10. The three-dimensional positioning prediction system for hidden ore bodies based on artificial intelligence according to claim 9, characterized in that: It also includes a data update module for continuously updating and improving the 3D data model based on new exploration data and geological information.

Images