Intelligent ore mining control method and system based on machine learning

Abstract

The invention discloses an intelligent ore mining control method and system based on machine learning, and relates to the technical field of mining intelligentization, and the method comprises the steps: building a mining area geologic model based on a convolutional neural network model and a support vector machine model, inputting an ore body geologic feature map into the mining area geologic model, and generating a geologic analysis report; fusing the ore body geologic feature map and the geologic analysis report through a Bayesian updating method to obtain a geomechanical map; through a data fusion technology and a real-time analysis algorithm, a geomechanical map and mining area real-time monitoring data are combined, ore mining risk factors are analyzed, and an ore mining strategy is dynamically adjusted to generate an optimized ore mining instruction. The mining area geological environment data is converted into high-quality graph database nodes and edges, and key geological features are identified by using a complex network analysis technology, so that the ore extraction efficiency, safety and scientific decision-making capability are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent mining technology, and in particular to an intelligent ore mining control method and system based on machine learning. Background Art

[0002] With the rapid development of information technology and artificial intelligence (AI), the mineral mining industry is constantly seeking more efficient, safe, and intelligent mining methods. Traditional mineral mining relies on the experience of geological exploration experts and limited data support, which to some extent limits mining efficiency and safety. In recent years, machine learning technology has begun to be applied to the mining industry, showing great potential in data processing and analysis. By collecting geological environmental data from mining areas and using machine learning algorithms for preprocessing and analysis, data quality can be significantly improved, providing a more scientific basis for subsequent mining decisions. However, effectively transforming this complex data into practical and guiding information remains a challenge. Existing technologies are generally limited to analyzing a single type of data (such as geological structure or chemical composition), making it difficult to achieve a comprehensive and integrated assessment. Furthermore, traditional methods often suffer from low computational efficiency and insufficient accuracy when used with large datasets.

[0003] Currently, although some studies have attempted to use machine learning methods to optimize the ore mining process, most of these methods focus on improving a specific link, such as geological exploration or risk assessment, and have failed to form a complete intelligent system from data collection to mining strategy adjustment. In particular, when processing complex mining area geological environment data, existing technologies often ignore the spatial correlation between data, resulting in the inability to accurately identify key information such as ore body boundaries, crack location information, and groundwater flow paths. In addition, due to the lack of an effective model fusion mechanism, existing technologies find it difficult to fully utilize the advantages of different models to improve the accuracy and reliability of geomechanical maps. Based on the above two points, the present invention proposes a method and system for intelligent ore mining control based on machine learning, which aims to overcome the above-mentioned shortcomings. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a machine learning-based intelligent mining control method for ore to solve the problems of existing technologies ignoring data spatial correlation and lacking an effective model fusion mechanism when processing complex mining area geological environment data.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a method for intelligent ore mining control based on machine learning, which includes collecting geological environment data of the mining area and preprocessing it to obtain high-quality mining area data; converting the high-quality mining area data into nodes and edges in a graph database through a spatial correlation analysis method, and calculating the topological indicators between the nodes in the graph database through complex network analysis technology, identifying the ore body boundary, crack location information and groundwater flow path, and obtaining the ore body geological characteristic map; constructing a mining area geological model based on a convolutional neural network model and a support vector machine model, inputting the ore body geological characteristic map into the mining area geological model, and generating a geological analysis report; through the Bayesian update method, the ore body geological characteristic map and the geological analysis report are fused to obtain a geomechanical map; through data fusion technology and real-time analysis algorithm, the geomechanical map is combined with real-time monitoring data of the mining area, analyzing ore mining risk factors, and dynamically adjusting the ore mining strategy to generate optimized ore mining instructions.

[0007] As a preferred solution of the machine learning-based intelligent mining control method of the present invention, the steps of collecting mining area geological environment data and preprocessing to obtain high-quality mining area data are as follows: The mining area geological environment data includes the mining area geological structure, ore body distribution and mining area environmental conditions; Through data integrity check, hash algorithm and Z-score, the geological environment data of the mining area is identified, incomplete, duplicate and abnormal records are removed, and K-means is used to identify and remove interference data to obtain high-quality mining area data.

[0008] As a preferred solution of the intelligent mining control method based on machine learning described in the present invention, wherein: the high-quality mining area data is converted into nodes and edges in the graph database through the spatial association analysis method, the specific steps are as follows: Convert high-quality mining area data into three-dimensional spatial coordinates through spatial interpolation technology; Extract the geological structure data of the mining area through spatial analysis tools, and map each mineral layer into a node according to the three-dimensional spatial coordinates; Based on the ore body distribution data, the spatial distribution of the ore body is obtained through remote sensing technology, and each ore body is mapped as an independent node; Through spatial analysis methods, mining area environmental condition data is extracted and mapped into independent nodes in the graph database; Through spatial data analysis methods, the spatial distance, relative position and potential physical contact between nodes are analyzed, and these spatial relationships are converted into edges in the graph database.

[0009] As a preferred solution of the machine learning-based intelligent mining control method of the present invention, the topological indicators between nodes in the graph database are calculated by complex network analysis technology to identify the ore body boundary, crack location information and groundwater flow path, and obtain the ore body geological characteristic map. The specific steps are as follows: Connect each node to other nodes through edges to form a graph structure; Represent the connection relationship between each pair of nodes in the graph in the form of a matrix and construct an adjacency matrix; Traverse each node and adjacent nodes in the graph through the adjacency matrix, calculate the number of connections between the node and other nodes, and obtain the node degree; Through graph structure analysis and topology algorithms, the connection status between each node and its neighboring nodes is analyzed to obtain the clustering coefficient; The shortest path is gradually expanded through the Dijkstra algorithm to calculate the shortest distance from the starting node to all other nodes; Based on the clustering coefficient and node degree, the DBSCAN algorithm is used to identify the areas with dense relative relationships between ore bodies and obtain the ore body boundaries; Based on the shortest path, identify the distance mutation between the ore body node and mark the crack location information; Through the shortest path analysis, the potential channels of groundwater flow are revealed, and combined with the clustering coefficient, the density of water flow at the node is revealed, the main channels of groundwater flow are identified, and the groundwater flow path is obtained; Based on the ore body boundary, fracture location information and groundwater flow path, through spatial analysis and topological relationships, the geometric shape of the ore body, the distribution of fractures and the impact of groundwater flow on mining are extracted, and finally the geological characteristic map of the ore body is obtained.

[0010] As a preferred solution of the machine learning-based intelligent mining control method of the present invention, the convolutional neural network model and the support vector machine model are used to construct a mining area geological model, input the ore body geological characteristic map into the mining area geological model, and generate a geological analysis report. The specific steps are as follows: The convolutional neural network model is used as the basic model; Input layer inputs historical ore body geological characteristic map; The convolution layer uses convolution operations to extract spatial features; The pooling layer reduces the dimensionality of spatial features through the maximum pooling operation; The fully connected layer connects the extracted features of the convolution and pooling layers, mapping the spatial features extracted in the deep layer to the prediction task; Combined with the multi-layer perceptron model, the fully connected layer output is received through the input layer; The MLP layer inputs the output of the fully connected layer into the single-layer MLP for further feature combination and transformation; The output layer outputs the final result; Finally, a geological model of the mining area is obtained; Input the geological characteristic map of the ore body into the geological model of the mining area to obtain the ore body stability assessment value; Taking the ore body stability assessment value as the basic indicator, combined with the ore body's geometric shape, fracture distribution and groundwater flow, a multi-factor analysis method is used to analyze and derive the comprehensive stability risk of the ore body; Collect data on other geological features through remote sensing techniques; Using data visualization technology, the ore body stability assessment value and other geological characteristic data are integrated and visualized; Generate geological analysis reports based on comprehensive ore body stability risks and visualization results.

[0011] As a preferred solution of the intelligent mining control method of ore based on machine learning described in the present invention, wherein: the geological characteristic map of the ore body and the geological analysis report are integrated by the Bayesian update method to obtain the geomechanical map. The specific steps are as follows: Extract topological indicators from the geological characteristic map of the ore body; Based on the historical geological analysis report, the joint probability distribution of each topological indicator is statistically analyzed to obtain the prior probability value; Through data analysis and numerical conversion methods, mechanical parameters are extracted from geological analysis reports and normalized; Convert the normalized mechanical parameters in the geomechanical analysis report into observation data and construct a likelihood function; Calculate the posterior probability based on the prior probability and likelihood function; The posterior probability is mapped to the three-dimensional spatial coordinates of the ore body geological characteristic map. Based on the spatial position of each node and the corresponding posterior probability value, a discrete probability density distribution map is generated. The discrete probability values ​​are spatially interpolated using the Kriging interpolation technique to construct a continuous geomechanical map.

[0012] As a preferred solution of the machine learning-based intelligent ore mining control method of the present invention, wherein: the data fusion technology and real-time analysis algorithm are used to combine the geomechanical map with the real-time monitoring data of the mining area, analyze the ore mining risk factors, and dynamically adjust the ore mining strategy to generate optimized ore mining instructions. The specific steps are as follows: Collect real-time monitoring data of the mining area through mining equipment sensors; Using the time synchronization algorithm and inverse distance weighted interpolation method, the real-time monitoring data of the mining area are synchronized in time and aligned in space; Using spatial hash tables and nearest neighbor matching algorithms, real-time monitoring data from the mining area is mapped to the corresponding spatial locations on the geomechanical map to extract ore mining risk factors. Quantitatively analyze various ore mining risk factors through fuzzy logic to obtain the current mining risk value of the mining area and adjust the ore mining strategy in real time; Based on the adjusted ore mining strategy, optimized ore mining instructions are generated through the rule engine and issued through the MQTT protocol.

[0013] In the second aspect, the present invention provides an intelligent ore mining control system based on machine learning, including a data acquisition module, a data analysis module, a report generation module, a data fusion module and a mining strategy adjustment module; the data acquisition module is used to collect mining area geological environment data and perform preprocessing to obtain high-quality mining area data; the data analysis module is used to convert high-quality mining area data into nodes and edges in a graph database through a spatial correlation analysis method, and calculate the topological indicators between the nodes in the graph database through complex network analysis technology, identify the ore body boundaries, crack location information and groundwater flow paths, and obtain the ore body geological characteristic map; the report generation module is used to construct a mining area geological model based on a convolutional neural network model and a support vector machine model, input the ore body geological characteristic map into the mining area geological model, and generate a geological analysis report; the data fusion module is used to fuse the ore body geological characteristic map and the geological analysis report through a Bayesian update method to obtain a geomechanical map; the mining strategy adjustment module is used to combine the geomechanical map with the real-time monitoring data of the mining area through data fusion technology and real-time analysis algorithm, analyze the ore mining risk factors, and dynamically adjust the ore mining strategy to generate optimized ore mining instructions.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the machine learning-based intelligent ore mining control method as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the machine learning-based intelligent ore mining control method as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: by converting the geological environment data of the mining area into high-quality graph database nodes and edges, and using complex network analysis technology to identify key geological features, combining the convolutional neural network model and the support vector machine model to construct a mining area geological model to generate a geological analysis report, and then using the Bayesian update method to fuse the ore body geological characteristic map and the geological analysis report to obtain a geomechanical map, and finally using real-time monitoring data to analyze mining risks and dynamically adjust mining strategies, the efficiency, safety and scientific decision-making ability of ore mining are significantly improved, resource waste and mining risks are reduced, and at the same time, the mining strategy is optimized to achieve higher economic benefits and extend the service life of the mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of the intelligent ore mining control method based on machine learning in Example 1.

[0019] Figure 2 Schematic diagram of the intelligent ore mining control system based on machine learning in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0023] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an intelligent ore mining control method based on machine learning, comprising the following steps: S1. Collect mining area geological environment data and pre-process it to obtain high-quality mining area data.

[0024] The geological environment data of the mining area include the geological structure of the mining area, the distribution of ore bodies and the environmental conditions of the mining area.

[0025] Through data integrity check, hash algorithm and Z-score, the geological environment data of the mining area is identified, incomplete, duplicate and abnormal records are removed, and K-means is used to identify and remove interference data to obtain high-quality mining area data.

[0026] It should be explained that a data integrity check is first performed to identify and remove records that lack necessary information, and then a hash algorithm is applied to detect duplicates and delete them from the mining area geological environment data. The Z-score method is used to calibrate abnormal records that deviate from the mean value by more than a set threshold and exclude them. Next, the K-means clustering algorithm is used to analyze the preprocessed mining area geological environment data. By identifying data points that do not belong to the mining area geological environment data, interference data is determined and removed, and finally a set of clean, accurate and representative high-quality mining area data sets is obtained.

[0027] S2. Use spatial association analysis methods to convert high-quality mining area data into nodes and edges in a graph database.

[0028] High-quality mining area data is converted into three-dimensional spatial coordinates through spatial interpolation technology.

[0029] It should be explained that appropriate spatial interpolation methods (such as Kriging interpolation, inverse distance weighted method, etc.) are used to predict the values ​​of unknown points based on high-quality mining area data of known sample points to construct a continuous geological surface model. This process takes into account the relative position relationship between sample points and their attribute values ​​to estimate the attribute value of each position and locate it in a three-dimensional spatial coordinate system, thereby realizing the transformation of high-quality mining area data from original measurement values ​​to three-dimensional spatial coordinates.

[0030] The geological structure data of the mining area is extracted through spatial analysis tools, and each mineral layer is mapped as a node according to the three-dimensional spatial coordinates.

[0031] It should be explained that geological exploration data and geographic information system (GIS) technology are first used to identify and extract the spatial extent of each mineral layer and its attribute information; then, based on the three-dimensional spatial coordinates of each mineral layer, a specific algorithm is used to accurately map it into an independent node in the graph database, where each node not only contains the specific coordinate position of the mineral layer, but is also associated with attributes such as mineral layer thickness and mineral type.

[0032] Based on the ore body distribution data, the spatial distribution of the ore body is obtained through remote sensing technology, and each ore body is mapped as an independent node.

[0033] It should be explained that remote sensing technology is first used to obtain high-resolution images of the mining area, and the spatial distribution characteristics of each ore body are identified through image processing and interpretation technology; then, based on the three-dimensional spatial coordinates of each ore body obtained by analysis, it is accurately mapped into an independent node in the graph database. These nodes not only record the specific location information of the ore body, but also associate key attributes such as the ore body size and mineral composition.

[0034] Through spatial analysis methods, mining area environmental condition data are extracted and mapped as independent nodes in the graph database.

[0035] It should be explained that first, the data layer containing environmental information is parsed using geographic information system (GIS) technology to extract key environmental parameters such as terrain, vegetation cover, and hydrological characteristics; then, based on the three-dimensional spatial coordinate position of the key environmental parameters, a specific algorithm is used to accurately map each environmental feature point into an independent node in the graph database. Each node not only stores specific coordinate information, but also associates relevant environmental attribute data.

[0036] Through spatial data analysis methods, the spatial distance, relative position and potential physical contact between nodes are analyzed, and these spatial relationships are converted into edges in the graph database.

[0037] It should be explained that the spatial distance and relative position between nodes are first calculated to identify whether there is potential physical contact or proximity between them; then, based on these analysis results, a specific algorithm is used to determine the strength and type of the relationship between nodes, and these spatial relationships are represented in the form of edges.

[0038] S3. Use complex network analysis technology to calculate the topological indicators between nodes in the graph database, identify the ore body boundaries, crack location information and groundwater flow paths, and obtain the geological characteristic map of the ore body.

[0039] It should be noted that topological indicators refer to node degree, clustering coefficient and shortest distance.

[0040] Each node is connected to other nodes through edges to form a graph structure.

[0041] The connection relationship between each pair of nodes in the graph is expressed in the form of a matrix to construct an adjacency matrix.

[0042] The node degree is obtained by traversing each node and adjacent nodes in the graph through the adjacency matrix and calculating the number of connections between the node and other nodes.

[0043] It should be noted that first, a corresponding row and column are initialized for each node in the graph; then, each node and its adjacent nodes in the graph are traversed. If there is a direct connection between the two nodes, a value (such as 1) is set in the corresponding position of the adjacency matrix, otherwise it is set to 0; then, each row in the adjacency matrix is ​​summed to calculate the number of connections between each node and other nodes. This total is the degree of the node.

[0044] Through graph structure analysis and topology algorithms, the connection status between each node and its neighboring nodes is analyzed to obtain the clustering coefficient.

[0045] It should be noted that the connection status between each node and its neighboring nodes is first identified through a topological algorithm. The specific steps are: for a given node, determine the set of all its directly connected neighbor nodes; then calculate the ratio of the actual number of edges between these neighbor nodes to the theoretically maximum possible number of edges. This ratio is the clustering coefficient of the node.

[0046] The shortest path is gradually expanded through the Dijkstra algorithm to calculate the shortest distance from the starting node to all other nodes.

[0047] It should be noted that first, the distance of the starting node is initialized to 0, the distances of all other nodes are infinite, and all nodes are added to the set of unprocessed nodes; then, the unprocessed node with the smallest current distance is selected, and the shortest distances of all its neighboring nodes are updated. If the distance to the neighboring node through the current node is shorter than the known distance, the shortest distance of the neighboring node is updated; repeat this process, gradually expanding the shortest path tree until all nodes have been processed or cannot be reached, and finally the shortest distance from the starting node to each node in the graph is obtained.

[0048] Based on the clustering coefficient and node degree, the DBSCAN algorithm is used to identify the areas with dense relative relationships between ore bodies and obtain the ore body boundaries.

[0049] It should be noted that the local density characteristics of each node in the graph, namely the clustering coefficient and node degree, are first calculated. Then, the DBSCAN (Density-Based Spatial Clustering Application) algorithm is used to identify areas of relatively dense relationships between ore bodies based on these density characteristics. Specifically, by setting an appropriate distance threshold and minimum point count requirement, the DBSCAN algorithm can discover areas of sufficiently high density and group densely connected nodes into the same cluster, thereby distinguishing the boundaries of different ore bodies.

[0050] Based on the shortest path, the distance mutation between the ore body nodes is identified and the crack location information is marked.

[0051] It should be noted that the Dijkstra algorithm or other shortest path algorithms are first used to calculate the shortest path distances between nodes within the ore body; then, these path distance data are analyzed to find abnormally increased distance values, namely distance mutation points. Such mutations usually indicate discontinuities or gaps in the geological structure; once a significant distance mutation is detected, it is marked as a potential crack location.

[0052] Through the shortest path analysis, the potential channels of groundwater flow are revealed, and combined with the clustering coefficient, the density of water flow at the node is revealed, the main channels of groundwater flow are identified, and the groundwater flow path is obtained.

[0053] It should be explained that the Dijkstra algorithm or other shortest path algorithms are first applied to calculate the shortest paths between nodes within the ore body to simulate possible groundwater flow channels; then, the density of water flow at each node is evaluated in combination with the clustering coefficient. Nodes with higher clustering coefficients indicate that the area has stronger connectivity and a higher possibility of water flow convergence; by analyzing the distribution of these nodes in the network, the main paths or main roads of groundwater flow can be identified, and the groundwater flow path can be obtained.

[0054] Based on the ore body boundary, fracture location information and groundwater flow path, through spatial analysis and topological relationships, the geometric shape of the ore body, the distribution of fractures and the impact of groundwater flow on mining are extracted, and finally the geological characteristic map of the ore body is obtained.

[0055] It should be explained that first, the geometric shape of the ore body is accurately extracted through spatial analysis technology, and the stability of the internal structure of the ore body is evaluated in combination with topological relationships; then, the fracture location information is used to analyze its impact on the stability of the ore body, and at the same time, the key water flow channels that may affect mining operations and their relationship with the ore body structure are identified based on the groundwater flow path; a comprehensive assessment is conducted on the geometric characteristics of the ore body, the distribution of fractures, and the groundwater activity to determine their specific impact on ore mining. Finally, all these analysis results are integrated together to form a detailed geological characteristic map of the ore body.

[0056] S4. Based on the convolutional neural network model and the support vector machine model, a mining area geological model is constructed, the geological characteristic map of the ore body is input into the mining area geological model, and a geological analysis report is generated.

[0057] The convolutional neural network model is used as the basic model; Input layer inputs historical ore body geological characteristic map; The convolution layer uses convolution operations to extract spatial features; The pooling layer reduces the dimensionality of spatial features through the maximum pooling operation; The fully connected layer connects the extracted features of the convolution and pooling layers, mapping the spatial features extracted in the deep layer to the prediction task; Combined with the multi-layer perceptron model, the fully connected layer output is received through the input layer; The MLP layer inputs the output of the fully connected layer into the single-layer MLP for further feature combination and transformation; The output layer outputs the final result; Finally, a geological model of the mining area is obtained.

[0058] It should be noted that compared with existing technologies, the mining area geological model constructed based on convolutional neural networks (CNN) and support vector machines (SVM) can process more complex geological data patterns, and automatically extract deep spatial features through CNN, solving the problem of insufficient feature extraction in traditional methods; at the same time, combined with SVM, high-dimensional data can be accurately classified and regressed to improve the accuracy of prediction. The mining area geological model can not only identify the geometric shape and crack distribution of the ore body, but also evaluate the impact of groundwater flow on mining, thereby providing more comprehensive and accurate risk assessment and mining strategy recommendations, significantly improving the depth and breadth of mining area geological analysis, and providing strong technical support for efficient and safe ore mining.

[0059] The geological characteristic map of the ore body is input into the geological model of the mining area to obtain the ore body stability assessment value.

[0060] It should be explained that the ore body stability assessment value is obtained, and the specific expression is: ; in, is the ore body stability assessment value, It is the feature extraction operation of the convolutional neural network model. It is a further transformation of the convolutional features by the multi-layer perceptron. is the classification result of the final feature by the SVM model, It is the geological characteristic map of the ore body. is the weight coefficient of the feature extracted in the convolution layer, is the weight coefficient of the dimensionality reduction operation in the pooling layer, is the combined weight coefficient of each feature in the fully connected layer, It is a function used in the convolutional neural network model to extract spatial features of input data. It is a function in the multi-layer perceptron used to further combine and transform the features extracted by the convolutional layer. It is a function in the support vector machine model used to perform the final classification on the features processed by the multi-layer perceptron.

[0061] Taking the ore body stability assessment value as the basic indicator, combined with the geometric shape of the ore body, crack distribution and groundwater flow, a multi-factor analysis method is used to analyze and obtain the comprehensive stability risk of the ore body.

[0062] It should be explained that first, the geometric shape, crack distribution and groundwater flow of the ore body are determined through geological exploration data; then, a multi-factor analysis method is used to comprehensively consider the impact on the stability of the ore body. For example, the complexity of the geometric shape may increase the difficulty of mining, the crack distribution indicates potential structural weaknesses, and groundwater flow may aggravate the internal erosion of the ore body or trigger the risk of landslides; then, statistical analysis or numerical simulation technology is used to quantify the contribution of each factor to the stability of the ore body, and finally a comprehensive stability risk of the ore body under the influence of various geological conditions is obtained.

[0063] Collect data on other geological features through remote sensing technology.

[0064] It should be explained that surface images and reflectance data of the mining area are obtained using sensors carried by satellites or aircraft (such as multispectral scanners, radars, etc.); then, image processing technology is used to correct, enhance and classify them to extract other geological feature data, for example, identifying surface vegetation cover to infer groundwater levels or soil moisture, analyzing the spectral characteristics of rocks and minerals to determine their types and distribution, monitoring surface deformation to assess potential geological disaster risks, or observing terrain changes to understand erosion and sedimentation patterns.

[0065] Data visualization technology is used to integrate the ore body stability assessment value and other geological characteristic data and display them visually.

[0066] It should be explained that first, the various types of collected data (such as the geometry of the ore body, fracture distribution, groundwater flow path, etc.) are standardized to ensure that they can be effectively displayed on the same platform; then, they are superimposed together using professional geographic information system (GIS) software or advanced visualization tools, and the spatial distribution of ore body stability assessment values ​​and other geological characteristics are intuitively presented through color coding, contour lines, three-dimensional models, etc.; finally, interactive charts and maps are created so that users can explore the relationship between different geological parameters and their impact on ore body stability through simple operations.

[0067] Generate geological analysis reports based on comprehensive ore body stability risks and visualization results.

[0068] It should be stated that first, all relevant geological data and analysis results are summarized, including the geometry of the ore body, fracture distribution, groundwater flow path and their impact on the stability of the ore body; then, this information is combined with the comprehensive stability risk value derived from the risk assessment model to conduct detailed interpretation and discussion to identify potential risk areas and key influencing factors; then, the data analysis results are presented through visualization tools such as charts, images and three-dimensional models to make complex information easy to understand; finally, a geological analysis report is written.

[0069] S5. Through the Bayesian updating method, the geological characteristic map of the ore body and the geological analysis report are integrated to obtain the geomechanical map.

[0070] Topological indicators are extracted from the geological characteristic map of the ore body.

[0071] Based on the historical geological analysis report, the joint probability distribution of each topological indicator is statistically analyzed to obtain the prior probability value.

[0072] It should be explained that the data of various topological indicators (such as node degree, clustering coefficient, etc.) are statistically collected, and then the joint probability distribution of various topological indicators is calculated to quantify the possibility of interaction between different indicators; the specific process includes collating relevant data from multiple historical reports, determining the value range and frequency of occurrence of each topological indicator, and then analyzing the correlation or independence between the topological indicators. Through this series of steps, the prior probability value is calculated for each topological indicator combination.

[0073] Through data analysis and numerical conversion methods, mechanical parameters are extracted from geological analysis reports and normalized.

[0074] It should be explained that the parameters related to geomechanics in the report, such as elastic modulus and Poisson's ratio, are first identified and extracted; then, these extracted geomechanics-related parameters are cleaned and formatted to ensure the consistency and accuracy of the data; then, normalization processing techniques are applied to convert mechanical parameters of different scales or magnitudes into a common standard range (for example, between 0 and 1).

[0075] The normalized mechanical parameters in the geomechanical analysis report are converted into observed data, and the likelihood function is constructed.

[0076] It should be explained that first, specific observation indicators related to mechanical parameters and geological conditions, such as formation pressure and rock strength, are identified, and their values ​​are mapped to actual physical observations or experimental test results. Then, based on these observation indicators and known probability distribution models (such as normal distribution, Poisson distribution, etc.), a likelihood function is constructed. This function quantifies the probability of observing the current geological state under given mechanical parameter conditions.

[0077] Based on the prior probability and the likelihood function, the posterior probability is calculated.

[0078] It should be noted that Bayes' theorem is first used to combine prior probabilities with likelihood functions. The specific process is as follows: for a given mechanical parameter, its prior probability distribution is first determined based on historical data, representing the probability estimate of the mechanical parameter before new observations are available. Then, a likelihood function is constructed using the current observations, reflecting the likelihood of observing these observations under specific parameter conditions. Finally, the Bayesian formula is applied to calculate the posterior probability.

[0079] The posterior probability is mapped to the three-dimensional spatial coordinates of the ore body geological characteristic map. Based on the spatial position of each node and the corresponding posterior probability value, a discrete probability density distribution map is generated. The discrete probability values ​​are spatially interpolated using the Kriging interpolation technique to construct a continuous geomechanical map.

[0080] It should be explained that first, a discrete probability density distribution map is generated based on the spatial position of each node and its corresponding posterior probability value. The map shows the probability distribution of mechanical parameters in different regions. Then, the Kriging interpolation technique is used to spatially interpolate these discrete probability values. By considering the positional relationship between nodes and the weights of known data points, the probability values ​​of unsampled points are predicted, thereby constructing a continuous geomechanical map.

[0081] S6. Through data fusion technology and real-time analysis algorithms, the geomechanical map is combined with the real-time monitoring data of the mining area to analyze the risk factors of ore mining, and the ore mining strategy is dynamically adjusted to generate optimized ore mining instructions.

[0082] Real-time monitoring data of the mining area is collected through mining equipment sensors.

[0083] It should be noted that real-time monitoring data of the mining area includes key information in many aspects, such as geological conditions (rock hardness, ore body stability), environmental parameters (temperature, humidity, air quality and groundwater level), equipment status (vibration, wear degree, operating efficiency) and safety indicators (ground pressure changes, slope stability, gas concentration).

[0084] The time synchronization algorithm and inverse distance weighted interpolation method are used to synchronize the real-time monitoring data of the mining area in time and align them in space.

[0085] It should be explained that first, the data collection time from different sensors is calibrated through the time synchronization algorithm to ensure that all data are aligned on the time axis and eliminate the errors caused by the difference in collection time; then, the inverse distance weighted (IDW) interpolation method is applied for spatial alignment. According to the location of the known monitoring points and their recorded data values, the data values ​​of the locations that are not directly monitored are estimated. The specific method is to give higher weights to points with closer distances, so that the data distribution in space is more continuous and smooth.

[0086] Through spatial hash table and nearest neighbor matching algorithm, the real-time monitoring data of the mining area are mapped to the corresponding spatial position of the geomechanical map to extract the risk factors of ore mining.

[0087] It should be noted that, first, a spatial hash table is used to quickly index the real-time monitoring data from the mining area into the corresponding three-dimensional spatial grid, thus achieving spatial localization of the real-time monitoring data in the mining area. Next, a nearest neighbor matching algorithm is applied to find the closest node or region on the geomechanical map to each monitoring point, accurately mapping the real-time monitoring data to the corresponding spatial location on the geomechanical map. Based on this, risk factors related to ore mining, such as ground pressure changes, structural instability, and groundwater activity, are extracted.

[0088] Through fuzzy logic, quantitative analysis of various ore mining risk factors is carried out to obtain the current mining risk value of the mining area and adjust the ore mining strategy in real time.

[0089] It should be explained that first, a series of fuzzy sets and membership functions are defined to describe the different states of risk factors such as ground pressure, structural stability, and groundwater activity; then, the complex relationship between these risk factors is processed using fuzzy logic rules, and real-time monitoring data is input into the fuzzy reasoning system to calculate a comprehensive current mining risk value of the mining area. Based on the current mining risk value of the mining area, the safety level of the current mining conditions is evaluated, and the ore mining strategy is adjusted in real time accordingly, such as changing the mining sequence, strengthening support measures, or suspending operations to avoid potential dangers.

[0090] Based on the adjusted ore mining strategy, optimized ore mining instructions are generated through the rule engine and issued through the MQTT protocol.

[0091] It should be noted that the key parameters and objectives of the mining strategy (such as reducing risk and improving efficiency) are first converted into specific logical rules. Next, the rules engine automatically derives the optimal set of operational instructions based on current geological conditions, equipment status, and real-time monitoring data. These instructions include, but are not limited to, adjusting equipment operating parameters, planning mining paths, and implementing safety measures. Finally, the rules engine outputs detailed optimized mining instructions, which are distributed in real time to various mining equipment and control systems at the mine site using the efficient communication capabilities of the MQTT protocol.

[0092] This embodiment also provides an intelligent ore mining control system based on machine learning, comprising: a data acquisition module, a data analysis module, a report generation module, a data fusion module, and a mining strategy adjustment module; Data acquisition module, used to collect mining area geological environment data and perform preprocessing to obtain high-quality mining area data; The data analysis module is used to convert high-quality mining area data into nodes and edges in a graph database through spatial correlation analysis methods. It also uses complex network analysis techniques to calculate the topological indicators between nodes in the graph database, identify ore body boundaries, fracture location information, and groundwater flow paths, and obtain ore body geological characteristic maps; The report generation module is used to construct a mining area geological model based on the convolutional neural network model and the support vector machine model, input the ore body geological characteristic map into the mining area geological model, and generate a geological analysis report; The data fusion module is used to fuse the ore body geological characteristic map and geological analysis report through the Bayesian updating method to obtain the geomechanical map; The mining strategy adjustment module is used to combine the geomechanical map with the real-time monitoring data of the mining area through data fusion technology and real-time analysis algorithms, analyze the risk factors of ore mining, and dynamically adjust the ore mining strategy to generate optimized ore mining instructions.

[0093] This embodiment also provides a computer device, which is suitable for the case of an intelligent ore mining control method based on machine learning, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the intelligent ore mining control method based on machine learning proposed in the above embodiment.

[0094] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0095] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for intelligent ore mining control based on machine learning as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0096] In summary, the present invention converts the geological environment data of the mining area into high-quality graph database nodes and edges, uses complex network analysis technology to identify key geological features, combines the convolutional neural network model and the support vector machine model to construct a mining area geological model to generate a geological analysis report, and then uses the Bayesian update method to fuse the ore body geological characteristic map and the geological analysis report to obtain a geomechanical map. Finally, real-time monitoring data is used to analyze mining risks and dynamically adjust mining strategies, which significantly improves the efficiency, safety and scientific decision-making ability of ore mining, reduces resource waste and mining risks, and optimizes mining strategies to achieve higher economic benefits and extend the service life of mines.

[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A machine learning-based intelligent ore mining control method, characterized by: include, Collect mining area geological environment data and pre-process it to obtain high-quality mining area data; Using spatial correlation analysis methods, high-quality mining area data is converted into nodes and edges in a graph database. Complex network analysis techniques are then used to calculate the topological indicators between nodes in the graph database, identifying ore body boundaries, fracture location information, and groundwater flow paths to obtain a geological feature map of the ore body. Based on the convolutional neural network model and the support vector machine model, a mining area geological model is constructed, the geological characteristic map of the ore body is input into the mining area geological model, and a geological analysis report is generated; By using the Bayesian updating method, the geological characteristic map of the ore body and the geological analysis report are integrated to obtain the geomechanical map; Through data fusion technology and real-time analysis algorithms, the geomechanical map is combined with the real-time monitoring data of the mining area to analyze the risk factors of ore mining, and the ore mining strategy is dynamically adjusted to generate optimized ore mining instructions.

2. The method for intelligent ore mining control based on machine learning according to claim 1, characterized in that: The mining area geological environment data is collected and pre-processed to obtain high-quality mining area data. The specific steps are as follows: The mining area geological environment data includes the mining area geological structure, ore body distribution and mining area environmental conditions; Through data integrity check, hash algorithm and Z-score, the geological environment data of the mining area is identified, incomplete, duplicate and abnormal records are removed, and K-means is used to identify and remove interference data to obtain high-quality mining area data.

3. The machine learning-based intelligent mining control method for ore according to claim 2, characterized in that: The spatial association analysis method is used to convert high-quality mining area data into nodes and edges in a graph database. The specific steps are as follows: Convert high-quality mining area data into three-dimensional spatial coordinates through spatial interpolation technology; Extract the geological structure data of the mining area through spatial analysis tools, and map each mineral layer into a node according to the three-dimensional spatial coordinates; Based on the ore body distribution data, the spatial distribution of the ore body is obtained through remote sensing technology, and each ore body is mapped as an independent node; Through spatial analysis methods, mining area environmental condition data is extracted and mapped into independent nodes in the graph database; Through spatial data analysis methods, the spatial distance, relative position and potential physical contact between nodes are analyzed, and these spatial relationships are converted into edges in the graph database.

4. The method for intelligent ore mining control based on machine learning according to claim 3, characterized in that: The above mentioned method calculates the topological indicators between nodes in the graph database through complex network analysis technology, identifies the ore body boundary, crack location information and groundwater flow path, and obtains the ore body geological characteristic map. The specific steps are as follows: Connect each node to other nodes through edges to form a graph structure; Represent the connection relationship between each pair of nodes in the graph in the form of a matrix and construct an adjacency matrix; Traverse each node and adjacent nodes in the graph through the adjacency matrix, calculate the number of connections between the node and other nodes, and obtain the node degree; Through graph structure analysis and topology algorithms, the connection status between each node and its neighboring nodes is analyzed to obtain the clustering coefficient; The shortest path is gradually expanded through the Dijkstra algorithm to calculate the shortest distance from the starting node to all other nodes; Based on the clustering coefficient and node degree, the DBSCAN algorithm is used to identify the areas with dense relative relationships between ore bodies and obtain the ore body boundaries; Based on the shortest path, identify the distance mutation between the ore body node and mark the crack location information; Through the shortest path analysis, the potential channels of groundwater flow are revealed, and the density of water flow at the nodes is revealed by combining the clustering coefficient, the main channels of groundwater flow are identified, and the groundwater flow path is obtained; Based on the ore body boundary, fracture location information and groundwater flow path, through spatial analysis and topological relationships, the geometric shape of the ore body, the distribution of fractures and the impact of groundwater flow on mining are extracted, and finally the geological characteristic map of the ore body is obtained.

5. The method for intelligent ore mining control based on machine learning according to claim 4, characterized in that: The method is based on the convolutional neural network model and the support vector machine model to construct a mining area geological model, input the ore body geological characteristic map into the mining area geological model, and generate a geological analysis report. The specific steps are as follows: The convolutional neural network model is used as the basic model; Input layer inputs historical ore body geological characteristic map; The convolution layer uses convolution operations to extract spatial features; The pooling layer reduces the dimensionality of spatial features through the maximum pooling operation; The fully connected layer connects the extracted features of the convolution and pooling layers, mapping the spatial features extracted in the deep layer to the prediction task; Combined with the multi-layer perceptron model, the fully connected layer output is received through the input layer; The MLP layer inputs the output of the fully connected layer into the single-layer MLP for further feature combination and transformation; The output layer outputs the final result; Finally, a geological model of the mining area is obtained; Input the geological characteristic map of the ore body into the geological model of the mining area to obtain the ore body stability assessment value; Taking the ore body stability assessment value as the basic indicator, combined with the ore body's geometric shape, fracture distribution and groundwater flow, a multi-factor analysis method is used to analyze and derive the comprehensive stability risk of the ore body; Collect data on other geological features through remote sensing techniques; Using data visualization technology, the ore body stability assessment value and other geological characteristic data are integrated and visualized; Generate geological analysis reports based on comprehensive ore body stability risks and visualization results.

6. The method for intelligent ore mining control based on machine learning according to claim 5, characterized in that: The Bayesian update method is used to fuse the geological characteristic map of the ore body and the geological analysis report to obtain the geomechanical map. The specific steps are as follows: Extract topological indicators from the geological characteristic map of the ore body; Based on the historical geological analysis report, the joint probability distribution of each topological indicator is statistically analyzed to obtain the prior probability value; Through data analysis and numerical conversion methods, mechanical parameters are extracted from geological analysis reports and normalized; Convert the normalized mechanical parameters in the geomechanical analysis report into observation data and construct a likelihood function; Calculate the posterior probability based on the prior probability and likelihood function; The posterior probability is mapped to the three-dimensional spatial coordinates of the ore body geological characteristic map. Based on the spatial position of each node and the corresponding posterior probability value, a discrete probability density distribution map is generated. The discrete probability values ​​are spatially interpolated using the Kriging interpolation technique to construct a continuous geomechanical map.

7. The method for intelligent ore mining control based on machine learning according to claim 6, characterized in that: The data fusion technology and real-time analysis algorithm are used to combine the geomechanical map with the real-time monitoring data of the mining area to analyze the risk factors of ore mining, and dynamically adjust the ore mining strategy to generate optimized ore mining instructions. The specific steps are as follows: Collect real-time monitoring data of the mining area through mining equipment sensors; Using the time synchronization algorithm and inverse distance weighted interpolation method, the real-time monitoring data of the mining area are synchronized in time and aligned in space; Using spatial hash tables and nearest neighbor matching algorithms, real-time monitoring data from the mining area is mapped to the corresponding spatial locations on the geomechanical map to extract ore mining risk factors. Quantitatively analyze various ore mining risk factors through fuzzy logic to obtain the current mining risk value of the mining area and adjust the ore mining strategy in real time; Based on the adjusted ore mining strategy, optimized ore mining instructions are generated through the rule engine and issued through the MQTT protocol.

8. A machine learning-based intelligent ore mining control system, based on the machine learning-based intelligent ore mining control method according to any one of claims 1 to 7, characterized in that: Including data acquisition module, data analysis module, report generation module, data fusion module and mining strategy adjustment module; Data acquisition module, used to collect mining area geological environment data and perform preprocessing to obtain high-quality mining area data; The data analysis module is used to convert high-quality mining area data into nodes and edges in a graph database through spatial correlation analysis methods. It also uses complex network analysis techniques to calculate the topological indicators between nodes in the graph database, identify ore body boundaries, fracture location information, and groundwater flow paths, and obtain ore body geological characteristic maps; The report generation module is used to construct a mining area geological model based on the convolutional neural network model and the support vector machine model, input the ore body geological characteristic map into the mining area geological model, and generate a geological analysis report; The data fusion module is used to fuse the ore body geological characteristic map and geological analysis report through the Bayesian updating method to obtain the geomechanical map; The mining strategy adjustment module is used to combine the geomechanical map with the real-time monitoring data of the mining area through data fusion technology and real-time analysis algorithms, analyze the risk factors of ore mining, and dynamically adjust the ore mining strategy to generate optimized ore mining instructions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the machine learning-based intelligent ore mining control method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the machine learning-based intelligent ore mining control method according to any one of claims 1 to 7 are implemented.

Images