Mining decision-making method and device based on geological guarantee information and electronic equipment

Abstract

The application discloses a mining decision-making method and device based on geological guarantee information and electronic equipment. According to the application, a complete three-dimensional geological entity model is built by integrating various types of geological information in the mining area, and various types of geological element space distributions such as strata, structures and hydrology are completely restored. In combination with real-time monitoring data, the risk evaluation basis is dynamically updated, and the defects of missing information of a single data source are made up. Therefore, the technical problems that the traditional mining geological risk analysis only relies on a single data source, the risk identification coverage is insufficient, and the evaluation result cannot be updated in real time following the field working conditions can be solved. The technical effects of completely mining the potential geological risks of the area, dynamically and accurately dividing the risk grades of the mining area, timely issuing an over-limit risk warning, improving the scientific nature of the mining operation scheme and the overall safety level of underground mining are achieved.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a mining decision-making method, apparatus and electronic equipment based on geological support information. Background Technology

[0002] Mining operations, as a core component of mineral resource development, are directly constrained by complex geological factors such as stratigraphic lithology, geological structure, hydrogeology, and gas occurrence. As mineral resource development advances into deeper and more complex geological areas, intelligent decision-making technologies based on multi-source geological information are becoming an industry trend.

[0003] Traditional methods rely on a single data source for risk analysis, resulting in incomplete geological risk identification and evaluation results that lag behind changes on-site. This affects the scientific validity and safety of mining plans and makes it difficult to meet the urgent need for high-precision, dynamic safety management in mining operations under complex geological conditions. Summary of the Invention

[0004] This disclosure provides a mining decision-making method, apparatus, and electronic equipment based on geological support information.

[0005] According to a first aspect of this disclosure, a mining decision-making method based on geological safeguard information is provided, comprising:

[0006] Collect multi-source geological support information of the mining area and preprocess the multi-source geological support information to obtain preprocessed geological data; Based on the preprocessed geological data, a full-element three-dimensional geological model of the mining area is constructed. Based on the aforementioned three-dimensional geological model, characteristic parameters of geological risk factors in the mining area are identified and extracted; The geological risk factor characteristic parameters are input into the risk dynamic evaluation model, and the risk level of the mining area is dynamically evaluated in combination with real-time monitoring data. An early warning is triggered when the risk level exceeds a preset threshold.

[0007] Optionally, the multi-source geological support information of the mining area is collected, and the multi-source geological support information is preprocessed to obtain preprocessed geological data, including: Collect at least one of the following multi-source geological support information: stratigraphic lithology, geological structure, hydrogeological conditions, gas occurrence, coal seam thickness and stability; The multi-source geological support information is subjected to data cleaning, data standardization, data fusion and alignment, and data compression and noise reduction in sequence. Data cleaning includes removing outliers and filling in missing values. Data standardization includes unifying data format and dimension conversion. Data fusion and alignment are performed based on a spatial coordinate system to obtain preprocessed geological data.

[0008] Optionally, constructing a full-element three-dimensional geological model of the mining area based on the preprocessed geological data includes: A three-dimensional stratigraphic framework model is constructed based on stratigraphic lithology data. Geological structure, hydrogeology, and gas occurrence data are associated with the three-dimensional stratigraphic framework model as attribute information. Spatial interpolation methods are used to supplement the information in the data gap areas. Based on machine learning algorithms, the fusion results of multi-source data are optimized and corrected to construct a full-element three-dimensional geological model with dynamic updating function. Based on the three-dimensional geological model, combined with an expert experience knowledge base and machine learning algorithms, at least one key geological risk factor is automatically identified, including fault fracture zones, water-rich areas, gas-rich areas, weak interlayers, and coal seam thickness abrupt change zones. Each risk factor undergoes feature extraction to obtain its spatial location, size, development level, and dynamic change trend. These features are then classified, coded, and prioritized to obtain the geological risk factor characteristic parameters.

[0009] Optionally, the step of inputting the geological risk factor characteristic parameters into the dynamic risk assessment model, combining real-time monitoring data to dynamically assess the risk level of the mining area, and triggering an early warning when the risk level exceeds a preset threshold includes: A dynamic geological risk assessment model based on an improved deep learning algorithm is constructed. The geological risk factor feature parameters are used as input, and a training sample set is constructed by combining historical accident case data and field monitoring data for model training. The subjective weights of each risk factor are determined by the analytic hierarchy process (AHP) and the objective weights of each risk factor are determined by the entropy weight method. The subjective and objective weights are then combined and weighted to achieve dynamic adjustment of the influence weights of risk factors. The system dynamically updates the risk level by accessing downhole monitoring data in real time. When the risk level exceeds a preset threshold, an early warning mechanism is automatically triggered, and the warning level and the location of the corresponding risk source are clearly identified.

[0010] Optionally, the method may also include: Based on the three-dimensional geological model and risk assessment results, combined with production capacity requirements, technical conditions and economic cost constraints, a variety of differentiated mining schemes are automatically generated through intelligent algorithms; Numerical simulation technology is used to simulate and extrapolate various schemes to obtain evaluation indicators such as safety factor, engineering difficulty, cost consumption and construction period. Based on the risk distribution characteristics of the optimal solution, at least one safety assurance measure is matched, including support parameter optimization, water control engineering layout, gas extraction scheme design, and emergency rescue plan formulation.

[0011] Optionally, the method further includes: The optimal mining scheme and safety measures are applied to the actual mining operation. The geological conditions, engineering implementation effect and safety indicators are continuously and dynamically monitored throughout the mining operation through a deployed real-time monitoring system. The real-time monitoring system includes at least one of the following: a surrounding rock displacement monitor, a gas sensor, a hydrological monitoring station and a stress sensor. The monitoring data is fed back to the intelligent decision-making platform in real time and compared with the simulation data of the plan. If deviations occur or new geological risks are detected, the mining plan and / or safety measures are adjusted and corrected.

[0012] According to a second aspect of this disclosure, a mining decision-making device based on geological safeguard information is provided, comprising: The data acquisition and preprocessing unit is used to acquire multi-source geological support information of the mining area and preprocess the multi-source geological support information to obtain preprocessed geological data. The three-dimensional modeling unit is used to construct a full-element three-dimensional geological model of the mining area based on the preprocessed geological data. The feature extraction unit is used to identify and extract geological risk factor feature parameters of the mining area based on the three-dimensional geological model; The risk assessment and early warning unit is used to input the geological risk factor characteristic parameters into the risk dynamic assessment model, combine real-time monitoring data to dynamically assess the risk level of the mining area, and trigger an early warning when the risk level exceeds a preset threshold.

[0013] Optionally, the acquisition preprocessing unit is further used for: Collect at least one of the following multi-source geological support information: stratigraphic lithology, geological structure, hydrogeological conditions, gas occurrence, coal seam thickness and stability; The multi-source geological support information is subjected to data cleaning, data standardization, data fusion and alignment, and data compression and noise reduction in sequence. Data cleaning includes removing outliers and filling in missing values. Data standardization includes unifying data format and dimension conversion. Data fusion and alignment are performed based on a spatial coordinate system to obtain preprocessed geological data.

[0014] Optionally, the 3D modeling unit is also used for: A three-dimensional stratigraphic framework model is constructed based on stratigraphic lithology data. Geological structure, hydrogeology, and gas occurrence data are associated with the three-dimensional stratigraphic framework model as attribute information. Spatial interpolation methods are used to supplement the information in the data gap areas. Based on machine learning algorithms, the fusion results of multi-source data are optimized and corrected to construct a full-element three-dimensional geological model with dynamic updating function. Based on the three-dimensional geological model, combined with an expert experience knowledge base and machine learning algorithms, at least one key geological risk factor is automatically identified, including fault fracture zones, water-rich areas, gas-rich areas, weak interlayers, and coal seam thickness abrupt change zones. Each risk factor undergoes feature extraction to obtain its spatial location, size, development level, and dynamic change trend. These features are then classified, coded, and prioritized to obtain the geological risk factor characteristic parameters.

[0015] Optionally, the risk assessment and early warning unit is further used for: A dynamic geological risk assessment model based on an improved deep learning algorithm is constructed. The geological risk factor feature parameters are used as input, and a training sample set is constructed by combining historical accident case data and field monitoring data for model training. The subjective weights of each risk factor are determined by the analytic hierarchy process (AHP) and the objective weights of each risk factor are determined by the entropy weight method. The subjective and objective weights are then combined and weighted to achieve dynamic adjustment of the influence weights of risk factors. The system dynamically updates the risk level by accessing downhole monitoring data in real time. When the risk level exceeds a preset threshold, an early warning mechanism is automatically triggered, and the warning level and the location of the corresponding risk source are clearly identified.

[0016] Optionally, it also includes a scheme generation and deduction unit, which is used for: Based on the three-dimensional geological model and risk assessment results, combined with production capacity requirements, technical conditions and economic cost constraints, a variety of differentiated mining schemes are automatically generated through intelligent algorithms; Numerical simulation technology is used to simulate and extrapolate various schemes to obtain evaluation indicators such as safety factor, engineering difficulty, cost consumption and construction period. Based on the risk distribution characteristics of the optimal solution, at least one safety assurance measure is matched, including support parameter optimization, water control engineering layout, gas extraction scheme design, and emergency rescue plan formulation.

[0017] Optionally, it also includes a dynamic monitoring and correction unit, which is used for: The optimal mining scheme and safety measures are applied to the actual mining operation. The geological conditions, engineering implementation effect and safety indicators are continuously and dynamically monitored throughout the mining operation through a deployed real-time monitoring system. The real-time monitoring system includes at least one of the following: a surrounding rock displacement monitor, a gas sensor, a hydrological monitoring station and a stress sensor. The monitoring data is fed back to the intelligent decision-making platform in real time and compared with the simulation data of the plan. If deviations occur or new geological risks are detected, the mining plan and / or safety measures are adjusted and corrected.

[0018] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0021] The mining decision-making method, apparatus, and electronic equipment disclosed herein, based on geological assurance information, integrate multiple types of geological information from the mining area to build a complete three-dimensional geological entity model, fully restoring the spatial distribution of various geological elements such as strata, structures, and hydrology. Combined with real-time on-site monitoring data, the risk assessment criteria are dynamically updated, compensating for the deficiencies of information lacking from a single data source. Therefore, it can solve the technical problems of traditional mining geological risk analysis relying solely on a single data source, resulting in insufficient risk identification coverage and evaluation results that cannot be updated in real-time with on-site conditions. This achieves the technical effects of fully excavating potential geological risks in the area, dynamically and accurately classifying the risk level of the mining area, issuing timely warnings of exceeding risk limits, and improving the scientific nature of mining operation plans and the overall safety level of underground mining.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A schematic flowchart illustrating a mining decision-making method based on geological support information provided in an embodiment of this disclosure; Figure 2 A schematic diagram of a mining decision-making device based on geological support information provided in this embodiment of the present disclosure; Figure 3 A schematic diagram of another mining decision-making device based on geological support information provided in this embodiment of the present disclosure; Figure 4A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0024] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] The following description, with reference to the accompanying drawings, outlines a mining decision-making method, apparatus, and electronic device based on geological support information, representing embodiments of this disclosure.

[0026] Figure 1 This is a flowchart illustrating a mining decision-making method based on geological support information, provided in an embodiment of this disclosure.

[0027] like Figure 1 As shown, the method includes the following steps: Step 101: Collect multi-source geological support information of the mining area and preprocess the multi-source geological support information to obtain preprocessed geological data; Multi-source geological support information covers data on various geological factors affecting operational safety within the mining area, including but not limited to stratigraphic lithology information, geological structure information, hydrogeological parameters, gas occurrence status, and coal seam characteristic data. Acquisition methods can include surface exploration, underground detection, remote sensing interpretation, and retrieval of existing geological data. The preprocessing operation aims to eliminate problems such as format differences, inconsistencies in units, spatial location deviations, and noise interference between data from different sources. Specifically, this includes the removal of outlier data and the completion of missing data, standardization of data formats and units of measurement, alignment and fusion of multi-source data based on a unified spatial coordinate system, and data compression and noise reduction operations, thereby ensuring that the quality of the preprocessed geological data meets the accuracy requirements of subsequent technical stages.

[0028] In one implementation, core data including geological structures such as stratigraphic lithology, fault folds and joints, hydrogeological conditions such as aquifer distribution and water pressure, gas occurrence and coal seam thickness stability can be collected through geological exploration borehole sampling, real-time recording of roadway exposure data, underground geophysical exploration (such as transient electromagnetic method and ground-penetrating radar method), remote sensing image interpretation and retrieval of existing geological data. After data cleaning, standardization, fusion alignment and compression and noise reduction, a high-quality geological dataset is obtained.

[0029] Step 102: Based on the preprocessed geological data, construct a full-element three-dimensional geological model of the mining area; Using stratigraphic and lithological data as the basic framework, other geological element data are spatially correlated and integrated with the stratigraphic framework in the form of attribute information. This enables the constructed 3D geological model to comprehensively reflect multi-dimensional geological information within the target area, including stratigraphic structure, geological structure, hydrogeological conditions, and gas occurrence. During the modeling process, for areas where sampling points may be sparse or spatially insufficient in the original geological data, spatial interpolation algorithms are used to extrapolate and supplement the geological attributes of the missing areas. At the same time, data fusion algorithms are used to optimize and correct the integrated results of multi-source data, eliminating potential information redundancy and conflicts between different data sources, thereby ensuring the overall accuracy and internal consistency of the model.

[0030] The constructed full-element 3D geological model supports the independent presentation of individual geological elements and the overlay analysis of multiple elements. It also possesses the ability to dynamically correct and update model parameters based on newly added geological survey data, ensuring the model consistently maintains an accurate representation of actual geological conditions. For example, in one implementation, a 3D stratigraphic framework model can be constructed first using stratigraphic and lithological data. Then, data on geological structures, hydrogeology, and gas occurrence can be correlated into this framework. Spatial interpolation methods such as Kriging interpolation or radial basis functions can be used to fill in data gaps. Furthermore, machine learning fusion algorithms can be combined to optimize and correct the integrated results of multi-source data, ultimately forming a dynamically updated full-element 3D geological model.

[0031] Step 103: Identify and extract the geological risk factor characteristic parameters of the mining area based on the three-dimensional geological model; By constructing a risk factor identification system covering multiple types of geological hazards, and based on multi-dimensional geological information such as stratigraphic structure, tectonic development, hydrological conditions, and gas occurrence represented by a three-dimensional geological model, and by comprehensively utilizing an expert experience knowledge base and machine learning algorithms, key geological risk sources that may cause safety accidents in mining areas are identified and located.

[0032] After identifying risk factors, core feature parameters such as spatial distribution, size, development level, and dynamic change trend of each risk factor are further extracted. Based on the degree of impact of each risk factor on mining safety, they are classified, coded, and prioritized. At the same time, the impact weight of each risk factor is initially assigned, thus forming a structured set of risk factor feature parameters, which provides standardized input data for subsequent risk dynamic assessment models based on intelligent algorithms.

[0033] In one implementation, an expert knowledge base and machine learning algorithms can be combined to automatically identify key geological risk factors in the mining area, such as fault fracture zones, water-rich areas, gas-rich areas, weak interlayers, and coal seam thickness abrupt change zones. Characteristic parameters such as their spatial location, scale, development degree, and change trend can be extracted, and they can be classified, coded, prioritized, and initially assigned influence weights.

[0034] Step 104: Input the geological risk factor characteristic parameters into the risk dynamic evaluation model, combine real-time monitoring data to dynamically evaluate the risk level of the mining area, and trigger an early warning when the risk level exceeds a preset threshold.

[0035] The aforementioned dynamic risk assessment model constructs a training sample set using historical mining safety accident case data and on-site monitoring data. After training and optimization, it can quantitatively assess the safety situation of the mining area based on the input risk factor characteristic parameters. During the assessment process, the influence weights of each risk factor are dynamically adjusted by integrating subjective and objective weighting methods to ensure that the weight allocation reflects both the professional judgment of domain experts and the statistical characteristics of the data itself, thereby improving the rationality and adaptability of the assessment results. Simultaneously, the assessment model accesses real-time on-site monitoring data such as underground surrounding rock stress, gas concentration, and water inflow, continuously updating the risk level based on real-time data. When the assessed risk level exceeds the system's preset safety threshold, an early warning is automatically triggered, clearly indicating the warning level and the corresponding spatial location of the risk source, providing timely safety alerts to operators.

[0036] In one implementation, a risk dynamic assessment model based on an improved deep learning algorithm can be constructed. The risk factor weights are dynamically corrected by combining the analytic hierarchy process (AHP) and the entropy weight method. Real-time access to downhole monitoring data enables dynamic updates and automatic early warnings of risk levels.

[0037] In some embodiments, the collection of multi-source geological support information of the mining area and the preprocessing of the multi-source geological support information to obtain preprocessed geological data include: Collect at least one of the following multi-source geological support information: stratigraphic lithology, geological structure, hydrogeological conditions, gas occurrence, coal seam thickness and stability; The multi-source geological support information is subjected to data cleaning, data standardization, data fusion and alignment, and data compression and noise reduction in sequence. Data cleaning includes removing outliers and filling in missing values. Data standardization includes unifying data format and dimension conversion. Data fusion and alignment are performed based on a spatial coordinate system to obtain preprocessed geological data.

[0038] During the information collection phase, based on the geological characteristics and safety requirements of the mining operation area, comprehensive core geological information affecting mining safety is collected. This includes: stratigraphic lithology information, such as the rock type, lithological combination characteristics, and spatial distribution patterns of each stratum within the mining area; geological structural information, covering the location, attitude, and width of fault zones, the morphology, axial direction, and limb characteristics of folds, as well as the development density and direction of joints and fractures; hydrogeological conditions, including the spatial distribution range of aquifers, water pressure, water-bearing capacity, and their hydraulic connection with the mining strata; gas occurrence information, including gas content, gas pressure, gas emission, and its occurrence state; and coal seam thickness and stability information, including changes in coal seam thickness, bifurcation and merging characteristics, and pinch-out trends. The methods for collecting the above information may include sampling from geological exploration boreholes, real-time recording of tunnel exposure data, underground geophysical exploration (such as transient electromagnetic methods to detect water-bearing structures and ground-penetrating radar methods to detect faults and cavities), interpretation of remote sensing images to obtain surface geological features, and systematic retrieval and summarization of historical archives such as existing geological exploration reports and mine geological data.

[0039] In the preprocessing stage, the first step is data cleaning. Outliers in the raw data (such as measurement readings significantly deviating from the normal range or incorrectly recorded data) are identified and removed. Missing values ​​caused by blind spots or instrument malfunctions are filled using interpolation or neighboring data references to ensure data integrity. Next, data standardization is performed, converting raw data from different acquisition methods and instruments into a unified data format and standardizing physical units to eliminate incomparability caused by inconsistent units of measurement. Then, data fusion and alignment are performed, projecting geological data from various sources onto the same coordinate frame using a unified spatial coordinate system to ensure accurate matching and overlay of information representing the same spatial location from different data sources. Finally, data compression and noise reduction are performed to remove redundant information and random noise interference from the raw data, further improving the signal-to-noise ratio. After these four sequential preprocessing steps, preprocessed geological data with completeness, consistency, and accuracy are obtained and can be directly used for subsequent 3D geological model construction.

[0040] In some embodiments, constructing a full-element three-dimensional geological model of the mining area based on the preprocessed geological data includes: A three-dimensional stratigraphic framework model is constructed based on stratigraphic lithology data. Geological structure, hydrogeology, and gas occurrence data are associated with the three-dimensional stratigraphic framework model as attribute information. Spatial interpolation methods are used to supplement the information in the data gap areas. Based on machine learning algorithms, the fusion results of multi-source data are optimized and corrected to construct a full-element three-dimensional geological model with dynamic updating function. Based on the three-dimensional geological model, combined with an expert experience knowledge base and machine learning algorithms, at least one key geological risk factor is automatically identified, including fault fracture zones, water-rich areas, gas-rich areas, weak interlayers, and coal seam thickness abrupt change zones. Each risk factor undergoes feature extraction to obtain its spatial location, size, development level, and dynamic change trend. These features are then classified, coded, and prioritized to obtain the geological risk factor characteristic parameters.

[0041] In the three-dimensional geological model construction stage, the preprocessed stratigraphic lithology data is used as the basic framework. Based on the lithological categories, sequence relationships, and spatial attitudes of each stratum, a three-dimensional stratigraphic framework model describing the vertical and lateral stratigraphic distribution characteristics of the mining area is constructed through layer-by-layer modeling. This framework model serves as the spatial carrier for subsequent multi-attribute geological data integration. On this basis, geological structural data (including fault attitude elements, fold geometric morphology parameters, and spatial distribution of joint and fracture networks) are embedded into the corresponding three-dimensional stratigraphic framework as geometric entities or attribute fields. Hydrogeological data (including aquifer distribution boundaries, permeability coefficient fields, and hydraulic pressure distribution) are superimposed onto the corresponding stratigraphic units as attribute fields or rasterized attribute layers. Similarly, gas occurrence data (including gas content distribution and gas pressure gradient) are associated with the three-dimensional framework of the coal seam and its adjacent strata as attribute fields, thus forming a multi-attribute integrated three-dimensional geological model. To address the data gaps caused by the uneven spatial distribution of original borehole and exploration data, spatial interpolation methods such as Kriging interpolation or radial basis functions are used to calculate the attribute values ​​of the gaps based on the geological attribute values ​​of known sampling points, thereby achieving continuous filling of the model space.

[0042] Based on machine learning algorithms, information redundancy and data conflicts that may occur during the fusion of the above multi-source data are optimized and corrected. By learning the reliability weights and mutual constraints of each data source, the algorithm automatically eliminates contradictory data and improves the accuracy of the fusion results. The final full-element three-dimensional geological model has a dynamic update function. When new geological exploration data is entered into the system, the model can correct the model parameters of the corresponding area in real time according to the new data, so as to maintain the model's continuous and accurate representation of the actual geological conditions. In the risk factor identification and feature extraction stage, based on the constructed three-dimensional geological model, the spatial distribution information of the geological attributes represented in the model is input into the risk factor identification module. This module comprehensively uses an expert experience knowledge base (which stores the correspondence rules between different types of geological hazards and their triggering geological conditions) and machine learning classification algorithms to automatically identify and locate areas in the model space that meet the risk triggering conditions. The identified key geological risk factors include at least one of the following: fault fracture zone (i.e., the rock mass fractured area formed on both sides of the fault due to tectonic stress), water-rich area (i.e., the area where the aquifer is highly water-rich or has a water-conducting channel), gas-rich area (i.e., the area where the gas content or gas pressure is significantly higher than the background value), weak interlayer (i.e., the thin rock mass in the strata with a significantly lower mechanical strength than the surrounding rocks above and below), and coal seam thickness abrupt change zone (i.e., the area where the coal seam thickness changes drastically over a short distance).

[0043] For the identified risk factors, core characteristic parameters such as spatial location coordinates (including precise distribution range in three-dimensional space), scale (including extension length, distribution area and influence depth), development degree (including quantitative indicators such as degree of fragmentation, water-bearing level, and gas concentration gradient) and dynamic change trend (including the time evolution law of each characteristic parameter as mining progresses) are further extracted. The risk factors are classified and coded according to their type and severity, and ranked according to the priority of their impact on mining safety. Finally, a structured set of geological risk factor characteristic parameters is formed, which serves as the input data for the subsequent dynamic risk assessment model.

[0044] Optionally, the step of inputting the geological risk factor characteristic parameters into the dynamic risk assessment model, combining real-time monitoring data to dynamically assess the risk level of the mining area, and triggering an early warning when the risk level exceeds a preset threshold includes: A dynamic geological risk assessment model based on an improved deep learning algorithm is constructed. The geological risk factor feature parameters are used as input, and a training sample set is constructed by combining historical accident case data and field monitoring data for model training. The subjective weights of each risk factor are determined by the analytic hierarchy process (AHP) and the objective weights of each risk factor are determined by the entropy weight method. The subjective and objective weights are then combined and weighted to achieve dynamic adjustment of the influence weights of risk factors. The system dynamically updates the risk level by accessing downhole monitoring data in real time. When the risk level exceeds a preset threshold, an early warning mechanism is automatically triggered, and the warning level and the location of the corresponding risk source are clearly identified.

[0045] In the risk dynamic assessment model construction stage, a geological risk dynamic assessment model is built based on an improved deep learning algorithm. This improved deep learning algorithm, compared to traditional deep learning networks, specifically optimizes the network structure and training strategy to address the characteristics of geological risk assessment, such as high dimensionality of sample data, complex inter-feature correlations, and strong nonlinearity of geological conditions. During model training, the geological risk factor feature parameters extracted in the preceding steps (including quantitative indicators such as the spatial location, scale, development level, and dynamic change trend of each risk factor) are used as model input features. Simultaneously, historical mining safety accident case data (including accident type, location, inducing geological conditions, and severity of accident consequences) and on-site monitoring data accumulated during previous mining operations are collected within the mining area. These data are labeled and aligned to construct a standardized training sample set, which is used for supervised training and iterative optimization of the risk dynamic assessment model. This enables the model to learn the mapping relationship between geological risk factor feature parameters and the probability and severity of safety accidents, thereby possessing the ability to output a quantitative risk level assessment value based on the input risk factor feature parameters.

[0046] In the dynamic adjustment stage of risk factor weights, a combined weighting strategy of subjective and objective weighting is adopted: First, the analytic hierarchy process (AHP) is used to construct a comparison judgment matrix based on the judgments of domain experts on the relative importance of each risk factor pairwise. After consistency testing, the subjective weights of each risk factor are calculated. Then, the entropy weight method is used to calculate the information entropy based on the data dispersion of the characteristic parameters of each risk factor in the training sample set, thereby determining the objective weights of each risk factor. The risk factor with greater data dispersion (i.e., higher discrimination) receives a higher objective weight. Finally, the subjective and objective weights are fused through linear weighting or other combinations to obtain the comprehensive impact weight of each risk factor. This comprehensive weight reflects both the experts' professional judgment on the geological risk formation mechanism and the actual discrimination ability of each factor under data-driven conditions. Furthermore, when the training sample set is updated due to new monitoring data or accident cases, the objective weights can be automatically recalculated as the data changes, realizing dynamic adjustment of the weights.

[0047] During the dynamic early warning phase, downhole monitoring data collected by real-time monitoring equipment deployed at the mining site, such as surrounding rock displacement monitors, gas sensors, hydrological monitoring stations, and stress sensors, is connected in real-time to the dynamic risk assessment model via a data interface. The model dynamically updates and calculates the current risk level based on the latest monitoring data. When the calculated risk level exceeds the system's pre-set safety threshold, the early warning mechanism is automatically triggered. The system clarifies the current early warning level according to the preset risk level classification standards (such as classifying it into general early warning, major early warning, and severe early warning levels). At the same time, it accurately locates and marks the corresponding risk source location based on the spatial location information in the risk factor characteristic parameters, providing timely and clear safety warning information for operators and managers.

[0048] In some embodiments, the method further includes: Based on the three-dimensional geological model and risk assessment results, combined with production capacity requirements, technical conditions and economic cost constraints, a variety of differentiated mining schemes are automatically generated through intelligent algorithms; Numerical simulation technology is used to simulate and extrapolate various schemes to obtain evaluation indicators such as safety factor, engineering difficulty, cost consumption and construction period. Based on the risk distribution characteristics of the optimal solution, at least one safety assurance measure is matched, including support parameter optimization, water control engineering layout, gas extraction scheme design, and emergency rescue plan formulation.

[0049] In the automatic generation stage of mining schemes, the constructed full-element three-dimensional geological model and the results of dynamic risk assessment are used as geological condition input constraints. At the same time, the production capacity demand of mining operations (i.e., the coal production or tunneling footage target that the mine or mining area needs to achieve within a certain period), technical conditions (i.e., the existing mining equipment level, ventilation capacity, hoisting and transportation capacity, and other technical support conditions of the mine), and economic cost constraints (i.e., the budget ceiling of mining projects, cost control targets per ton of coal, and other economic requirements) are comprehensively considered. The above multi-dimensional constraints are transformed into objective functions and constraint equations in the mathematical model. Through intelligent optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, or multi-objective evolutionary algorithms), a global search is performed in the feasible solution space defined by various constraints. Multiple mining schemes with differences in roadway layout, mining sequence arrangement, support form selection, ventilation system configuration, and water prevention and control measures are automatically generated, forming a multi-scenario mining engineering scheme generation library.

[0050] During the scheme simulation and deduction phase, numerical simulation technology is used to simulate and deduct the entire process of each mining scheme in the scheme generation library. Mechanical simulation calculations are performed on the redistribution of the surrounding rock stress field, the expansion range of the plastic zone, and the deformation and displacement of the surrounding rock during mining and excavation. Detailed simulation analysis is conducted on the block slippage, opening, and collapse behavior in areas cut by geological structures such as faults or joints. Through these numerical simulations, key quantitative evaluation indicators such as the surrounding rock stability safety factor, the technical difficulty level of engineering implementation, the comprehensive cost consumption of materials and labor, and the expected construction period from commencement to completion are obtained for each scheme at different mining advancement stages. In the optimal scheme selection and safety assurance measure matching phase, a multi-objective decision-making evaluation system is established, prioritizing safety and reliability while considering economic rationality and technical feasibility. The quantitative evaluation indicators obtained from the simulation and deduction of each scheme are comprehensively scored. The TOPSIS method (Approximation Ideal Solution Ranking Method) is used to calculate the relative closeness of each scheme to the positive and negative ideal solutions. Combined with expert review opinions, the schemes are comprehensively ranked, and the mining scheme with the best overall performance is selected.

[0051] For this optimal solution, the risk distribution characteristics revealed in its numerical simulation results are further analyzed, namely the location and type of risk concentration in each mining stage and spatial area during the implementation of the solution. Based on this, targeted safety assurance measures are matched from the perspective of risk prevention and control. Specifically, these measures include: optimizing support parameters in areas with insufficient surrounding rock stability (such as adjusting anchor bolt length, spacing, pre-tightening force, or increasing anchor cable reinforcement); arranging water control projects in areas threatened by aquifers (such as constructing drainage boreholes, building waterproof gate walls, or setting up grouting curtains); designing gas extraction schemes in gas-rich areas (such as constructing pre-extraction boreholes in the coal seam, pressure relief extraction boreholes in adjacent layers, or buried pipe extraction in goaf areas); and preparing emergency rescue plans for possible emergencies (such as specifying evacuation routes, locations of rescue material reserves, and emergency response procedures). Finally, a complete decision-making package of "optimal solution + specific safety measures" is formed.

[0052] In some embodiments, the method further includes: The optimal mining scheme and safety measures are applied to the actual mining operation. The geological conditions, engineering implementation effect and safety indicators are continuously and dynamically monitored throughout the mining operation through a deployed real-time monitoring system. The real-time monitoring system includes at least one of the following: a surrounding rock displacement monitor, a gas sensor, a hydrological monitoring station and a stress sensor. The monitoring data is fed back to the intelligent decision-making platform in real time and compared with the simulation data of the plan. If deviations occur or new geological risks are detected, the mining plan and / or safety measures are adjusted and corrected.

[0053] During the implementation phase, the optimal mining plan, determined through comprehensive ranking and screening, along with its corresponding specialized safety measures, will be distributed to the mining site. Actual mining operations will be organized according to the technical requirements outlined in the plan, including roadway layout, mining sequence, support parameters, ventilation configuration, and water control measures. Regarding the deployment of the real-time monitoring system, based on the risk distribution characteristics revealed by the optimal plan simulation, real-time monitoring equipment will be strategically deployed at key locations and high-risk areas within the mining site: Rock displacement monitoring instruments will be installed in areas sensitive to rock stability to continuously collect data on roadway roof subsidence, sidewall convergence, and floor heave; gas sensors will be deployed in areas with abnormal gas occurrence and in the return airflow of the mining face to continuously monitor gas concentration and its rate of change within the mining space; hydrological monitoring stations will be set up near areas threatened by aquifers to monitor hydrogeological parameters such as roadway water inflow, water pressure changes, and water quality characteristics in real time; and stress sensors will be embedded in key parts of the surrounding rock where mining disturbances are significant to monitor the redistribution of stress and the degree of stress concentration.

[0054] The aforementioned monitoring devices continuously transmit real-time monitoring data, such as surrounding rock displacement, gas concentration, water inflow, and surrounding rock stress, to the data receiving and storage module of the intelligent decision-making platform at a preset sampling frequency via wired or wireless data transmission networks. At the intelligent decision-making platform, the received real-time monitoring data is preprocessed and then compared item by item with the theoretical prediction data for the corresponding location and mining stage obtained from the numerical simulation of each mining scheme in the preceding steps. The platform calculates the degree of deviation between the measured and simulated values ​​using a set deviation judgment algorithm. When the deviation between the measured and predicted values ​​of a certain monitoring indicator exceeds the preset allowable deviation range, or when new geological risk signals unforeseen in the scheme design stage appear in the monitoring data (such as previously unidentified abnormal gas outbursts, unforeseen sudden increases in water inflow, or abnormal concentration of surrounding rock stress), the platform automatically activates... The optimization and adjustment process involves updating and correcting the relevant regional parameters in the 3D geological model based on the latest geological support information and real-time monitoring data. A dynamic risk assessment is then re-executed to refresh the risk level. This leads to targeted adjustments and corrections to the relevant technical parameters (such as support strength, advance speed, and mining strata) and / or the relevant design parameters (such as gas drainage borehole density, water drainage borehole depth, and support reinforcement range) in the original optimal mining plan. The revised plan is then reissued to the mining site for execution, thus achieving a closed-loop management process encompassing "data acquisition—modeling—evaluation—decision-making—implementation—monitoring—optimization."

[0055] Corresponding to the above-described mining decision-making method based on geological assurance information, this invention also proposes a mining decision-making device based on geological assurance information. Since the device embodiments of this invention correspond to the above-described method embodiments, details not disclosed in the device embodiments can be referred to in the above-described method embodiments, and will not be repeated here.

[0056] Figure 2 A schematic diagram of a mining decision-making device based on geological support information provided in this disclosure embodiment is shown below. Figure 2 As shown, it includes: The data acquisition and preprocessing unit 21 is used to acquire multi-source geological support information of the mining area and preprocess the multi-source geological support information to obtain preprocessed geological data. The three-dimensional modeling unit 22 is used to construct a full-element three-dimensional geological model of the mining area based on the preprocessed geological data. Feature extraction unit 23 is used to identify and extract geological risk factor feature parameters of the mining area based on the three-dimensional geological model; The risk assessment and early warning unit 24 is used to input the geological risk factor characteristic parameters into the risk dynamic assessment model, combine real-time monitoring data to dynamically assess the risk level of the mining area, and trigger an early warning when the risk level exceeds a preset threshold.

[0057] Furthermore, in one possible implementation of this disclosure embodiment, the acquisition preprocessing unit 21 is further configured to: Collect at least one of the following multi-source geological support information: stratigraphic lithology, geological structure, hydrogeological conditions, gas occurrence, coal seam thickness and stability; The multi-source geological support information is subjected to data cleaning, data standardization, data fusion and alignment, and data compression and noise reduction in sequence. Data cleaning includes removing outliers and filling in missing values. Data standardization includes unifying data format and dimension conversion. Data fusion and alignment are performed based on a spatial coordinate system to obtain preprocessed geological data.

[0058] Furthermore, in one possible implementation of this disclosure embodiment, the three-dimensional modeling unit 22 is further used for: A three-dimensional stratigraphic framework model is constructed based on stratigraphic lithology data. Geological structure, hydrogeology, and gas occurrence data are associated with the three-dimensional stratigraphic framework model as attribute information. Spatial interpolation methods are used to supplement the information in the data gap areas. Based on machine learning algorithms, the fusion results of multi-source data are optimized and corrected to construct a full-element three-dimensional geological model with dynamic updating function. Based on the three-dimensional geological model, combined with an expert experience knowledge base and machine learning algorithms, at least one key geological risk factor is automatically identified, including fault fracture zones, water-rich areas, gas-rich areas, weak interlayers, and coal seam thickness abrupt change zones. Each risk factor undergoes feature extraction to obtain its spatial location, size, development level, and dynamic change trend. These features are then classified, coded, and prioritized to obtain the geological risk factor characteristic parameters.

[0059] Furthermore, in one possible implementation of this disclosure embodiment, the risk assessment and early warning unit 24 is further configured to: A dynamic geological risk assessment model based on an improved deep learning algorithm is constructed. The geological risk factor feature parameters are used as input, and a training sample set is constructed by combining historical accident case data and field monitoring data for model training. The subjective weights of each risk factor are determined by the analytic hierarchy process (AHP) and the objective weights of each risk factor are determined by the entropy weight method. The subjective and objective weights are then combined and weighted to achieve dynamic adjustment of the influence weights of risk factors. The system dynamically updates the risk level by accessing downhole monitoring data in real time. When the risk level exceeds a preset threshold, an early warning mechanism is automatically triggered, and the warning level and the location of the corresponding risk source are clearly identified.

[0060] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, it also includes a scheme generation and deduction unit 25, which is used for: Based on the three-dimensional geological model and risk assessment results, combined with production capacity requirements, technical conditions and economic cost constraints, a variety of differentiated mining schemes are automatically generated through intelligent algorithms; Numerical simulation technology is used to simulate and extrapolate various schemes to obtain evaluation indicators such as safety factor, engineering difficulty, cost consumption and construction period. Based on the risk distribution characteristics of the optimal solution, at least one safety assurance measure is matched, including support parameter optimization, water control engineering layout, gas extraction scheme design, and emergency rescue plan formulation.

[0061] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, it also includes a dynamic monitoring and correction unit 26, which is used for: The optimal mining scheme and safety measures are applied to the actual mining operation. The geological conditions, engineering implementation effect and safety indicators are continuously and dynamically monitored throughout the mining operation through a deployed real-time monitoring system. The real-time monitoring system includes at least one of the following: a surrounding rock displacement monitor, a gas sensor, a hydrological monitoring station and a stress sensor. The monitoring data is fed back to the intelligent decision-making platform in real time and compared with the simulation data of the plan. If deviations occur or new geological risks are detected, the mining plan and / or safety measures are adjusted and corrected.

[0062] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0063] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0064] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0065] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0066] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0067] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as mining decision-making methods based on geological safeguard information. For example, in some embodiments, the mining decision-making method based on geological safeguard information can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned mining decision-making method based on geological safeguard information by any other suitable means (e.g., by means of firmware).

[0068] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0069] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0070] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0071] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0072] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0073] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0074] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0075] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0076] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A mining decision-making method based on geological support information, characterized in that, include: Collect multi-source geological support information of the mining area and preprocess the multi-source geological support information to obtain preprocessed geological data; Based on the preprocessed geological data, a full-element three-dimensional geological model of the mining area is constructed. Based on the aforementioned three-dimensional geological model, characteristic parameters of geological risk factors in the mining area are identified and extracted; The geological risk factor characteristic parameters are input into the risk dynamic evaluation model, and the risk level of the mining area is dynamically evaluated in combination with real-time monitoring data. An early warning is triggered when the risk level exceeds a preset threshold.

2. The method according to claim 1, characterized in that, The multi-source geological support information of the mining area is collected and preprocessed to obtain preprocessed geological data, including: Collect at least one of the following multi-source geological support information: stratigraphic lithology, geological structure, hydrogeological conditions, gas occurrence, coal seam thickness and stability; The multi-source geological support information is subjected to data cleaning, data standardization, data fusion and alignment, and data compression and noise reduction in sequence. Data cleaning includes removing outliers and filling in missing values. Data standardization includes unifying data format and dimension conversion. Data fusion and alignment are performed based on a spatial coordinate system to obtain preprocessed geological data.

3. The method according to claim 1, characterized in that, The construction of a full-element three-dimensional geological model of the mining area based on the preprocessed geological data includes: A three-dimensional stratigraphic framework model is constructed based on stratigraphic lithology data. Geological structure, hydrogeology, and gas occurrence data are associated with the three-dimensional stratigraphic framework model as attribute information. Spatial interpolation methods are used to supplement the information in the data gap areas. Based on machine learning algorithms, the fusion results of multi-source data are optimized and corrected to construct a full-element three-dimensional geological model with dynamic updating function. Based on the three-dimensional geological model, combined with an expert experience knowledge base and machine learning algorithms, at least one key geological risk factor is automatically identified, including fault fracture zones, water-rich areas, gas-rich areas, weak interlayers, and coal seam thickness abrupt change zones. Each risk factor undergoes feature extraction to obtain its spatial location, size, development level, and dynamic change trend. These features are then classified, coded, and prioritized to obtain the geological risk factor characteristic parameters.

4. The method according to claim 1, characterized in that, The step of inputting the geological risk factor characteristic parameters into the risk dynamic evaluation model, combining real-time monitoring data to dynamically evaluate the risk level of the mining area, and triggering an early warning when the risk level exceeds a preset threshold includes: A dynamic geological risk assessment model based on an improved deep learning algorithm is constructed. The geological risk factor feature parameters are used as input, and a training sample set is constructed by combining historical accident case data and field monitoring data for model training. The subjective weights of each risk factor are determined by the analytic hierarchy process (AHP) and the objective weights of each risk factor are determined by the entropy weight method. The subjective and objective weights are then combined and weighted to achieve dynamic adjustment of the influence weights of risk factors. The system dynamically updates the risk level by accessing downhole monitoring data in real time. When the risk level exceeds a preset threshold, an early warning mechanism is automatically triggered, and the warning level and the location of the corresponding risk source are clearly identified.

5. The method according to claim 1, characterized in that, The method further includes: Based on the three-dimensional geological model and risk assessment results, combined with production capacity requirements, technical conditions and economic cost constraints, a variety of differentiated mining schemes are automatically generated through intelligent algorithms; Numerical simulation technology is used to simulate and extrapolate various schemes to obtain evaluation indicators such as safety factor, engineering difficulty, cost consumption and construction period. Based on the risk distribution characteristics of the optimal solution, at least one safety assurance measure is matched, including support parameter optimization, water control engineering layout, gas extraction scheme design, and emergency rescue plan formulation.

6. The method according to claim 1, characterized in that, The method further includes: The optimal mining scheme and safety measures are applied to the actual mining operation. The geological conditions, engineering implementation effect and safety indicators are continuously and dynamically monitored throughout the mining operation through a deployed real-time monitoring system. The real-time monitoring system includes at least one of the following: a surrounding rock displacement monitor, a gas sensor, a hydrological monitoring station and a stress sensor. The monitoring data is fed back to the intelligent decision-making platform in real time and compared with the simulation data of the plan. If deviations occur or new geological risks are detected, the mining plan and / or safety measures are adjusted and corrected.

7. A mining decision-making device based on geological support information, characterized in that, include: The data acquisition and preprocessing unit is used to acquire multi-source geological support information of the mining area and preprocess the multi-source geological support information to obtain preprocessed geological data. The three-dimensional modeling unit is used to construct a full-element three-dimensional geological model of the mining area based on the preprocessed geological data. The feature extraction unit is used to identify and extract geological risk factor feature parameters of the mining area based on the three-dimensional geological model; The risk assessment and early warning unit is used to input the geological risk factor characteristic parameters into the risk dynamic assessment model, combine real-time monitoring data to dynamically assess the risk level of the mining area, and trigger an early warning when the risk level exceeds a preset threshold.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images