A mine geological disaster dynamic prediction method based on multi-source geophysical data

Abstract

The application provides a mine geological disaster dynamic prediction method based on multi-source geophysical prospecting data, and relates to the field of data processing. In the method, geophysical prospecting monitoring data in a mine area is obtained, and is associated with mining data, historical disaster data and geological structure data for correlation processing to form multi-source geological state data; the rock mass change state is analyzed according to the multi-source geological state data, and a geological state conversion relationship is established; the change correlation between different geophysical prospecting data is analyzed through the geological state conversion relationship, and an abnormal change process is determined; the abnormal region diffusion direction is analyzed according to the abnormal change process, and a disaster development path is generated; the disaster development path is matched with a historical disaster process to determine a disaster development stage; and a mine geological disaster dynamic prediction result is generated based on the disaster development stage and the disaster development path. The technical solution provided by the application facilitates improving the accuracy of mine geological disaster dynamic prediction.

Description

Technical Field

[0001] This application relates to the technical field of data processing, specifically to a method for dynamic prediction of geological disasters in mines based on multi-source geophysical data. Background Technology

[0002] As mining depths increase, the underground rock structure is affected by factors such as mining disturbance, changes in geostress, groundwater migration, and the formation of goaf, gradually increasing the likelihood of geological disasters in mines. To improve mine safety management, existing technologies typically acquire geophysical monitoring data of mining areas by deploying microseismic monitoring equipment, ground-penetrating radar equipment, deformation monitoring equipment, stress monitoring equipment, and groundwater monitoring equipment. This data is then combined with analysis methods to predict geological disasters such as landslides, collapses, water inrushes, and rock instability.

[0003] However, existing disaster prediction methods based on multi-source geophysical data typically focus on identifying anomalous changes in a single monitoring indicator or simply fusing monitoring data from different sources for risk assessment. These methods struggle to accurately describe the continuous evolution of mine geological hazards from early anomalous changes to the instability stage. Because the geological response processes corresponding to different geophysical data exhibit temporal and spatial differences—for example, microseismic changes, stress adjustments, fracture propagation, groundwater changes, and regional deformation often occur in different sequences—there are early, synchronous, and delayed response relationships among different geophysical data. Existing methods struggle to effectively identify the spatiotemporal evolution relationships between these multi-source geophysical anomaly responses. Furthermore, mine geological hazards typically undergo multiple stages, including rock mass stability, local anomalies, fracture propagation, and structural instability. The geophysical data change characteristics corresponding to different stages differ significantly. Existing methods lack continuous tracking and state transition analysis of geophysical anomaly changes, making it impossible to determine whether the current anomaly is developing along the disaster evolution direction or predict the trend of the anomaly spreading from local changes to surrounding areas.

[0004] Therefore, how to use multi-source geophysical data to identify the spatiotemporal evolution relationship between different geophysical anomaly responses, and dynamically judge the development trend of mine geological disasters from early anomalies to instability based on the anomaly change process, so as to improve the accuracy of dynamic prediction of mine geological disasters, has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method for dynamic prediction of geological hazards in mines based on multi-source geophysical data, which can help improve the accuracy of dynamic prediction of geological hazards in mines.

[0006] The first aspect of this application provides a method for dynamic prediction of geological hazards in mines based on multi-source geophysical data. The method includes: acquiring geophysical monitoring data within a mining area and performing correlation processing with mining data, historical hazard data, and geological structure data to form multi-source geological state data; analyzing the rock mass change state based on the multi-source geological state data to establish geological state transformation relationships; analyzing the change correlation between different geophysical data through the geological state transformation relationships to determine abnormal change processes; analyzing the diffusion direction of abnormal areas based on the abnormal change processes to generate hazard development paths; matching the hazard development paths with historical hazard processes to determine hazard development stages; and generating dynamic prediction results for geological hazards in mines based on the hazard development stages and the hazard development paths.

[0007] A second aspect of this application provides a dynamic prediction device for mine geological hazards based on multi-source geophysical data. The device includes an acquisition module and a processing module. The acquisition module acquires geophysical monitoring data within a mining area and performs correlation processing with mining data, historical hazard data, and geological structure data to form multi-source geological state data. The processing module analyzes the rock mass change state based on the multi-source geological state data and establishes geological state transformation relationships. The processing module further analyzes the change correlations between different geophysical data through the geological state transformation relationships to determine abnormal change processes. The processing module also analyzes the diffusion direction of abnormal areas based on the abnormal change processes to generate hazard development paths. The processing module further matches the hazard development paths with historical hazard processes to determine the hazard development stage. Finally, the processing module generates dynamic prediction results for mine geological hazards based on the hazard development stage and the hazard development path.

[0008] A third aspect of this application provides an electronic device, the electronic device including a processor and a memory; the memory has a computer program stored therein, wherein the computer program, when executed by the processor, implements a dynamic prediction method for mine geological hazards based on multi-source geophysical data as described above.

[0009] In a fourth aspect, this application provides a non-transitory computer-readable storage medium storing instructions that, when executed, perform a dynamic prediction method for mine geological hazards based on multi-source geophysical data as described above.

[0010] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By integrating geophysical monitoring data, mining data, historical disaster data, and geological structure data within the mining area, a multi-source geological state data system is established, enabling comprehensive perception of rock mass changes in the mining area. Compared to traditional methods that rely solely on single monitoring data for anomaly detection, this approach fully leverages the correlations between different data sources, improving the completeness and accuracy of geological state identification in complex mining environments and reducing the risk of misjudgments due to missing single data points or localized anomalies.

[0011] By analyzing the rock mass variation characteristics in multi-source geological state data and establishing geological state transformation relationships, the evolution process of mine disasters is transformed from static anomaly detection to continuous state change analysis. This enables the identification of the rock mass's evolution from a stable state to an abnormal state, fracture propagation state, and instability state, achieving early identification of potential disaster risks. By utilizing geological state transformation relationships to analyze the correlation between changes in different geophysical data, the synergistic variation patterns among data such as microseismic, stress, groundwater, and deformation can be uncovered, identifying the abnormal change processes that truly reflect rock mass changes and reducing misjudgments caused by non-hazardous factors such as production disturbances.

[0012] By analyzing the diffusion direction of abnormal changes, a disaster development path is generated, enabling dynamic tracking of the spatial expansion process of abnormal areas. This is combined with historical disaster processes to match the current disaster development stage, ensuring that the prediction results reflect the formation, development, and diffusion trends of disasters. Ultimately, dynamic prediction results are generated based on the disaster development stage and path, providing a basis for identifying mine disaster risk areas, issuing safety warnings, and implementing proactive mitigation measures. This scheme represents a shift from anomaly detection to disaster evolution prediction, improving the accuracy, predictability, and dynamic adaptability of mine geological disaster prediction. Attached Figure Description

[0013] Figure 1 A flowchart illustrating a method for dynamic prediction of mine geological hazards based on multi-source geophysical data, provided in this application embodiment; Figure 2 A schematic diagram of a module for a dynamic prediction device for mine geological disasters based on multi-source geophysical data provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0014] Explanation of reference numerals in the attached figures: 21. Acquisition module; 22. Processing module; 31. Processor; 32. Communication bus; 33. User interface; 34. Network interface; 35. Memory. Detailed Implementation

[0015] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0016] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0017] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0018] To address the aforementioned technical problems, this application provides a method for dynamic prediction of mine geological hazards based on multi-source geophysical data, referring to... Figure 1 , Figure 1 The flowchart illustrates a method for dynamic prediction of mine geological hazards based on multi-source geophysical data, provided in this application embodiment. The method is applied to a server and includes steps S110 to S160, as follows: S110. Obtain geophysical monitoring data within the mining area, and combine it with mining data, historical disaster data, and geological structure data for correlation processing to form multi-source geological status data.

[0019] Specifically, the server first acquires geophysical monitoring data collected by different geophysical monitoring devices within the mining area. This data reflects changes in the state of the rock mass within the mining area, including microseismic monitoring data, ground-penetrating radar monitoring data, surface deformation monitoring data, underground stress monitoring data, and groundwater monitoring data. Specifically, microseismic monitoring data reflects energy release and local fracturing changes within the rock mass; ground-penetrating radar data reflects changes in underground structure and fracture distribution; surface deformation monitoring data reflects changes in surface displacement within the mining area; underground stress monitoring data reflects changes in the stress state of the rock mass; and groundwater monitoring data reflects the impact of groundwater activity on rock mass stability. By continuously acquiring this geophysical monitoring data, the server forms fundamental monitoring data that reflects real-time changes in the mining area.

[0020] The server further acquires mining data corresponding to the mining area. This data describes the impact of mining activities on the rock mass condition, including mining location, depth, time, scope, and distribution of goaf areas. Based on this data, the server determines the current mining status of the mining area and correlates it with geophysical monitoring data. For example, it determines whether the corresponding area is affected by mining disturbance based on the mining location, and whether there is a risk of rock mass structure change based on the distribution of goaf areas, thus avoiding misinterpreting monitoring changes caused by normal mining activities as abnormal geological hazard changes.

[0021] The server acquires historical disaster data corresponding to the mining area. This historical disaster data records past geological disaster processes in the mining area, including the location, time, type, formation process, and corresponding geophysical monitoring changes prior to the disaster. By analyzing the historical disaster data, the server extracts rock mass change characteristics prior to different types of geological disasters and correlates these characteristics with the currently acquired geophysical monitoring data. This provides a reference for subsequently determining whether current rock mass changes indicate a disaster evolution trend.

[0022] The server acquires geological structure data corresponding to the mining area. This data describes the distribution and spatial structure of rock strata within the mining area, including strata distribution, fault locations, fracture distribution, rock mass connections, and underground spatial structure information. Based on this data, the server determines the geological relationships between different areas and analyzes the potential geological structural impacts of abnormal changes in conjunction with geophysical monitoring data. This ensures that subsequent analyses are based on actual mine geological conditions, rather than solely relying on changes in monitoring data.

[0023] The server performs correlation processing on geophysical monitoring data, mining data, historical disaster data, and geological structure data. First, it performs time matching based on the acquisition time of each type of data, so that different data correspond to the same time period. Then, it performs regional matching based on the spatial location of each type of data, so that different data correspond to the same mining area. Finally, based on the rock mass changes reflected in the geophysical monitoring data, the disturbance effects corresponding to the mining data, the evolution patterns corresponding to the historical disaster data, and the spatial constraints corresponding to the geological structure data, it establishes correlation relationships between different data to form multi-source geological state data.

[0024] Multi-source geological state data is not simply a collection of data, but rather comprehensive state data used to describe the rock mass change process in a mining area. By converting data from different sources into unified geological state description information, the server can simultaneously acquire the current rock mass changes, historical evolution patterns, mining influencing factors, and geological structural constraints in the mining area. This provides a data foundation for subsequently establishing geological state transformation relationships, identifying abnormal change processes, and generating disaster development paths.

[0025] S120. Analyze the rock mass change state based on multi-source geological state data and establish geological state transformation relationships.

[0026] Specifically, the server first performs time-based segmentation and feature extraction processing on the multi-source geological state data. Continuously acquired geophysical monitoring data is divided into multiple time stages according to a preset time window, and the corresponding rock mass response change information for each time stage is extracted. This rock mass response change information describes the changes in the rock mass within the mining area after being affected by mining activities, changes in geostress, and groundwater activity. Specifically, it includes changes in microseismic activity, fracture changes, stress changes, groundwater changes, and regional deformation changes. By analyzing the changing trends of various monitoring data within different time stages, characteristic information reflecting changes in the internal state of the rock mass is obtained.

[0027] The server determines the rock mass change state at different time stages based on rock mass response change information. Specifically, a state recognition algorithm is used to classify the rock mass response change information at different time stages. Based on the similarity and trend of the rock mass response change information between different time stages, data with the same change pattern are grouped into the same rock mass change state. The state recognition algorithm can use cluster analysis to classify historical and current monitoring data. By analyzing the change characteristics corresponding to different time stages, the mining area is divided into multiple continuous change states, transforming discrete monitoring data into state information that can describe the rock mass evolution process.

[0028] The server classifies rock mass changes into different states based on historical disaster data. Specifically, it acquires the rock mass change processes preceding historical disasters, analyzes the evolution of rock mass changes during the formation of different disaster types, and matches the current rock mass change state with typical states observed during historical disasters. Based on the matching results, the rock mass change states are categorized into stable, stress-adjusted, fracture-propagated, and structurally unstable states. A stable state indicates that the rock mass has not been significantly disturbed; a stress-adjusted state indicates a redistribution of stress within the rock mass; a fracture-propagated state indicates the continuous development of fractures within the rock mass; and a structurally unstable state indicates reduced structural stability and a risk of disaster.

[0029] The server establishes geological state transition relationships based on the change processes between different state types. Specifically, by analyzing the transition patterns between historical disaster processes and the current rock mass change state, it determines the direction, sequence, and conditions of transition between different state types. For example, based on a large number of historical disaster evolution processes, it is determined that a stable state typically transitions gradually from a stress adjustment state to a fracture propagation state, and further develops towards a structural instability state. Simultaneously, by combining current geophysical monitoring data changes, it identifies the corresponding microseismic changes, stress changes, and deformation changes during different state transition processes, thereby establishing geological state transition relationships describing the evolution of the rock mass from a normal state to a disaster state.

[0030] The server dynamically assesses rock mass changes in the current mining area using geological state transition relationships. Specifically, it matches the current rock mass change state with the geological state transition relationship to determine whether the current rock mass change state conforms to a preset evolution path. When the rock mass change state continuously changes in the direction of stable state, stress adjustment state, fracture propagation state, and structural instability state, it is determined that there is a disaster evolution trend in the current area, and the corresponding state transition process is used as the basis for subsequent abnormal change process analysis.

[0031] Through the above processing, multi-source geophysical monitoring data is converted into state information that can reflect the rock mass evolution process. The geological state transformation relationship is used to describe the change process of the mining area from normal state to disaster state, so that disaster analysis is transformed from single anomaly identification to continuous state evolution analysis, providing a basis for subsequent anomaly change process identification and disaster development path generation.

[0032] S130. By analyzing the relationship between geological state transformations, the correlation between changes in different geophysical data is determined to identify the process of abnormal changes.

[0033] Specifically, the server first obtains the geophysical data change characteristics corresponding to different rock mass change states based on the geological state transformation relationship. Specifically, based on the established geological state transformation relationship, it reads the geophysical response change patterns corresponding to stable state, stress adjustment state, fracture propagation state, and structural instability state, and establishes a correspondence between rock mass change states and geophysical data change characteristics. The geophysical data change characteristics describe the manifestation of different geophysical data during rock mass state changes. For example, in a stable state, all geophysical data maintain low-amplitude fluctuations; in a stress adjustment state, underground stress monitoring data and microseismic monitoring data begin to change; in a fracture propagation state, microseismic monitoring data, ground-penetrating radar monitoring data, and deformation monitoring data show continuous changes; in a structural instability state, multiple geophysical data simultaneously show significant abnormal changes. Through the above processing, different geophysical data changes can be mapped to specific rock mass change states.

[0034] The server analyzes the sequence and relationships of changes in geophysical data corresponding to different rock mass change states. Specifically, the server performs correlation analysis on microseismic monitoring data, stress monitoring data, groundwater monitoring data, and deformation monitoring data from multi-source geological state data in chronological order to determine the sequential relationship of changes in different geophysical data. The sequence of changes indicates the temporal relationship of abnormal changes in different geophysical data; for example, increased microseismic activity precedes increased stress changes, followed by regional deformation changes. The relationship of changes indicates whether multiple geophysical data collectively reflect the same rock mass change process. The server compares the changing trends of different geophysical data using time series analysis algorithms to identify synchronous, lagging, and continuous changes among multiple geophysical data, thereby forming correlations between geophysical data changes.

[0035] The server determines whether changes in geophysical data conform to the geological state transition process based on the sequence and relationship of changes. Specifically, the server matches the changes in geophysical data corresponding to the current mining area with the preset state transition processes in the geological state transition relationship to determine whether the current changes in geophysical data meet the corresponding rock mass state transition conditions. For example, when the current area experiences increased microseismic activity, increased stress changes, and gradually expanding deformation, and the sequence of these changes conforms to the process of transitioning from a stable state to a stress adjustment state and a fracture propagation state, the server determines that the current changes in geophysical data conform to the geological state transition relationship; when there is only a single abnormal change in geophysical data, or when the sequence of changes in multiple geophysical data does not conform to the rock mass state transition law, the server determines that the current changes do not belong to the disaster evolution process.

[0036] To improve the accuracy of identifying correlations and changes among multiple geophysical data, the server can employ a multi-source change consistency analysis algorithm to assess the degree of consistency in changes between different geophysical data. Specifically, by analyzing whether the direction, duration, and area of ​​change in multiple geophysical data points remain consistent within the same time frame, it determines whether the multiple data points collectively reflect the same anomalous change process. This multi-source change consistency analysis algorithm is used to determine whether geophysical data from different sources exhibit common changing trends, avoiding erroneous judgments caused by environmental interference, equipment errors, or local disturbances affecting individual monitoring devices.

[0037] After determining that multiple geophysical data points have undergone consecutive and correlated changes, the server identifies the corresponding change process as an anomalous change process. Specifically, when multiple geophysical data points change continuously in a sequence corresponding to geological state transformation relationships, and there is a correlation between the change area, change time, and change trend, the server determines that an anomalous change process exists in the current area and records the corresponding geophysical data type, change sequence, change stage, and corresponding rock mass change state, forming anomalous change information. This anomalous change process describes the continuous change process of a mining area from a normal state to a potential disaster state, providing a basis for subsequent analysis of the anomalous area's diffusion direction and the generation of disaster development paths.

[0038] Through the above processing, the server uses the geological state transformation relationship to constrain the correlation analysis between different geophysical data, transforming the traditional anomaly detection method based on a single monitoring indicator into an anomaly process identification method based on the coordinated changes of multi-source geophysical data. This can identify the rock mass evolution process reflected by multiple geophysical data, and improve the accuracy of early anomaly identification in mine geological disasters.

[0039] In one possible implementation, the server first reads the geophysical response change patterns corresponding to the different rock mass states in the geological state transition relationship, establishing a correspondence between the rock mass state changes and the sequence of geophysical data changes. The sequence of geophysical data changes represents the order in which different types of geophysical data appear during the rock mass state transition process. For example, when transitioning from a stable state to a stress adjustment state, underground stress monitoring data typically changes first, followed by an increase in microseismic monitoring data; when transitioning from a stress adjustment state to a fracture propagation state, microseismic monitoring data, ground-penetrating radar monitoring data, and deformation monitoring data change continuously. Based on historical disaster processes and the current geological state transition relationship, the server organizes the sequence of geophysical data changes corresponding to different rock mass states, forming a geophysical change sequence corresponding to the state transition.

[0040] The server acquires the real-time change process corresponding to different geophysical data within the current mining area and matches the current geophysical data change process with the sequence of geophysical data changes. Specifically, the server divides the microseismic monitoring data, stress monitoring data, groundwater monitoring data, and deformation monitoring data according to time windows, extracts the change time, direction, and duration corresponding to each geophysical data, and generates the current geophysical data change process according to the chronological order. Subsequently, the server compares the current geophysical data change process with the standard geophysical data change sequence in the geological state transformation relationship to determine whether the current geophysical data has changed according to the preset rock mass change state transformation process.

[0041] To improve the accuracy of matching the current geophysical data change process with the geophysical data change sequence, the server can employ a time-series matching algorithm to perform correlation analysis. This algorithm analyzes the correspondence between two time series by comparing the change nodes in the current geophysical data change process with the change sequence of standard geophysical data to determine whether the changes in different geophysical data are in the same evolutionary process. Specifically, it matches the microseismic change nodes, stress change nodes, and deformation change nodes in the current geophysical data change process with their corresponding change nodes in the change sequence of standard geophysical data. When multiple change nodes appear in the same order, it is determined that the current geophysical data change process and the geophysical data change sequence are consistent.

[0042] The server further determines whether at least two geophysical data points change continuously in the order of their changes. In practice, the server makes correlation judgments based on the time intervals, directions of change, and areas of change between different geophysical data points. When at least two geophysical data points change continuously within the same area according to the order corresponding to the geological state transition relationship, a correlation is determined between the multiple geophysical data points. For example, if a region first shows a continuous increase in underground stress monitoring data, followed by increased microseismic activity and further surface deformation, the server determines that the aforementioned geophysical data change process conforms to the change law of the rock mass transitioning from a stress adjustment state to a fracture propagation state.

[0043] The server can determine whether changes in geophysical data meet the criteria for abnormal changes based on the correlation between multiple geophysical data sets. Specifically, it comprehensively judges the current geophysical data change process based on the matching results of the geophysical data change sequence, the duration of the change, and the consistency of the change area. When multiple geophysical data sets change continuously, and the change process conforms to the state transition law corresponding to the geological state transition relationship, the current geophysical data change is determined to conform to the geological state transition relationship; when only a single change occurs in the geophysical data, or the change sequence is inconsistent with the geological state transition relationship, the current geophysical data change is determined not to be an abnormal change process.

[0044] Once it is determined that the changes in geophysical data conform to geological state transition relationships, the server identifies the anomalous change process based on the geophysical data change process. Specifically, the server extracts the change area, change sequence, change time, and corresponding rock mass change state from the geophysical data change process that conforms to the geological state transition relationship, and correlates this information to form the anomalous change process. This anomalous change process describes the anomalous evolution process of the rock mass reflected by multiple geophysical data within the mining area. It can characterize the process of the rock mass developing from a normal state to a potential disaster state, providing a basis for subsequent analysis of the direction of anomalous area diffusion and the generation of disaster development paths.

[0045] Through the above processing, the server uses the geological state transformation relationship to constrain the change process of different geophysical data, transforming the judgment of anomalies in single geophysical data into the judgment of collaborative changes in multiple geophysical data, so that the abnormal change process can correspond to the actual rock mass state transformation process, improve the accuracy of early identification of geological disasters in mines, and reduce the problem of misjudgment caused by fluctuations in single data or local disturbances.

[0046] S140. Analyze the direction of the spread of the abnormal area based on the abnormal change process, and generate the disaster development path.

[0047] Specifically, the server first determines the abnormal change areas based on the abnormal change process. Specifically, based on the location, time, and corresponding rock mass change state of the geophysical data contained in the abnormal change process, the mining area is spatially divided, and areas exhibiting continuous abnormal changes are identified as abnormal change areas. An abnormal change area represents a spatial region within the mining area affected by changes in rock mass structure, stress, or groundwater activity, where multiple geophysical data continuously reflect an abnormal state. The server spatially merges the abnormal locations corresponding to different geophysical data by associating the location coordinates of microseismic monitoring data, deformation monitoring data, stress monitoring data, and groundwater monitoring data, forming a set of abnormal areas that includes the location distribution of abnormal change areas.

[0048] The server further analyzes the correlation between anomalous change areas by combining geological structure data and rock mass change state. Specifically, the server acquires information such as fault distribution, fracture distribution, rock strata orientation, and spatial location of goaf from the geological structure data to analyze whether there is a geological connection between different anomalous change areas. Simultaneously, based on the rock mass change state corresponding to each anomalous change area, the server determines whether there is a state transmission relationship between the anomalous change areas. For example, when two anomalous change areas are located in the same fault zone or fracture extension direction, and the rock mass change states corresponding to the two areas show a continuous transition from a stress adjustment state to a fracture propagation state, the server determines that there is a correlation between the two anomalous change areas.

[0049] To quantify the correlation between different areas of anomalous change, the server can establish an anomalous area correlation evaluation model. This model comprehensively assesses the connection strength between anomalous areas based on their location, geological structure, and state change relationships. The anomalous area correlation evaluation model is as follows:

[0050] in, Indicates the first The first abnormal change region and the first The degree of correlation between the abnormal change regions; This parameter represents the positional correlation between abnormal change areas. It is determined based on the spatial distance and directional relationship between the two abnormal change areas and has a value range of 0 to 1. This represents a geological structure correlation parameter, which is determined based on whether two abnormal change areas are located within the same fault, fissure, or goaf influence range, and its value ranges from 0 to 1. This represents the rock mass state correlation parameter, which is determined based on the conversion relationship between the rock mass change states corresponding to two abnormal change areas, and its value ranges from 0 to 1. , , These represent the weighting coefficients corresponding to the location-related parameters, geological structure-related parameters, and rock mass state-related parameters, respectively, with values ​​ranging from 0 to 1, and the sum of the weighting coefficients being 1. This model can comprehensively determine whether areas of abnormal change belong to the same disaster evolution process.

[0051] The server determines the sequence and direction of anomalous changes in regions based on their correlations. Specifically, the server sorts multiple anomalous change regions according to the degree of correlation between them and the time of occurrence of the anomalous changes, determining the sequence of development from the initial occurrence region to the subsequently affected regions. The sequence of changes describes the order in which anomalous states appear in the regions, while the direction of diffusion describes the spatial direction of the anomalous change's propagation from one region to others. When a region first shows geophysical data anomalies, and adjacent regions subsequently show corresponding rock mass changes, the server determines that the anomalous change has spread from the preceding region to the following region.

[0052] The server further combines geological state transformation relationships to determine the disaster development process corresponding to the abnormal change areas. Specifically, the server matches the rock mass change state corresponding to the abnormal change areas with geological state transformation relationships, analyzing whether the abnormal change areas conform to the evolution laws of stable state, stress adjustment state, fracture propagation state, and structural instability state. For example, when the initial abnormal change area is in a stress adjustment state, adjacent abnormal change areas gradually transform into a fracture propagation state, and subsequent areas show a structural instability state, the server determines that the current abnormal change area conforms to the disaster evolution process.

[0053] The server generates a disaster development path based on the relationships between areas of abnormal change, the order of change, the direction of diffusion, and the disaster development process. Specifically, the area where the abnormal change first occurs is determined as the starting point of the disaster development path, and subsequent related areas of abnormal change are connected in order of change to form a continuous path describing the development of the disaster from a local area to the surrounding areas. The disaster development path is used to represent the spatial diffusion process and state change process of the disaster risk area, including the locational relationships of areas of abnormal change, the direction of diffusion, and the corresponding rock mass change state transformation process, providing a basis for subsequently determining the disaster development stage and generating dynamic prediction results.

[0054] Through the above processing, the abnormal change process is transformed from single-region anomaly identification to disaster evolution path analysis based on spatial correlation and state transformation. This can identify the diffusion pattern of mine geological disasters from local anomalies to regional disasters, and improve the accuracy of disaster development trend judgment.

[0055] S150. Based on the matching of disaster development path with historical disaster processes, determine the disaster development stage.

[0056] Specifically, the server extracts the location range, initial anomaly time, anomaly duration, anomaly diffusion direction, associated geophysical data types, and rock mass change state of each anomalous change area based on the disaster development path. These are then arranged according to the connection order in the disaster development path to form the current disaster evolution characteristics. These current disaster evolution characteristics are not individual monitoring values, but rather a combination of information describing how anomalous change areas appear, how they spread, and how the rock mass change state transforms. Here, the anomalous change area represents the spatial range of the mine where multiple geophysical data show continuous and correlated changes; the change order indicates the sequential arrangement of the anomalous change areas; and the rock mass change state represents the stable state, stress adjustment state, fracture propagation state, or structural instability state corresponding to each anomalous change area.

[0057] The server filters historical disaster events from historical disaster data that have similar geological structures, mining methods, and disaster types to the current mining area. It then extracts historical anomaly change areas, the sequence of historical changes, the direction of historical diffusion, and the state of historical rock mass changes in chronological order before the historical disasters occurred, forming multiple historical disaster processes. For each historical disaster process, the server uses the actual time of the disaster as the ending point and traces back the time range of continuous anomaly changes in geophysical data. This time range is divided into the initial stage of the disaster, the development stage of the disaster, and the instability stage of the disaster, and the server records the historical disaster evolution characteristics corresponding to each stage of the disaster development.

[0058] The server aligns the current disaster evolution characteristics with historical disaster processes according to the order in which anomalous change areas appear. Node alignment means that when the current disaster development path differs from historical disaster processes in length or rate of change, corresponding anomalous nodes are determined based on the sequential relationship of anomalous change areas and the transformation relationship of rock mass change states. For example, stress adjustment state nodes in the current disaster development path can correspond to stress adjustment state nodes in historical disaster processes, without requiring them to have exactly the same occurrence time. The server uses a dynamic time warping algorithm to search for the node-corresponding path with the smallest cumulative difference, thereby reducing the impact of differences in disaster development speed on the matching results.

[0059] The server, based on the current and historical disaster evolution characteristics after node alignment, comprehensively analyzes the degree of spatial overlap of abnormal change areas, the consistency of change sequence, the consistency of rock mass change state transformation, the consistency of diffusion direction, the similarity of anomaly duration, and the correlation of geophysical data. It also calculates the current disaster development path and its correlation with the previous one. The disaster evolution matching value is the value between historical disaster events. The formula for calculating the disaster evolution matching value is:

[0060] In the formula, Indicates the current disaster development path and the first The disaster evolution matching value between historical disaster processes ranges from 0 to 1. The larger the value, the closer the disaster evolution processes are. This represents the set of nodes determined by the Dynamic Time Warping algorithm, where each node... Indicates the first step in the current disaster development path. The abnormal node and the first The first in the historical disaster process A corresponding relationship is formed between the abnormal nodes; This represents the trust weight of the corresponding node, which is determined based on the number of geophysical data involved in the anomaly detection, the completeness rate of the geophysical data, and the stability of the anomaly's persistence. The value ranges from 0 to 1.

[0061] The spatial difference parameter reflects the differences in location, influence range, and geological structure of two corresponding anomaly nodes in the normalized mine space. Its value ranges from 0 to 1. The server normalizes the location coordinates, coverage range, and relative position with faults, fissures, and goaf areas of the anomaly change area, and then determines the parameter based on the distance between the normalization results. The closer the spatial location and influence range are, the closer the spatial difference parameter is to 0.

[0062] The time difference parameter reflects the difference in the occurrence time of two corresponding abnormal nodes relative to the start time of their respective disaster development paths. Its value ranges from 0 to 1. The server first calculates the time interval between the occurrence time of the abnormal node and the start time of the corresponding disaster development path, then divides it by the total duration of the corresponding disaster process to complete the normalization, and determines the time difference parameter based on the difference between the two normalized time intervals.

[0063] The rock mass change state difference parameter is used to reflect whether the rock mass change states of two corresponding anomaly nodes and the relationship between their states are consistent. Its value ranges from 0 to 1. When two anomaly nodes correspond to the same rock mass change state and have the same state transition direction, the rock mass change state difference parameter is 0. When the two nodes differ by one adjacent rock mass change state, the rock mass change state difference parameter can be 0.25 to 0.5. When the state transition directions of the two nodes are opposite or span multiple rock mass change states, the rock mass change state difference parameter can be 0.5 to 1.

[0064] The diffusion direction difference parameter reflects the difference in diffusion direction between two corresponding abnormal nodes relative to the previous abnormal node. Its value ranges from 0 to 1. The server determines the diffusion direction based on the center position of the abnormal change area and normalizes the diffusion direction difference parameter based on the angle between the two diffusion directions. The smaller the angle, the closer the diffusion direction difference parameter is to 0.

[0065] The duration difference parameter is used to reflect the difference in the duration of anomalies between two corresponding anomaly nodes. Its value ranges from 0 to 1. The server determines the time between the first occurrence of the anomaly and the time when the anomaly recovers or enters the next rock mass change state as the anomaly duration, and then determines the duration difference parameter based on the relative difference between the two anomaly durations.

[0066] The geophysical data correlation difference parameter reflects the differences between the types of geophysical data involved in two corresponding anomaly nodes, the order of geophysical data changes, and the continuous change relationship of geophysical data. Its value ranges from 0 to 1. The server establishes a set of geophysical data identifiers based on whether microseismic monitoring data, stress monitoring data, groundwater monitoring data, ground-penetrating radar monitoring data, and deformation monitoring data participate in the anomaly change process, and determines the geophysical data correlation difference parameter in combination with the order of changes of each geophysical data.

[0067] to These represent the local difference weights corresponding to spatial difference parameters, temporal difference parameters, rock mass change state difference parameters, diffusion direction difference parameters, duration difference parameters, and geophysical data association difference parameters, respectively. Each of these local difference weights ranges from 0 to 1, and the sum of the six local difference weights is 1. The local difference weights can be set based on historical disaster verification results. For example, for mines with obvious fracture propagation and rock mass instability, the weights corresponding to the rock mass change state difference parameters and diffusion direction difference parameters can be increased. For mines with obvious water inrush risk, the weights corresponding to the geophysical data association difference parameters can be increased.

[0068] This represents a stable parameter to prevent the denominator from being zero, and can be taken as... to This parameter is only used to ensure calculation stability and is not used for comparing disaster evolution characteristics. The parameter indicating the consistency of change order is used to reflect the order of the current abnormal nodes and the order of the sequence. Whether the order of abnormal nodes in a historical disaster process is consistent, with a value range of 0 to 1; the server determines this parameter based on the ratio between the number of nodes with consistent order and the total number of valid node pairs. This represents the path coverage parameter, used to reflect the path coverage of the disaster in the current disaster development path. The proportion of corresponding nodes found during a historical disaster process, with a value ranging from 0 to 1; the server determines this parameter based on the ratio between the number of current abnormal nodes that have completed node alignment and the total number of current abnormal nodes. This represents the complete parameters of the state transition, used to reflect the rock mass changes and state transitions that have already occurred in the current disaster development path. Whether the state transitions in the corresponding stages of a historical disaster process are completely matched, with a value ranging from 0 to 1; the server determines this parameter based on the ratio between the number of matched state transition edges and the total number of state transition edges in the current disaster development path.

[0069] , and These represent the overall matching weights corresponding to the parameters of consistent change order, path coverage, and complete state transition, respectively. Each weight ranges from 0 to 1, and the sum of the three is 1. The overall matching weights are used to limit historical disaster processes that only have similar local nodes but inconsistent overall disaster development paths from obtaining excessively high disaster evolution matching values.

[0070] The formula first weights and accumulates the spatial, temporal, state, direction, duration, and geophysical data correlation differences for each group of corresponding anomalous nodes. Then, it converts the accumulated differences into a local similarity level between 0 and 1 through exponential mapping. Subsequently, it uses parameters such as consistency of change order, path coverage, and completeness of state transition to make an overall correction to the local similarity level. Therefore, only historical disaster processes with similar local features of anomalous nodes and consistent overall disaster development path structure can obtain a high disaster evolution matching value.

[0071] The server calculates the matching values ​​between the current disaster evolution characteristics and the disaster evolution of each historical disaster process at different stages of disaster development, and retains historical disaster processes that meet the preset matching threshold as candidate historical disaster processes. The preset matching threshold can be determined based on the historical disaster playback verification results, and is usually set to 0.60 to 0.85. When the disaster evolution matching value is lower than the preset matching threshold, it indicates that the current disaster development path lacks sufficient consistency with the corresponding historical disaster process, and the historical disaster process is not used to determine the disaster development stage.

[0072] When multiple candidate historical disaster events exist, the server further integrates the disaster evolution matching value of each candidate historical disaster event, the credibility of historical disaster samples, and the corresponding disaster development stage to calculate the stage support value for each disaster development stage. The formula for calculating the stage support value is:

[0073] In the formula, Indicates the stage of disaster development The corresponding stage support value ranges from 0 to 1. This represents a set of disaster development stages, which may include the initial stage of the disaster, the development stage of the disaster, and the instability stage of the disaster. This represents the number of candidate historical disaster events, and its value is an integer greater than or equal to 1. Indicates the stage indicator function, when the first stage... Disaster development stages corresponding to each candidate historical disaster event With the development stage of the disaster to be evaluated If the values ​​are the same, take 1; otherwise, take 0.

[0074] Indicates the first The sample reliability parameters for each candidate historical disaster process are determined based on the completeness rate of historical geophysical data, the completeness rate of disaster records, and the verification of disaster occurrence results, with a value range of 0 to 1. Indicates the first Disaster evolution matching values ​​corresponding to each candidate historical disaster process; This represents the matching enhancement parameter, which can be set from 1 to 5. The larger the value, the more significant the impact of the highly matched historical disaster process on the stage judgment. Indicates the current terminal state of the disaster development path and the first The state distance between the end states of corresponding stages of each candidate historical disaster process ranges from 0 to 1. This represents the state distance suppression parameter, which can be set from 0.5 to 5. It is used to reduce the impact of inconsistent historical disaster processes on stage judgment.

[0075] This formula weights and summarizes multiple candidate historical disaster processes according to disaster evolution matching values, sample reliability parameters, and the degree of consistency of terminal states, so that the disaster development stage is not directly determined by a single historical disaster process, thereby reducing the impact of the randomness of historical samples and single matching errors on the judgment of the disaster development stage.

[0076] The server identifies the disaster development stage with the highest stage support value as a candidate disaster development stage and determines whether the stage support value corresponding to the candidate disaster development stage reaches the stage confirmation threshold. The stage confirmation threshold can be set from 0.55 to 0.80. When the stage confirmation threshold is reached, the candidate disaster development stage is identified as the disaster development stage corresponding to the disaster development path. When the stage confirmation threshold is not reached, the disaster development stage is identified as a stage to be confirmed, and the disaster evolution matching value and stage support value are recalculated after acquiring new multi-source geological state data.

[0077] Through the above processing, the server can simultaneously utilize the spatial distribution, change sequence, rock mass change state, diffusion direction, duration, and geophysical data correlation of the abnormal change area to perform non-equal length time sequence matching of the current disaster development path with multiple historical disaster processes, and jointly determine the disaster development stage through multiple historical disaster processes, avoiding the stage judgment bias caused by simple weighted summation or single similarity comparison.

[0078] S160. Based on the disaster development stage and disaster development path, generate dynamic prediction results of mine geological disasters.

[0079] Specifically, the server determines the abnormal change areas, abnormal diffusion directions, and disaster impact range based on the disaster development stage and path. Specifically, the server first reads the sequence of abnormal change areas contained in the disaster development path, and correlates the location coordinates, rock mass change state, geophysical data anomaly degree, and state transition relationships corresponding to each abnormal change area to form disaster spatial evolution information. Here, the abnormal change area represents a mining area where multiple geophysical data show continuous abnormal changes; the abnormal diffusion direction indicates the direction in which the abnormal change area spreads to adjacent areas according to the disaster development path; and the disaster impact range represents the potential risk area predicted based on the current disaster development stage and disaster diffusion trend.

[0080] The server classifies the risk status of different abnormal change areas based on the disaster development stage. Specifically, the server determines the degree of danger corresponding to the abnormal change areas based on the current disaster development stage. When the disaster development stage is in the initial stage, the areas where abnormal changes have already occurred are identified as the risk initiation areas, and the subsequent potentially affected areas are predicted based on the disaster development path. When the disaster development stage is in the disaster development stage, the areas distributed along the abnormal diffusion direction are identified as key affected areas based on the diffusion relationship between multiple abnormal change areas. When the disaster development stage is in the disaster instability stage, the areas corresponding to the structural instability state and the related areas spreading along the disaster development path are identified as the main affected areas.

[0081] The server analyzes the spatial diffusion relationships between areas of abnormal change based on the disaster development path. Specifically, the server determines the spatial range within which the disaster may continue to spread based on the connectivity, diffusion direction, and geological structural constraints between areas of abnormal change. For areas of abnormal change located within the same fault, fracture extension direction, or goaf influence area, the server increases the likelihood of disaster diffusion; for areas without geological connectivity or blocked by stable rock strata, the server reduces the likelihood of disaster diffusion, thus forming a disaster impact range constrained by geological conditions.

[0082] The server further generates dynamic prediction results for mine geological disasters based on the areas of abnormal change, the direction of abnormal spread, and the scope of disaster impact. Specifically, it correlates the disaster development stage, disaster development path, areas of abnormal change, the direction of abnormal spread, and the scope of disaster impact to form dynamic prediction results that include the current disaster status and future development trends. The dynamic prediction results for mine geological disasters include the current risk area, the predicted impact area, the disaster development stage, the direction of disaster spread, and the expected impact scope, which are used to describe the possible future disaster evolution process in the mining area.

[0083] To comprehensively consider the interrelationships between multiple areas of abnormal change, the server establishes a dynamic risk assessment model based on the disaster evolution path to calculate the degree of disaster impact corresponding to each area of ​​abnormal change. The dynamic risk assessment model is as follows:

[0084] in, Indicates the first The dynamic risk assessment value corresponding to each abnormal change area ranges from 0 to 1. The larger the value, the greater the impact of the abnormal change area on the disaster development process. This represents the normalization function, used to map the calculation results to the range of 0 to 1; Indicates the relationship with the first The number of abnormal change areas that are associated with disaster spread is an integer greater than or equal to 1.

[0085] Indicates the first The rock mass state risk parameter for each abnormal change area is used to describe the degree of danger of the current rock mass change state in the corresponding area. It is divided into stable state, stress adjustment state, crack propagation state and structural instability state, with a value range of 0 to 1; among them, the stable state corresponds to a lower value and the structural instability state corresponds to a higher value.

[0086] Indicates the first The path association parameter for each anomalous change area is used to describe the importance of the area in the disaster development path. It is determined based on whether the area is located in the main propagation direction of the disaster development path, whether it connects multiple anomalous change areas, and whether it is at a critical node in the path. The value range is from 0 to 1.

[0087] Indicates the first Geological structure influence parameters for anomaly change areas are used to describe the degree of influence of faults, fissures, goaf areas, and rock strata on disaster spread. They are determined by analysis based on geological structure data and range from 0 to 1.

[0088] Indicates the first Historical disaster matching parameters for each abnormal change area are used to describe the similarity between the current abnormal change area and the corresponding area during the historical disaster process. They are determined based on the matching results of the historical disaster process and range from 0 to 1.

[0089] Indicates the first The time evolution parameter of each abnormal change region is used to describe the duration and rate of change of the abnormal change in the region. It is determined based on the time of first occurrence of the abnormal change, the duration, and the state transition rate, and the value ranges from 0 to 1.

[0090] , , , , These represent the association weights corresponding to the rock mass state risk parameters, path association parameters, geological structure influence parameters, historical disaster matching parameters, and time evolution parameters, respectively, with values ​​ranging from 0 to 1. Each weight is adjusted according to different mine disaster types, and the sum of all weights is 1, used to represent the degree of influence of different factors on the dynamic development of disasters.

[0091] This parameter represents the disaster development stage correction parameter, used to adjust the risk assessment results according to the current disaster development stage. It takes a smaller value when the disaster is in the initial stage and a larger value when the disaster is in the development or instability stage. The value range is 0 to 1.

[0092] This represents the time decay parameter, which describes the trend of the impact of the abnormal change area as the prediction time increases. Its value ranges from 0 to 1. Indicates the first The predicted time interval between each abnormal change area and the current monitoring time is determined based on the time information in the disaster development path.

[0093] This dynamic risk assessment model, by comprehensively analyzing the spatial correlation between abnormal change areas, the correlation of disaster development paths, changes in rock mass state, geological structure constraints, similarity of historical disasters, and temporal evolution characteristics, can avoid making risk judgments based solely on the degree of anomaly in a single area, and can generate dynamic prediction results that reflect the continuous development trend of disasters in space and time.

[0094] The server determines the final disaster impact range based on the dynamic risk assessment values ​​corresponding to each abnormal change area. Specifically, the server sets a risk assessment threshold, identifies abnormal change areas with dynamic risk assessment values ​​exceeding the threshold as disaster impact areas, and considers adjacent areas with a disaster development path as potential impact areas. The risk assessment threshold is determined based on historical disaster verification results and can be set to 0.60 to 0.85.

[0095] The server adjusts the dynamic prediction results of mine geological hazards based on the updated hazard development path. Specifically, the server continuously acquires new geophysical monitoring data and re-executes the rock mass change state analysis, abnormal change process identification, and hazard development path generation processes. When new data indicates that the abnormal change area has expanded, the abnormal diffusion direction has changed, or the hazard development stage has shifted, the server updates the original hazard development path and recalculates the dynamic risk assessment value corresponding to each abnormal change area, thereby adjusting the hazard impact range and dynamic prediction results.

[0096] Through the above processing, the server jointly analyzes the disaster development stage and the disaster development path, which can not only determine the current disaster risk area, but also predict the future impact range based on the disaster evolution process, and dynamically correct the prediction results by combining real-time monitoring data, so as to realize the transformation of mine geological disaster from static risk assessment to dynamic evolution prediction, and improve the accuracy and timeliness of disaster early warning.

[0097] This application also provides a dynamic prediction device for mine geological hazards based on multi-source geophysical data, referring to... Figure 2 , Figure 2 This is a schematic diagram of a dynamic prediction device for mine geological disasters based on multi-source geophysical data, provided in an embodiment of this application. The device is a server, which includes an acquisition module 21 and a processing module 22. The acquisition module 21 is used to acquire geophysical monitoring data within the mining area and perform correlation processing with mining data, historical disaster data, and geological structure data to form multi-source geological state data. The processing module 22 is used to analyze the rock mass change state based on the multi-source geological state data and establish geological state transformation relationships. The processing module 22 is also used to analyze the change correlation between different geophysical data through geological state transformation relationships to determine abnormal change processes. The processing module 22 is also used to analyze the diffusion direction of abnormal areas based on abnormal change processes and generate disaster development paths. The processing module 22 is also used to match the disaster development path with historical disaster processes to determine the disaster development stage. The processing module 22 is also used to generate dynamic prediction results for mine geological disasters based on the disaster development stage and disaster development path.

[0098] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0099] This application also provides an electronic device, with reference to... Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 31, at least one network interface 34, a user interface 33, a memory 35, and at least one communication bus 32.

[0100] The communication bus 32 is used to enable communication between these components.

[0101] The user interface 33 may include a display screen and a camera, and may also include standard wired and wireless interfaces.

[0102] The network interface 34 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0103] The processor 31 may include one or more processing cores. The processor 31 connects to various parts of the server via various interfaces and lines, executing instructions, programs, code sets, or instruction sets stored in the memory 35, and calling data stored in the memory 35 to perform various server functions and process data. Optionally, the processor 31 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 31 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 31 and may be implemented as a separate chip.

[0104] The memory 35 may include random access memory (RAM) or read-only memory. Optionally, the memory 35 may include a non-transitory computer-readable storage medium. The memory 35 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 35 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 35 may also be at least one storage device located remotely from the aforementioned processor 31. Figure 3 As shown, the memory 35, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a dynamic prediction method of mine geological disasters based on multi-source geophysical data.

[0105] exist Figure 3 In the electronic device shown, the user interface 33 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 31 can be used to call the application program stored in the memory 35, which is a dynamic prediction method for mine geological disasters based on multi-source geophysical data. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0106] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0107] This application also provides a non-transitory computer-readable storage medium storing instructions. When executed by one or more processors, these instructions cause an electronic device to perform one or more of the methods described in the above embodiments.

[0108] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0111] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0112] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0113] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for dynamic prediction of geological hazards in mines based on multi-source geophysical data, characterized in that, The method includes: Obtain geophysical monitoring data within the mining area, and combine it with mining data, historical disaster data, and geological structure data for correlation processing to form multi-source geological status data; Based on the multi-source geological state data, analyze the rock mass change state and establish geological state transformation relationships; By analyzing the geological state transformation relationship, the correlation between changes in different geophysical data is determined to identify the abnormal change process; Based on the analysis of the abnormal change process, the direction of the abnormal area's spread is determined, and a disaster development path is generated; Based on the matching of the disaster development path with historical disaster processes, the disaster development stage is determined; Based on the disaster development stage and the disaster development path, dynamic prediction results of mine geological disasters are generated.

2. The method for dynamic prediction of mine geological hazards based on multi-source geophysical data according to claim 1, characterized in that, The step of analyzing the rock mass change state based on the multi-source geological state data and establishing geological state transformation relationships specifically includes: Based on the multi-source geological state data, rock mass response change information is extracted, and the rock mass change state corresponding to different time stages is determined; Based on the changes in the rock mass and historical disaster data, state types are classified, and the transformation relationships between different state types are analyzed to establish the geological state transformation relationships.

3. The method for dynamic prediction of mine geological hazards based on multi-source geophysical data according to claim 1, characterized in that, The process of analyzing the correlation between changes in different geophysical data through the geological state transformation relationship to determine the abnormal change process specifically includes: Based on the geological state transformation relationship, the geophysical data change characteristics corresponding to different rock mass change states are obtained, and the change order and relationship between different geophysical data are analyzed; Based on the order and relationship of change, it is determined whether the changes in geophysical data conform to the change process corresponding to the geological state transformation relationship. When multiple geophysical data undergo consecutive correlated changes, an abnormal change process is identified.

4. The method for dynamic prediction of mine geological hazards based on multi-source geophysical data according to claim 3, characterized in that, The process of determining whether changes in geophysical data conform to the geological state transformation relationship based on the order and relationship of changes, and identifying abnormal change processes when multiple geophysical data undergo consecutive correlated changes, specifically includes: Based on the geological state transformation relationship, the sequence of geophysical data changes corresponding to different rock mass change states is determined, and the current geophysical data change process is matched with the sequence of geophysical data changes. When at least two geophysical data change continuously in the order of the geophysical data change, it is determined that the change of the geophysical data conforms to the geological state transformation relationship, and the abnormal change process is determined based on the change process of the geophysical data.

5. The method for dynamic prediction of mine geological hazards based on multi-source geophysical data according to claim 1, characterized in that, The process of analyzing the direction of the spread of the abnormal area based on the abnormal change process and generating a disaster development path specifically includes: The abnormal change process is used to identify the abnormal change areas, and the correlation between the abnormal change areas is analyzed by combining geological structure data and rock mass change state. Based on the aforementioned correlation, the sequence of changes and the direction of diffusion of the abnormal change areas are determined, and combined with the aforementioned geological state transformation relationship, the disaster development process corresponding to the abnormal change areas is determined, thereby generating the disaster development path.

6. The method for dynamic prediction of mine geological hazards based on multi-source geophysical data according to claim 1, characterized in that, The process of matching the disaster development path with historical disaster processes to determine the disaster development stage specifically includes: Based on the disaster development path, the abnormal change areas, change sequence, and rock mass change state are extracted to form the current disaster evolution characteristics; Obtain the abnormal change process corresponding to the historical disaster process, and match the current disaster evolution characteristics with the historical disaster process to obtain the matching result; The disaster development stage corresponding to the disaster development path is determined based on the matching results.

7. The method for dynamic prediction of mine geological hazards based on multi-source geophysical data according to claim 6, characterized in that, The generation of dynamic prediction results for mine geological disasters based on the disaster development stage and the disaster development path specifically includes: The abnormal change areas, abnormal diffusion directions, and disaster impact ranges are determined by the disaster development stages and disaster development paths. Based on the abnormal change area, the abnormal diffusion direction, and the disaster impact range, a dynamic prediction result of mine geological disaster is generated, and the dynamic prediction result of mine geological disaster is adjusted according to the updated disaster development path.

8. A dynamic prediction device for mine geological hazards based on multi-source geophysical data, characterized in that, The device is used to execute the dynamic prediction method for mine geological hazards based on multi-source geophysical data as described in any one of claims 1 to 7. The device includes an acquisition module and a processing module, wherein... The acquisition module is used to acquire geophysical monitoring data within the mining area, and to perform correlation processing with mining data, historical disaster data and geological structure data to form multi-source geological state data; The processing module is used to analyze the rock mass change state based on the multi-source geological state data and establish geological state transformation relationships; The processing module is also used to analyze the correlation between changes in different geophysical data through the geological state transformation relationship, and to determine the abnormal change process; The processing module is also used to analyze the direction of the spread of the abnormal area based on the abnormal change process and generate a disaster development path; The processing module is also used to match the disaster development path with historical disaster processes to determine the disaster development stage; The processing module is also used to generate dynamic prediction results of mine geological disasters based on the disaster development stage and the disaster development path.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements a dynamic prediction method for mine geological hazards based on multi-source geophysical data as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores instructions that, when executed, perform a dynamic prediction method for mine geological hazards based on multi-source geophysical data as described in any one of claims 1 to 7.

Images