A mine three-dimensional safety situation visual simulation method based on real-time stream calculation

Abstract

The application provides a mine three-dimensional safety situation visual simulation method based on real-time stream calculation, and relates to the field of data processing. In the method, the long-term slow evolution process of surrounding rock is mapped to the continuous consumption of plastic capacity under the event time driving by encapsulating the mine multi-source real-time stream data and binding it to the structural semantic unit in the mine three-dimensional model. By constructing the plastic space domain, voxelizing the space unit and the capacity migration channel, the release and transfer of capacity consumption between the structural semantic units are realized, and the accumulation of the consumption which cannot be closed is accumulated as the structural extrusion residual, and the space lock zone is further identified and expanded. Finally, the continuous visual expression of the slow variable risk is realized in the three-dimensional model in the superimposed rendering mode of the plastic capacity remaining body and the space lock zone. The technical scheme provided by the application facilitates to improve the accuracy of the mine three-dimensional safety situation visual simulation.

Description

Technical Field

[0001] This application relates to the technical field of data processing, specifically to a method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing. Background Technology

[0002] Under deep mining or high-stress mining conditions, the surrounding rock is subjected to complex stress redistribution and slow creep over a long period of time. This process usually does not manifest as a sudden mechanical response, but rather as a monotonous but nonlinear cumulative change in the load-bearing structure and load-bearing path of the surrounding rock. The amplitude of this change is small within a single time scale and is often masked by short-term fluctuations such as blasting disturbances, equipment operation, and personnel activities.

[0003] Currently, most mine safety monitoring systems employ real-time stream computing-based processing frameworks to identify abnormal events or risk states exceeding preset thresholds. However, these real-time stream computing methods typically focus on short-term fluctuations, abrupt events, or significant anomalies, lacking sensitivity to long-term, slowly evolving processes such as stress redistribution and rock creep, which have irreversible structural effects. This results in slow variables being consistently classified as "normal fluctuations" at the data level, failing to generate effective risk representations in subsequent visualization simulations and reducing the accuracy of the simulations.

[0004] Therefore, there is an urgent need for a visualization and simulation method for the three-dimensional safety situation in mines based on real-time stream computing. Summary of the Invention

[0005] This application provides a method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing, which can improve the accuracy of the visualization and simulation of the three-dimensional safety situation in mines.

[0006] The first aspect of this application provides a method for visualizing and simulating the three-dimensional safety situation of a mine based on real-time stream computing. The method includes: acquiring multi-source real-time stream data for the mine, generating an event encapsulation for each real-time stream data, and binding the multi-source real-time stream data to structural semantic units in a three-dimensional mine model. The event encapsulation includes event time, semantic anchoring, and working condition phase. Based on the structural semantic units, a plastic space domain is constructed, and the plastic space domain is mapped to a set of voxelized spatial units corresponding to the three-dimensional mine model, so that each voxelized spatial unit is configured with a corresponding plastic capacity and capacity migration channel to characterize the bearing rearrangement margin of the surrounding rock under current geological and mining conditions and its transfer relationship between structural semantic units. Driven by the event time, the event encapsulation is written into the plastic space domain, the corresponding structural semantic unit is determined according to the semantic anchoring, and the structural semantic unit is mapped according to the working condition phase. The plastic capacity is directionally deducted to uniformly express the evolution of slow variables as a continuous consumption process of plastic capacity in structural semantic units. After the plastic capacity deduction is completed, capacity self-consistency constraint processing is performed based on the capacity migration channel to enable the capacity consumption in the structural semantic unit to form a release or transfer relationship between adjacent structural semantic units, and the capacity portion that cannot form a self-consistent closure is accumulated as a structural compression residual. Based on the plastic spatial domain and the structural compression residual, the spatial locking front of the structural semantic unit is identified, and the spatial locking front is extended according to the stress transfer connectivity relationship to form a spatial locking zone. The plastic spatial domain and the spatial locking zone are projected onto the three-dimensional mine model to perform a three-dimensional safety situation visualization simulation. By rendering the remaining volume of plastic capacity in the set of voxelized spatial units and superimposing the spatial locking zone, the expression of the safety situation of slow variables from long-term invisible to continuous observable is realized.

[0007] A second aspect of this application provides a visualization simulation device for a three-dimensional safety situation in a mine based on real-time stream computing. The device includes an acquisition module and a processing module. The acquisition module is used to acquire multi-source real-time stream data for the mine, generate an event encapsulation for each real-time stream data, and bind the multi-source real-time stream data to structural semantic units in a three-dimensional mine model. The event encapsulation includes event time, semantic anchoring, and working condition phase. The processing module is used to construct a plastic space domain based on the structural semantic units and map the plastic space domain to a set of voxelized spatial units corresponding to the three-dimensional mine model, so that each voxelized spatial unit is configured with a corresponding plastic capacity and capacity migration channel to characterize the bearing rearrangement margin of the surrounding rock under current geological and mining conditions and its transfer relationship between structural semantic units. The processing module is also used to write the event encapsulation into the plastic space domain under the drive of the event time, determine the corresponding structural semantic unit according to the semantic anchoring, and determine the working condition phase according to the working condition phase. The processing module performs directional deduction on the plastic capacity to uniformly express the evolution of slow variables as a continuous consumption process of plastic capacity in structural semantic units. After completing the plastic capacity deduction, the module performs capacity self-consistency constraint processing based on the capacity migration channel to ensure that capacity consumption in the structural semantic units forms a release or transfer relationship between adjacent structural semantic units, and accumulates the capacity portion that cannot form a self-consistent closure as a structural compression residual. The module also identifies the spatial locking front of the structural semantic unit based on the plastic spatial domain and the structural compression residual, and expands the spatial locking front according to the stress transfer connectivity relationship to form a spatial locking zone. Furthermore, the module projects the plastic spatial domain and the spatial locking zone onto the three-dimensional mine model to perform three-dimensional safety situation visualization simulation. By rendering the remaining plastic capacity in the voxelized spatial unit set and superimposing the spatial locking zone, the slow variable is transformed from long-term invisible to a continuously observable safety situation expression.

[0008] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, and both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method described above.

[0009] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing instructions that, when executed, perform the method described above.

[0010] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By transforming the long-standing but difficult-to-identify stress redistribution and slow creep processes in non-coal mines—which are often difficult to detect using immediate thresholds—from imperceptible background changes into continuously observable spatial evolution objects, this method achieves unified alignment of multi-source real-time streaming data across time, space, and operating conditions through event encapsulation. A plastic spatial domain is constructed with structural semantic units as the core, allowing the surrounding rock bearing capacity to be continuously expressed in three-dimensional space as plastic capacity. Through directional deduction and capacity self-consistency constraints, the long-term accumulation of slow variables is solidified into structural compression residuals and spatial locking evolution processes. Finally, through the three-dimensional visualization of the spatial locking front and spatial locking zone, instability risks that would otherwise only manifest during a disaster are revealed in advance as a traceable and interpretable gradual trend. This effectively compensates for the insensitivity of existing real-time streaming computation and three-dimensional safety situation systems to slow variables such as surrounding rock bearing capacity, significantly improving the ability to proactively perceive risks and make safety decisions in deep or high-stress areas of non-coal mines. Therefore, it facilitates improved accuracy in three-dimensional safety situation visualization simulation of mines. Attached Figure Description

[0011] Figure 1 A flowchart illustrating a method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing, provided in an embodiment of this application; Figure 2 A schematic diagram of a module for a mine three-dimensional safety situation visualization simulation device based on real-time stream computing, provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0012] 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

[0013] 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.

[0014] 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.

[0015] 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.

[0016] To address the aforementioned technical problems, this application provides a method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing, referring to... Figure 1 , Figure 1 This is a flowchart illustrating a method for visualizing and simulating the three-dimensional safety situation in a mine based on real-time stream computing, provided in an embodiment of this application. The method is applied to a server and includes steps S110 to S160, as follows:

[0017] S110. Acquire multi-source real-time streaming data for the mine, generate an event encapsulation for each real-time streaming data, and bind the multi-source real-time streaming data to the structural semantic unit in the 3D model of the mine. The event encapsulation includes event time, semantic anchoring, and working condition phase.

[0018] Specifically, a server refers to a computing and control entity that undertakes the access, processing, status maintenance, and result output of multi-source real-time streaming data in the mine. Its role is not simply a data storage or forwarding node, but rather the core execution carrier of the entire real-time streaming computing and 3D security situation generation process. Servers are deployed on ground dispatch centers, mine data centers, or highly reliable edge computing nodes to continuously run key functions such as real-time streaming access, event timing processing, semantic anchoring, flexible spatial domain updates, and 3D situation visualization.

[0019] When the server uniformly accesses microseismic event streams, acoustic emission event streams, surrounding rock displacement streams, surrounding rock convergence streams, support stress streams, borehole stress streams, seepage pore pressure streams, temperature and humidity environment streams, and production behavior streams through the real-time stream access layer, data reporting channels are configured for various sensors and production systems both above and below ground in the mine. This ensures that all types of data enter the server's real-time stream access layer using a unified message carrier. The real-time stream access layer is used to access, aggregate, and normalize data from different protocols, links, and sampling rhythms. Microseismic event streams are used to characterize events caused by surrounding rock fracturing or stress release. Acoustic emission event streams are used to characterize high-frequency elastic wave events generated by the propagation of microcracks within materials. Surrounding rock displacement and convergence streams are used to characterize the displacement changes of the surrounding rock at different locations and the convergence changes of the roadway cross-section. Support stress streams are used to characterize support components such as anchor bolts, anchor cables, and steel arches. The stress state changes are represented by various parameters: borehole stress flow, which characterizes stress changes obtained through borehole stress gauges or similar devices; seepage pore pressure flow, which characterizes changes in pore water pressure or seepage pressure over time; temperature and humidity environment flow, which characterizes environmental quantities such as temperature and humidity to describe material deterioration or condensation corrosion conditions; and production behavior flow, which characterizes the occurrence time, duration, and area of ​​production behaviors such as blasting, loading, transportation, filling, drainage, and ventilation switching. During unified access, the original timestamps, original spatial indication information, and equipment identification information carried by various types of data are kept unaltered. The original timestamps characterize the acquisition time recorded by the equipment, the original spatial indication information characterizes the installation location, measuring point number, or positioning coordinates corresponding to the data, and the equipment identification information characterizes the unique equipment identity of the data source, so that the source can be traced and consistency verification can be performed when time standardization and semantic anchoring are completed later.

[0020] When generating the event encapsulation while keeping the original timestamps, original spatial indication information, and device identification information of the multi-source real-time streaming data unchanged, the server uses the event time as a unified time reference to resolve arrival disorder, retransmission, and jitter caused by different sampling frequencies and different communication links. This ensures that subsequent real-time streaming calculations proceed in the order of event occurrence rather than the order of arrival. The event time is obtained from the original timestamp through time standardization. The time standardization process first establishes clock offset and clock drift estimates for each device identifier, and then maps the original timestamp to the event time. The mapping relationship can be expressed as:

[0021] in, Indicates the event time, used as a unified sorting time for real-time stream computing; This represents the original timestamp, recorded by the device at the moment of data collection. This represents the time offset correction function for device identifier d, used to characterize the offset and drift over time between the device's clock and the server's reference clock. The value can be estimated through time synchronization messages between devices and servers, the arrival relationship of the same physical event on multiple devices, or a marker event with a clear occurrence time in the production flow. When generating the event encapsulation, the event time is written into the event encapsulation and the original timestamp, arrival time and device identification information are retained at the same time. This allows the event encapsulation to be used for subsequent unified sorting by event time, as well as for backtracking and verification of late data, retransmitted data and device clock anomalies. The sampling frequency difference is reflected by aligning the event time to the same event time series, which means that various types of data are projected onto the same time axis as comparable positions. High-frequency data enters the sequence with more dense event time points, and low-frequency data enters the sequence with sparser event time points. Real-time stream computing achieves cross-source alignment on the same event time series based on the event time window, thereby avoiding slow variables being submerged by high-frequency fluctuations in short window aggregation.

[0022] When performing semantic anchoring processing based on a pre-established 3D mine model space, the server predefines structural semantic units in the 3D mine model and establishes a spatial index for each structural semantic unit, enabling event encapsulation to map from the original spatial indication information to structural semantic units with engineering semantics. Structural semantic units are used to represent stope units, roadway units, goaf units, filling body units, fracture zone units, or support component units. Stope units describe the operational space range of mining or tunneling; roadway units describe the centerline, cross-section, and mileage segments of roadways; goaf units describe the boundaries of the formed goaf space and the interface with adjacent surrounding rock; filling body units describe the spatial range and interface after the filling material is formed; fracture zone units describe the distribution range and influence area of ​​faults or fracture zones in 3D space; and support component units describe the spatial arrangement of support objects such as anchor bolts, anchor cables, steel arches, and shotcrete layers. Semantic anchoring processing affects event encapsulation. The system reads the original spatial indication information and performs spatial matching. Spatial matching maps the measurement point number or positioning coordinates to the spatial index of the mine's 3D model. Then, based on the spatial index, it determines the structural semantic unit to which the event encapsulation belongs and writes the structural semantic unit identifier into the event encapsulation, so that the event encapsulation is no longer just attached to geometric coordinate points but is stably bound to the structural semantic unit. When the original spatial indication information is a measurement point number, the mapping is achieved through the pre-binding table between the measurement point number and the structural semantic unit. When the original spatial indication information is positioning coordinates, the mapping is completed by determining the boundary of the mining unit, the buffer zone of the roadway unit, the boundary body of the goaf unit, or the influence body of the fracture zone unit where the positioning coordinates fall. After the mapping is completed, the binding relationship between the event encapsulation and the structural semantic unit enters the subsequent plastic spatial domain processing link, so that the same structural semantic unit can continuously gather event encapsulations from multi-source real-time streaming data and express the gradual evolution of the surrounding rock bearing structure over time on the same engineering semantic object.

[0023] S120. Construct a plastic spatial domain based on structural semantic units, and map the plastic spatial domain to a set of voxelized spatial units corresponding to the three-dimensional model of the mine, so that each voxelized spatial unit is configured with a corresponding plastic capacity and capacity migration channel to characterize the bearing rearrangement margin of the surrounding rock under the current geological and mining conditions and the transfer relationship between structural semantic units.

[0024] Specifically, in order to ensure that the configuration of plastic capacity is no longer limited to a linear form of benchmark capacity multiplied by weights, but can simultaneously characterize the nonlinear coupling relationship between geological attribute parameters, mining method attribute parameters, structural sensitivity distribution, and the spatial location within the structural semantic unit, the plastic capacity benchmark is first generated by a multi-parameter coupling function at the structural semantic unit level. Then, spatial potential field superposition, anisotropic direction projection, and phase modulation are introduced at the voxelized spatial unit level. This allows the plastic capacity of different voxelized spatial units within the same structural semantic unit to reflect both the spatial differences that are more sensitive to the weak surface of the structure and the temporal differences in the weakening rate of the bearing rearrangement margin at different mining stages, while avoiding scale distortion and boundary abrupt changes caused by linear superposition.

[0025] The plastic capacity benchmark can be obtained by performing nonlinear compression, mutual coupling, and robust saturation on geological and mining attribute parameters. A two-layer gating approach is used to ensure that the parameter influence has a structure of initial suppression followed by saturation, thereby avoiding excessive amplification or reduction of the plastic capacity benchmark due to a single parameter anomaly. Its expression is:

[0026] in, A benchmark for the plasticity capacity of structural semantic units; This indicates the upper limit of the plastic capacity reference, used to constrain the plastic capacity reference from exceeding a preset available range; This represents the Sigmoid function, which maps the combined effect within the parentheses to a finite interval, thereby achieving nonlinear compression and saturation. The reference offset represents the coupling between geology and mining methods; This represents a vector of geological attribute parameters, whose values ​​are encoded by parameters such as lithology, integrity level, degree of joint and fracture development, degree of influence of fault fracture zones, in-situ stress level distribution, water content, and permeability characteristics. This represents a vector of mining method attribute parameters, the values ​​of which are encoded by parameters such as mining sequence constraints, blasting intensity characteristics, advance speed characteristics, filling method characteristics, and support type characteristics; Indicates the first A geological feature mapping function is used to... Several elements in the form are combined to form a single interpretable eigenvalue, the value of which can be obtained by piecewise function, exponential compression or robust normalization; Indicates the first Each sampling feature mapping function is used to... Several elements in the form combine to form a single interpretable eigenvalue; and These represent the coefficients of influence of geological features and mining method features on the plastic capacity benchmark, respectively. Their values ​​can be determined by historical calibration, expert prior knowledge, or online correction. It represents the coupling coefficient between geological features and mining method features, and is used to characterize the interactive effect of a certain mining method condition that significantly affects the plastic capacity benchmark only under specific geological conditions. Indicates the reference bias for penalty gating; This represents the risk penalty factor vector, used to aggregate factors that would further weaken the load-bearing rearrangement margin, such as high stress concentration, high disturbance frequency, continuous high pore pressure, and strong corrosive environment. This represents the risk penalty weight vector, used to adjust the relative impact of each risk penalty factor; the last... This indicates a penalty gating term, used to further reduce the plastic capacity benchmark under high-risk conditions, making the plastic capacity benchmark more sensitive to adverse conditions and having saturation constraints.

[0027] At the voxelized spatial unit level, to avoid the problem that the linear attenuation caused by using only distance weighting is too smooth and fails to represent the sharp effects of weak surfaces, a spatial potential field superposition term composed of multiple types of structural objects is introduced. Combined with the anisotropic direction projection term, this allows the plastic capacity of the voxelized spatial unit to exhibit differentiated attenuation along the fracture zone strike, the roadway axis, or the tangential direction of the goaf boundary. The expression is as follows:

[0028] in, Indicates the first The plasticity capacity of individualized spatial units; Indicates the first The spatial position of an individualized spatial unit in the three-dimensional coordinate system of a mine; It represents the spatial potential field value, used to characterize the comprehensive sensitivity of the location to structural objects such as the goaf boundary, fracture zone, roadway intersection area and support component unit; This represents the space potential attenuation coefficient, used to adjust the strength of the space potential's suppression of the plastic capacity; This represents the anisotropy reduction factor, used to adjust the magnitude of directional influence; It still represents the Sigmoid function, used to map directional projection results to a finite reduction ratio; Indicates the relationship with the first The local interface normal or dominant local structure direction associated with the individualized spatial unit can be obtained from the contact interface or local structure geometry of the plastic spatial domain. The dominant stress transmission direction or weak surface orientation at this location can be determined by stress transmission connectivity or the orientation information of fracture zone units. Indicates directional projection gain, used for adjustment Sensitivity to reduction; This indicates the directional projection offset, used to adjust the trigger position of directional reduction; It represents the azimuth angle of a voxelized spatial unit relative to the reference axis of a structural semantic unit, used to characterize the relative relationship between spatial position and structural orientation; It represents the phase modulation amplitude, used to map the periodic weakening band or segmented features within the structural semantic unit to the plastic capacity; This indicates the phase modulation frequency, used to control the band density; This indicates the phase offset, used to align with the actual structural zone start point.

[0029] Spatial potential field It can be composed of the superposition of distance field, interface influence, and state influence of multiple types of structural objects, so that the influence of goaf boundary, fracture zone, filling interface, and support component unit on plastic capacity can be both cumulative and state-modulated. The expression is:

[0030] in, Indicates the number of structural object categories included in the potential field modeling; Indicates the first The basic weights of a class of structural objects on the spatial potential field are used to reflect the degree to which the class of objects contributes to the structural sensitivity. Indicates the first Individualized spatial unit to the first Distance metrics for class-structured objects can be calculated from the nearest boundary distance, the nearest axis distance, or the nearest interface distance. Indicates the first The influence radius threshold of a class structure object is used to determine the location where the influence of the potential field begins to increase significantly; Indicates the first The steepness coefficient of the influence of class structure objects is used to control the steepness of the potential field as it changes with distance; This represents the Softplus function, used to create a smooth but sharp nonlinear growth near a threshold, avoiding the non-differentiable abrupt changes introduced by piecewise functions; Represents the state modulation coefficient, used to map the state of a structured object to the gain of the potential field strength; Indicates the first State variables of class structure objects are used to characterize states that can change over time, such as the degree of filling material formation, the proportion of support components involved, or the activity level of fracture zones. The values ​​can be obtained by updating the aggregated state of the event encapsulation body on the corresponding structural semantic unit.

[0031] The above three sets of formulas together realize the plastic capacity configuration from structural semantic units to voxelized spatial units. The plastic capacity benchmark determines the overall level through the nonlinear coupling of geological attribute parameters and mining method attribute parameters. The plastic capacity of voxelized spatial units characterizes spatial non-uniformity and anisotropy through spatial potential field, directional projection and phase modulation. Thus, the plastic capacity can not only express the long-term difference in bearing rearrangement margin under the background of slow variable accumulation, but also provide a calculation basis that is more in line with the complex structural conditions of non-coal mines for subsequent capacity migration channels and directional deduction.

[0032] S130. Driven by the event time, the event encapsulation is written into the plastic space domain, the corresponding structural semantic unit is determined according to the semantic anchor, and the plastic capacity is directionally deducted according to the working condition phase, so that the evolution of slow variables is uniformly expressed as the continuous consumption process of plastic capacity on the structural semantic unit.

[0033] Specifically, driven by event time, when determining the structural semantic unit corresponding to the event encapsulation body and locating it to the voxelized spatial unit set based on semantic anchoring, the real-time stream computing framework uses event time as the sole sorting and triggering benchmark. Arriving event encapsulation bodies are written into the event time queue according to their event time, and processing is triggered sequentially within the event time queue according to the event time order. This avoids processing order deviations caused by out-of-order arrivals, retransmissions, and link jitter. Semantic anchoring refers to the structural semantic unit identifier carried in the event encapsulation body or mapping information from which the structural semantic unit identifier can be deduced. The event encapsulation body can be determined by reading the structural semantic unit identifier based on the semantic anchoring. The structural semantic unit to which it belongs; the index relationship between the structural semantic unit and the voxelized spatial unit refers to a mapping table with the structural semantic unit identifier as the key and the set of voxelized spatial unit identifiers as the value. The mapping table is written into the state storage during the plastic space domain construction stage and is locally maintained with geometric updates, so that the target voxelized spatial unit set can be obtained in constant time or logarithmic time during the localization stage. After localization is completed, the event encapsulation body is bound to the voxelized spatial unit set, so that subsequent deduction only acts on the voxelized spatial unit set and does not overflow to other structural semantic units, thereby ensuring that the plastic capacity consumption trajectory is consistent with the structural semantic unit.

[0034] When reading the working condition phase after determining the structural semantic unit and selecting the capacity deduction strategy based on the working condition phase, the working condition phase refers to the production stage label obtained from the parsing of the production behavior flow, used to characterize the blasting phase, loading phase, transportation phase, filling phase, drainage phase, or ventilation phase corresponding to the occurrence of the event package. The capacity deduction strategy refers to the set of strategies that map the observation semantics of the event package to the plastic capacity deduction method. The capacity deduction strategy includes at least three types of parameters: deduction intensity, deduction direction, and deduction diffusion radius. The deduction intensity is used to characterize the magnitude of the plastic capacity consumption caused by the event package under the working condition phase. The deduction direction is used to characterize the dominant direction of plastic capacity consumption along the structural weak surface, goaf boundary, or roadway axis. The deduction diffusion radius is used to characterize the propagation range of the deduction effect within the voxelized spatial unit set. The working condition phase and the capacity deduction strategy are established through a strategy selection function. The strategy selection function outputs the strategy parameter vector of the event package under the current working condition phase, and its expression is:

[0035] in, Represents the event encapsulation body The corresponding capacity reduction strategy parameter vector; This represents the strategy selection function, used to determine the deduction intensity, deduction direction, and deduction diffusion radius under given operating phase conditions; Represents the event encapsulation body The carried operating condition phase; Represents the event encapsulation body The observation type label is used to distinguish the different observation semantics corresponding to microseismic event flow, acoustic emission event flow, surrounding rock displacement flow, surrounding rock convergence flow, support stress flow, borehole stress flow, seepage pore pressure flow, or temperature and humidity environment flow. Represents the event encapsulation body The combined value of link trustworthiness and device trustworthiness is used to conservatively reduce the deduction intensity when data quality is poor. The value can be obtained by fusing the link credibility and device credibility according to a preset weight; the output of the strategy selection function includes at least the deduction intensity component, the deduction direction component, and the deduction diffusion radius component, which are used to drive the subsequent directional deduction calculation.

[0036] When performing directional deduction processing on voxelized spatial units corresponding to structural semantic units based on the capacity deduction strategy, a directional weight field is first constructed according to the deduction direction component in the capacity deduction strategy parameter vector. This gives each voxelized spatial unit in the voxelized spatial unit set a directional weight related to its spatial position. The directional weight is used to characterize the proportion of consumption undertaken by the voxelized spatial unit in the dominant deduction direction, so that the deduction is no longer uniform decay but forms a spatial gradient along the dominant direction. Then, based on the deduction intensity component and the deduction diffusion radius component, the deduction effect of the event encapsulation is normalized and distributed within the voxelized spatial unit set, so that the deduction effect reflects the dominant directionality and is limited to the spatial neighborhood covered by the deduction diffusion radius, thus forming a continuous and traceable consumption trajectory at the spatial level. Directional deduction can be achieved by distributing the total deduction amount according to the directional weight within the voxelized spatial unit set, the expression of which is:

[0037] in, Represents the voxelized spatial unit The amount of plastic capacity deducted, with negative values ​​indicating consumption; Represents the event encapsulation body The total deduction intensity determined under the current operating phase and observation type conditions is given by the deduction intensity component in the capacity deduction strategy parameter vector, and can be corrected according to the link credibility and device credibility. Represents the event encapsulation body The effective reduced neighborhood formed by the set of voxelized spatial units obtained from the localization under the constraint of reduced diffusion radius, where the reduced diffusion radius is given by the reduced diffusion radius component in the capacity reduction strategy parameter vector, and Includes all voxelized spatial units that satisfy the condition that the distance from the spatial anchor position of the event encapsulation body does not exceed the subtracted diffusion radius and belong to the same structural semantic unit; Represents voxelized spatial units The directional weights are used to characterize the relative contribution of the voxelized spatial unit in the dominant subtraction direction. The value of can be determined based on the angle between the position vector of the voxelized spatial unit and the subtraction direction vector, as well as its proximity to the weak surface of the structure; the denominator This is used to normalize the directional weights within the effective deduction neighborhood, thereby ensuring that the sum of the deduction amounts of all voxelized spatial units equals the total deduction intensity. After the deduction is completed, the updated plastic capacity is written to the state storage, so that the subsequent event encapsulation continuously superimposes the deduction effect on the event time series, thereby making the evolution of slow variables manifest as the long-term continuous consumption of plastic capacity at the structural semantic unit level, and as a continuous consumption trajectory that gradually advances along the dominant direction at the spatial level.

[0038] S140. After completing the reduction of plastic capacity, perform capacity self-consistency constraint processing based on the capacity migration channel so that the capacity consumption in the structural semantic unit forms a release or transfer relationship between adjacent structural semantic units, and accumulate the capacity part that cannot form a self-consistent closure as structural extrusion residual.

[0039] Specifically, when locating the target structural semantic unit in the plastic space domain where plastic capacity deduction occurs and summarizing the capacity consumption and direction, the set of structural semantic unit identifiers that have been written into the event encapsulation body within the current event time processing sequence is first read from the state storage, and the target structural semantic unit is determined by the set of structural semantic unit identifiers. Subsequently, within the set of voxelized spatial units corresponding to the target structural semantic unit, the change in plastic capacity of each voxelized spatial unit within the event time processing sequence is counted, all negative changes are merged into the capacity consumption, and the capacity consumption is bound to the target structural semantic unit. The capacity consumption direction is obtained by back-calculating the directional weight field formed in the directional deduction stage, that is, using the voxelized spatial unit position vector as the basis and the voxelized spatial unit deduction amount as the weight, the dominant consumption direction vector of the target structural semantic unit is calculated, so that the subsequent self-consistent constraint processing has clear directional consistency constraints. The capacity consumption and capacity consumption direction can be expressed as:

[0040] in, Represents the target structural semantic unit Capacity consumption within the event-time processing sequence; Represents the target structural semantic unit The corresponding set of voxelized spatial units; Represents voxelized spatial units The change in plastic capacity within the time sequence of this event; a negative value indicates a deduction. This is used to accumulate only the deducted portion and ignore the portion where the plastic capacity increases or remains unchanged; the direction of capacity consumption can be represented as:

[0041] in, Represents the target structural semantic unit The capacity consumption direction vector; Represents voxelized spatial units Spatial location vector; Represents the target structural semantic unit The geometric center position vector of the set of voxelized spatial units can take values ​​from... All The mean is obtained; the norm of the denominator is used to normalize the direction vector to obtain the unit direction, which facilitates subsequent consistency comparison with the channel directionality.

[0042] When reading internal migration channels and cross-semantic migration channels based on the capacity migration channel set corresponding to the structural semantic unit and filtering the candidate channel set, the capacity migration channel set connected to the target structural semantic unit is first read from the state storage. The capacity migration channel set is stored with channel endpoint structural semantic unit identifier pairs, channel directionality, channel strength, and channel availability as channel attributes. Among them, internal migration channels are used to characterize the capacity migration path between voxelized spatial units within the target structural semantic unit, and cross-semantic migration channels are used to characterize the capacity migration path between the target structural semantic unit and adjacent structural semantic units along the stress transfer connectivity. Channel availability refers to whether a channel is allowed to release or transfer capacity under the current event time and current operating phase. Channel directivity refers to the dominant propagation direction vector of the channel, and channel strength refers to the upper limit of the capacity transfer ratio that the channel can carry. During screening, the operating phase is first used as a phase consistency constraint to eliminate channels marked as unavailable under the current operating phase. Then, the capacity consumption direction is used as a directional consistency constraint to calculate the alignment degree between the channel directivity and the capacity consumption direction, and channels with insufficient alignment are eliminated. Finally, a candidate channel set is formed for capacity release or capacity transfer. The alignment degree can be expressed using cosine similarity:

[0043] in, Represents the semantic unit of the target structure Pointing to adjacent structural semantic units The degree of directional alignment across semantic transfer channels; This represents the capacity consumption direction vector; This represents the channel directionality vector across the semantic transfer channel; the denominator is used for normalization to make... Reflecting the degree of consistency of directional angles, the candidate channel set can be obtained by setting an alignment threshold and combining it with channel availability.

[0044] When performing capacity release determination or capacity transfer allocation processing on capacity consumption under the constraints of the candidate channel set, the capacity release determination is used to identify whether adjacent structural semantic units exhibit a closed response consistent with the capacity consumption direction and phase with the current operating condition within the same event time processing sequence. The closed response can manifest as a decrease in the plastic capacity decrement rate of adjacent structural semantic units, an improvement in the availability of capacity migration channels, or a slowdown in the growth rate of structural extrusion residuals, all consistent with the release state. When a closed response that satisfies both time and phase consistency exists, a portion of the capacity consumption is marked as the capacity release amount and a release relationship is established with the corresponding adjacent structural semantic units. When the capacity release is insufficient for closure or no available release relationship exists, capacity transfer allocation processing is performed. The remaining capacity consumption is normalized and allocated according to the channel strength of the candidate channel set, and the capacity transfer amount is written into the voxelized spatial unit set corresponding to the adjacent structural semantic units through cross-semantic migration channels, so that the capacity consumption is closed in the form of load rearrangement formed by transferring to the adjacent structural semantic units. The capacity transfer allocation can be expressed as:

[0045] in, Represents the semantic unit of the target structure To adjacent structural semantic units The amount of capacity transferred in the allocation; Indicates the amount of capacity consumed; This indicates the capacity release amount obtained through capacity release determination, and the value is no greater than [value missing]. ; This represents the set of adjacent structural semantic units corresponding to the candidate channel set; Indicates cross-semantic transfer channels The channel strength is used to characterize the channel's ability to carry capacity transfer; Indicates cross-semantic transfer channels The channel availability threshold value is used to characterize whether the channel is allowed to transfer capacity under the current operating phase and event time. The value can be 0 or 1 for hard gating, or a continuous value between 0 and 1 for soft gating; the denominator is used to normalize the available strength of all candidate channels, thereby ensuring that the sum of the capacity transfers obtained by all adjacent structural semantic units is equal to the total capacity to be transferred. .

[0046] When applying joint constraints of time consistency, direction consistency, phase consistency, and channel consistency during capacity release and transfer, time consistency means that the states of adjacent structural semantic units referenced in the capacity release determination and capacity transfer allocation must fall within the same event time processing sequence or a preset allowable lag window. Direction consistency means that the directional alignment of the selected candidate channels must meet preset requirements to avoid reverse closure. Phase consistency means that the candidate channel is allowed under the current operating phase and the closing response of adjacent structural semantic units does not conflict with the engineering interpretation under this operating phase. Channel consistency means that capacity release or capacity transfer can only be achieved through available internal migration channels or cross-semantic migration channels in the capacity migration channel set, and undefined closed paths must not be constructed. The above four types of consistency constraints are combined into a closure determination gating function, which outputs the determination result of whether any candidate closure relationship is valid, and retains the capacity portion that is determined to be invalid as unclosed capacity to avoid over-closure masking structural compression. The gating function can be expressed as:

[0047] in, Represents the semantic unit of the target structure To adjacent structural semantic units The results of closed-loop gating; This indicates an indicator function that takes the value 1 when the condition is met and 0 when the condition is not met. It represents the time deviation used for closure determination, and its value is the absolute value of the difference between the event time of the target structural semantic unit and the event time of the referenced state of the adjacent structural semantic unit; Indicates the maximum allowable time deviation, used to limit time consistency; Indicates the degree of directional alignment; The minimum alignment threshold representing directional consistency; This indicates the operating phase corresponding to the target structural semantic unit. The phase of the working condition used for closure determination of adjacent structural semantic units; Indicates the channel availability threshold value; when When the value is 0, the candidate closure relationship is not included in the capacity release or capacity transfer closure amount, and the corresponding capacity portion is retained as unclosed capacity.

[0048] When accumulating unclosed capacity that cannot form a self-consistent closure in the capacity consumption as structural squeeze residual and establishing a binding relationship, after completing the calculation of capacity release and capacity transfer, the unclosed capacity is calculated as the remaining part of the capacity consumption, and the unclosed capacity is written into the structural squeeze residual accumulation item of the target structural semantic unit. This ensures that the structural squeeze residual continues to grow with the event time processing sequence and is not cleared due to window sliding. Establishing a binding relationship between the structural squeeze residual and the structural semantic unit means maintaining the state of the structural squeeze residual in the state storage using the structural semantic unit identifier as the key, and simultaneously recording the current operating condition phase and capacity consumption direction during each update. This allows the structural squeeze residual to not only quantify the capacity that failed to close, but also explain in which production stage the closure failure occurred and along which spatial direction. The update of unclosed capacity and structural squeeze residual can be represented as:

[0049] in, Represents the target structural semantic unit The unclosed capacity within the event time processing sequence; Indicates the amount of capacity consumed; Indicates the amount of capacity released; Indicates the semantic units of adjacent structures The amount of capacity transferred in the allocation; The closure relation gating result is used to ensure that only the transfer quantities that satisfy the joint constraints are included in the closure quantity; the cumulative update of the structural extrusion residual can be expressed as:

[0050] in, Represents the target structural semantic unit The cumulative value of structural compression residuals at the end of the current event time processing sequence; This represents the cumulative value of the structural compression residuals before the start of the event time processing sequence; This indicates the newly added unclosed capacity; at the same time, the operating phase will be... With respect to capacity consumption direction The data is written into the state storage along with the updated record of the structural compression residuals, so that the subsequent spatial locking front identification stage can continuously identify the structural compression characteristics of the surrounding rock bearing path rearrangement based on the growth trend of the structural compression residuals, the phase distribution of the working conditions, and the consistency of the direction.

[0051] S150. Based on the plastic spatial domain and structural extrusion residual, the spatial locking front of the structural semantic unit is identified, and the spatial locking front is extended according to the stress transfer connectivity relationship to form a spatial locking zone.

[0052] Specifically, when a structural semantic unit satisfies the spatial dead front determination condition and is identified as a spatial dead front within multiple consecutive event-time processing sequences, a state trajectory arranged by event time is first maintained for each structural semantic unit in the state storage. The state trajectory includes at least the plastic capacity surplus trajectory, the structural extrusion residual trajectory, and the capacity migration channel availability trajectory. The plastic capacity surplus refers to the sum or average of the plastic capacity currently retained by the set of voxelized spatial units corresponding to the structural semantic unit. The structural extrusion residual refers to the cumulative value of the unclosed capacity that the structural semantic unit cannot form a self-consistent closure in the capacity self-consistency constraint processing. The capacity migration channel availability refers to the cross-semantic relationship between the structural semantic unit and its adjacent structural semantic units. The availability of the migration channel under the current operating phase and structural conditions allows for capacity release or transfer. Subsequently, trend extraction is performed on a sliding discriminant window consisting of multiple consecutive event time processing sequences. A remaining plastic capacity greater than a preset threshold is used to exclude structural semantic units that have completely lost stability or exhausted their plastic capacity (e.g., a preset threshold of 0). The cumulative growth trend of structural compression residuals is used to confirm the continued failure of load-bearing path rearrangement at the structural level. The decreasing trend of capacity migration channel availability is used to confirm that the release or transfer path is being restricted. These three conditions jointly characterize the spatially locked critical state where there is still plastic margin, but the plastic margin is becoming increasingly difficult to migrate. The determination can be achieved by simultaneously satisfying both statistical and trend quantities within the window, and its expression is:

[0053] in, Represents structural semantic units The determination result of whether it is identified as the spatial lock-up front; This indicates an indicator function that takes the value 1 if the condition is true and 0 otherwise. Represents structural semantic units The mean or weighted mean of the remaining plastic capacity within the sliding discrimination window is obtained by summing or averaging the plastic capacity of the corresponding voxelized spatial units of the structural semantic unit. This represents the remaining plastic capacity threshold, used to define the minimum level at which there is still a plastic margin. Represents structural semantic units The growth slope or growth intensity of the structural extrusion residual within the sliding discrimination window can be obtained from the linear fitting slope or the first and last difference of the structural extrusion residual sequence within the window. This represents the threshold for the growth of structural compression residuals, used to define the minimum level at which the cumulative growth trend is significant; Represents structural semantic units The slope of the change in availability of the content migration channel in the sliding discrimination window can be obtained from the linear fitting slope or the first and last difference of the availability sequence of the content migration channel in the window. This represents the threshold for reduced availability of capacity migration channels, used to define the minimum level at which a significant trend of decreasing availability is observed; when At that time, the structural semantic unit Mark it as a spatially locked front element and write it into the spatially locked front set so that subsequent extended processing can start from this spatially locked front set.

[0054] When performing connectivity expansion processing on the spatially locked front and consistency checks on adjacent structural semantic units based on the pre-established stress transfer connectivity relationships between structural semantic units, a stress transfer connectivity graph is first established in the semantic layer of the 3D mine model. This graph uses structural semantic units as nodes and stress transfer connectivity edges as edges. The stress transfer connectivity edges characterize the structural paths through which the redistribution of surrounding rock stress can propagate from one structural semantic unit to another. These paths are constrained by geological structural relationships, goaf boundary relationships, filling interface relationships, and roadway network relationships. The connectivity expansion processing starts from the set of spatially locked fronts, traverses adjacent structural semantic units along the stress transfer connectivity edges, and checks each... Adjacent structural semantic units undergo a consistency check. This check determines whether adjacent structural semantic units exhibit the same trend of structural compression residual growth, the same trend of limited availability of capacity migration channels, and the continuity of capacity consumption direction as the spatially locked-up front unit within the same event timeframe. Continuity of capacity consumption direction means that the capacity consumption direction of adjacent structural semantic units and the capacity consumption direction of the spatially locked-up front unit are spatially continuous and do not conflict with the direction of the stress transfer connection between them. This avoids mistakenly incorporating isolated anomalies unrelated to spatial locking evolution into the expansion range. The consistency check can be achieved by jointly gating trend similarity, degree of limited availability, and directional continuity, and its expression is:

[0055] in, Represents adjacent structural semantic units Compared to the space-locked front unit Whether the consistency test results are passed; This indicates the similarity of the growth trend of structural compression residuals, used to measure... and The degree of consistency in magnitude and direction can be obtained by normalized difference, correlation coefficient, or a combination of sign consistency and amplitude consistency. Indicates the trend similarity threshold; and Representing structural semantic units respectively With structural semantic units The growth slope of structural compression residuals within the same event time range; Represents structural semantic units The slope of the change in capacity migration channel availability within the same event time range, taking a negative value and less than 1. The trend of limited usability of characterization is significant; and Representing structural semantic units respectively With structural semantic units The capacity consumption direction vector is obtained by weighting and normalizing the deduction distribution of each voxelized spatial unit; This represents the continuity threshold for capacity consumption direction, used to limit the angle between the two directions to be sufficiently small. The stress transfer connected edge direction vector is used to characterize the structural semantic unit. Pointing to structural semantic units The direction of connectivity propagation can be determined by the direction of the line connecting the geometric centers of the two structural semantic units or the normal direction of the contact interface. This represents the consistency threshold along the connected edge direction, used to limit the spatial deadlock evolution direction from conflicting with the connected propagation direction; when Time-determined structural semantic unit If the consistency check passes, the consistency check fails and the expansion along the connected edge is terminated.

[0056] When adjacent structural semantic units pass the consistency test and are incorporated into the spatial locking front, and continue to expand to form a spatial locking zone, the adjacent structural semantic units that pass the consistency test are added to the spatial locking front set. The spatial locking front set continues to iteratively expand outward on the stress transfer connectivity graph until no new structural semantic units pass the consistency test or the preset expansion depth limit is reached, thus obtaining a spatial locking zone composed of multiple connected structural semantic units. The spatial locking zone refers to the connected structural semantic unit subgraph obtained by expanding the spatial locking front set, used to characterize the continuous spatial region where the recoverability of the surrounding rock is gradually lost. The continuity is guaranteed by the stress transfer connectivity, and the gradual loss is maintained by the structural compression residual. The continued growth and limited availability of capacity migration channels are jointly characterized; the binding relationship between the spatial deadband and the corresponding structural semantic unit refers to maintaining the set of structural semantic unit identifiers contained in the spatial deadband in the state storage, and simultaneously maintaining the entry event time, working condition phase at the time of entry, and capacity consumption direction of each structural semantic unit in the spatial deadband. This allows the spatial deadband to continuously update its range with the event time processing sequence and retain a traceable evolution trajectory. At the same time, it enables the subsequent three-dimensional situation projection stage to directly and stably superimpose the spatial deadband onto the corresponding spatial area of ​​the mine three-dimensional model according to the structural semantic unit identifier, thereby forming a spatial deadband visualization expression with engineering semantic consistency.

[0057] S160. Project the plastic space domain and the spatial dead zone onto the three-dimensional model of the mine to perform a three-dimensional safety situation visualization simulation. By rendering the remaining volume of plastic capacity in the set of voxelized spatial units and superimposing the spatial dead zone, the safety situation expression of slow variables from long-term invisible to continuous observable can be realized.

[0058] Specifically, when limiting the projection range of voxelized spatial units in the 3D mine model to maintain spatial consistency through the plastic space domain, the boundary volume of the plastic space domain is first maintained for each structural semantic unit in the state storage. The binding relationship between the voxelized spatial unit and the structural semantic unit is used as the sole semantic basis for projection positioning, so that the voxelized spatial unit does not directly depend on the triangular mesh details of the 3D mine model but depends on the plastic space domain of the structural semantic unit. The plastic space domain refers to the set of boundary constraints that limit the spatial coverage and contact interface range of the structural semantic unit, and the projection range refers to the voxel. The visualization of the position and volume range of the voxelized spatial unit in the coordinate system of the 3D mine model is shown. When the 3D mine model undergoes local geometric updates, only the boundary volume of the plastic spatial domain of the affected structural semantic unit and the geometric shell of its corresponding voxelized spatial unit set are updated, while the identifier of the structural semantic unit and the identifier of the voxelized spatial unit remain unchanged. This ensures that the same voxelized spatial unit can still obtain a consistent projection position through the boundary volume of the plastic spatial domain in different versions of the 3D mine model, thereby avoiding the displacement or breakage of the remaining plastic volume in space due to geometric refinement, mesh reconstruction or local hole filling.

[0059] After spatial alignment, when performing plastic capacity surplus volume rendering on the set of voxelized spatial units, the plastic capacity surplus of each voxelized spatial unit is first read from the state storage, and the plastic capacity surplus is mapped to the volume rendering attribute of the voxelized spatial unit, so that each voxelized spatial unit is presented in the 3D model of the mine as a volumetrically continuous 3D volume. The plastic capacity surplus volume refers to the volume rendering volume composed of the set of voxelized spatial units. The volume rendering intensity of each voxelized spatial unit is determined by the plastic capacity surplus of that voxelized spatial unit, thereby transforming the spatial distribution of the rearrangement of the surrounding rock bearing capacity into a visual expression of continuous volume change. To ensure that the plastic capacity surplus volumes between different structural semantic units are comparable and not affected by extreme values, the plastic capacity surplus is first robustly normalized and then mapped to the volume rendering intensity. Robust normalization can be achieved by a combination of quantile truncation and nonlinear compression, and its expression is as follows:

[0060] in, Represents voxelized spatial units The volume rendering intensity is used to drive the volume continuity display of the remaining plastic capacity; This represents the Sigmoid function, which is used to perform non-linear compression on the normalization results to suppress high-value saturation and enhance the contrast between medium and low values. Indicates compression gain, used to adjust visual contrast; This indicates the bias term, used to adjust the overall brightness or transparency baseline; Represents voxelized spatial units The remaining amount of plastic capacity is obtained by subtracting the cumulative deduction from the initial value of plastic capacity and then processing it with capacity self-consistency constraints. This represents a truncation function used to truncate... Limiting to quantile intervals to suppress extreme values; This represents the lowest quantile value of the remaining plastic capacity within the current rendering frame or the current event time window, and is used as a robust normalization lower bound. The denominator represents the high quantile of remaining plastic capacity within the current rendering frame or the current event time window, used as an upper bound for robust normalization; This is used to map the remaining amount of truncated plastic capacity to a range of 0 to 1, making the volume rendering intensity comparable between different structural semantic units.

[0061] When projecting the spatially locked zone as an independent overlay rendering layer onto the 3D mine model and displaying it on top of the rendered plastic capacity surplus, the set of structural semantic unit identifiers contained in the spatially locked zone is first read, and the corresponding set of voxelized spatial units is retrieved based on the set of structural semantic unit identifiers, thus obtaining the overlay mask of the spatially locked zone on the voxel mesh. The spatially locked zone refers to a continuous spatial region composed of multiple connected structural semantic units. The independent overlay rendering layer refers to a visualization channel separated from the plastic capacity surplus, used to overlay and display the structural state with limited capacity migration without covering the plastic capacity surplus. The overlay display adopts a mask overlay method, so that the voxelized spatial units covered by the mask increase the locked overlay intensity while maintaining the original rendering intensity of the plastic capacity surplus, thereby simultaneously expressing the composite spatial semantics of remaining plastic capacity and limited capacity migration. The locked overlay intensity can be jointly determined by the robust normalization result of the structural extrusion residual and the degree of limitation of the availability of the capacity migration channel, and its expression is:

[0062] in, Represents voxelized spatial units The lock-overlay strength is used to drive the overlay rendering of the spatial lock-overlay band; Represents the Sigmoid function; This indicates the gain of the structural extrusion residual on the superposition strength, used to enhance the locked display of areas with large structural extrusion residuals; Represents voxelized spatial units Belonging to the structural semantic unit The cumulative value of structural extrusion residuals; This represents the truncation function; and These represent the low quantile and high quantile values ​​of the structural compression residual within the current rendering frame or the current event time window, respectively, for robust normalization. The suppression gain represents the availability of the capacity migration channel, which is used to increase the lockout superposition strength as the channel availability decreases. Represents structural semantic units The aggregated value of capacity migration channel availability within the current event timeframe can be determined by structural semantic units. The mean or weighted mean of availability across connected semantic transfer channels is obtained; This indicates the overlay bias term, used to adjust the baseline strength of the locked overlay layer; This represents the lock-up mask indicator function, when the voxelized spatial unit... The set of voxelized spatial units corresponding to the spatial dead zone The value is 1 when the condition is met, and 0 otherwise, thus ensuring that the locking superposition only applies to the area covered by the spatial locking zone.

[0063] During the overlay rendering of spatial locked zones, while maintaining the binding between spatial locked zones and structural semantic units and synchronously associating them with source feature records, a source feature record is first maintained for each spatial locked zone in the state storage. The source feature record includes at least the dominant working condition phase, the dominant capacity consumption direction, and the dominant stress transmission path. The dominant working condition phase is used to characterize the production stage background when the spatial locked zone forms and expands, the dominant capacity consumption direction is used to characterize the dominant advancement direction of plastic capacity deduction in space, and the dominant stress transmission path is used to characterize the main connecting links for the expansion of the spatial locked zone along the stress transmission connectivity relationship. Binding refers to maintaining a one-to-one correspondence between the spatial locked zone identifier and the set of structural semantic unit identifiers it contains, and association refers to maintaining a one-to-one correspondence between the spatial locked zone identifier and the source feature record. On the rendering side, the coverage area of ​​the structural semantic unit and the source feature record are read simultaneously through the spatial locked zone identifier, so that the spatial locked zone can not only display its spatial location and range in the 3D scene, but also display the corresponding working condition phase label, capacity consumption direction arrow, and stress transmission path link in interactive prompts, time playback, or situation annotations. This achieves an interpretable display of the spatial locked zone and avoids the semantic loss caused by only presenting it with color or intensity.

[0064] When updating the rendering states of the plastic space domain and spatial deadband based on event time to achieve continuous evolution of the 3D security posture, the rendering engine does not refresh the state according to arrival time, but subscribes to the plastic space domain snapshot and spatial deadband snapshot in the state store according to event time, and uses event time as the rendering frame advancement benchmark, so that the remaining plastic capacity and spatial deadband change strictly and continuously with event time on the timeline; the plastic space domain snapshot refers to the set of voxelized spatial unit plastic capacity remaining state at a specific event time point or at the end of a specific event time window, and the spatial deadband snapshot refers to the set of voxelized spatial unit plastic capacity remaining state at a specific event time point or at the end of a specific event time window, and the spatial deadband snapshot refers to the set of voxelized spatial unit plastic capacity remaining state at a specific event time point or at the end of a specific event time window. The spatial dead zone coverage and source feature record set at the end of the same event time point or the same event time window; when a late event encapsulation causes the historical event time interval to be corrected, the plastic spatial domain snapshot and spatial dead zone snapshot of the corresponding event time interval are incrementally recalculated through the event time backfilling mechanism, and the corrected state is replayed on the rendering side with the event time as the index, so that the evolution process of slow variables presents a smooth and gradual evolution in the 3D safety situation rather than an abrupt jump; the event time-driven rendering state update can be represented as a state selection function indexed by the event time:

[0065] in, Indicates the event time as The 3D security posture status used for rendering at that time; Indicates that at the event time is The remaining volume rendering intensity vector of the plastic capacity of all voxelized spatial units, whose elements can be obtained from the aforementioned Obtained from the snapshot corresponding to the event time; Indicates that at the event time is The spatial locked band superposition intensity vector of all voxelized spatial units, whose elements can be obtained from the aforementioned Obtained from the snapshot corresponding to the event time; Indicates that at the event time is A set of source feature records for spatiotemporal deadbands, used for interpretive annotation and interactive display on the rendering side; through... As a rendering input, the three-dimensional safety situation in the three-dimensional model of the mine evolves continuously over time, thereby transforming slow variables from long-term invisible to a continuously observable situational expression of the remaining plastic capacity and spatial dead zone.

[0066] In summary, based on the embodiments of this application, taking the deep segmented open-hole subsequent backfilling mining method in a metal mine as an example, the three-dimensional model of the mine pre-divides the stope, roadways, goaf, backfill, fractured zones, and support components into structural semantic units. The server uniformly accesses multi-source real-time streaming data, including microseismic data, acoustic emission data, surrounding rock displacement, surrounding rock convergence, support stress, borehole stress, seepage pore pressure, and production behavior. Each data point generates an event encapsulation containing event time, semantic anchoring, and operating phase, and is bound to the corresponding structural semantic unit through semantic anchoring, ensuring consistency of data from different sources under the same event time axis and the same engineering semantic object. A plastic spatial domain is constructed around the stope structural semantic unit, and the three-dimensional space of the mine is voxelized and discretized within this spatial domain to form a set of voxelized spatial units. Based on the geological conditions of the mining area, which has hard lithology but well-developed fractures, significant fracture effects and high in-situ stress, as well as the mining conditions of frequent blasting, fast advance speed and delayed filling, a non-uniform plastic capacity is configured for the voxelized spatial unit, and a directional and time-varying capacity migration channel is established between the mining area and the fracture zone and roadway unit.

[0067] During production, after entering the blasting phase, micro-vibrations and acoustic emission events continue to occur but have not yet triggered any immediate alarms. The server writes the event encapsulations into the plastic space domain according to the event time sequence and performs directional deduction along the fracture strike on the mined voxelized spatial units according to the working condition phase, so that the plastic capacity forms a continuous consumption trajectory in space. In the subsequent loading and transportation phases, the surrounding rock convergence and support stress slowly increase, and the corresponding plastic capacity continues to be consumed in a low-amplitude, long-term manner, thus uniformly expressing the long-term slow change as a continuous decrease in plastic capacity. In the capacity self-consistency constraint processing, the server attempts to release or transfer the capacity consumption in the mined area to adjacent structural semantic units through capacity migration channels. However, due to the incomplete filling and the decreased availability of fracture fracture zone channels, some capacity cannot be closed and is accumulated as the structural compression residual of the mined structural semantic units. As multiple event time-processing sequences progressed, the stope exhibited a continuous increase in structural compression residuals and a decrease in access availability, despite the existence of plastic capacity. Consequently, it was identified as a spatial lock-up front and extended along the stress transfer connectivity of the fracture zone and adjacent roadways to form a spatial lock-up zone.

[0068] In three-dimensional safety situation visualization, voxelized spatial units are rendered as plastic capacity surplus volumes, allowing dispatchers to intuitively see the spatial distribution changes of the load rearrangement surplus in the mining area through the three-dimensional model of the mine. At the same time, spatial locking zones are overlaid on them, so that even if sudden instability has not yet occurred, the capacity migration restricted areas that gradually form along the fault direction can be clearly identified. Thus, before the arrival of the critical state of disaster, the slow variable evolution process is revealed in a continuous and observable three-dimensional situation.

[0069] This application also provides a mine three-dimensional safety situation visualization simulation device based on real-time stream computing, referring to... Figure 2 , Figure 2 This application provides a schematic diagram of a module for a real-time stream computing-based visualization simulation device for a 3D mine safety situation. The device is a server, comprising an acquisition module 21 and a processing module 22. The acquisition module 21 acquires multi-source real-time stream data for the mine, generates an event encapsulation for each stream, and binds the multi-source real-time stream data to structural semantic units in the 3D mine model. The event encapsulation includes event time, semantic anchoring, and working condition phase. The processing module 22 constructs a plastic space domain based on the structural semantic units and maps the plastic space domain to a set of voxelized spatial units corresponding to the 3D mine model. This allows each voxelized spatial unit to be configured with corresponding plastic capacity and capacity migration channels, characterizing the bearing rearrangement margin of the surrounding rock under current geological and mining conditions and its transfer relationship between structural semantic units. The processing module 22 also writes the event encapsulation into the plastic space domain driven by event time and determines the corresponding structure based on semantic anchoring. The system constructs semantic units and performs directional deduction of plastic capacity based on the phase of the working condition, so that the evolution of slow variables is uniformly expressed as the continuous consumption process of plastic capacity on the structural semantic units. The processing module 22 is also used to perform capacity self-consistency constraint processing based on the capacity migration channel after the plastic capacity deduction is completed, so that the capacity consumption in the structural semantic units forms a release or transfer relationship between adjacent structural semantic units, and the capacity part that cannot form a self-consistent closure is accumulated as the structural compression residual. The processing module 22 is also used to identify the spatial locking front of the structural semantic units based on the plastic spatial domain and the structural compression residual, and expand the spatial locking front to form a spatial locking zone according to the stress transfer connection relationship. The processing module 22 is also used to project the plastic spatial domain and the spatial locking zone onto the three-dimensional model of the mine to perform three-dimensional safety situation visualization simulation. By rendering the remaining volume of plastic capacity in the voxelized spatial unit set and superimposing the rendering of the spatial locking zone, the slow variable is transformed from long-term invisible to continuous observable safety situation expression.

[0070] 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.

[0071] This application also provides an electronic device, with reference to... Figure 3 , Figure 3This 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.

[0072] The communication bus 32 is used to enable communication between these components.

[0073] The user interface 33 may include a display screen and a camera. Optionally, the user interface 33 may also include a standard wired interface and a wireless interface.

[0074] The network interface 34 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0075] 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.

[0076] 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 real-time stream computing-based visualization and simulation method for three-dimensional safety situation in mines.

[0077] 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 an application program stored in the memory 35 that is a real-time stream computing-based three-dimensional safety situation visualization simulation method for mines. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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 visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing, characterized in that, The method includes: Acquire multi-source real-time streaming data for the mine, generate an event encapsulation for each real-time streaming data, and bind the multi-source real-time streaming data to the structural semantic unit in the three-dimensional model of the mine. The event encapsulation includes event time, semantic anchor, and working condition phase. Based on the structural semantic units, a plastic space domain is constructed, and the plastic space domain is mapped to a set of voxelized space units corresponding to the three-dimensional model of the mine, so that each voxelized space unit is configured with a corresponding plastic capacity and capacity migration channel to characterize the bearing rearrangement margin of the surrounding rock under the current geological and mining conditions and the transfer relationship between the structural semantic units. Driven by the event time, the event encapsulation is written into the plastic space domain, the corresponding structural semantic unit is determined according to the semantic anchor, and the plastic capacity is directionally deducted according to the working condition phase, so that the evolution of slow variables is uniformly expressed as the continuous consumption process of plastic capacity on the structural semantic unit. After the plastic capacity deduction is completed, capacity self-consistency constraint processing is performed based on the capacity migration channel so that the capacity consumption in the structural semantic unit forms a release or transfer relationship between adjacent structural semantic units, and the capacity part that cannot form a self-consistent closure is accumulated as structural extrusion residual. Based on the plastic spatial domain and the structural extrusion residual, the spatial locking front of the structural semantic unit is identified, and the spatial locking front is extended according to the stress transfer connectivity relationship to form a spatial locking zone; The plastic space domain and the spatial dead zone are projected onto the three-dimensional model of the mine to perform a three-dimensional safety situation visualization simulation. By rendering the remaining volume of plastic capacity in the set of voxelized spatial units and superimposing the spatial dead zone, the safety situation expression of slow variables can be transformed from long-term invisible to continuous observable.

2. The method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing as described in claim 1, characterized in that, The process of acquiring multi-source real-time streaming data for the mine, generating an event encapsulation for each real-time streaming data, and binding the multi-source real-time streaming data to structural semantic units in the mine's 3D model specifically includes: The real-time stream access layer unifies the access of microseismic event streams, acoustic emission event streams, surrounding rock displacement streams, surrounding rock convergence streams, support stress streams, borehole stress streams, seepage pore pressure streams, temperature and humidity environment streams, and production behavior streams to form the multi-source real-time stream data. While keeping the original timestamps, original spatial indication information, and device identification information of the multi-source real-time stream data unchanged, the event time is used as a unified time reference, and the multi-source real-time stream data under different sampling frequencies and different communication links are aligned to the same event time sequence through time standardization processing to generate the event encapsulation. Semantic anchoring processing is performed based on a pre-established 3D mine model space. The event encapsulation is mapped and bound to the structural semantic unit in the 3D mine model. The structural semantic unit is used to represent mining units, roadway units, goaf units, filling units, fractured zone units, or support component units with engineering semantics.

3. The method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing as described in claim 1, characterized in that, The construction of a plastic spatial domain based on the structural semantic units, and mapping the plastic spatial domain to a set of voxelized spatial units corresponding to the three-dimensional mine model, so that each voxelized spatial unit is configured with a corresponding plastic capacity and capacity migration channel, to characterize the bearing rearrangement margin of the surrounding rock under the current geological and mining conditions and the transfer relationship between structural semantic units, specifically includes: Based on the three-dimensional model of the mine, a set of structural semantic units is established synchronously, and a corresponding plastic space domain is constructed for each structural semantic unit to limit the spatial coverage of the structural semantic unit in the three-dimensional coordinate system of the mine and the contact interface range with adjacent structural semantic units. Under the constraints of the plastic space domain, the three-dimensional model of the mine is subjected to voxelization discretization to generate the set of voxelized spatial units. Based on the spatial inclusion or overlap relationship between the voxelized spatial units and the plastic space domain, each voxelized spatial unit is bound to a unique structural semantic unit so that the voxelized spatial unit semantically belongs to the corresponding structural semantic unit. After binding the voxelized spatial units with the structural semantic units, the corresponding geological attribute parameters and mining method attribute parameters are obtained for each structural semantic unit. Based on the geological attribute parameters and the mining method attribute parameters, a plastic capacity benchmark is configured for the structural semantic unit. At the same time, the plastic capacity benchmark is allocated according to the spatial position distribution and structural sensitivity distribution of the voxelized spatial units within the structural semantic units to form the plastic capacity. The capacity migration channel is constructed based on the spatial adjacency relationship of voxelized spatial units and the stress transfer connectivity relationship between structural semantic units. Specifically, an internal migration channel is established between voxelized spatial units within the same structural semantic unit, and a cross-semantic migration channel is established between different structural semantic units based on the contact interface of the plastic spatial domain. The cross-semantic migration channel is subject to directional and time-varying constraints corresponding to the fracture zone unit, the filling unit, and the support component unit.

4. The method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing as described in claim 1, characterized in that, Driven by the event time, the event encapsulation is written into the plastic space domain, the corresponding structural semantic unit is determined according to the semantic anchor, and the plastic capacity is directionally deducted according to the operating phase, so that the slow variable evolution is uniformly expressed as the continuous consumption process of plastic capacity on the structural semantic unit, specifically including: Driven by the event time, based on the semantic anchoring, the structural semantic unit corresponding to the event encapsulation body is determined, and through the index relationship between the structural semantic unit and the voxelized spatial unit, the event encapsulation body is located to the set of voxelized spatial units under the structural semantic unit. After determining the structural semantic unit, the operating condition phase is read, and the corresponding capacity deduction strategy is selected based on the operating condition phase; Based on the capacity reduction strategy, directional reduction processing is performed on the voxelized spatial units corresponding to the structural semantic units, so that the evolution of slow variables forms a continuous and traceable consumption trajectory at the spatial level.

5. The method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing according to claim 1, characterized in that, After the plastic capacity deduction is completed, capacity self-consistency constraint processing is performed based on the capacity migration channel to ensure that the capacity consumption in the structural semantic unit forms a release or transfer relationship between adjacent structural semantic units, and the capacity portion that cannot form a self-consistent closure is accumulated as structural extrusion residual. Specifically, this includes: Locate the target structural semantic unit in the plastic space domain where plastic capacity deduction occurs, and summarize the capacity consumption and capacity consumption direction formed by the target structural semantic unit in the event time processing sequence, using the capacity consumption direction as the direction consistency constraint condition for self-consistent constraint processing. Based on the set of capacity migration channels corresponding to the structural semantic unit, the internal migration channels and cross-semantic migration channels connected to the structural semantic unit are read, and the capacity migration channels that meet the phase constraints of the current operating condition are screened according to the channel availability, channel directionality and channel strength, so as to form a set of candidate channels for capacity release or capacity transfer. Under the constraints of the candidate channel set, capacity release determination or capacity transfer allocation processing is performed on the capacity consumption. The capacity release determination is used to identify adjacent structural semantic units that are consistent with the capacity consumption direction and form a closed relationship under the same operating phase. The capacity transfer allocation processing is used to allocate the capacity consumption to multiple adjacent structural semantic units according to the channel strength, and write the allocated capacity transfer amount into the corresponding structural semantic unit through the capacity migration channel. During the execution of capacity release and capacity transfer, a joint constraint condition of time consistency, direction consistency, phase consistency and channel consistency is applied to the closed relationship, and the capacity portion that does not meet the joint constraint condition is retained as unclosed capacity; The unclosed capacity that cannot form a self-consistent closure in the capacity consumption is accumulated as the structural compression residual, and the structural compression residual is bound to the corresponding structural semantic unit. At the same time, the working condition phase and capacity consumption direction corresponding to the structural compression residual are recorded so that the structural compression residual can be used to characterize the structural compression characteristics that cannot achieve self-consistent closure through the capacity migration channel during the rearrangement of the surrounding rock bearing path.

6. The method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing according to claim 1, characterized in that, The process of identifying the spatial locking front of the structural semantic unit based on the plastic spatial domain and the structural extrusion residual, and extending the spatial locking front to form a spatial locking zone according to the stress transfer connectivity relationship, specifically includes: When the structural semantic unit simultaneously meets the following conditions in a series of consecutive event time processing sequences: the remaining plastic capacity is greater than a preset threshold, the structural extrusion residual shows a cumulative growth trend, and the availability of the capacity migration channel shows a decreasing trend, the structural semantic unit is identified as a spatially locked frontier. Based on the pre-established stress transfer connectivity between structural semantic units, connectivity expansion processing is performed on the spatial locking front. Consistency checks are performed on adjacent structural semantic units that have stress transfer connectivity with the spatial locking front. The consistency check is used to determine whether adjacent structural semantic units exhibit the same structural compression residual growth trend, capacity migration channel availability limitation trend, and capacity consumption direction continuity as the spatial locking front unit within the same event time range. When the adjacent structural semantic units pass the consistency test, the adjacent structural semantic units are incorporated into the spatial locking front and continue to expand along the stress transmission connectivity relationship to form a spatial locking zone composed of multiple structural semantic units. The spatial locking zone is then bound to the corresponding structural semantic units to characterize the continuous spatial region where the recoverability of the surrounding rock is gradually lost.

7. The method for visualizing and simulating the three-dimensional safety situation in mines based on real-time stream computing as described in claim 1, characterized in that, The process of projecting the plastic space domain and the spatial dead zone onto the 3D mine model to perform a 3D safety situation visualization simulation involves rendering the remaining plastic capacity in the voxelized spatial unit set and overlaying the spatial dead zone to achieve a safety situation expression that transforms slow variables from long-term invisible to continuously observable. Specifically, this includes: The plastic spatial domain is used to limit the projection range of the voxelized spatial unit in the 3D model of the mine, so as to ensure that the plastic spatial domain maintains spatial consistency with the corresponding structural semantic unit when the 3D model of the mine undergoes local geometric updates. After spatial alignment is completed, the set of voxelized spatial units is subjected to plastic capacity surplus volume rendering processing, so that the plastic capacity surplus recorded in each voxelized spatial unit is presented in the three-dimensional model of the mine in the form of a volumetrically continuous three-dimensional volume, so as to characterize the spatial distribution state of the surrounding rock bearing rearrangement surplus in the structural semantic unit. Based on rendering the remaining plastic capacity, the spatial dead zone is projected as an independent overlay rendering layer onto the 3D model of the mine, and the spatial dead zone is overlaid and displayed on the corresponding remaining plastic capacity, so as to simultaneously express the composite spatial semantics of plastic capacity still existing but capacity migration limited. During the overlay rendering process of the spatial dead zone, the spatial dead zone is bound to its corresponding structural semantic unit and its source feature record is synchronously associated, so that the spatial dead zone can reflect the corresponding working condition phase, capacity consumption direction and stress transmission path in the three-dimensional safety situation. The rendering states of the plastic spatial domain and the spatial dead zone are updated based on the event time, so that the three-dimensional safety situation evolves continuously with the event time, thereby realizing the expression of the safety situation from slow variables that are not visible for a long time to continuous observable in the three-dimensional model of the mine.

8. A three-dimensional safety situation visualization simulation device for mines based on real-time stream computing, characterized in that, The device is used to execute the real-time stream computing-based three-dimensional safety situation visualization simulation method for mines 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 multi-source real-time stream data for the mine, generate an event encapsulation for each real-time stream data, and bind the multi-source real-time stream data to the structural semantic unit in the three-dimensional model of the mine. The event encapsulation includes event time, semantic anchoring, and working condition phase. The processing module is used to construct a plastic spatial domain based on the structural semantic unit, and map the plastic spatial domain to a set of voxelized spatial units corresponding to the three-dimensional model of the mine, so that each voxelized spatial unit is configured with a corresponding plastic capacity and capacity migration channel to characterize the bearing rearrangement margin of the surrounding rock under the current geological and mining conditions and the transfer relationship between the structural semantic units. The processing module is further configured to, under the drive of the event time, write the event encapsulation into the plastic space domain, determine the corresponding structural semantic unit according to the semantic anchor, and perform directional deduction on the plastic capacity according to the working condition phase, so that the evolution of slow variables is uniformly expressed as the continuous consumption process of plastic capacity on the structural semantic unit. The processing module is also used to perform capacity self-consistency constraint processing based on the capacity migration channel after completing the plastic capacity deduction, so that the capacity consumption in the structural semantic unit forms a release or transfer relationship between adjacent structural semantic units, and the capacity part that cannot form a self-consistent closure is accumulated as structural extrusion residual. The processing module is also used to identify the spatial locking front of the structural semantic unit based on the plastic space domain and the structural extrusion residual, and to extend the spatial locking front to form a spatial locking zone according to the stress transmission connectivity relationship; The processing module is also used to project the plastic space domain and the spatial dead zone onto the three-dimensional mine model to perform a three-dimensional safety situation visualization simulation. By rendering the remaining plastic capacity in the set of voxelized spatial units and superimposing the spatial dead zone, the slow variable can be transformed from long-term invisible to a continuously observable safety situation expression.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method 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 the method as described in any one of claims 1 to 7.

Images