HE event early warning method, device, equipment, medium and product

Abstract

The invention discloses an HE event early warning method, device and equipment, a medium and a product, and relates to the field of mine earthquake early warning. The method comprises the following steps: analyzing space-time correlation of mine earthquake data energy by adopting a semi-variation function according to acquired mine earthquake monitoring data, and determining a historical data window; constructing a dynamic sliding mechanism; based on a dynamic sliding mechanism, adopting a principal component analysis method and a kernel density estimation method to extract a kernel density peak value of the micro-seismic event, and adopting a fractal dimension analysis method to determine a fractal dimension index so as to analyze and quantify the geometric complexity change condition and obtain a quantification result; based on a quantification result, optimizing early warning parameters by adopting grid search, and determining a sliding window joint early warning model; and monitoring a kernel density peak value and a fractal dimension index in real time by adopting a sliding window combined early warning model based on the optimized early warning parameters so as to realize early warning of the HE event. The invention aims to improve the accuracy and timeliness of HE event prediction.

Description

Technical Field

[0001] The present application relates to the field of mine earthquake early warning, and in particular to a HE event early warning method, device, equipment, medium and product. Background Art

[0002] Mine tremors are ground responses triggered by mining activities, manifesting as rock fractures, slippage, and energy release. As coal mining depths continue to increase (some reaching 1,500 meters), the frequency and intensity of mine tremors have increased significantly. High-energy mine tremor events (HE events) pose a serious threat to mine safety. Despite advances in mine tremor monitoring technology, existing early warning methods primarily rely on static models and single-indicator analysis, which are unable to fully capture the temporal and spatial heterogeneity of mine tremors and the complexity of their precursors.

[0003] Current single-metric analysis methods, such as source location and time series statistical analysis, analyze microseismic data within fixed time windows to extract single features (such as event frequency, total energy, or fractal dimension) to predict HE events. However, these methods suffer from the following shortcomings: First, static time windows limit analytical flexibility and fail to adapt to the dynamic nature of mine earthquake activity, which varies with mining depth and time, resulting in insufficient early warning effectiveness. Second, single-metric analysis struggles to fully characterize the spatiotemporal heterogeneity of mine earthquakes, leading to false alarms or missed alarms, and particularly low prediction accuracy for high-energy mine earthquakes. This is because mine earthquake activity is influenced by complex geological conditions and mining disturbances, resulting in highly dynamic and heterogeneous spatiotemporal distribution. Existing methods fail to incorporate multidimensional features for dynamic adjustment. Furthermore, traditional methods lack a detailed characterization of spatial clustering characteristics, making it difficult to accurately locate the mine earthquake occurrence area, limiting the spatial accuracy of early warnings. These shortcomings make currently available methods incapable of meeting the real-time and precision requirements for mine safety production. Summary of the Invention

[0004] The purpose of this application is to provide a HE event early warning method, device, equipment, medium and product, which can improve the accuracy and timeliness of HE event prediction.

[0005] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a HE event early warning method, comprising: Obtain mine earthquake monitoring data; Using a semivariogram function to analyze the spatiotemporal correlation of the energy of the mine earthquake data based on the mine earthquake monitoring data, and determining a historical data window; Constructing a dynamic sliding mechanism; the dynamic sliding mechanism includes: determining a dynamic sliding time window based on a historical data window and a time resolution determined according to a mine production cycle; Based on the dynamic sliding mechanism, principal component analysis and kernel density estimation methods were used to extract the kernel density peak of microseismic events. Fractal dimension analysis was also used to determine the fractal dimension index. This was used to analyze and quantify the changes in geometric complexity, resulting in quantitative results. These quantitative results included the regular information that the kernel density peak showed an upward trend before the HE event, while the fractal dimension index showed a downward trend. Constructing a sliding window joint warning model; the sliding window joint warning model is determined by optimizing warning parameters based on the quantification results, taking F1 score maximization as the objective function, and using grid search; the warning parameters include: kernel density peak threshold, fractal dimension threshold, and warning window; Grid search process: warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score, and select the parameter combination with the highest F1 score as the optimized warning parameter; among them, is the resolution; is the lower limit of the kernel density peak threshold; is the upper limit of the kernel density peak threshold; is the lower threshold of fractal dimension; is the upper threshold of fractal dimension; A sliding window joint early warning model is used to monitor the kernel density peak and fractal dimension index in real time based on the optimized early warning parameters to achieve early warning of HE events. The fractal dimension analysis method adopts the correlation integral method; the mathematical expression corresponding to the correlation integral method is: ; ; in, is the correlation integral method function; is the scale index factor; is the total number of earthquake events; For the earthquake events and the distance to the earthquake event; is the Heaviside step function; The expression of the fractal dimension index is: ; in, is the relevant score; is the fractal dimension index; The principal component analysis method and kernel density estimation method are used to extract the kernel density peak of microseismic events, including: The principal component analysis method was used for dimensionality reduction, and the kernel density estimation method was used to quantify the spatiotemporal aggregation characteristics and determine the probability density; A Gaussian kernel density function is used to extract the kernel density peak based on the probability density to determine the spatiotemporal aggregation degree; The expression corresponding to the probability density is: ; The expression of the Gaussian kernel density function is: ; in, is the probability density; is a data point; is the total number of data points in the earthquake event group; is the bandwidth parameter; For the data points for earthquake events; is the Gaussian kernel density function.

[0006] In one embodiment, the semivariogram is a mathematical function used to characterize the change in semivariability corresponding to the result curve at different hysteresis values; the calculation formula of the semivariogram is: ; in, is semivariability; Lag interval the number of pairs of data points separated; For the earthquake data; For Paired, lag interval is data.

[0007] In a second aspect, the present application provides a HE event warning device, comprising: Data acquisition module, used to obtain mine earthquake monitoring data; A correlation analysis module, configured to analyze the spatiotemporal correlation of the energy of the mine earthquake data using a semivariogram based on the mine earthquake monitoring data, and determine a historical data window; A window determination module is used to construct a dynamic sliding mechanism; the dynamic sliding mechanism includes: a dynamic sliding time window determined based on a historical data window and a time resolution determined according to a mine production cycle; A quantification module is configured to extract the kernel density peak of the microseismic event based on the dynamic sliding mechanism using principal component analysis and kernel density estimation, and to determine the fractal dimension index using a fractal dimension analysis method, so as to analyze the change in the quantitative geometric complexity and obtain a quantified result; the quantified result includes regular information that the kernel density peak shows an upward trend and the fractal dimension index shows a downward trend before the HE event; A model building module is used to build a sliding window joint warning model; the sliding window joint warning model is determined by optimizing warning parameters based on the quantization results, taking F1 score maximization as the objective function, and using grid search; the warning parameters include: kernel density peak threshold, fractal dimension threshold and warning window; Grid search process: warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score, and select the parameter combination with the highest F1 score as the optimized warning parameter; among them, is the resolution; is the lower limit of the kernel density peak threshold; is the upper limit of the kernel density peak threshold; is the lower threshold of fractal dimension; is the upper threshold of fractal dimension; The monitoring and early warning module is used to use the sliding window joint early warning model to monitor the kernel density peak and fractal dimension indicators in real time based on the optimized early warning parameters to achieve early warning of HE events; The fractal dimension analysis method adopts the correlation integral method; the mathematical expression corresponding to the correlation integral method is: ; ; in, is the correlation integral method function; is the scale index factor; is the total number of earthquake events; For the earthquake events and the distance to the earthquake event; is the Heaviside step function; The expression of the fractal dimension index is: ; in, is the relevant score; is the fractal dimension index; The principal component analysis method and kernel density estimation method are used to extract the kernel density peak of microseismic events, including: The principal component analysis method was used for dimensionality reduction, and the kernel density estimation method was used to quantify the spatiotemporal aggregation characteristics and determine the probability density; A Gaussian kernel density function is used to extract the kernel density peak based on the probability density to determine the spatiotemporal aggregation degree; The expression corresponding to the probability density is: ; The expression of the Gaussian kernel density function is: ; in, is the probability density; is a data point; is the total number of data points in the earthquake event group; is the bandwidth parameter; For the data points for earthquake events; is the Gaussian kernel density function.

[0008] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the HE event warning method described above.

[0009] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the HE event warning method described above when executed by a processor.

[0010] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the above-mentioned HE event warning method when executed by a processor.

[0011] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a HE event early warning method, device, equipment, medium and product. The semivariogram function is used to analyze the correlation between microseismic data in the mine earthquake monitoring data to comprehensively consider the temporal distribution characteristics of microseismic events. At the same time, a dynamic sliding time window is constructed according to the resolution determined by the mine production cycle to fully capture the spatiotemporal dynamic evolution characteristics of microseismic activities as the mining process changes. The sliding window joint early warning model adopts the principal component analysis method, combined with the kernel density estimation method to determine the spatiotemporal aggregation characteristics, and extract the kernel density peak. At the same time, the fractal dimension analysis method is used to generate the fractal dimension index, and the grid search method is used for optimization and determination. It can ensure adaptability and stability under different geological conditions. Based on the dynamic sliding time window and the sliding window joint early warning model, it can dynamically monitor the spatiotemporal aggregation characteristics and the trend of geometric complexity changes, realize real-time prediction of HE events, and significantly improve the accuracy and timeliness of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 It is a flow chart of the HE incident early warning method; Figure 2 Design a flow chart for the HE incident early warning method; Figure 3 is the magnitude frequency histogram; Figure 4 Schematic diagram of the calculation and goodness of fit of the local magnitude b value of microseismic events; Figure 5 is the semivariogram of mine earthquake energy; Figure 6 This is a cluster diagram of mine earthquake events before HE event A; Figure 6 (a) Schematic diagram of PCA transformation of data sets M and A; Figure 6 (b) Schematic diagram of the maximum value of the probability density function obtained by kernel density estimation of data sets M and A; Figure 7 The fractal dimension fitting diagrams of three events A, B, and C are shown below; Figure 8 for Time evolution diagram; Figure 9 for D Schematic diagram of warning results of a single indicator value; Figure 10 It is a joint early warning heat map; Figure 11 This is a schematic diagram of the joint early warning results; Figure 12 This is a schematic diagram of the joint warning confusion matrix; Figure 13 This is a structural diagram of the HE incident warning device; Figure 14 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] To address the shortcomings of existing solutions, there is an urgent need to develop an early warning method that dynamically integrates multidimensional features. By introducing a dynamic sliding time window, fractal dimension analysis, and joint feature extraction using spatiotemporal aggregation, the accuracy and timeliness of HE event prediction can be improved, providing reliable technical support for mine safety management. This application aims to address the limitations of existing technologies in dynamic analysis and multi-feature fusion, thereby achieving more accurate and timely HE event warnings.

[0016] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0017] In an exemplary embodiment, Figure 1 As shown, a HE event early warning method is provided, comprising: Step 100: Acquire mine earthquake monitoring data.

[0018] Step 200: Using a semivariogram to analyze the spatiotemporal correlation of the energy of the mine earthquake data based on the mine earthquake monitoring data, and determining a historical data window.

[0019] Step 300: Constructing a dynamic sliding mechanism. The dynamic sliding mechanism includes: determining a dynamic sliding time window based on a historical data window and a time resolution determined according to a mine production cycle.

[0020] The semivariogram is a mathematical function used to characterize the change in semivariability at different lag values, corresponding to the result curve. The calculation formula for semivariability is: .

[0021] in, is semivariability; Lag interval the number of pairs of data points separated; For the earthquake data; For Paired, lag interval is data.

[0022] Step 400: Based on the dynamic sliding mechanism, principal component analysis and kernel density estimation are used to extract the kernel density peak of the microseismic event. Fractal dimension analysis is also used to determine the fractal dimension index. This analysis quantifies the changes in geometric complexity and yields quantitative results. These quantitative results include information indicating that the kernel density peak shows an upward trend before the HE event, while the fractal dimension index shows a downward trend.

[0023] The fractal dimension analysis method uses the correlation integral method; the mathematical expression corresponding to the correlation integral method is: .

[0024] .

[0025] in, is the correlation integral method function; is the scale index factor; is the total number of earthquake events; For the earthquake events and the distance to the earthquake event; is the Heaviside step function.

[0026] The expression of the fractal dimension indicator is: .

[0027] in, is the relevant score; is the fractal dimension index.

[0028] In one embodiment, a principal component analysis method and a kernel density estimation method are used to extract the kernel density peak of microseismic events, specifically including: Principal component analysis was used for dimensionality reduction, and kernel density estimation was used to quantify spatiotemporal clustering characteristics and determine probability density.

[0029] The Gaussian kernel density function was used to extract the kernel density peak based on the probability density to determine the spatiotemporal aggregation degree.

[0030] The expression corresponding to the probability density is: .

[0031] The expression of the Gaussian kernel density function is: .

[0032] in, is the probability density; is a data point; is the total number of data points in the earthquake event group; is the bandwidth parameter; For the data points for earthquake events; is the Gaussian kernel density function.

[0033] Step 500: Construct a sliding window joint warning model. This sliding window joint warning model is based on the quantitative results, with F1 score maximization as the objective function. Warning parameters are optimized using grid search. Warning parameters include: kernel density peak threshold, fractal dimension threshold, and warning window.

[0034] Among them, the grid search process: warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score, and select the parameter combination with the highest F1 score as the optimized warning parameter; among them, is the resolution; is the lower limit of the kernel density peak threshold; is the upper limit of the kernel density peak threshold; is the lower threshold of fractal dimension; is the upper threshold of the fractal dimension.

[0035] Step 600: Using the sliding window joint warning model based on the optimized warning parameters, the kernel density peak and fractal dimension index are monitored in real time to achieve early warning of HE events.

[0036] like Figure 2As shown, the present application mentions an early warning method for large-energy mine earthquake events (HE events) based on spatiotemporal aggregation and fractal dimension analysis. First, the microseismic monitoring data (mine earthquake monitoring data) is analyzed by semivariogram, and the temporal distribution characteristics of microseismic events are comprehensively considered to optimize the length of the historical data window to ensure that sufficient event sequences are covered. At the same time, the real-time resolution is set according to the actual situation of the mine production cycle, and a dynamic sliding time window is constructed to fully capture the spatiotemporal dynamic evolution characteristics of microseismic activities as the mining process changes. Then, principal component analysis (PCA) is used to reduce the dimensionality of the spatial distribution data of microseismic events, and kernel density estimation (KDES) is used to estimate the spatial distribution of microseismic events. The KDE (Knowledge Dynamic Estimation) method is used to quantify the spatiotemporal clustering characteristics of microseismic events in different time periods, and the kernel density peak is extracted as a dynamic precursor signal in the time dimension. At the same time, the fractal dimension analysis method is used to calculate the geometric complexity of microseismic events and generate a fractal dimension index to characterize the changing trend of microseismic activity on the time scale. Then, a grid search method is used to systematically optimize the key thresholds and warning time windows of the early warning model to ensure the adaptability and stability of the model under different geological conditions. Finally, a sliding window joint early warning model is constructed by combining the kernel density peak and fractal dimension indicators. By dynamically monitoring the spatiotemporal clustering characteristics and geometric complexity changing trends of microseismic activity, real-time prediction of HE events is achieved, significantly improving the accuracy and timeliness of early warnings, and providing reliable support for mine safety management in complex geological environments.

[0037] This example analyzes microseismic monitoring data from the 6306 working face of a coal mine. The monitoring period was from October 1, 2023, to April 1, 2024, and a total of 3,084 valid microseismic event data points were acquired. The monitoring system was configured in full-waveform continuous recording mode with a sampling frequency of 500 Hz, meeting the requirements for high-precision detection of high-energy mine tremors. Calibration shot experiments verified that the system's positioning error was less than 30 meters, demonstrating the high reliability of the spatiotemporal positioning results.

[0038] 1. Definition of high-energy mine earthquake events.

[0039] For a set of earthquake data distribution, the first problem that needs to be solved is how to quantitatively define high-energy (HE) earthquake events. According to the theory of Gutenberg and Richer, the magnitude and cumulative number of earthquake events follow formula (1): (1) in, is the total number of earthquake events, referring to the magnitude Greater than the local magnitude The number of earthquake events, and are all constants.

[0040] Figure 3 The magnitude distribution histogram shows that the magnitude frequency reaches a peak around -0.3. This application uses the Maximum Likelihood Estimation (MLE) method. This method assumes that the magnitude-frequency graph of earthquake events follows a Poisson process. It estimates the parameter values ​​of the Poisson distribution model so as to maximize the likelihood of the observed value. By applying MLE, The value is estimated to be 2.89. In order to evaluate the quality of fitting, the concept of Goodness of Fit (GoF) is introduced for each earthquake magnitude interval. , as shown in formula (2).

[0041] (2) in, and represent the number of observed earthquake events and the number of expected earthquake events, respectively. is the mean of the Poisson distribution prediction obtained by maximum likelihood estimation. The goodness of fit changes with , such as Figure 4 As shown. In the relatively high energy region, GoF gradually decreases. This value indicates the error between the observed time and the predicted value, which may represent a different earthquake catalog with a different magnitude-frequency response in the high-energy range. The threshold for high-energy (HE) events is set as Table 1 shows the distribution of events with a magnitude greater than 0.96 during this monitoring period. There are a total of 17 high-energy mining earthquake events, which are defined as high-energy earthquake events and numbered.

[0042] Table 1 High-energy earthquake event information

[0043] 2. Event window parameterization.

[0044] In order to quantitatively analyze the correlation between unevenly spaced microseismic data, this application uses the semivariogram function, which shows the transformation of the semivariability under different lag values. , semivariability of seismic data The calculation method is: (3) The semivariogram is a curve that plots the semivariability results at different lags and is usually fitted according to a specific model. As the lag increases, the semivariability between the data increases until it reaches a maximum value at a certain lag. The increase in semivariability indicates that the autocorrelation is gradually weakening. In order to further describe the correlation of the semivariogram, it has three main parameters: Nugget represents the lag, k =0; Sill represents the maximum variability of the data array; Range represents the scale fluctuation and indicates the critical lag time required for the semi-variability to reach its maximum value.

[0045] By analyzing the semivariogram of the instance, such as Figure 5 As shown in Figure 2, it is determined that the energy of microseismic events shows significant spatial correlation within the 5-day time scale. Set it to 5 days (the time range of historical data) and set the sliding time window The time resolution is set to 8 hours (the time resolution of real-time monitoring) to capture the spatiotemporal evolution characteristics of the energy correlation of microseismic events. Select past-current microseismic event set , by sliding this time window , the past-current dataset is updated sequentially, Recorded microseismic events represent future events, The recorded mine earthquake events represent past events, and large energy events are studied through the mine earthquake data set within each past-to-present time window.

[0046] 3. Calculation and analysis of spatiotemporal aggregation.

[0047] This application uses a spatiotemporal clustering calculation method based on principal component analysis and kernel density estimation. First, a five-day microseismic event dataset is selected as the baseline data. Principal component analysis (PCA) is used to convert the four-dimensional spatiotemporal data (x, y, z, t) into a two-dimensional plane. Kernel density estimation (KDE) is then used to calculate the probability density function of the microseismic events in the PCA space.

[0048] Given a set of microseismic events , KDE can estimate each data point The probability density in this group : (5) Gaussian kernel density function Usually smooth, symmetric, and positive, the bandwidth parameter Determines the smoothness of the estimate. KDE is calculated by adding Convert it into a small Gaussian distribution density curve, and then merge these small density blocks to obtain the final probability density estimate. The Gaussian kernel density function expression used is: (6) In order to analyze a specific HE event, assuming that the day of the HE event is the moment of the event, the past data set (microseismic event set) represents all earthquake data before the event. This data was transformed into a two-dimensional coordinate system using PCA for kernel density estimation, which allowed the calculation of the event's PDF. The probability density was then presented as contour lines, allowing the relationship between HE events and the overall microseismic event population to be assessed. The locations of high-energy events exhibited significant spatial proximity to the regions with the maximum kernel density, indicating that their occurrence was closely associated with high-density clustering of microseismic events. The kernel density peak can characterize the spatial clustering characteristics of microseismic events and can serve as an effective indicator for predicting the onset of high-energy microseismic events. Figure 6 The process of analyzing the spatiotemporal aggregation of large energy event A.

[0049] Figure 6 is the cluster of mine earthquake events before HE event A, where Figure 6 (a) is the PCA transformation of data sets M and A; Figure 6 (b) is the maximum value of the probability density function obtained by kernel density estimation of data sets M and A.

[0050] 4. Analysis of time characteristics of fractal dimension.

[0051] The fractal dimension calculation method based on the correlation integral method. The mathematical expression corresponding to the correlation integral method is: (7) (8) H is the Heaviside step function, which takes the value '1' for positive arguments and '0' for negative arguments.

[0052] From formula (7), we can see that Depends on the scale exponent factor , that is, the scale distance, formula (7) can be expressed as follows: (9) By plotting the relevant integral on a logarithmic scale and scale exponent factor The fractal dimension index is obtained from the linear fitting slope of the curve: (10) Use dynamic sliding window mechanism to calculate each timestamp tThe corresponding fractal dimension index , evaluated by the coefficient of determination R² The linear fitting relationship of Figure 7 The results show that the fractal dimensions of high-energy mine earthquake events (such as events A, B, and C) are 1.18, 1.59, and 1.45, respectively, and their determination coefficients R² are 0.98, 1.00, and 0.99, respectively, indicating a good fitting effect.

[0053] 5. Warning parameter optimization and sliding window warning.

[0054] In order to quantify the performance of the early warning indicators and determine the optimal parameters, this application adopts the following evaluation indicators: true positives (TP): the number of successful large-energy mine earthquake events; false positives (FP): the number of incorrectly issued warnings; false negatives (FN): the number of large-energy mine earthquake events that were not predicted; true negatives (TN): the number of time windows in which warnings were correctly issued.

[0055] Based on the above indicators, the following performance evaluation indicators are calculated: precision (P), recall (R), and F1 score: .

[0056] .

[0057] .

[0058] Taking the F1 score maximization as the objective function, the warning parameters are optimized through grid search. The grid search process is as follows: set the grid search parameters, the warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score and select the parameter combination with the highest F1 score as the optimal parameter.

[0059] Based on the warning threshold and warning window determined after grid search, this application implements a sliding window warning function for real-time monitoring and warning of large-energy mine earthquake events. , starting from the first data point, the warning window moves gradually, each time moving one real-time resolution , by counting the median, average, maximum and minimum values ​​in each window, the kernel density peak and fractal dimension value (fractal dimension index) in the window are determined.

[0060] 6. Results.

[0061] To quantify the spatiotemporal clustering characteristics of microseismic activity before an earthquake, this paper first analyzes the kernel density peak The time evolution law before the large-energy mine earthquake event. Based on the dynamic update mechanism of 5-day historical data window and 8-hour real-time resolution window, It can effectively capture the changes in the temporal and spatial aggregation of mine earthquake events. Figure 8 Shows the entire monitoring range The evolution of the sequence, where the red dotted line marks the number of occurrences of 17 high-energy mine earthquake events. The results show that before most high-energy mine earthquake events, It shows a significant upward trend and reaches a local peak 1 to 2 days before the main shock. There is a certain time lag, such as events A, B, C, G, N, etc., but this phenomenon is not found in events P and Q.

[0062] D As an important parameter to characterize the complexity of microseismic activity, the fractal dimension index D It can effectively reflect the geometric characteristic transformation of rock mass fracture. Figure 9 Demonstrates the Fractal Dimension indicator calculated using a dynamic update mechanism based on a 5-day historical data window and an 8-hour real-time resolution window. D The geometric changes during the entire monitoring period showed that before a large-energy mine earthquake occurred, the fractal dimension index D The values ​​generally show a downward trend first and form an obvious local minimum before the HE event.

[0063] This application constructs a joint early warning model based on two indicators. Specifically, the best and D threshold, Figure 10 Displayed under the best warning window of 40h and D The heat map distribution of the value threshold, the best warning window is 40h, and D The threshold values ​​are 0.13 and 1.3 respectively.

[0064] Based on the optimized threshold and warning window, the kernel density peak and fractal dimension indicators are monitored in real time. When both meet the threshold conditions (the kernel density peak exceeds 0.13 and D When the value is lower than 1.3, an alert is triggered.

[0065] The warning results are as follows Figure 11 As shown, the green solid line indicates The maximum value within the warning window, represented by the blue solid line D The value is the minimum value within the warning window. The green circle indicates the location where the trigger occurred, the green triangle indicates the location of the actual HE event, the purple diamond indicates the location of the false trigger, and the red cross indicates the location of the HE event without error. Figure 12The following is a detailed analysis of the results. Under this condition, 14 HE events were warned, 3 were missed, and 12 were false alarms. The precision, recall, and F1 were 0.538, 0.824, and 0.651, respectively.

[0066] In order to comprehensively evaluate the advantages of the joint early warning model over the single indicator early warning, this application conducted a comparative analysis of the key performance indicators of the three early warning methods. The results are shown in Table 2. The results show that the joint early warning model significantly reduces the false alarm rate while maintaining a high recall rate, and the precision rate is relatively high. It increased by 17.1%, compared with D The value increased by 32.1%, and the F1 score increased by 18.3% and 30.2%, respectively, which confirmed the effectiveness and optimization of the joint early warning strategy in mine earthquake early warning.

[0067] Table 2 Performance comparison of three early warning models

[0068] This application adopts a dynamic sliding time window optimization method, which can adjust the analysis range in real time according to the spatiotemporal distribution characteristics of microseismic activities, breaking through the limitations of traditional static time windows, thereby significantly improving the timeliness of early warning and the ability to respond to rapidly evolving disasters. Secondly, this application constructs a multi-parameter joint early warning model by combining spatiotemporal aggregation and fractal dimension analysis to comprehensively characterize the spatiotemporal heterogeneity and geometric complexity changes of microseismic activities. Compared with the single indicator analysis method, it effectively reduces the false alarm rate and improves the prediction accuracy. In addition, this application proposes a set of systematic analysis frameworks, including data window optimization, feature extraction and parameter optimization steps, which enhances the adaptability and universality of the model under different geological conditions, and provides reliable technical support for safety management in complex mining environments. These advantages work together to enable this application to achieve more accurate and timely early warning of large-energy mine earthquake events, thereby significantly reducing the risk of mine disasters and economic losses.

[0069] In an exemplary embodiment, Figure 13 As shown, a HE event warning device is provided, comprising: The data acquisition module is used to obtain mine earthquake monitoring data.

[0070] The correlation analysis module is used to analyze the spatiotemporal correlation of the energy of mine earthquake data based on the mine earthquake monitoring data using the semivariogram function and determine the historical data window.

[0071] The window determination module is used to construct a dynamic sliding mechanism; the dynamic sliding mechanism includes: a dynamic sliding time window determined based on the historical data window and the time resolution determined according to the mine production cycle.

[0072] The quantification module is used to extract the kernel density peak of microseismic events based on the dynamic sliding mechanism using principal component analysis and kernel density estimation. It also uses fractal dimension analysis to determine the fractal dimension index, thereby analyzing and quantifying the changes in geometric complexity and obtaining quantitative results. These quantitative results include information indicating that the kernel density peak shows an upward trend and the fractal dimension index shows a downward trend before HE events. The process for determining the kernel density peak and fractal dimension index has been discussed above and will not be repeated here.

[0073] The model building module is used to construct a sliding window joint warning model. This sliding window joint warning model is based on quantitative results, with F1 score maximization as the objective function. Warning parameters are determined by grid search optimization. Warning parameters include: kernel density peak threshold, fractal dimension threshold, and warning window.

[0074] Grid search process: warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score, and select the parameter combination with the highest F1 score as the optimized warning parameter; among them, is the resolution; is the lower limit of the kernel density peak threshold; is the upper limit of the kernel density peak threshold; is the lower threshold of fractal dimension; is the upper threshold of the fractal dimension.

[0075] The monitoring and early warning module is used to use the sliding window joint early warning model to monitor the kernel density peak and fractal dimension indicators in real time based on the optimized early warning parameters to achieve early warning of HE events.

[0076] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 14As shown. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store HE event warning data. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the HE event warning method is implemented.

[0077] Those skilled in the art will understand that Figure 14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0078] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0079] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0080] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0082] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0083] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0084] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A HE event early warning method, characterized in that: include: Obtain mine earthquake monitoring data; Using a semivariogram function to analyze the spatiotemporal correlation of the energy of the mine earthquake data based on the mine earthquake monitoring data, and determining a historical data window; Build a dynamic sliding mechanism; The dynamic sliding mechanism includes: a dynamic sliding time window determined based on a historical data window and a time resolution determined according to a mine production cycle; Based on the dynamic sliding mechanism, principal component analysis and kernel density estimation methods were used to extract the kernel density peak of microseismic events. Fractal dimension analysis was also used to determine the fractal dimension index. This was used to analyze and quantify the changes in geometric complexity, resulting in quantitative results. These quantitative results included the regular information that the kernel density peak showed an upward trend before the HE event, while the fractal dimension index showed a downward trend. Constructing a sliding window joint warning model; the sliding window joint warning model is determined by optimizing warning parameters based on the quantification results, taking F1 score maximization as the objective function, and using grid search; the warning parameters include: kernel density peak threshold, fractal dimension threshold, and warning window; Grid search process: warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score, and select the parameter combination with the highest F1 score as the optimized warning parameter; among them, is the resolution; is the lower limit of the kernel density peak threshold; is the upper limit of the kernel density peak threshold; is the lower threshold of fractal dimension; is the upper threshold of fractal dimension; A sliding window joint early warning model is used to monitor the kernel density peak and fractal dimension index in real time based on the optimized early warning parameters to achieve early warning of HE events. The fractal dimension analysis method adopts the correlation integral method; the mathematical expression corresponding to the correlation integral method is: ； ； in, is the correlation integral method function; is the scale index factor; is the total number of earthquake events; For the earthquake events and the distance to the earthquake event; is the Heaviside step function; The expression of the fractal dimension index is: ； in, is the relevant score; is the fractal dimension index; The principal component analysis method and kernel density estimation method are used to extract the kernel density peak of microseismic events, including: The principal component analysis method was used for dimensionality reduction, and the kernel density estimation method was used to quantify the spatiotemporal aggregation characteristics and determine the probability density; A Gaussian kernel density function is used to extract the kernel density peak based on the probability density to determine the spatiotemporal aggregation degree; The expression corresponding to the probability density is: ； The expression of the Gaussian kernel density function is: ； in, is the probability density; is a data point; is the total number of data points in the earthquake event group; is the bandwidth parameter; For the data points for earthquake events; is the Gaussian kernel density function.

2. The HE event early warning method according to claim 1, characterized in that: The semivariogram is a mathematical function used to characterize the corresponding result curve of the change of semivariability under different hysteresis values; the calculation formula of the semivariability is: ； in, is semivariability; Lag interval the number of pairs of data points separated; For the earthquake data; For Paired, lag interval is data.

3. A HE event warning device, characterized in that: include: Data acquisition module, used to obtain mine earthquake monitoring data; A correlation analysis module, configured to analyze the spatiotemporal correlation of the energy of the mine earthquake data using a semivariogram based on the mine earthquake monitoring data, and determine a historical data window; Window determination module, used to build a dynamic sliding mechanism; The dynamic sliding mechanism includes: a dynamic sliding time window determined based on a historical data window and a time resolution determined according to a mine production cycle; A quantification module is configured to extract the kernel density peak of the microseismic event based on the dynamic sliding mechanism using principal component analysis and kernel density estimation, and to determine the fractal dimension index using a fractal dimension analysis method, so as to analyze the change in the quantitative geometric complexity and obtain a quantified result; the quantified result includes regular information that the kernel density peak shows an upward trend and the fractal dimension index shows a downward trend before the HE event; A model building module is used to build a sliding window joint warning model; the sliding window joint warning model is determined by optimizing warning parameters based on the quantization results, taking F1 score maximization as the objective function, and using grid search; the warning parameters include: kernel density peak threshold, fractal dimension threshold and warning window; Grid search process: warning window range , kernel density peak threshold range , fractal dimension threshold range , for each combination, calculate the F1 score, and select the parameter combination with the highest F1 score as the optimized warning parameter; among them, is the resolution; is the lower limit of the kernel density peak threshold; is the upper limit of the kernel density peak threshold; is the lower threshold of fractal dimension; is the upper threshold of fractal dimension; The monitoring and early warning module is used to use the sliding window joint early warning model to monitor the kernel density peak and fractal dimension indicators in real time based on the optimized early warning parameters to achieve early warning of HE events; The fractal dimension analysis method adopts the correlation integral method; the mathematical expression corresponding to the correlation integral method is: ； ； in, is the correlation integral method function; is the scale index factor; is the total number of earthquake events; For the earthquake events and the distance to the earthquake event; is the Heaviside step function; The expression of the fractal dimension index is: ； in, is the relevant score; is the fractal dimension index; The principal component analysis method and kernel density estimation method are used to extract the kernel density peak of microseismic events, including: The principal component analysis method was used for dimensionality reduction, and the kernel density estimation method was used to quantify the spatiotemporal aggregation characteristics and determine the probability density; A Gaussian kernel density function is used to extract the kernel density peak based on the probability density to determine the spatiotemporal aggregation degree; The expression corresponding to the probability density is: ； The expression of the Gaussian kernel density function is: ； in, is the probability density; is a data point; is the total number of data points in the earthquake event group; is the bandwidth parameter; For the data points for earthquake events; is the Gaussian kernel density function.

4. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the HE event warning method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the HE event warning method according to any one of claims 1 to 2 is implemented.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the HE event warning method according to any one of claims 1 to 2 is implemented.

Images