Method and device for predicting vibration monitoring data of coal mine vibration event based on integrated model, and medium

Abstract

The invention discloses a coal mine vibration event vibration monitoring data prediction method and device based on an integrated model and a medium, and the method comprises the steps: obtaining a vibration probability detection model of each station through feature extraction and integrated model training testing, and building a mine vibration data enhancement integrated model based on the vibration probability detection model of each station; carrying out vibration event probability detection on the historical data of the target vibration event by using the mine earthquake data enhancement integration model, and calculating the probability that the target vibration event is detected by a preset number of stations after permutation and combination; according to the historical data of all the target vibration events, the probability that each target vibration event is detected by a preset number of stations is calculated, and vibration monitoring data is calculated according to the probability; according to the method, the generalization ability of the mine earthquake data enhancement integration model is enhanced, the over-fitting risk of the model is reduced, the accuracy of vibration event detection and the representativeness of vibration monitoring data are improved, and then the accuracy of coal mine rock burst early warning is improved.

Description

Technical Field

[0001] The present application relates to the field of coal mine vibration detection, and in particular to a method, device and medium for predicting vibration monitoring data of coal mine vibration events based on an integrated model. Background Art

[0002] In the process of coal mining, rock burst is one of the most serious safety hazards, which is usually accompanied by the sudden destruction of coal and rock mass and the instantaneous release of elastic strain energy. In order to predict and prevent rock burst, vibration monitoring technology is widely used. By analyzing the changes in the time and space of the monitored seismic activity, the risk of rock burst can be effectively assessed.

[0003] However, the mine vibration monitoring network cannot fully capture all earthquake event data, and the capabilities of each mine monitoring network vary greatly. When using the same method (such as the energy and frequency of earthquake events) to detect the risk of rock burst in different mines, this difference may lead to unfair detection results, low accuracy of vibration event detection, incomplete vibration monitoring data, and poor representativeness, resulting in low accuracy of coal mine rock burst warning. Summary of the invention

[0004] The purpose of this application is to provide a method, device and medium for predicting vibration monitoring data of coal mine vibration events based on an integrated model, which can enhance the generalization ability of the mine seismic data enhancement integrated model, reduce the risk of model overfitting, improve the accuracy of vibration event detection and the representativeness of vibration monitoring data, and thus improve the accuracy of coal mine impact ground pressure warning.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In the first aspect, the present application provides a method for predicting vibration monitoring data of coal mine vibration events based on an integrated model, and the method for predicting vibration monitoring data of coal mine vibration events based on an integrated model includes: for any station: obtaining the coordinates of the station, and the historical data of multiple vibration events; the historical data of the vibration events include: the coordinates of the vibration event and the energy of the vibration event; extracting features from the coordinates of the station, and the historical data of multiple vibration events, and constructing a feature data set of the station; training and testing each sub-model of the integrated model based on the feature data set of the station, and constructing a vibration probability detection model of the station using the loss function value, precision and recall rate of each trained sub-model; the The integrated model includes multiple sub-models; a mine earthquake data enhancement integrated model is constructed according to the vibration probability detection model of each station; for any target vibration event: the mine earthquake data enhancement integrated model is used to perform vibration event probability detection on the historical data of the target vibration event, and the probability of the target vibration event being detected by each station is obtained, and the probability of the target vibration event being detected by a preset number of stations is calculated through permutations and combinations; the probability of each target vibration event being detected by a preset number of stations is calculated; vibration monitoring data is obtained by calculating the probability of each target vibration event being detected by a preset number of stations; the vibration monitoring data includes: the predicted total energy of the vibration event, and the predicted total frequency of the vibration event.

[0007] In the second aspect, the present application provides a computer device, including: 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 above-mentioned method for predicting vibration monitoring data of coal mine vibration events based on the integrated model.

[0008] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting vibration monitoring data of coal mine vibration events based on an integrated model.

[0009] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0010] This application enhances the representativeness of the data set used for model training by extracting features from the coordinates of the station and the historical data of multiple vibration events; through the combination of various sub-models, a mine earthquake data enhancement integrated model is finally constructed, which effectively reduces the risk of overfitting of the model and improves the accuracy and generalization ability of the vibration event detection model; the mine earthquake data enhancement integrated model is used to perform vibration event probability detection on the historical data of the target vibration event, and the probability of the target vibration event being detected by each station is obtained, and the probability of the target vibration event being detected by a preset number of stations is calculated after permutation and combination, thereby improving the accuracy of vibration event detection. The vibration monitoring data is obtained by calculating the probability of each target vibration event being detected by a preset number of stations, thereby realizing the accurate correction of the vibration detection data, effectively solving the problem of incomplete vibration event data due to missed detection, making the vibration detection data more real and reasonable, and improving the representativeness of the vibration monitoring data, and then warning of coal mine rock burst is carried out based on accurate vibration monitoring data, thereby improving the accuracy of coal mine rock burst warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0012] Figure 1 A schematic flow chart of a method for predicting vibration monitoring data of coal mine vibration events based on an integrated model provided in an embodiment of the present application.

[0013] Figure 2 A schematic diagram of the training and testing process of the mine seismic data enhancement integrated model provided in an embodiment of the present application.

[0014] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

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

[0017] Embodiment 1, as Figure 1-Figure 2 As shown, this embodiment provides a method for predicting vibration monitoring data of coal mine vibration events based on an integrated model. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model includes the following steps.

[0018] S1. For any station: obtain the coordinates of the station and the historical data of multiple vibration events; the historical data of the vibration events include: the coordinates of the vibration events and the energy of the vibration events.

[0019] In actual application, the coordinates of each station are shown in Table 1, and the historical data of each vibration event are shown in Table 2.

[0020] Table 1 Example of station coordinates

[0021] Table 2 Historical data of vibration events

[0022] S2. Extract features from the station coordinates and historical data of multiple vibration events, and construct a feature data set of the station.

[0023] Step S2 specifically includes the following steps.

[0024] S21. According to the coordinates of the station and the coordinates of each vibration event, the horizontal distance between the station and the coordinates of each vibration event and the vertical distance between the station and the coordinates of each vibration event are respectively obtained to obtain a horizontal distance feature set and a vertical distance feature set.

[0025] Optionally, the horizontal distance feature set and the vertical distance feature set enable the integrated model to learn the spatial relationship pattern between the detection probability of the vibration event and the coordinates of the station.

[0026] In actual application, it is assumed that the numbers in Table 1 are i The station location is used Indicates that represents the x-coordinate of station 0, assuming that the numbers in Table 2 are j The historical shock event locations are Indicates that Represents the x-coordinate of the 0th shock event, and the calculation formulas for the generated horizontal distance and vertical distance are as follows.

[0027] .

[0028] .

[0029] In the formula, Indicates a vibration eventj With station i The vertical distance between Indicates a vibration event j With station i The horizontal distance between .

[0030] S22. Determine whether each vibration event is located in the first area according to the coordinates of each vibration event, and obtain a first set of judgment results; determine whether each vibration event is located in the second area according to the coordinates of each vibration event, and obtain a second set of judgment results; determine whether each vibration event is located in the third area according to the coordinates of each vibration event, and obtain a third set of judgment results; the first area is the goaf area range of the adjacent working face; the second area is the goaf area range of the current working face; the third area is the area to be mined of the current working face.

[0031] Optionally, the characteristic elements in the first judgment result set, the second judgment result set and the third judgment result set are all Boolean characteristics. The first judgment result set, the second judgment result set and the third judgment result set can enable the integrated model to identify the relationship between the detection probability of the vibration event and the area (medium) where the vibration event is located.

[0032] In actual application, due to the influence of coal mining, the first area, the second area and the third area all have different medium conditions.

[0033] S23. Construct a vibration event energy set based on the energy of each vibration event.

[0034] S24. Obtain the logarithmic value of each vibration event energy based on the calculation of each vibration event energy, and construct a set of logarithmic value of vibration event energy.

[0035] In actual applications, calculating the logarithm of the energy of each vibration event will generate a numerical feature, and based on multiple numerical features, a set of logarithmic values ​​of the vibration event energy will be obtained. Because the energy range of vibration events is very wide, ranging from single-digit joules to hundreds of thousands of megajoules, and the detection probability is exponentially related to the energy rather than linearly. Therefore, using the logarithm of the vibration event energy as a feature can enable the model to better capture the law.

[0036] Optionally, the logarithmic value of the vibration event energy is calculated as follows.

[0037] .

[0038] In the formula, is the logarithmic value of the energy of the shock event; For shock events energy.

[0039] S25. Construct a feature data set of the station based on the horizontal distance feature set, the vertical distance feature set, the first judgment result set, the second judgment result set, the third judgment result set, the vibration event energy set and the logarithmic value set of the vibration event energy.

[0040] S3. Train and test each sub-model of the integrated model based on the characteristic data set of the station, and use the loss function value, precision and recall rate of each trained sub-model to build a vibration probability detection model of the station; the integrated model includes multiple sub-models.

[0041] Step S3 specifically includes the following steps.

[0042] S31. Divide the characteristic data sets of the stations into training sets and test sets according to the preset ratio.

[0043] S32. Taking the probability of a vibration event being detected by a station as a label and minimizing the loss function value as a goal, each sub-model is trained using the training set of the station to obtain trained sub-models.

[0044] Optionally, the calculation formula for the loss function value of the trained sub-model is as follows.

[0045] .

[0046] In the formula, is the loss function value of the trained sub-model, n is the number of vibration events, For shock events The actual label, For shock events The probability of belonging to the positive class.

[0047] S33. Use the test set to evaluate the model performance of each trained sub-model to obtain the precision and recall rate of each trained sub-model.

[0048] Optionally, the calculation formulas for the precision and recall of the trained sub-model are as follows.

[0049] .

[0050] .

[0051] in, Precision is the accuracy of the trained sub-model, Recall is the recall rate of the trained sub-model, TP is the number of true positive examples (the number of samples correctly predicted as positive), FP is the number of false positives (number of samples incorrectly predicted as positive), FNis the number of false negative examples (the number of actual positive samples that are incorrectly predicted as negative).

[0052] S34. Calculate the weight score of each sub-model of the station using the loss function value, precision and recall rate of each trained sub-model.

[0053] Furthermore, the calculation process of the weight score of each sub-model of the station is as follows.

[0054] .

[0055] In the formula, The sub-models of the station k The weight score of , and They are the sub-models of the stations. k The loss function value, precision, and recall. By multiplying the average of precision and recall with the inverse of log loss, the accuracy of the model is balanced with its ability to distinguish specific categories.

[0056] S35. Normalize the weight scores of each sub-model of the station to obtain the weight of each sub-model of the station.

[0057] Optionally, the weight of the sub-model of a station is calculated as follows.

[0058] .

[0059] In the formula, Submodel for the station The weight of Submodel for the station The weight score of The sum of the weight scores of all sub-models for a station.

[0060] S36. Construct a vibration probability detection model for the station according to the weights of each sub-model of the station.

[0061] Furthermore, the preset ratio is 7:3.

[0062] In actual application, step S3 uses the idea of ​​ensemble model, combining multiple high-variance sub-models together through voting to reduce variance and improve the generalization ability of the model.

[0063] Optionally, the sub-model is a gradient boosting model or a probability generation model.

[0064] Optionally, the gradient boosting model (binary classification sub-model) includes at least one of XGBoost, LightGBM and CatBoost.

[0065] Optionally, the voting method for the weights of the sub-models may be soft voting or hard voting.

[0066] S4. Construct a mining seismic data augmentation ensemble (MSDAE) based on the vibration probability detection model of each station.

[0067] This embodiment constructs a mine earthquake data enhancement integrated model by training a vibration probability detection model for each station, thereby avoiding the problem of model overfitting (the probability of vibration event detection at a specific location is too high) caused by directly using spatial coordinates and event energy for training and prediction, and improving the generalization ability of the model.

[0068] S5. For any target vibration event: use the mine earthquake data enhancement integrated model to perform vibration event probability detection on the historical data of the target vibration event, and obtain the probability of the target vibration event being detected by each station. After permutations and combinations, calculate the probability of the target vibration event being detected by a preset number of stations (i.e., soft voting classification).

[0069] Furthermore, the calculation formula for the probability that the target vibration event is detected by a preset number of stations is as follows.

[0070] .

[0071] .

[0072] In the formula, is the probability that the target vibration event is detected by a preset number of stations; For target vibration events only The probability of detection at a station; is the preset quantity; The total number of slave stations Select i The number of combinations of stations; The total number of target vibration events that can be detected from the station Select The first station in the combination b The product of the probabilities of detection of permutations and combinations; The total number of target vibration events that cannot be detected from the station Select The first station in the combination The product of the probabilities of detection of permutations and combinations; Indicates that it can be detected. It means that it cannot be detected, and when used together with the multiplication symbol, it means that the probabilities contained in the corresponding combinations are multiplied respectively.

[0073] Optional, .

[0074] In practical applications, the core concept of the probability of each earthquake event being detected revolves around the combined probability of each station detecting the event. The probability of a earthquake event being detected is equal to the probability that it is detected by at least n stations. Since earthquake location usually requires the participation of at least four effective stations, n is usually assigned a value of 4.

[0075] Optionally, the probability that the target vibration event is detected by 0 stations is calculated as follows.

[0076] .

[0077] In the formula, is the probability that the target earthquake event is detected by 0 stations, For target vibration events only The probability of detection at a station is is the total number of stations.

[0078] S6. Calculate the probability that each target vibration event (new sample) is detected by a preset number of stations.

[0079] S7. Vibration monitoring data is obtained by calculating the probability of each target vibration event being detected by a preset number of stations; the vibration monitoring data includes: the predicted total energy of the vibration event, and the predicted total frequency of the vibration event.

[0080] Furthermore, the calculation formula for the predicted total energy of the vibration event is as follows.

[0081] .

[0082] .

[0083] In the formula, is the predicted total energy of the shock event, Theoretically, the target vibration event The energy is the observed target vibration event The energy Is the target vibration event Preset quantity The probability of detection by a station is is the total number of samples of the target vibration event.

[0084] Furthermore, the calculation formula for the predicted total frequency of the vibration events is as follows.

[0085] .

[0086] .

[0087] In the formula, is the predicted total frequency of vibration events, Theoretically, the target vibration event The frequency of Is the target vibration event Preset quantity The probability of detection by a station is is the total number of samples of the target vibration event.

[0088] In actual application, the total energy and total frequency of all vibration events obtained in this embodiment can effectively reduce the unfairness of different mine networks in the process of comparing the dangers of rock burst, thereby improving the fairness and reliability of the comparison results.

[0089] The specific implementation process of this embodiment in actual application is as follows.

[0090] Step 1: Obtain data (station coordinates, and historical data of multiple earthquake events).

[0091] Step 2: Feature extraction, constructing the monitoring dataset for each station.

[0092] Taking station 0 as an example, the monitoring data set of station 0 is constructed. The constructed data set is shown in Table 3.

[0093] Table 3 Characteristic data set of station 0

[0094] Among them, the horizontal distance (horizontal distance feature) represents the horizontal distance from each event to station 0, the vertical distance (vertical distance feature) represents the vertical distance from each vibration event to station 0, range 1 (first area) represents whether the event is in the goaf of the adjacent working face, range 2 (second area) represents whether the event is in the goaf of the current working face, range 3 (third area) represents whether the event is in the area to be mined of the current working face, energy represents the energy of the vibration event, the logarithm of the energy represents the logarithm of the energy of the vibration event, and the label represents whether station 0 participates in the location of the event.

[0095] Step 3: Model building.

[0096] In this embodiment, three gradient boosting algorithms, XGBoost, LightGBM and CatBoost, are used to build an integrated model. According to the test set, the average logarithmic loss of the XGBoost model is 6.98, and the average values ​​of precision and recall are 0.80 and 0.76 respectively; the average logarithmic loss of the LightGBM model is 7.27, and the precision and recall are 0.79 and 0.76 respectively; and the average logarithmic loss of the CatBoost model is 6.92, and the precision and recall are 0.81 and 0.77. Based on these performance indicators, the final integrated model weight distribution is as follows.

[0097] .

[0098] in is the final output of the integrated model, , and These are the outputs of the three framework models.

[0099] Step 4: Calculate the detection probability.

[0100] Step 5: Improve vibration data integrity.

[0101] Among them, the total energy and total frequency of the original data are 611949 and 6, respectively, while the total energy and total frequency after enhancement (the predicted total energy of vibration events in the vibration monitoring data, and the predicted total frequency of vibration events) are 625362.16 and 6.31, respectively.

[0102] Using the predicted total energy and the predicted total frequency of vibration events to judge the rock burst hazard of each mine can effectively eliminate the unfairness caused by different detection capabilities of the station network.

[0103] Embodiment 2, the present application also provides a computer device, which may be a server or a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store processing data. The input / output 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 through a network connection. When the computer program is executed by the processor, a method for predicting vibration monitoring data of coal mine vibration events based on an integrated model is implemented.

[0104] Those skilled in the art will understand that Figure 3 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] Embodiment 3: The present application also provides a computer-readable storage medium storing a computer program, which implements the above methods when executed by a processor.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium 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), magnetoresistive 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).

[0107] All actions to obtain signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0108] The technical features of the above embodiments may 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.

[0109] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will 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 method for predicting vibration monitoring data of coal mine vibration events based on an integrated model, characterized in that: The coal mine vibration event vibration monitoring data prediction method based on the integrated model includes: For any station: Acquire the coordinates of the station and the historical data of a plurality of vibration events; the historical data of the vibration events include: the coordinates of the vibration events and the energy of the vibration events; Extract features from the station coordinates and historical data of multiple earthquake events, and construct a feature dataset of the station; Based on the characteristic data set of the station, each sub-model of the integrated model is trained and tested, and the vibration probability detection model of the station is constructed using the loss function value, precision and recall rate of each trained sub-model; the integrated model includes multiple sub-models; Construct an integrated model for mine earthquake data enhancement based on the probability detection model of each station; For any target vibration event: The mine earthquake data enhancement integrated model is used to detect the probability of the target vibration event on the historical data of the target vibration event, and the probability of the target vibration event being detected by each station is obtained. The probability of the target vibration event being detected by a preset number of stations is calculated through permutations and combinations; Calculate the probability of each target vibration event being detected by a preset number of stations; The vibration monitoring data is obtained by calculating the probability that each target vibration event is detected by a preset number of stations; the vibration monitoring data includes: the predicted total energy of the vibration event, and the predicted total frequency of the vibration event.

2. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 1, characterized in that: The station coordinates and historical data of multiple earthquake events are extracted, and the station feature data set is constructed, including: According to the coordinates of the station and the coordinates of each vibration event, the horizontal distance between the station and the coordinates of each vibration event and the vertical distance between the station and the coordinates of each vibration event are respectively obtained to obtain a horizontal distance feature set and a vertical distance feature set; Determine whether each vibration event is located in the first area according to the coordinates of each vibration event, and obtain a first judgment result set; determine whether each vibration event is located in the second area according to the coordinates of each vibration event, and obtain a second judgment result set; determine whether each vibration event is located in the third area according to the coordinates of each vibration event, and obtain a third judgment result set; the first area is the goaf area range of the adjacent working face; the second area is the goaf area range of the current working face; the third area is the area to be mined of the current working face; Constructing a vibration event energy set based on the energy of each vibration event; The logarithmic value of each vibration event energy is calculated based on each vibration event energy, and a set of logarithmic value of vibration event energy is constructed; A feature data set of the station is constructed based on the horizontal distance feature set, the vertical distance feature set, the first judgment result set, the second judgment result set, the third judgment result set, the vibration event energy set and the logarithmic value set of the vibration event energy.

3. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 1, characterized in that: Based on the characteristic data set of the station, each sub-model of the integrated model is trained and tested, and the vibration probability detection model of the station is constructed using the loss function value, precision and recall rate of each trained sub-model, including: The characteristic data sets of the stations are divided into training sets and test sets according to the preset ratio; Taking the probability of a vibration event being detected by a station as a label and minimizing the loss function value as the goal, each sub-model is trained using the training set of the station to obtain the trained sub-models. Use the test set to evaluate the performance of each trained sub-model and obtain the precision and recall of each trained sub-model; The weight scores of each sub-model of the station are calculated using the loss function values, precision and recall of each sub-model trained; Normalize the weight scores of each sub-model of the station to obtain the weight of each sub-model of the station; The vibration probability detection model of the station is constructed according to the weights of each sub-model of the station.

4. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 3, characterized in that: The preset ratio is 7:

3.

5. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 3, characterized in that: The calculation process of the weight score of each sub-model of the station is as follows: ； In the formula, is the weight score of each sub-model k of the station; , and are the loss function value, precision and recall rate of each sub-model k of the station respectively.

6. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 1, characterized in that: The calculation formula for the probability that the target vibration event is detected by a preset number of stations is as follows: ； ； In the formula, is the probability that the target vibration event is detected by a preset number of stations; For target vibration events only The probability of detection at a station; is the preset quantity; The total number of slave stations Select i The number of combinations of stations; The total number of target vibration events that can be detected from the station Select The first station in the combination b The product of the probabilities of detection of permutations and combinations; The total number of target vibration events that cannot be detected from the station Select The first The product of the probabilities of detection of permutations and combinations; Indicates that it can be detected. Indicates that it cannot be detected.

7. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 1, characterized in that: The calculation formula for the predicted total energy of the vibration event is as follows: ； ； In the formula, is the predicted total energy of the shock event, Theoretically, the target vibration event The energy is the observed target vibration event The energy Is the target vibration event Preset quantity The probability of detection by a station is is the total number of samples of the target vibration event.

8. The method for predicting vibration monitoring data of coal mine vibration events based on an integrated model according to claim 1, characterized in that: The calculation formula for the predicted total frequency of the vibration event is as follows: ； ； In the formula, is the predicted total frequency of vibration events, Theoretically, the target vibration event The frequency of Is the target vibration event Preset quantity The probability of detection by a station is is the total number of samples of the target vibration event.

9. 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 method for predicting vibration monitoring data of coal mine vibration events based on an integrated model as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting vibration monitoring data of coal mine vibration events based on an integrated model as described in any one of claims 1 to 8 is implemented.

Images