Rockburst probability prediction method, device and equipment based on probability distribution function

A rockburst database was constructed using microseismic monitoring data and geological and construction information. By employing the Johnson distribution and decision group weighting method, the problem of difficulty in judging the relationship between multiple sources of information in existing rockburst prediction methods was solved, thus achieving scientific prediction and accurate forecasting of rockburst probability.

CN118780647BActive Publication Date: 2024-11-29SICHUAN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411266472.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-11-29
Estimated Expiration
2044-09-11

AI Technical Summary

Technical Problem

Existing rockburst prediction methods cannot accurately determine the relationship between multiple sources of information such as geology, microseismic activity, geophysical exploration, and construction during the construction process, making it difficult to predict the probability of rockburst occurrence and lacking scientific basis.

Method used

Data is acquired through microseismic monitoring, combined with geological and construction information, to construct a rockburst database. Cluster analysis is performed to determine indicators, and the data is converted to a normal distribution using the Johnson distribution method. A joint probability prediction model is then constructed, and the probability of rockburst is predicted by combining decision group weights and a projected objective function.

Benefits of technology

It enables scientific prediction of rockburst occurrence probability from the perspective of multi-source information, improves the accuracy and reliability of prediction, and can comprehensively evaluate the rockburst gestation and development process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118780647B_ABST
    Figure CN118780647B_ABST
Patent Text Reader

Abstract

The present application provides a rockburst probability prediction method, device and equipment based on a probability distribution function, which relates to the field of rockburst prediction technology. Microseismic monitoring is carried out in high-risk rockburst areas of underground projects to obtain microseismic monitoring data and collect geological information and construction information; microseismic monitoring data is analyzed to obtain microseismic information; a rockburst database is constructed and abnormal rockburst data in the rockburst database is removed to determine indicators for rockburst probability prediction; three primary indicators and ten secondary indicators are constructed respectively, the rockburst probability distribution model corresponding to the secondary indicators is determined and a joint rockburst probability prediction model of the three primary indicators is constructed; according to the joint rockburst probability prediction model, the rockburst occurrence probability of the underground project to be tested is obtained in combination with the information of on-site monitoring of the underground project to be tested. The above method can evaluate the gestation and development process of rockburst from a more comprehensive perspective and accurately predict the probability of rockburst.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of rockburst prediction, and in particular to a method, device and equipment for predicting rockburst probability based on a probability distribution function. Background Art

[0002] Rockburst is a dynamic phenomenon in which the elastic deformation potential accumulated in the rock mass is suddenly and violently released under deep underground engineering excavation or external disturbance, resulting in the rapid ejection of the rock mass. Due to its high risk and great destructiveness, it seriously threatens the safety of on-site construction personnel and equipment. Therefore, accurate prediction of rockburst is of great significance to the safe construction of underground engineering.

[0003] In recent years, microseismic monitoring technology, as a new type of rock microfracture monitoring technology, has played a key role in monitoring and early warning of disasters such as rock bursts and rock bursts in tunnels and underground projects. By analyzing the microfracture signal to obtain the source time, location and source parameter information, the spatial distribution of rock crack extension is determined, and the rock stability is evaluated in combination with the surrounding rock microseismic intensity and parameter evolution trend, further realizing rock burst early warning.

[0004] However, rockburst is a complex geological disaster with a complicated mechanism. It is difficult to predict the probability of rockburst by relying solely on the evolution trend of earthquake source parameters, and it is also impossible to determine the relationship between multiple sources of information such as geology, microseismic, geophysical exploration, and construction during the construction process. In addition, the traditional rockburst prediction method is a fuzzy prediction and has no scientific basis for the actual probability of rockburst.

[0005] Based on this, a new rockburst probability prediction method is urgently needed to predict the probability of rockburst. Summary of the invention

[0006] The present application provides a rockburst probability prediction method, device and equipment based on probability distribution function to solve the above-mentioned problems existing in the existing rockburst prediction methods.

[0007] In a first aspect of an embodiment of the present application, a rockburst probability prediction method based on a probability distribution function is proposed, the method comprising:

[0008] Conduct microseismic monitoring in high-risk rockburst areas of underground projects, obtain microseismic monitoring data, and collect geological information and construction information corresponding to high-risk rockburst areas;

[0009] Analyzing the microseismic monitoring data to obtain microseismic characteristic parameters, and calculating and analyzing the changing laws of the microseismic characteristic parameters during the rockburst incubation process to obtain microseismic information;

[0010] Combine the geological information, construction information and microseismic information corresponding to the high-risk rockburst areas of underground engineering projects to obtain typical rockburst examples, and build a rockburst database based on multiple typical rockburst examples;

[0011] Performing cluster analysis on typical rock burst instances in the rock burst database, removing abnormal rock burst data in the rock burst database, and determining an index for rock burst probability prediction;

[0012] Combining the rockburst data corresponding to the microseismic information, geological information and construction information, three primary indicators and ten secondary indicators are constructed respectively;

[0013] The distribution of each secondary indicator is statistically analyzed, and combined with the statistical results, a joint prediction function of the rockburst probability distribution corresponding to each secondary indicator is constructed;

[0014] Determine the rockburst probability distribution model corresponding to the secondary indicator according to the rockburst probability distribution joint prediction function of each secondary indicator, and construct a joint rockburst probability prediction model of the three primary indicators based on the rockburst probability distribution model;

[0015] According to the joint rockburst probability prediction model, the rockburst occurrence probability of the underground project to be tested is obtained by combining the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested.

[0016] In an optional embodiment of the present application, the indicators used to predict the probability of rockburst are determined as follows: geological information indicators include at least: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology; construction information indicators include at least: support density, construction intensity, and construction method; microseismic information indicators include at least: cumulative number of events, cumulative energy, cumulative apparent volume, and maximum apparent stress.

[0017] In an optional embodiment of the present application, the three first-level indicators include: geological information, construction information and microseismic information; the second-level indicators corresponding to the geological information include: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology; the second-level indicators corresponding to the construction information include: support density, construction intensity, and construction method; the second-level indicators corresponding to the microseismic information include: cumulative energy, cumulative number of events, cumulative apparent volume, and maximum apparent stress.

[0018] In an optional embodiment of the present application, the rockburst probability distribution joint prediction function is constructed by a Johnson distribution method, and the parameters corresponding to each secondary indicator are converted into normally distributed data by the Johnson distribution method, including:

[0019] According to the Johnson distribution method, the parameters corresponding to the secondary indicators used to construct the rockburst probability distribution joint prediction function and the type of each parameter are defined respectively to obtain the defined parameters and types;

[0020] According to the defined parameters and types, determine the Johnson distribution type to which the corresponding parameters of the secondary indicators belong;

[0021] According to the Johnson distribution type, the parameters corresponding to the secondary indicators are converted into normal distribution data;

[0022] Perform normal distribution test on different parameters, take the significance level as 0.05, determine whether the normal distribution test result is greater than 0.05, and verify whether the transformed data meets the significance level;

[0023] Normal distribution data that meets the significant level are used to construct the rockburst probability distribution joint prediction function.

[0024] In an optional embodiment of the present application, a rockburst probability distribution model corresponding to the secondary indicator is determined according to the rockburst probability distribution joint prediction function of each secondary indicator, and a joint rockburst probability prediction model of three primary indicators is constructed based on the rockburst probability distribution model, including:

[0025] Based on the decision weight of each member of the decision-making group and the comprehensive weight of the decision-making group, the weight of each first-level indicator is obtained;

[0026] Based on the rockburst grade and the projection objective function, the weights of each secondary indicator are obtained, and the rockburst probability distribution model is constructed according to the weights of each secondary indicator;

[0027] Based on the weights of the first-level indicators and the rockburst probability distribution models corresponding to the second-level indicators, a joint rockburst probability prediction model of the three first-level indicators is constructed.

[0028] In an optional embodiment of the present application, based on the decision weights of each member of the decision-making group and the comprehensive weight of the decision-making group, the weights of each primary indicator are obtained, including:

[0029] The importance of the first-level index is expressed by using a 5-level fuzzy evaluation language, and the trapezoidal fuzzy number of each level of the first-level index is obtained;

[0030] Determine the decision weight of each expert in the decision-making group;

[0031] The importance of the primary indicators is evaluated by using fuzzy words applied by experts, and the comprehensive weight of the decision group is calculated by combining the trapezoidal fuzzy numbers of each level of the primary indicators;

[0032] Calculating a fuzzy weight based on the decision weight of each expert and the comprehensive weight of the decision group;

[0033] Normalizing the fuzzy weights to construct a weight vector formula;

[0034] Based on the weight vector formula, the weights of the first-level indicators are obtained.

[0035] In an optional embodiment of the present application, based on the rockburst level and the projection objective function, the weights of the secondary indicators are obtained, including:

[0036] The rock burst levels are divided into four levels: severe, moderate, slight and none;

[0037] A plurality of sample data and their corresponding levels are randomly generated within each rockburst level, and the randomly generated plurality of sample data are normalized to obtain projection data;

[0038] Projecting the projection data onto a projection direction to obtain a one-dimensional projection value;

[0039] Establishing a projection objective function based on the one-dimensional projection value;

[0040] The maximum value of the projection objective function is calculated to obtain the weights of the secondary indicators.

[0041] In an optional embodiment of the present application, the combined rockburst probability prediction model is as follows:

[0042] F(x)=g(z)*w1+f(z)*w2+h(z)*w3,

[0043] In the formula, g(z) represents the rockburst probability distribution model of the secondary indicator corresponding to geological information; w1 represents the primary indicator weight of geological information, f(z) represents the rockburst probability distribution model of the secondary indicator corresponding to construction information; w2 represents the primary indicator weight of construction information, h(z) represents the rockburst probability distribution model of the secondary indicator corresponding to microseismic information; w3 represents the primary indicator weight of microseismic information; where, z i represents the i-th secondary indicator, the value range of i is 1 to n, ω1 represents the weight of the secondary indicator corresponding to geological information, ω2 represents the weight of the secondary indicator corresponding to construction information, and ω3 represents the weight of the secondary indicator corresponding to microseismic information.

[0044] In a second aspect of an embodiment of the present application, a rockburst probability prediction device based on a probability distribution function is proposed, the device comprising:

[0045] The information acquisition module is used to carry out microseismic monitoring in high-risk rockburst areas of underground projects, obtain microseismic monitoring data, and collect geological information and construction information corresponding to high-risk rockburst areas;

[0046] A microseismic information acquisition module is used to analyze the microseismic monitoring data to obtain microseismic characteristic parameters, and calculate and analyze the changing laws of the microseismic characteristic parameters during the rockburst incubation process to obtain microseismic information;

[0047] A database construction module is used to combine geological information, construction information and microseismic information corresponding to high-risk rockburst areas of underground engineering projects to obtain typical rockburst examples and construct a rockburst database based on multiple typical rockburst examples;

[0048] A determination module, used to perform cluster analysis on typical rock burst instances in the rock burst database, remove abnormal rock burst data in the rock burst database, and determine indicators for rock burst probability prediction;

[0049] An indicator construction module, for combining the rock burst data corresponding to the microseismic information, geological information and construction information to respectively construct three primary indicators and ten secondary indicators;

[0050] The function construction module is used to collect statistics on the distribution of each secondary indicator and, based on the statistical results, to construct a joint prediction function for the rockburst probability distribution corresponding to each secondary indicator;

[0051] A model building module is used to determine the rockburst probability distribution model corresponding to the secondary indicator according to the rockburst probability distribution joint prediction function of each secondary indicator, and to build a joint rockburst probability prediction model of the three primary indicators based on the rockburst probability distribution model;

[0052] The prediction module is used to obtain the rockburst occurrence probability of the underground project to be tested based on the combined rockburst probability prediction model and in combination with the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested.

[0053] In a third aspect of an embodiment of the present application, an electronic device is proposed, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the rockburst probability prediction method based on a probability distribution function as described in any one of the first aspects above.

[0054] The present application includes the following advantages: the present application provides a rockburst probability prediction method, device and equipment based on a probability distribution function, carries out microseismic monitoring in high-risk rockburst areas of underground engineering, obtains microseismic monitoring data, and collects geological information and construction information corresponding to the high-risk rockburst areas; analyzes the microseismic monitoring data to obtain microseismic characteristic parameters, and calculates and analyzes the changing laws of the microseismic characteristic parameters in the rockburst incubation process to obtain microseismic information; combines the geological information, construction information and microseismic information corresponding to the high-risk rockburst areas of underground engineering to obtain typical rockburst examples, and constructs a rockburst database based on multiple typical rockburst examples; performs cluster analysis on typical rockburst examples in the rockburst database, and removes abnormal rockburst data in the rockburst database. According to the rockburst information, indicators for rockburst probability prediction are determined; three first-level indicators and ten second-level indicators are constructed respectively in combination with the rockburst data corresponding to the microseismic information, geological information and construction information; statistics are made on the distribution of each second-level indicator, and in combination with the statistical results, a joint prediction function of rockburst probability distribution corresponding to each second-level indicator is constructed; according to the joint prediction function of rockburst probability distribution of each second-level indicator, a rockburst probability distribution model corresponding to the second-level indicator is determined, and based on the rockburst probability distribution model, a joint rockburst probability prediction model of the three first-level indicators is constructed; according to the joint rockburst probability prediction model, the rockburst occurrence probability of the underground project to be tested is obtained in combination with the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested.

[0055] By statistically analyzing microseismic monitoring data under different geological conditions and construction intensities, we summarized and sorted out multi-source characteristic information including geological and construction factors, summarized the characteristic indicators of the rockburst probability distribution model, calculated the probability distribution model of each indicator, and realized the scientific prediction of the probability of rockburst. At the same time, this application is a case database constructed through data of rockbursts that have occurred. When performing characteristic value statistics, the data changes for seven days are taken as a stage. Through a large number of rockburst cases, the key parameters in the probability prediction model are obtained. The prediction method of this application can evaluate the gestation and development process of rockburst from a more comprehensive perspective and accurately predict the probability of rockburst. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application 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 labor.

[0057] Figure 1 It is a flowchart of a method for predicting rockburst probability based on a probability distribution function provided in an embodiment of the present application;

[0058] Figure 2It is an architecture diagram of a rockburst probability prediction device based on a probability distribution function provided in an embodiment of the present application;

[0059] Figure 3 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] 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 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.

[0061] Rockburst is a dynamic phenomenon in which the elastic deformation potential accumulated in the rock mass is suddenly and violently released under deep underground engineering excavation or external disturbance, resulting in the rapid ejection of the rock mass. Due to its high risk and great destructiveness, it seriously threatens the safety of on-site construction personnel and equipment. Therefore, accurate prediction of rockburst is of great significance to the safe construction of underground engineering.

[0062] In recent years, microseismic monitoring technology, as a new type of rock microfracture monitoring technology, has played a key role in monitoring and early warning of disasters such as rock bursts and rock bursts in tunnels and underground projects. By analyzing the microfracture signal to obtain the source time, location and source parameter information, the spatial distribution of rock crack extension is determined, and the rock stability is evaluated in combination with the surrounding rock microseismic intensity and parameter evolution trend, further realizing rock burst early warning.

[0063] However, rockburst is a complex geological disaster with a complicated mechanism. It is difficult to predict the probability of rockburst by relying solely on the evolution trend of earthquake source parameters, and it is also impossible to determine the relationship between multiple sources of information such as geology, microseismic, geophysical exploration, and construction during the construction process. In addition, the traditional rockburst prediction method is a fuzzy prediction and has no scientific basis for the actual probability of rockburst.

[0064] Based on this, the present application provides a rockburst probability prediction method based on a probability distribution function, which is used to predict the probability of rockburst occurrence.

[0065] See also Figure 1 , Figure 1 : is a flowchart of a method for predicting rockburst probability based on a probability distribution function provided by an embodiment of the present application, the method comprising the following steps:

[0066] Step 101: Conduct microseismic monitoring in the rockburst high-risk area of ​​the underground project, obtain microseismic monitoring data, and collect geological information and construction information corresponding to the rockburst high-risk area;

[0067] Step 102: Analyze the microseismic monitoring data to obtain microseismic characteristic parameters, and calculate and analyze the changing rules of the microseismic characteristic parameters during the rockburst incubation process to obtain microseismic information;

[0068] Step 103: combining geological information, construction information and microseismic information corresponding to the rockburst high-risk area of ​​the underground engineering, obtaining typical rockburst examples, and constructing a rockburst database based on multiple typical rockburst examples;

[0069] Step 104: performing cluster analysis on typical rock burst instances in the rock burst database, removing abnormal rock burst data in the rock burst database, and determining an index for rock burst probability prediction;

[0070] Step 105: combining the rockburst data corresponding to the microseismic information, geological information and construction information, respectively constructing three primary indicators and ten secondary indicators;

[0071] Step 106: Count the distribution of each secondary indicator, and build a joint prediction function of rockburst probability distribution corresponding to each secondary indicator based on the statistical results;

[0072] Step 107: determining a rockburst probability distribution model corresponding to the secondary indicator according to the rockburst probability distribution joint prediction function of each secondary indicator, and constructing a joint rockburst probability prediction model of the three primary indicators based on the rockburst probability distribution model;

[0073] Step 108: According to the joint rockburst probability prediction model, the rockburst occurrence probability of the underground project to be tested is obtained by combining the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested.

[0074] When specifically implementing step 101, microseismic data monitoring is performed on high-risk rockburst areas of different underground projects to obtain microseismic monitoring data; the geological data and construction data of the rockburst risk area are of great significance for the prediction of rockburst risks of underground projects. While microseismic data monitoring is performed on the rockburst risk area, geological information and construction information corresponding to the high-risk rockburst area are collected, so that the subsequently constructed rockburst database and rockburst prediction model can more accurately predict the rockburst risks of underground projects.

[0075] When step 102 is specifically implemented, the acquired microseismic monitoring data is analyzed, useless or repeated data is removed, and microseismic characteristic parameters are obtained, such as the cumulative number of events, cumulative energy, cumulative apparent volume, apparent stress, etc., and typical rockburst examples are obtained by analyzing the changing rules of the microseismic characteristic parameters during the rockburst incubation process. The typical rockburst examples include data on geological information, construction information, microseismic information, etc. in high-risk rockburst areas of different underground projects. Among them, the analysis of the changing rules of the microseismic characteristic parameters during the rockburst incubation process mainly analyzes the precursor information of the rockburst incubation and the changes of the microseismic characteristic parameters during the rockburst process.

[0076] When implementing step 103 specifically, when establishing a rockburst database, it is necessary to select rockburst microseismic monitoring data under different geological conditions and different construction conditions according to the geological characteristics of the underground project, and integrate the above information to construct a rockburst database. Therefore, combining the geological information and construction information collected in step 101, and the microseismic information analyzed in step 102, multiple typical rockburst instances are obtained, and a rockburst database is constructed based on multiple typical rockburst instances. The rockburst data in the typical rockburst instances contained in the rockburst database are counted in a stage seven days before the rockburst occurs. The statistics for a stage of seven days can collect a sufficient amount of data, and the collected data is more obvious. Each typical rockburst instance contains geological information, construction information and its corresponding microseismic information.

[0077] Exemplarily, referring to Table 1, Table 2 and Table 3, Table 1, Table 2 and Table 3 are respectively the microseismic information, geological information and construction information of the same typical rock burst example.

[0078] Table 1 Microseismic information of typical rockburst cases

[0079]

[0080]

[0081] Table 2 Geological information of typical rockburst cases

[0082]

[0083]

[0084] Table 3 Construction information of typical rock burst cases

[0085]

[0086]

[0087] When step 104 is specifically implemented, it can be seen from the data in Tables 1 to 3 that there are a lot of rock burst data in each typical rock burst instance, but some rock burst case data are abnormal (not in accordance with the distribution law), and analyzing such data will affect the accuracy of the final rock burst probability prediction. Therefore, cluster analysis is performed on the data in the typical rock burst instance, and based on the results of the cluster analysis, the abnormal rock burst data in the rock burst database is removed, and the microseismic information index for rock burst probability prediction is determined. Optionally, the above cluster analysis method can be K-Means clustering, hierarchical clustering, etc.

[0088] In an optional embodiment of the present application, the indicators used for predicting rockburst probability are determined as follows: geological information indicators include at least: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology; construction information indicators include at least: support density, construction intensity, and construction method; microseismic information indicators include at least: cumulative number of events, cumulative energy, cumulative apparent volume, and maximum apparent stress. The microseismic information indicators corresponding to the above geological information, construction information, and microseismic information can be added or deleted according to the rules of actual rockburst data.

[0089] When the specific implementation step 105 is performed, after the abnormal rock burst data in the rock burst database is removed, the rock burst data in the remaining typical rock burst instances in the rock burst database have certain regularities. By analyzing the remaining data, prediction indicators related to the rock burst data can be obtained. Therefore, the rock burst data corresponding to the microseismic information, geological information and construction information are combined to construct three primary indicators and ten secondary indicators respectively. The three primary indicators include: geological information, construction information and microseismic information. The secondary indicators corresponding to the geological information include: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology. The secondary indicators corresponding to the construction information include: support density, construction intensity, and construction method. The secondary indicators corresponding to the microseismic information include: cumulative energy, cumulative number of events, cumulative apparent volume, and maximum apparent stress. The rock burst data corresponding to the above-mentioned microseismic information, geological information, and construction information refer to the rock burst data corresponding to the microseismic information, geological information, and construction information in each typical instance.

[0090] When specifically implementing step 106, after determining each first-level indicator and the second-level indicator corresponding to each first-level indicator, the distribution of each second-level indicator under different geological information and different construction information is statistically analyzed, and combined with the statistical results, a joint prediction function of the rock burst probability distribution corresponding to each second-level indicator is constructed. The joint prediction function of the rock burst probability distribution corresponding to each second-level indicator is used to construct a rock burst probability prediction model.

[0091] In an optional embodiment of the present application, the above-mentioned rockburst probability distribution joint prediction function is constructed by the Johnson distribution method. The Johnson distribution method is a method for data conversion through the Johnson distribution conversion formula. The Johnson distribution conversion formula is based on the conversion of the probability density function. By converting the probability density function of the original data into the probability density function of the Johnson distribution, the data distribution is transformed. This conversion makes the original data more consistent with the required analysis model, so as to perform more accurate and effective analysis. Since the data distribution corresponding to the secondary indicators is relatively scattered and difficult to analyze, the data corresponding to the secondary indicators can be converted into data that meets the analysis requirements through the Johnson distribution method to obtain more accurate analysis results.

[0092] Specifically, the parameters corresponding to each secondary indicator are converted into normally distributed data through the Johnson distribution method, including: first, according to the Johnson distribution method, the parameters corresponding to the secondary indicators used to construct the rockburst probability distribution joint prediction function, and the type to which each parameter belongs are defined respectively to obtain the defined parameters and types; according to the defined parameters and types, the Johnson distribution type to which the parameters corresponding to the secondary indicators belong is determined; according to the Johnson distribution type, the parameters corresponding to the secondary indicators are converted into normally distributed data; a KS normal distribution test is performed on different parameters, and the significance level value α is taken as 0.05 to determine whether the normal distribution test result is greater than 0.05, that is, to determine whether the p value in the KS normal distribution test is greater than 0.05, so as to verify whether the converted data meets the significance level; and the normally distributed data that meets the significance level is used to construct the rockburst probability distribution joint prediction function.

[0093] Exemplarily, in the above-mentioned Johnson distribution method, the adopted Johnson transformation model is as follows:

[0094]

[0095] In the formula, Z is the secondary index, γ, η, ε, λ and γ * is the distribution parameter. U , S B and S L There are three types of distributions in the Johnson system: S U (unbounded system), S B (bounded system) and S L (Lognormal system), x represents the original data.

[0096] In the above Johnson transformation model, the definition of each parameter is as follows:

[0097] ①γ: The shape parameter of the Johnson distribution. It is responsible for defining the slope of the left and right tails of the probability density function and determines the degree of skewness of the distribution. When γ>0, the distribution is right-skewed (positive skewness); when γ<0, the distribution is left-skewed (negative skewness).

[0098] ②η: Location parameter of Johnson distribution. It determines the center position of the distribution, that is, the location of the peak of the probability density function.

[0099] ③ε: The scale parameter of Johnson distribution. It controls the degree of discreteness or dispersion of the distribution and determines the kurtosis of the distribution. ε≥0, when ε=0, the distribution is normal distribution.

[0100] ④λ: shape parameter of Johnson distribution. It is another commonly used shape parameter, similar to the γ parameter, used to adjust the skewness of the distribution.

[0101] ⑤γ*: Standardized shape parameter of Johnson distribution. γ* is sometimes used instead of γ, mainly to eliminate the influence of units and make the parameters of different distributions comparable.

[0102] In the above Johnson transformation model, the type of each parameter is defined as follows: Define x 3z , x z , x -z , x -3z , are the values ​​of 3z, z, -z and -3z respectively. Let:

[0103] m=x 3z -x z

[0104] n=x -z -x -3z

[0105] p=x z -x -z ,

[0106] Where: m represents the scale parameter of the upper tail (right tail) of the Johnson distribution, n represents the scale parameter of the lower tail (left tail) of the distribution, n and m reflect the thickness or sparsity of the tail of the Johnson distribution, p represents the scale parameter of the center position of the Johnson distribution, which is related to the center position of the distribution and reflects the width or concentration of the Johnson distribution, z value is the data converted from the original data to the standard normal distribution, and x represents the original data.

[0107] The type of each parameter is determined as follows:

[0108] mn / p 2 >1, the parameter type is S U Distribution, when mn / p 2When <1, the type of this parameter is S B Distribution, when mn / p 2 =1, the type of this parameter is S L distributed.

[0109] The rockburst probability distribution joint prediction function constructed by the above Johnson method is as follows:

[0110]

[0111] Since the transformed data follows a standard normal distribution, the mean vector μ in the above formula can be expressed as: μ = [μ1μ2…μ n ] T =0, T means transpose.

[0112] The covariance matrix C can be expressed as:

[0113]

[0114] In the formula, σ is the standard deviation, ρ is ij is the correlation coefficient between parameters, which can be expressed as follows:

[0115]

[0116] In the formula, f represents the number of samples, q represents the sequence number of the current parameter, and z i,q represents the value of the i-th variable at the q-th parameter, z j,q represents the value of the jth variable on the qth parameter, E() represents the expected value, std(z i ) and std(z j ) represent the standard deviation of the ith variable and the jth variable respectively.

[0117] When step 107 is specifically implemented, since the secondary indicators of surrounding rock integrity, strength-stress ratio, and surrounding rock lithology correspond to the same primary indicator geological information, the secondary indicators of support density, construction intensity, and construction method correspond to the same primary indicator construction information, and the secondary indicators of cumulative energy, cumulative number of events, cumulative apparent volume, and maximum apparent stress correspond to the same primary indicator microseismic information, when the rockburst probability prediction model of the three primary indicators is determined by the rockburst probability distribution joint prediction function of each secondary indicator, a rockburst probability distribution model of multiple secondary indicators corresponding to each primary indicator is constructed, that is, a rockburst probability distribution model is constructed for the secondary indicators of surrounding rock integrity, strength-stress ratio, and surrounding rock lithology; a rockburst probability distribution model is constructed for the secondary indicators of support density, construction intensity, and construction method; and a rockburst probability distribution model is constructed for the secondary indicators of cumulative energy, cumulative number of events, cumulative apparent volume, and maximum apparent stress. Then, the rockburst probability distribution models corresponding to the three secondary indicators can be constructed by the rockburst probability distribution joint prediction function of each secondary indicator, which are respectively expressed as follows:

[0118]

[0119] In the formula, g(z) represents the rockburst probability distribution model of the secondary indicators corresponding to geological information; f(z) represents the rockburst probability distribution model of the secondary indicators corresponding to construction information; h(z) represents the rockburst probability distribution model of the secondary indicators corresponding to microseismic information; z i represents the i-th secondary indicator, i ranges from 1 to n, ω1 represents the weight of the secondary indicator corresponding to geological information, ω2 represents the weight of the secondary indicator corresponding to construction information, and ω3 represents the weight of the secondary indicator corresponding to microseismic information. Then, based on the above probability distribution model, a joint rockburst probability prediction model of the three primary indicators is constructed.

[0120] In an optional embodiment of the present application, a rockburst probability distribution model corresponding to the secondary indicator is determined according to the joint prediction function of the rockburst probability distribution of each secondary indicator, and a joint rockburst probability prediction model of three primary indicators is constructed based on the rockburst probability distribution model, specifically including: obtaining the weight of each primary indicator based on the decision weight of each member of the decision group and the comprehensive weight of the decision group; obtaining the weight of each secondary indicator based on the rockburst grade and the projection objective function, and constructing a rockburst probability distribution model according to the weight of each secondary indicator; constructing a joint rockburst probability prediction model of three primary indicators based on the weights of the above-mentioned primary indicators and the rockburst probability distribution model corresponding to the secondary indicators.

[0121] In an optional embodiment of the present application, the weight of each first-level indicator is obtained based on the decision weight of each member of the decision-making group and the comprehensive weight of the decision-making group, specifically including: using 5 levels of fuzzy evaluation language to express the importance of the first-level indicator, and obtaining a trapezoidal fuzzy number for each level of the first-level indicator; for example, a "very low" degree of attribute factor can be represented by a trapezoidal fuzzy number (0, 0, 0, 3), a "low" degree of attribute factor can be represented by a trapezoidal fuzzy number as (0, 3, 3, 5), a "medium" degree of attribute factor can be represented by a trapezoidal fuzzy number as (3, 5, 5, 7), a "high" degree of attribute factor can be represented by a trapezoidal fuzzy number as (5, 7, 7, 10), and a "very high" degree of attribute factor can be represented by a trapezoidal fuzzy number as (7, 10, 10, 10).

[0122] Then, determine the decision weight of each expert in the decision group; assuming a decision group consisting of k experts, the decision weight of each expert is R t (t=1,2,…,k), where Rt∈(0,1) and ΣRt=1. t The definition is as follows:

[0123]

[0124] In the formula, w t It represents the original score of the t-th expert, t represents the expert sequence number or serial number in the decision-making group, and its value range is 1 to k.

[0125] If R1=R2=……=R k =1 / k, then the expert group is an equal-power decision-making group, otherwise the expert group is an unequal-power decision-making group.

[0126] Furthermore, experts in the decision-making group are asked to use fuzzy words to evaluate the importance of the first-level indicators, and the comprehensive weight of the decision-making group is calculated by combining the trapezoidal fuzzy numbers of each level of the first-level indicators; the comprehensive weight w′ of the decision-making group for the first-level indicators is j It can be expressed as follows:

[0127]

[0128] In the formula, a j The left endpoint of the trapezoidal fuzzy number representing the attribute factor with a “very low” degree, b j The left shoulder point of the trapezoidal fuzzy number representing the attribute factor with a “low” degree, c j The common shoulder point of the trapezoidal fuzzy numbers representing the attribute factors of “medium”, “high”, and “very high” degree, d j The right endpoint of the trapezoidal fuzzy number representing the attribute factor with a “very high” degree, j represents different attribute levels, k represents the number of experts in the decision-making group, and R trepresents the decision weight of each expert in the decision group, t=1,2,…,t,a jt represents the evaluation of the left endpoint of the trapezoidal fuzzy number of attribute level j by the tth expert, b jt represents the evaluation of the left shoulder point of the trapezoidal fuzzy number of attribute level j by the t-th expert, c jt represents the evaluation of the shoulder point of the trapezoidal fuzzy number of attribute level j by the t-th expert (the shoulder point is the same for the levels of “medium”, “high”, and “very high”), d jt It represents the evaluation of the right endpoint of the trapezoidal fuzzy number of attribute level j by the t-th expert.

[0129] Furthermore, based on the decision weight of each expert and the comprehensive weight of the decision group, the fuzzy weight is calculated; the fuzzy weight d(w′ j ) can be expressed as follows:

[0130] d(w' j )=(a j +b j +c j +d j ) / 4; j = 1, 2, ..., 5,

[0131] In the formula, j represents 5 levels, a j represents the average or comprehensive value of the left endpoint evaluation given by all experts at the jth level, b j represents the average or comprehensive value of the left shoulder point evaluation given by all experts at the jth level, c j represents the average or comprehensive value of the common shoulder point evaluation given by all experts at the jth level. For the "medium", "high", and "very high" levels, the shoulder points are the same, d j It represents the average or comprehensive value of the right endpoint evaluations given by all experts at the jth level.

[0132] Then, the above fuzzy weights are normalized to construct a weight vector formula; the above weight vector formula is as follows:

[0133]

[0134] In the formula, w ij represents the weight vector of the first-level index, j represents 5 levels, d(w′ j ) represents the fuzzy weight.

[0135] Finally, the weights of each primary indicator are calculated based on the weight vector formula. During the calculation process, w ij Set a calculation condition, that is, the sum of the weights of the first-level indicators of the five levels is 1. The calculation condition can be expressed as follows:

[0136]

[0137] In an optional embodiment of the present application, based on the rockburst level and the projection objective function, the weights of the secondary indicators are obtained, specifically including: first, the rockburst level is divided into four levels: strong, medium, slight and none; for example, the divided rockburst level F is expressed as: strong (I), medium (II), slight (III), none (IV), and satisfies C1<C2<…<C k , then (C1,C2,…,C k ) is an ordered partition of F. Since the attribute sets are "comparable", in rockburst evaluation, it can be considered that the stronger the rockburst, the more stable it is. Therefore, a "strong" order can be established for comprehensive evaluation. The grading standard judgment matrix constructed according to the known grading standards is:

[0138]

[0139] Where: I m represents the interval of the mth class on the attribute space F, which is used to evaluate the index of different rockburst levels. jl ,b jl (1≤j≤m,1≤l≤k) are the left and right endpoints of the j-th index in the l-th interval in the attribute space F, and satisfy a j1 j2 <… jk ,b j1 j2 <… jk or a j1 >a j2 >…>a jk ,b j1 >b j2 >…>b jk , C i Indicates the classification of rockburst levels, and the value of i ranges from 1 to k.

[0140] Then, multiple sample data and their corresponding levels are randomly generated in each rockburst level, and the randomly generated multiple sample data are normalized to obtain projection data; for example, a number of sample data x are randomly generated in each level. * ij (i=1,2,…,n p ; j = 1, 2, ..., m) and its corresponding level y i (i=1,2,…,n p ), n p , m are the number of random samples and indicators respectively. To eliminate the inconsistency of dimensions, x * ij Normalized to x ij , which is expressed as follows: ​​​​

[0141]

[0142] Where: x jmax 、x jmin are the maximum and minimum values ​​of the j-th indicator respectively.

[0143] Furthermore, the above projection data is projected onto the projection direction to obtain a one-dimensional projection value; assuming that the index weight ω=(ω1,ω2,…,ω m ), the projection direction, i.e. the index weight, is expressed as:

[0144]

[0145] Projecting the above projection data to the projection direction is to put x ij Projected onto ω, we get the one-dimensional projection value z i .

[0146] Furthermore, a projection objective function is established based on the above one-dimensional projection value; when comprehensive projection is performed, the projection value z is required to be i x should be extracted as large as possible ij The variation information in z i The standard deviation S z and z i With y i The absolute value of the correlation coefficient R zy As large as possible, the projection objective function is expressed as follows:

[0147] f(ω)=S z ·|R zy |.

[0148] Finally, since the projection objective function f(ω) changes with the change of the projection direction ω, the maximum value of the above projection objective function is calculated and the maximum value of the projection objective function is used as the weight of the secondary index. The optimal projection direction ω is estimated by solving the maximum value of the projection objective function * , which is expressed as follows:

[0149]

[0150] In the formula, ω j represents the weight of the secondary indicator of the jth level, and st represents the constraint condition, that is, the secondary weights must satisfy the condition that the sum is 1.

[0151] Based on the weights of the first-level indicators and the rockburst probability distribution models corresponding to the second-level indicators, a joint rockburst probability prediction model of the three first-level indicators is constructed as follows:

[0152] F(x)=g(z)*w1+f(z)*w2+h(z)*w3,

[0153] In the formula, g(z) represents the rockburst probability distribution model of the secondary indicator corresponding to geological information; w1 represents the primary indicator weight of geological information, f(z) represents the rockburst probability distribution model of the secondary indicator corresponding to construction information; w2 represents the primary indicator weight of construction information, h(z) represents the rockburst probability distribution model of the secondary indicator corresponding to microseismic information; w3 represents the primary indicator weight of microseismic information; where, In the formula, z i represents the i-th secondary indicator, the value range of i is 1 to n, ω1 represents the weight of the secondary indicator corresponding to geological information, ω2 represents the weight of the secondary indicator corresponding to construction information, and ω3 represents the weight of the secondary indicator corresponding to microseismic information.

[0154] When implementing step 108, the rockburst probability of the underground project to be tested is obtained based on the above-mentioned joint rockburst probability prediction model, combined with the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested. By statistically analyzing the microseismic monitoring data under different geological conditions and different construction intensities, the multi-source characteristic information including geological and construction factors is summarized, the characteristic indicators of the rockburst probability distribution model are summarized, and the probability distribution model of each indicator is calculated to achieve a scientific prediction of the rockburst probability.

[0155] The embodiment of the present application provides a rockburst probability prediction method based on a probability distribution function, which carries out microseismic monitoring in high-risk rockburst areas of underground engineering, obtains microseismic monitoring data, and collects geological information and construction information corresponding to the high-risk rockburst areas; analyzes the microseismic monitoring data to obtain microseismic characteristic parameters, and calculates and analyzes the changing laws of the microseismic characteristic parameters in the rockburst incubation process to obtain microseismic information; combines the geological information, construction information and microseismic information corresponding to the high-risk rockburst areas of underground engineering to obtain typical rockburst examples, and constructs a rockburst database based on multiple typical rockburst examples; performs cluster analysis on typical rockburst examples in the rockburst database, removes abnormal rockburst data in the rockburst database, and determines the rockburst prediction method used for prediction. Indicators for predicting rockburst probability; combining the rockburst data corresponding to the microseismic information, geological information and construction information, respectively constructing three primary indicators and ten secondary indicators; statistically analyzing the distribution of each secondary indicator, and combining the statistical results to construct a joint prediction function for the rockburst probability distribution corresponding to each secondary indicator; determining a rockburst probability distribution model corresponding to the secondary indicator according to the joint prediction function for the rockburst probability distribution of each secondary indicator, and constructing a joint rockburst probability prediction model for the three primary indicators based on the rockburst probability distribution model; obtaining the rockburst occurrence probability of the underground project to be tested according to the joint rockburst probability prediction model, combining the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested.

[0156] By statistically analyzing microseismic monitoring data under different geological conditions and construction intensities, we summarized and sorted out multi-source characteristic information including geological and construction factors, summarized the characteristic indicators of the rockburst probability distribution model, calculated the probability distribution model of each indicator, and realized the scientific prediction of the probability of rockburst. At the same time, this application is a case database constructed through data of rockbursts that have occurred. When performing characteristic value statistics, the data changes for seven days are taken as a stage. Through a large number of rockburst cases, the key parameters in the probability prediction model are obtained. The prediction method of this application can evaluate the gestation and development process of rockburst from a more comprehensive perspective and accurately predict the probability of rockburst.

[0157] Based on the same application concept, the embodiment of the present application provides a rockburst probability prediction device based on a probability distribution function in a second aspect, see Figure 2 , Figure 2 : is an architecture diagram of a rockburst probability prediction device based on a probability distribution function provided in an embodiment of the present application, the device comprising:

[0158] The information acquisition module 201 is used to carry out microseismic monitoring in the high-risk rockburst area of ​​the underground project, obtain microseismic monitoring data, and collect geological information and construction information corresponding to the high-risk rockburst area;

[0159] A microseismic information acquisition module 202 is used to analyze the microseismic monitoring data to obtain microseismic characteristic parameters, and calculate and analyze the changing rules of the microseismic characteristic parameters during the rockburst incubation process to obtain microseismic information;

[0160] A database construction module 203 is used to obtain typical rock burst examples by combining geological information, construction information and microseismic information corresponding to the high-risk rock burst area of ​​underground engineering, and to construct a rock burst database based on multiple typical rock burst examples;

[0161] A determination module 204 is used to perform cluster analysis on typical rock burst instances in the rock burst database, remove abnormal rock burst data in the rock burst database, and determine an index for rock burst probability prediction;

[0162] An indicator construction module 205 is used to construct three primary indicators and ten secondary indicators respectively by combining the rock burst data corresponding to the microseismic information, geological information and construction information;

[0163] Function construction module 206, used to collect statistics on the distribution of each secondary indicator, and to construct a joint prediction function of rockburst probability distribution corresponding to each secondary indicator based on the statistical results;

[0164] A model building module 207 is used to determine the rockburst probability distribution model corresponding to the secondary indicator according to the rockburst probability distribution joint prediction function of each secondary indicator, and to build a joint rockburst probability prediction model of the three primary indicators based on the rockburst probability distribution model;

[0165] The prediction module 208 is used to obtain the rockburst occurrence probability of the underground project to be tested based on the combined rockburst probability prediction model and in combination with the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested.

[0166] Among them, the indicators for rockburst probability prediction in the determination module are determined as follows: geological information indicators include at least: surrounding rock integrity, strength-stress ratio, surrounding rock lithology, construction information indicators include at least: support density, construction intensity, construction method, and microseismic information indicators include at least: cumulative number of events, cumulative energy, cumulative apparent volume, and maximum apparent stress.

[0167] Among them, the three first-level indicators constructed in the indicator construction module include: geological information, construction information and microseismic information; the second-level indicators corresponding to the geological information include: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology; the second-level indicators corresponding to the construction information include: support density, construction intensity, and construction method; the second-level indicators corresponding to the microseismic information include: cumulative energy, cumulative number of events, cumulative apparent volume, and maximum apparent stress.

[0168] The rockburst probability distribution joint prediction function in the function construction module is constructed by the Johnson distribution method, and the parameters corresponding to each secondary indicator are converted into normally distributed data by the Johnson distribution method. The function construction module includes:

[0169] The first construction submodule is used to define the parameters corresponding to the secondary indicators used to construct the rockburst probability distribution joint prediction function and the type of each parameter respectively according to the Johnson distribution method to obtain the defined parameters and types;

[0170] A distribution type determination submodule is used to determine the Johnson distribution type to which the parameters corresponding to the secondary index belong according to the defined parameters and types;

[0171] The conversion submodule is used to convert the parameters corresponding to the secondary indicators into normal distribution data according to the Johnson distribution type;

[0172] The significance level judgment submodule is used to perform normal distribution tests on different parameters, taking the significance level value as 0.05, to determine whether the normal distribution test result is greater than 0.05, and to verify whether the transformed data meets the significance level;

[0173] The second construction submodule is used to use the normal distribution data that meets the significance level to construct the rockburst probability distribution joint prediction function.

[0174] Wherein, the model building module includes:

[0175] The weight calculation submodule of the first-level indicators is used to obtain the weight of each first-level indicator based on the decision weight of each member of the decision-making group and the comprehensive weight of the decision-making group;

[0176] The rockburst probability distribution model construction submodule is used to obtain the weights of each secondary indicator based on the rockburst grade and the projection objective function, and to construct the rockburst probability distribution model according to the weights of each secondary indicator;

[0177] The joint rockburst probability prediction model construction submodule is used to construct a joint rockburst probability prediction model of three first-level indicators based on the weights of the first-level indicators and the rockburst probability distribution models corresponding to the second-level indicators.

[0178] The weight calculation submodule of the first-level index includes:

[0179] The first evaluation unit is used to express the importance of the first-level index by using a fuzzy evaluation language of five levels, and obtain a trapezoidal fuzzy number of each level of the first-level index;

[0180] A determination unit, used to determine the decision weight of each expert in the decision group;

[0181] A second evaluation unit is used to evaluate the importance of the primary indicator using fuzzy words applied by experts, and calculate the comprehensive weight of the decision group in combination with the trapezoidal fuzzy number of each level of the primary indicator;

[0182] A fuzzy weight calculation unit, used for calculating the fuzzy weight based on the decision weight of each expert and the comprehensive weight of the decision group;

[0183] A weight vector formula construction unit, used for normalizing the fuzzy weights and constructing a weight vector formula;

[0184] The first-level indicator weight calculation unit is used to obtain the weight of each first-level indicator based on the weight vector formula.

[0185] The rockburst probability distribution model construction submodule includes:

[0186] The division unit is used to classify the rockburst level into four levels: severe, moderate, slight and none;

[0187] A projection data acquisition unit is used to randomly generate a plurality of sample data and their corresponding levels within each rockburst level, and perform normalization processing on the randomly generated plurality of sample data to obtain projection data;

[0188] A one-dimensional projection value acquisition unit, used for projecting the projection data into a projection direction to obtain a one-dimensional projection value;

[0189] A projection objective function establishing unit, used to establish a projection objective function based on the one-dimensional projection value;

[0190] The secondary index weight calculation unit is used to calculate the maximum value of the projection objective function to obtain the weight of each secondary index.

[0191] The joint rockburst probability prediction model in the model building module is as follows:

[0192] F(x)=g(z)*w1+f(z)*w2+h(z)*w3,

[0193] In the formula, g(z) represents the rockburst probability distribution model of the secondary indicator corresponding to geological information; w1 represents the primary indicator weight of geological information, f(z) represents the rockburst probability distribution model of the secondary indicator corresponding to construction information; w2 represents the primary indicator weight of construction information, h(z) represents the rockburst probability distribution model of the secondary indicator corresponding to microseismic information; w3 represents the primary indicator weight of microseismic information; where, z i represents the i-th secondary indicator, the value range of i is 1 to n, ω1 represents the weight of the secondary indicator corresponding to geological information, ω2 represents the weight of the secondary indicator corresponding to construction information, and ω3 represents the weight of the secondary indicator corresponding to microseismic information.

[0194] Based on the same application concept, the embodiment of the present application discloses an electronic device in a third aspect. Figure 3 A schematic diagram of an electronic device disclosed in an embodiment of the present application is shown. Figure 3 As shown, the electronic device 100 includes: a memory 110 and a processor 120, the memory of the electronic device is not less than 12G, the main frequency of the processor is not less than 2.4GHz, the memory 110 and the processor 120 are connected via a bus communication, and a computer program is stored in the memory 110. The computer program can be run on the processor 120 to implement a rockburst probability prediction method based on a probability distribution function disclosed in an embodiment of the present application.

[0195] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0196] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0197] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0198] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0199] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0200] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0201] The above is a detailed introduction to a rockburst probability prediction method, device and equipment based on a probability distribution function provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A rockburst probability prediction method based on probability distribution function, characterized in that: The method comprises: Conduct microseismic monitoring in high-risk rockburst areas of underground projects, obtain microseismic monitoring data, and collect geological information and construction information corresponding to high-risk rockburst areas; Analyzing the microseismic monitoring data to obtain microseismic characteristic parameters, and calculating and analyzing the changing laws of the microseismic characteristic parameters during the rockburst incubation process to obtain microseismic information; Combine the geological information, construction information and microseismic information corresponding to the high-risk rockburst areas of underground engineering projects to obtain typical rockburst examples, and build a rockburst database based on multiple typical rockburst examples; Performing cluster analysis on typical rock burst instances in the rock burst database, removing abnormal rock burst data in the rock burst database, and determining an index for rock burst probability prediction; Combining the rockburst data corresponding to the microseismic information, geological information and construction information, three primary indicators and ten secondary indicators are constructed respectively; The distribution of each secondary indicator is statistically analyzed, and combined with the statistical results, a joint prediction function of the rockburst probability distribution corresponding to each secondary indicator is constructed; Determine the rockburst probability distribution model corresponding to the secondary indicator according to the rockburst probability distribution joint prediction function of each secondary indicator, and construct a joint rockburst probability prediction model of the three primary indicators based on the rockburst probability distribution model; According to the joint rockburst probability prediction model, the probability of rockburst occurrence of the underground project to be tested is obtained by combining the microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested; The rockburst probability distribution joint prediction function is constructed by the Johnson distribution method, and the parameters corresponding to each secondary indicator are converted into normal distribution data by the Johnson distribution method, including: According to the Johnson distribution method, the parameters corresponding to the secondary indicators used to construct the rockburst probability distribution joint prediction function and the type of each parameter are defined respectively to obtain the defined parameters and types; According to the defined parameters and types, determine the Johnson distribution type to which the corresponding parameters of the secondary indicators belong; According to the Johnson distribution type, the parameters corresponding to the secondary indicators are converted into normal distribution data; Perform normal distribution test on different parameters, take the significance level as 0.05, determine whether the normal distribution test result is greater than 0.05, and verify whether the transformed data meets the significance level; Using the normal distribution data that meets the significant level to construct the rockburst probability distribution joint prediction function; The combined rockburst probability prediction model is as follows: F(x)=g(z)*w1+f(z)*w2+h(z)*w3, In the formula, g(z) represents the rockburst probability distribution model of the secondary indicator corresponding to geological information; w1 represents the primary indicator weight of geological information, f(z) represents the rockburst probability distribution model of the secondary indicator corresponding to construction information; w2 represents the primary indicator weight of construction information, h(z) represents the rockburst probability distribution model of the secondary indicator corresponding to microseismic information; w3 represents the primary indicator weight of microseismic information; where, z i represents the i-th secondary indicator, the value range of i is 1 to n, ω1 represents the weight of the secondary indicator corresponding to geological information, ω2 represents the weight of the secondary indicator corresponding to construction information, and ω3 represents the weight of the secondary indicator corresponding to microseismic information.

2. The rockburst probability prediction method based on probability distribution function according to claim 1 is characterized in that: The indicators used for predicting the probability of rock burst are determined as follows: geological information indicators include at least: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology; construction information indicators include at least: support density, construction intensity, and construction method; microseismic information indicators include at least: cumulative number of events, cumulative energy, cumulative apparent volume, and maximum apparent stress.

3. The rockburst probability prediction method based on probability distribution function according to claim 2 is characterized in that: The three first-level indicators include: geological information, construction information and microseismic information. The second-level indicators corresponding to the geological information include: surrounding rock integrity, strength-stress ratio, and surrounding rock lithology. The second-level indicators corresponding to the construction information include: support density, construction intensity, and construction method. The second-level indicators corresponding to the microseismic information include: cumulative energy, cumulative number of events, cumulative apparent volume, and maximum apparent stress.

4. The rockburst probability prediction method based on probability distribution function according to claim 1 is characterized in that: The rockburst probability distribution model corresponding to the secondary indicator is determined according to the joint prediction function of the rockburst probability distribution of each secondary indicator. Based on the rockburst probability distribution model, a joint rockburst probability prediction model of the three primary indicators is constructed, including: Based on the decision weight of each member of the decision-making group and the comprehensive weight of the decision-making group, the weight of each first-level indicator is obtained; Based on the rockburst grade and the projection objective function, the weights of each secondary indicator are obtained, and the rockburst probability distribution model is constructed according to the weights of each secondary indicator; Based on the weights of the first-level indicators and the rockburst probability distribution models corresponding to the second-level indicators, a joint rockburst probability prediction model of the three first-level indicators is constructed.

5. The rockburst probability prediction method based on probability distribution function according to claim 4 is characterized in that: Based on the decision weights of each member of the decision-making group and the comprehensive weight of the decision-making group, the weights of each first-level indicator are obtained, including: The importance of the first-level index is expressed by using a 5-level fuzzy evaluation language, and the trapezoidal fuzzy number of each level of the first-level index is obtained; Determine the decision weight of each expert in the decision-making group; The importance of the primary indicators is evaluated by using fuzzy words applied by experts, and the comprehensive weight of the decision group is calculated by combining the trapezoidal fuzzy numbers of each level of the primary indicators; Calculating a fuzzy weight based on the decision weight of each expert and the comprehensive weight of the decision group; Normalizing the fuzzy weights to construct a weight vector formula; Based on the weight vector formula, the weights of the first-level indicators are obtained.

6. The rockburst probability prediction method based on probability distribution function according to claim 4 is characterized in that: Based on the rockburst grade and the projection objective function, the weights of each secondary index are obtained, including: The rock burst levels are divided into four levels: severe, moderate, slight and none; A plurality of sample data and their corresponding levels are randomly generated within each rockburst level, and the randomly generated plurality of sample data are normalized to obtain projection data; Projecting the projection data onto a projection direction to obtain a one-dimensional projection value; Establishing a projection objective function based on the one-dimensional projection value; The maximum value of the projection objective function is calculated to obtain the weights of the secondary indicators.

7. A rockburst probability prediction device based on probability distribution function, characterized in that: The device comprises: The information acquisition module is used to carry out microseismic monitoring in high-risk rockburst areas of underground projects, obtain microseismic monitoring data, and collect geological information and construction information corresponding to high-risk rockburst areas; A microseismic information acquisition module is used to analyze the microseismic monitoring data to obtain microseismic characteristic parameters, and calculate and analyze the changing laws of the microseismic characteristic parameters during the rockburst incubation process to obtain microseismic information; A database construction module is used to combine geological information, construction information and microseismic information corresponding to high-risk rockburst areas of underground engineering projects to obtain typical rockburst examples and construct a rockburst database based on multiple typical rockburst examples; A determination module, used to perform cluster analysis on typical rock burst instances in the rock burst database, remove abnormal rock burst data in the rock burst database, and determine indicators for rock burst probability prediction; An indicator construction module, for combining the rock burst data corresponding to the microseismic information, geological information and construction information to respectively construct three primary indicators and ten secondary indicators; The function construction module is used to collect statistics on the distribution of each secondary indicator and, based on the statistical results, to construct a joint prediction function for the rockburst probability distribution corresponding to each secondary indicator; A model building module is used to determine the rockburst probability distribution model corresponding to the secondary indicator according to the rockburst probability distribution joint prediction function of each secondary indicator, and to build a joint rockburst probability prediction model of the three primary indicators based on the rockburst probability distribution model; A prediction module, for obtaining the probability of rockburst occurrence of the underground project to be tested according to the combined rockburst probability prediction model and in combination with microseismic information, geological information and construction information of the on-site monitoring of the underground project to be tested; The rockburst probability distribution joint prediction function in the function construction module is constructed by the Johnson distribution method, and the parameters corresponding to each secondary indicator are converted into normally distributed data by the Johnson distribution method. The function construction module includes: The first construction submodule is used to define the parameters corresponding to the secondary indicators used to construct the rockburst probability distribution joint prediction function and the type of each parameter respectively according to the Johnson distribution method to obtain the defined parameters and types; A distribution type determination submodule is used to determine the Johnson distribution type to which the corresponding parameters of the secondary index belong according to the defined parameters and types; The conversion submodule is used to convert the parameters corresponding to the secondary indicators into normal distribution data according to the Johnson distribution type; The significance level judgment submodule is used to perform normal distribution tests on different parameters, taking the significance level value as 0.05, to determine whether the normal distribution test result is greater than 0.05, and to verify whether the transformed data meets the significance level; The second construction submodule is used to use the normal distribution data that meets the significant level to construct the rockburst probability distribution joint prediction function; The joint rockburst probability prediction model in the model building module is as follows: F(x)=g(z)*w1+f(z)*w2+h(z)*w3, In the formula, g(z) represents the rockburst probability distribution model of the secondary indicator corresponding to geological information; w1 represents the primary indicator weight of geological information, f(z) represents the rockburst probability distribution model of the secondary indicator corresponding to construction information; w2 represents the primary indicator weight of construction information, h(z) represents the rockburst probability distribution model of the secondary indicator corresponding to microseismic information; w3 represents the primary indicator weight of microseismic information; where, z i represents the i-th secondary indicator, the value range of i is 1 to n, ω1 represents the weight of the secondary indicator corresponding to geological information, ω2 represents the weight of the secondary indicator corresponding to construction information, and ω3 represents the weight of the secondary indicator corresponding to microseismic information.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the rockburst probability prediction method based on probability distribution function according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Coal mine rock burst prevention and control dynamic early warning method based on microseism

    CN112324506A

  • Rock burst prediction method and device and computer equipment

    CN115688046A