Microseismic activity parameter time sequence feature fusion method

Abstract

The invention discloses a micro-seismic activity parameter time sequence feature fusion method. The method comprises the following steps: 1, acquiring micro-seismic monitoring data; 2, obtaining a b value fusion characteristic value based on a WFTBlock module in the WFTNet; 3, obtaining an energy index fusion characteristic value based on a WFTBlock module in the WFTNet; 4, obtaining a Schmidt number fusion feature value based on a WFTBlock module in the WFTNet; and 5, acquiring a comprehensive fusion characteristic value of the micro-seismic activity parameters. The method is simple in steps and reasonable in design, feature extraction and fusion are carried out on a b value original sequence, an energy index original sequence and a Schmidt number original sequence through a WFTBlock module in WFTNet, then fusion feature values of all parameters are averaged to obtain a micro-seismic activity parameter comprehensive fusion feature value, and the fusion feature values of all the parameters are analyzed to obtain the micro-seismic activity parameter comprehensive fusion feature value. And the rock burst can be predicted accurately through the micro-seismic activity parameter comprehensive fusion characteristic value subsequently.

Description

Technical Field

[0001] The invention belongs to the technical field of microseismic activity feature fusion, and in particular relates to a microseismic activity parameter time series feature fusion method. Background Art

[0002] In recent years, the prediction of rock burst disasters based on the characterization of microseismic activity parameters has provided valuable theoretical and practical experience for improving the accuracy of rock burst warning. However, due to the complexity of the microseismic activity parameters themselves in the process of data collection, processing and analysis, the spatiotemporal characteristics of the impact manifestation events represented by them are often vague and uncertain, resulting in the current stage of rock burst disaster prediction based on microseismic activity parameters still mainly relying on pure data-driven deep learning methods. Although these data-driven prediction methods can be trained using a large amount of historical data, they are highly dependent on the potential characteristic patterns of the data. The prediction method based on deep learning directly predicts based on activity parameters such as b-value, energy index and Schmidt number, fails to extract and fuse the features of microseismic activity parameters, and cannot understand the local periodicity characteristics and global periodicity of the data.

[0003] Therefore, there is a lack of a reasonably designed method for fusion of microseismic activity parameter time series features. The b-value original sequence, energy index original sequence and Schmidt number original sequence are extracted and fused through the WFTBlock module in WFTNet to obtain the b-value fusion eigenvalue, energy index fusion eigenvalue and Schmidt number fusion eigenvalue, and then the fusion eigenvalues ​​of each parameter are averaged to obtain the comprehensive fusion eigenvalue of the microseismic activity parameter, which is convenient for the subsequent accurate prediction of rock burst pressure through the comprehensive fusion eigenvalue of the microseismic activity parameter. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for fusion of time series features of microseismic activity parameters in view of the deficiencies in the above-mentioned prior art. The method has simple steps and reasonable design. The b-value original sequence, the energy index original sequence and the Schmidt number original sequence are feature extracted and fused through the WFTBlock module in WFTNet to obtain b-value fusion eigenvalues, energy index fusion eigenvalues ​​and Schmidt number fusion eigenvalues, and then the fusion eigenvalues ​​of each parameter are averaged to obtain the comprehensive fusion eigenvalues ​​of the microseismic activity parameters, which is convenient for the subsequent accurate prediction of impact ground pressure through the comprehensive fusion eigenvalues ​​of the microseismic activity parameters.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for fusion of microseismic activity parameter time series features, characterized in that the method comprises the following steps:

[0006] Step 1: Obtain microseismic monitoring data:

[0007] Step 101, using a microseismic monitoring system to monitor the mine area to be monitored, and obtaining microseismic events per unit time and the microseismic magnitude and energy corresponding to each microseismic event; wherein the mine area to be monitored is a mine tunnel or goaf;

[0008] Step 102, using a computer to obtain a b value, an energy index and a Schmidt number based on the microseismic events in a unit time and the microseismic magnitude and energy corresponding to each microseismic event;

[0009] Step 103, repeating steps 101 to 102 multiple times to obtain the original sequence of b values, the original sequence of energy indexes and the original sequence of Schmidt numbers for n time units; wherein n is a positive integer;

[0010] Step 2: Obtain the b-value fusion feature value based on the WFTBlock module in WFTNet:

[0011] Step 201, setting the block length, dividing the original b-value sequence into multiple b-value sequence blocks;

[0012] Step 202: Use a computer to input each b-value sequence block into the WFTBlock module in WFTNet to obtain the period weighting coefficient α and Fourier transform eigenvalue of each b-value sequence block. and wavelet transform eigenvalues

[0013] Step 203: Using a computer according to the formula Get the b-value fusion eigenvalues ​​of each b-value sequence block in, Preset weights for the wavelet transform corresponding to the b-value sequence block, Preset weights for the Fourier transform corresponding to the b-value sequence block,

[0014] Step 3: Obtain the energy index fusion eigenvalue based on the WFTBlock module in WFTNet;

[0015] According to the method of step 2, input the original energy index sequence to obtain the energy index fusion eigenvalues ​​of each energy index sequence block.

[0016] Step 4: Obtain the Schmidt number fusion eigenvalue based on the WFTBlock module in WFTNet;

[0017] According to the method of step 2, input the original sequence of Schmidt numbers and obtain the Schmidt number fusion eigenvalues ​​of each Schmidt number sequence block.

[0018] Step 5: Obtain comprehensive fusion characteristic values ​​of microseismic activity parameters:

[0019] Step 501: Merge the b value of the corresponding block into the eigenvalue Energy index fusion eigenvalue Schmidt number fusion eigenvalue Average processing is performed to obtain the comprehensive fusion characteristic value F of the microseismic activity parameters of each block;

[0020] Step 502: record the ratio of the comprehensive fusion characteristic value F of the microseismic activity parameters of each block to the block length as the comprehensive fusion characteristic value of the microseismic activity parameters per unit time.

[0021] The above-mentioned method for fusing characteristics of microseismic activity parameter time series is characterized in that: Step 202, the specific process is as follows:

[0022] Step 2021: Use a computer to input any b-value sequence block into the WFTBlock module in WFTNet; wherein the WFTBlock module includes a feature extraction stage and a feature fusion stage, and the feature extraction stage includes a Fourier transform branch and a wavelet transform branch;

[0023] Step 2022: Use a computer to process any b-value sequence block through the Fourier transform branch of the feature extraction stage in the WFTBlock module to obtain each frequency and the corresponding amplitude;

[0024] Step 2023, using a computer to process any b-value sequence block through the wavelet transform branch of the feature extraction stage in the WFTBlock module to obtain a time-frequency diagram;

[0025] Step 2024: Each frequency and the corresponding amplitude are subjected to the feature fusion stage in the WFTBlock module to obtain the Fourier transform eigenvalue The time-frequency graph is passed through the feature fusion stage in the WFTBlock module to obtain the wavelet transform eigenvalue

[0026] The above-mentioned method for fusing characteristics of microseismic activity parameter time series is characterized in that: Step 2022, the specific process is as follows:

[0027] Step A: Arrange the frequencies in descending order, and obtain the first m frequencies and the amplitudes corresponding to the first m frequencies; the amplitude corresponding to the i-th frequency is recorded as A i ; i is a positive integer, 1≤i≤m; m is a positive integer;

[0028] Step B: Use a computer to calculate the Get the period weighting coefficient α; where, It represents the maximum value of the square of the amplitude corresponding to the first m frequencies.

[0029] Compared with the prior art, the present invention has the following advantages:

[0030] 1. The method of the present invention has simple steps and reasonable design, and solves the current problem of intelligent prediction of rock burst based on multiple variables.

[0031] 2. Based on the WFTBlock module in WFTNet, the present invention performs feature extraction and fusion on each microseismic activity parameter to obtain b-value fusion eigenvalues, energy index fusion eigenvalues ​​and Schmidt number fusion eigenvalues. Through the feature extraction of each microseismic activity parameter, the local periodic characteristics and global periodic characteristics of the data can be captured simultaneously, and the periodic weighting coefficient adaptively balances these characteristics, further improving the fusion performance of data sets with various characteristics.

[0032] 3. The present invention obtains the comprehensive fusion characteristic value of microseismic activity parameters through the average processing of b-value fusion characteristic value, exponential fusion characteristic value and Schmidt number fusion characteristic value, and converts it into the comprehensive fusion characteristic value of microseismic activity parameters per unit time, so as to facilitate the subsequent impact ground pressure prediction and early warning based on the comprehensive fusion characteristic value of microseismic activity parameters per unit time, thereby improving the prediction performance.

[0033] In summary, the method of the present invention has simple steps and reasonable design. The original sequence of b value, the original sequence of energy index and the original sequence of Schmidt number are feature extracted and fused through the WFTBlock module in WFTNet to obtain the b value fusion eigenvalue, the energy index fusion eigenvalue and the Schmidt number fusion eigenvalue. Then, the fusion eigenvalues ​​of each parameter are averaged to obtain the comprehensive fusion eigenvalue of microseismic activity parameters, which is convenient for the subsequent accurate prediction of rock burst pressure through the comprehensive fusion eigenvalue of microseismic activity parameters.

[0034] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The figure is a flowchart of the method of the present invention. DETAILED DESCRIPTION

[0036] like Figure 1 As shown, the microseismic activity parameter time series feature fusion method of the present invention comprises the following steps:

[0037] Step 1: Obtain microseismic monitoring data:

[0038] Step 101, using a microseismic monitoring system to monitor the mine area to be monitored, and obtaining microseismic events per unit time and the microseismic magnitude and energy corresponding to each microseismic event; wherein the mine area to be monitored is a mine tunnel or goaf;

[0039] Step 102, using a computer to obtain a b value, an energy index and a Schmidt number based on the microseismic events in a unit time and the microseismic magnitude and energy corresponding to each microseismic event;

[0040] Step 103, repeating steps 101 to 102 multiple times to obtain the original sequence of b values, the original sequence of energy indexes and the original sequence of Schmidt numbers for n time units; wherein n is a positive integer;

[0041] Step 2: Obtain the b-value fusion feature value based on the WFTBlock module in WFTNet:

[0042] Step 201, setting the block length, dividing the original b-value sequence into multiple b-value sequence blocks;

[0043] Step 202: Use a computer to input each b-value sequence block into the WFTBlock module in WFTNet to obtain the period weighting coefficient α and Fourier transform eigenvalue of each b-value sequence block. and wavelet transform eigenvalues

[0044] Step 203: Using a computer according to the formula Get the b-value fusion eigenvalues ​​of each b-value sequence block in, Preset weights for the wavelet transform corresponding to the b-value sequence block, Preset weights for the Fourier transform corresponding to the b-value sequence block,

[0045] Step 3: Obtain the energy index fusion eigenvalue based on the WFTBlock module in WFTNet;

[0046] According to the method of step 2, input the original energy index sequence to obtain the energy index fusion eigenvalues ​​of each energy index sequence block.

[0047] Step 4: Obtain the Schmidt number fusion eigenvalue based on the WFTBlock module in WFTNet;

[0048] According to the method of step 2, input the original sequence of Schmidt numbers and obtain the Schmidt number fusion eigenvalues ​​of each Schmidt number sequence block.

[0049] Step 5: Obtain comprehensive fusion characteristic values ​​of microseismic activity parameters:

[0050] Step 501: Merge the b value of the corresponding block into the eigenvalue Energy index fusion eigenvalue Schmidt number fusion eigenvalue Average processing is performed to obtain the comprehensive fusion characteristic value F of the microseismic activity parameters of each block;

[0051] Step 502: record the ratio of the comprehensive fusion characteristic value F of the microseismic activity parameters of each block to the block length as the comprehensive fusion characteristic value of the microseismic activity parameters per unit time.

[0052] In this embodiment, step 202, the specific process is as follows:

[0053] Step 2021: Use a computer to input any b-value sequence block into the WFTBlock module in WFTNet; wherein the WFTBlock module includes a feature extraction stage and a feature fusion stage, and the feature extraction stage includes a Fourier transform branch and a wavelet transform branch;

[0054] Step 2022: Use a computer to process any b-value sequence block through the Fourier transform branch of the feature extraction stage in the WFTBlock module to obtain each frequency and the corresponding amplitude;

[0055] Step 2023, using a computer to process any b-value sequence block through the wavelet transform branch of the feature extraction stage in the WFTBlock module to obtain a time-frequency diagram;

[0056] Step 2024: Each frequency and the corresponding amplitude are subjected to the feature fusion stage in the WFTBlock module to obtain the Fourier transform eigenvalue The time-frequency graph is passed through the feature fusion stage in the WFTBlock module to obtain the wavelet transform eigenvalue

[0057] In this embodiment, step 2022, the specific process is as follows:

[0058] Step A: Arrange the frequencies in descending order, and obtain the first m frequencies and the amplitudes corresponding to the first m frequencies; the amplitude corresponding to the i-th frequency is recorded as A i ; i is a positive integer, 1≤i≤m; m is a positive integer;

[0059] Step B: Use a computer to calculate the Get the period weighting coefficient α; where, It represents the maximum value of the square of the amplitude corresponding to the first m frequencies.

[0060] In this embodiment, it should be noted that the acquisition of b value, energy index and Schmidt number can refer to patent CN202410667273.5, a multivariable intelligent prediction method for mine rock burst, for parameter acquisition.

[0061] In this embodiment, it should be noted that the value of m is 5.

[0062] In this embodiment, it should be noted that the value of n is not less than 100.

[0063] In this embodiment, it should be noted that: and The value of is 0 to 1, and The weights will represent the importance of local periodic features and global periodic features in calculating the fused feature value. and The value can be adjusted according to actual requirements.

[0064] In this embodiment, it should be noted that since the block contains multiple unit timestamps, these periodic features need to be converted into comprehensive fusion feature values ​​corresponding to each unit timestamp for subsequent time series analysis. In order to simplify this process, the averaging method of periodic weighted features is adopted. The comprehensive fusion feature value of the microseismic activity parameters of the block and the average feature value of the block length are assigned to all unit timestamps in the block.

[0065] In this embodiment, it should be noted that the block length is 3, that is, one block represents the overall characteristics of 3 days.

[0066] In this embodiment, the unit time is day, which can be adjusted according to actual requirements.

[0067] In summary, the method of the present invention has simple steps and reasonable design. The original sequence of b value, the original sequence of energy index and the original sequence of Schmidt number are feature extracted and fused through the WFTBlock module in WFTNet to obtain the b value fusion eigenvalue, the energy index fusion eigenvalue and the Schmidt number fusion eigenvalue. Then, the fusion eigenvalues ​​of each parameter are averaged to obtain the comprehensive fusion eigenvalue of microseismic activity parameters, which is convenient for the subsequent accurate prediction of rock burst pressure through the comprehensive fusion eigenvalue of microseismic activity parameters.

[0068] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for fusion of microseismic activity parameter time series features, characterized in that: The method comprises the following steps: Step 1: Obtain microseismic monitoring data: Step 101, using a microseismic monitoring system to monitor the mine area to be monitored, and obtaining microseismic events per unit time and the microseismic magnitude and energy corresponding to each microseismic event; wherein the mine area to be monitored is a mine tunnel or goaf; Step 102, using a computer to obtain a b value, an energy index and a Schmidt number based on the microseismic events in a unit time and the microseismic magnitude and energy corresponding to each microseismic event; Step 103, repeating steps 101 to 102 multiple times to obtain the original sequence of b values, the original sequence of energy indexes and the original sequence of Schmidt numbers for n time units; wherein n is a positive integer; Step 2: Obtain the b-value fusion feature value based on the WFTBlock module in WFTNet: Step 201, setting the block length, dividing the original b-value sequence into multiple b-value sequence blocks; Step 202: Use a computer to input each b-value sequence block into the WFTBlock module in WFTNet to obtain the period weighting coefficient α and Fourier transform eigenvalue of each b-value sequence block. and wavelet transform eigenvalues Step 203: Using a computer according to the formula Get the b-value fusion eigenvalues ​​of each b-value sequence block in, Preset weights for the wavelet transform corresponding to the b-value sequence block, Preset weights for the Fourier transform corresponding to the b-value sequence block, Step 3: Obtain the energy index fusion eigenvalue based on the WFTBlock module in WFTNet; According to the method of step 2, input the original energy index sequence to obtain the energy index fusion eigenvalues ​​of each energy index sequence block. Step 4: Obtain the Schmidt number fusion eigenvalue based on the WFTBlock module in WFTNet; According to the method of step 2, input the original sequence of Schmidt numbers and obtain the Schmidt number fusion eigenvalues ​​of each Schmidt number sequence block. Step 5: Obtain comprehensive fusion characteristic values ​​of microseismic activity parameters: Step 501: Merge the b value of the corresponding block into the eigenvalue Energy index fusion eigenvalue Schmidt number fusion eigenvalue Average processing is performed to obtain the comprehensive fusion characteristic value F of the microseismic activity parameters of each block; Step 502: record the ratio of the comprehensive fusion characteristic value F of the microseismic activity parameters of each block to the block length as the comprehensive fusion characteristic value of the microseismic activity parameters per unit time.

2. A method for fusing microseismic activity parameter time series features according to claim 1, characterized in that: Step 202, the specific process is as follows: Step 2021: Use a computer to input any b-value sequence block into the WFTBlock module in WFTNet; wherein the WFTBlock module includes a feature extraction stage and a feature fusion stage, and the feature extraction stage includes a Fourier transform branch and a wavelet transform branch; Step 2022: Use a computer to process any b-value sequence block through the Fourier transform branch of the feature extraction stage in the WFTBlock module to obtain each frequency and the corresponding amplitude; Step 2023, using a computer to process any b-value sequence block through the wavelet transform branch of the feature extraction stage in the WFTBlock module to obtain a time-frequency diagram; Step 2024: Each frequency and the corresponding amplitude are subjected to the feature fusion stage in the WFTBlock module to obtain the Fourier transform eigenvalue The time-frequency graph is passed through the feature fusion stage in the WFTBlock module to obtain the wavelet transform eigenvalue 3. A method for fusing microseismic activity parameter time series features according to claim 1, characterized in that: Step 2022, the specific process is as follows: Step A: Arrange the frequencies in descending order, and obtain the first m frequencies and the amplitudes corresponding to the first m frequencies; the amplitude corresponding to the i-th frequency is recorded as A i ; i is a positive integer, 1≤i≤m; m is a positive integer; Step B: Use a computer to calculate the Get the period weighting coefficient α; where, It represents the maximum value of the square of the amplitude corresponding to the first m frequencies.

Images