Method and device for intelligently analyzing mining-while-mining seismic signals for mining operation

Abstract

The invention provides a while-mining seismic signal intelligent analysis method and device for mining operation, and relates to the technical field of seismic signal analysis, and the method comprises the steps: collecting while-mining seismic signals of a plurality of positions; frequency criticality analysis and magnitude criticality analysis are carried out on the plurality of seismic signal sequences collected at any time, and the average criticality is calculated; according to the plurality of while-mining seismic signal sequences, while-mining seismic volatility analysis is carried out; and carrying out centralized analysis according to the plurality of frequency criticalities and the plurality of earthquake magnitude criticalities, carrying out while-mining earthquake risk prediction, and obtaining a risk prediction probability as a while-mining earthquake signal analysis result. The technical problem that accurate real-time early warning is difficult to provide due to the fact that earthquake risk events have burstiness in the prior art can be solved, accurate assessment of earthquake signals and real-time early warning of potential geological risks are achieved by monitoring the signals in real time and training the risk prediction model in combination with historical data, and the risk prediction method and device have the advantages of being high in practicability and easy to popularize. And the accuracy of mining earthquake risk prediction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of seismic signal analysis, and in particular to an intelligent analysis method and device for in-process seismic signals used in mining operations. Background Art

[0002] Mining operations are high-risk, high-intensity engineering activities, especially in underground mining, where mining areas are often in complex geological environments. Earthquake risk events in mining operations, such as rock collapse, mine vibration, and mine tremors, are highly sudden and uncertain, which may not only threaten the safety of mining equipment and miners, but also make it particularly difficult to accurately predict and identify earthquake risks in a timely manner due to the closed nature of the underground environment. Existing technologies still have some limitations in monitoring and early warning of earthquake risks in mining operations, especially in complex underground operating environments. Although there are some advanced technologies and equipment that can monitor and alarm earthquake signals, the types, sources, and volatility of earthquake signals are very complex, so existing technologies cannot adapt to all situations when analyzing and identifying these signals in real time. In addition, there are usually multiple different working areas in a mining area, and the frequency and magnitude of earthquake signals in each area may be different. In addition, the propagation of earthquake signals is affected by multiple factors such as geological structure, mining activities, and equipment operation, which further increases the difficulty of signal analysis. In the face of complex environments, it is often difficult to provide sufficiently accurate and timely early warning information, which affects the safety and efficiency of mining operations.

[0003] In summary, the existing technology has the technical problem that it is difficult to accurately evaluate and provide real-time warning of seismic signals in different areas in the complex environment of mining areas due to the suddenness and uncertainty of earthquake risk events. Summary of the invention

[0004] The purpose of this application is to provide an intelligent analysis method and device for on-the-spot seismic signals for mining operations, so as to solve the technical problem in the prior art that it is difficult to accurately evaluate and provide real-time early warning of seismic signals in different areas in the complex environment of the mining area due to the suddenness and uncertainty of seismic risk events.

[0005] In view of the above problems, the present application provides a method and device for intelligent analysis of in-process seismic signals for mining operations.

[0006] In a first aspect, the present application provides an intelligent analysis method for on-the-spot seismic signals for mining operations, which is implemented by an intelligent analysis device for on-the-spot seismic signals for mining operations, wherein the intelligent analysis method for on-the-spot seismic signals for mining operations comprises: in mining operations, by means of a sensor array arranged in a mining area, collecting on-the-spot seismic signals at multiple locations, and obtaining multiple on-the-spot seismic signal sequences, wherein each on-the-spot seismic signal includes a signal frequency and a signal magnitude; performing frequency criticality analysis on the multiple on-the-spot seismic signal sequences to obtain multiple frequency criticalities, and performing magnitude criticality analysis to obtain multiple magnitude criticalities, and calculating and obtaining an average criticality; performing on-the-spot seismic volatility analysis based on the multiple on-the-spot seismic signal sequences to obtain on-the-spot seismic volatility parameters; performing centralized analysis based on the multiple frequency criticalities and multiple magnitude criticalities to obtain critical centralized parameters, and performing on-the-spot seismic risk prediction based on the on-the-spot seismic volatility parameters, the average criticality and the critical centralized parameters to obtain a risk prediction probability as an on-the-spot seismic signal analysis result.

[0007] In a second aspect, the present application further provides an intelligent analysis device for in-mining seismic signals for mining operations, which is used to execute the intelligent analysis method for in-mining seismic signals for mining operations as described in the first aspect, wherein the intelligent analysis device for in-mining seismic signals for mining operations comprises: a signal acquisition module, which is used to collect in-mining seismic signals at multiple locations in the mining operation through a sensor array arranged in the mining area to obtain multiple in-mining seismic signal sequences, wherein each in-mining seismic signal includes a signal frequency and a signal magnitude; a critical analysis module, which is used to perform frequency analysis on the multiple in-mining seismic signal sequences A rate criticality analysis is performed to obtain multiple frequency criticalities, and a magnitude criticality analysis is performed to obtain multiple magnitude criticalities, and the average criticality is calculated; a fluctuation analysis module, the fluctuation analysis module is used to perform fluctuation analysis of in-mining earthquakes according to the multiple in-mining earthquake signal sequences, and obtain fluctuation parameters of in-mining earthquakes; a risk prediction module, the risk prediction module is used to perform concentrated analysis according to the multiple frequency criticalities and multiple magnitude criticalities, and obtain critical concentrated parameters, and perform in-mining earthquake risk prediction according to the in-mining earthquake fluctuation parameters, the average criticality and the critical concentrated parameters, and obtain the risk prediction probability as the in-mining earthquake signal analysis result.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] During the mining operation, a sensor array is arranged in the mining area to collect in-mining seismic signals at multiple locations to obtain multiple in-mining seismic signal sequences, wherein each in-mining seismic signal includes a signal frequency and a signal magnitude; frequency criticality analysis is performed on the multiple in-mining seismic signal sequences to obtain multiple frequency criticalities, and magnitude criticality analysis is performed to obtain multiple magnitude criticalities, and the average criticality is calculated to obtain; based on the multiple in-mining seismic signal sequences, an in-mining seismic volatility analysis is performed to obtain in-mining seismic volatility parameters; based on the multiple frequency criticalities and multiple magnitude criticalities, a centralized analysis is performed to obtain critical centralized parameters; based on the in-mining seismic volatility parameters, the average criticality and the critical centralized parameters, an in-mining seismic risk prediction is performed to obtain a risk prediction probability as an in-mining seismic signal analysis result. That is to say, by deploying sensor arrays in the mining area, collecting sequences of earthquake signals from multiple locations, including signal frequency and magnitude, conducting criticality analysis on the signal frequency and magnitude, and using criticality indicators to evaluate the risk level of the signal; analyzing the degree of fluctuation in signal frequency and magnitude, calculating fluctuation parameters and conducting centralized analysis; training an earthquake risk prediction model through historical earthquake event data and risk probability sets, and applying it to real-time signal prediction, achieving accurate assessment of earthquake signals and real-time early warning of potential geological risks, and improving the accuracy of earthquake risk prediction during mining.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 This is a flow chart of the intelligent analysis method of seismic signals during mining operations used in this application;

[0013] Figure 2 This is a schematic diagram of the structure of the intelligent analysis device for in-process seismic signals used in mining operations in this application.

[0014] Explanation of the reference numerals: signal acquisition module 11 , criticality analysis module 12 , fluctuation analysis module 13 , risk prediction module 14 . DETAILED DESCRIPTION

[0015] This application solves the technical problem in the prior art that it is difficult to accurately evaluate and warn seismic signals in different areas in a complex environment of a mining area due to the suddenness and uncertainty of earthquake risk events by providing an intelligent analysis method and device for on-the-spot seismic signals used in mining operations. By deploying a sensor array in the mining area, a multi-location on-the-spot seismic signal sequence is collected, including signal frequency and magnitude, and criticality analysis is performed on the signal frequency and magnitude, and the risk level of the signal is evaluated using a criticality index; the degree of fluctuation of the signal frequency and magnitude is analyzed, and the fluctuation parameters are calculated and analyzed in a centralized manner; through historical earthquake event data and risk probability sets, an earthquake risk prediction model is trained and applied to real-time signal prediction, thereby achieving accurate evaluation of seismic signals and real-time warning of potential geological risks, and improving the accuracy of on-the-spot earthquake risk prediction.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 The present application provides an intelligent analysis method of seismic signals during mining operations, wherein the intelligent analysis method of seismic signals during mining operations is performed by an intelligent analysis device of seismic signals during mining operations, and the intelligent analysis method of seismic signals during mining operations specifically comprises the following steps:

[0018] Step 1: During mining operations, a sensor array is deployed in the mining area to collect in-mining seismic signals at multiple locations to obtain multiple in-mining seismic signal sequences, wherein each in-mining seismic signal includes a signal frequency and a signal magnitude.

[0019] Specifically, mining operations refer to various resource mining activities carried out in mining areas, such as coal, metal, and non-metallic mining. Mining operations may be accompanied by stratum vibrations or changes in rock formations, which can cause seismic signals to be generated. Sensor arrays are deployed at multiple locations in the mining area to monitor seismic signals generated during the mining process. The sensor array is a grid-like distribution structure composed of multiple sensors. It is a series of seismic monitoring sensors deployed at different locations in the mining area to monitor different locations in the mining area. Each sensor collects local seismic signals in real time and transmits data. The sensor array can improve the coverage and accuracy of the signal, making it easier to analyze geological activities at different locations. Each sensor records the seismic signal at the point at different times, including the signal frequency and magnitude, and continuously collects seismic signals at multiple time points to obtain multiple mining seismic signal sequences.

[0020] Each sequence contains continuous frequency and magnitude data, indicating the geological activity at that location. Mining seismic signals refer to seismic signals generated during mining operations and recorded in real time by sensors, including magnitude changes caused by vibration, extrusion, blasting, etc. during mining, reflecting the real-time status of geological activities in the mining area. Collecting these mining seismic signals can help detect stratum changes and provide timely warnings of potential dangers. Signal frequency refers to the frequency of seismic signals, that is, the number of vibrations per unit time, usually in Hertz (Hz). The high or low signal frequency can reflect the nature of the vibration. For example, the larger the signal frequency, the larger the magnitude of the earthquake reflected by the signal. The signal magnitude indicates the amount of energy released by the seismic event, usually expressed as a relative value, and can be used to assess the intensity of geological activities in the mining area in mining. In mining operations, an increase in magnitude may indicate greater rock activity or stress accumulation. Through sensors at multiple locations, comprehensive monitoring of seismic signals in the mining area is achieved.

[0021] Step 2: Perform frequency criticality analysis on the multiple random seismic signal sequences to obtain multiple frequency criticalities, perform magnitude criticality analysis to obtain multiple magnitude criticalities, and calculate the average criticality.

[0022] Specifically, the critical signal frequency and critical signal magnitude are set as benchmarks through historical earthquake data or geological models, as thresholds that may trigger dangerous events, indicating that when the frequency and magnitude of the earthquake signal reach this value, the risk of geological disasters (such as collapse or landslide) increases significantly. The ratio of the frequency of the on-site earthquake signal to the critical signal frequency in each on-site earthquake signal sequence is calculated separately to indicate the degree of proximity between the signal frequency and the critical value of danger. For each frequency critical ratio sequence, the mean of all ratios is calculated, which is the frequency criticality of the sequence, and multiple frequency criticalities are obtained. Similarly, the ratio of the magnitude of the on-site earthquake signal to the critical signal magnitude in each on-site earthquake signal sequence is calculated to indicate the degree of proximity between the signal magnitude and the critical value of danger. For each magnitude critical ratio sequence, the mean of all ratios is calculated, which is the magnitude criticality of the sequence, and multiple magnitude criticalities are obtained. All frequency criticalities and magnitude criticalities are averaged to obtain the overall average criticality. By analyzing the frequency criticality and magnitude criticality and calculating the average criticality, we can more accurately assess the probability of dangerous events occurring as the seismic signal approaches mining. The larger the criticality, the closer the current signal frequency or magnitude is to the known danger level, thus requiring more stringent monitoring and prevention measures, which will help improve the safety of mining operations and reduce the occurrence of earthquake disasters.

[0023] Step three: performing a mining seismic wave analysis based on the multiple mining seismic signal sequences to obtain mining seismic wave parameters.

[0024] Specifically, multiple signal frequency sequences and multiple signal magnitude sequences are extracted from multiple in-mining seismic signal sequences. Based on multiple signal frequency sequences and critical signal frequencies, an in-mining seismic volatility analysis is performed. By analyzing multiple in-mining seismic signal sequences, a parameter that can reflect the degree of fluctuation of seismic signals, namely, the in-mining seismic volatility parameter, is obtained. In-mining seismic volatility analysis refers to obtaining the degree of fluctuation (i.e., volatility) of seismic signals by analyzing the changes in frequency and magnitude in in-mining seismic signals. In-mining seismic volatility analysis includes data collection (collecting multiple in-mining seismic signal sequences), feature extraction (extracting multiple signal frequency sequences and multiple signal magnitude sequences), volatility calculation (calculating the frequency fluctuation parameters and magnitude fluctuation parameters of each signal sequence), and finally performing weighted calculation on the frequency fluctuation parameters and the magnitude fluctuation parameters to obtain the in-mining seismic volatility parameters. The in-mining seismic volatility parameters obtained through the in-mining seismic volatility analysis provide a comprehensive indicator that reflects the fluctuation of seismic signals, which helps to accurately assess the seismic risks in mining operations because it takes into account the changes in frequency and magnitude at the same time. The higher the mining seismic fluctuation parameter, the more violent the fluctuation of the seismic signal, which may indicate a higher earthquake risk. This helps to identify potential earthquake risks in advance, so that corresponding preventive measures can be taken to ensure mining safety.

[0025] Step 4: Perform concentrated analysis based on the multiple frequency criticalities and multiple magnitude criticalities to obtain critical concentrated parameters, and perform on-site earthquake risk prediction based on the on-site earthquake fluctuation parameters, average criticality and critical concentrated parameters to obtain risk prediction probability as the on-site earthquake signal analysis result.

[0026] Specifically, a centralized analysis is performed based on the multiple frequency criticalities and magnitude criticalities to obtain critical centralized parameters, and the variance of the frequency criticalities and magnitude criticalities is calculated to evaluate whether the distribution of these criticalities is uniform. For frequency criticality, the variance of all frequency criticalities (i.e., frequency critical centralized parameters) is calculated, and for magnitude criticality, the variance of all magnitude criticalities (i.e., magnitude critical centralized parameters) is calculated. The larger the variance, the more uneven the distribution of frequency or magnitude criticality, and the greater the degree of concentration, that is, the frequency or magnitude of the critical signal varies greatly at different times, which usually means that the signal fluctuates more and the potential risk increases. The smaller the variance, the more concentrated the frequency or magnitude of the signal, the better the stability, and the lower the risk.

[0027] By extracting the obtained mining earthquake fluctuation parameters (such as the fluctuation analysis results of frequency and magnitude), average criticality (average criticality of frequency and magnitude) and critical concentration parameters (variance calculation results of frequency and magnitude criticality), the mining earthquake fluctuation parameters, average criticality and critical concentration parameters are input into the mining earthquake risk predictor to predict the mining earthquake risk and predict the risk probability of mining earthquake. Through the prediction of the model, the risk prediction probability is obtained, which is a value, usually between 0 and 1, indicating the probability of the occurrence of mining earthquake risk events. The risk prediction probability provides a quantitative indicator for evaluating the size of mining earthquake risk in mining operations. The higher the probability, the greater the possibility of earthquake risk events, and more stringent monitoring and prevention measures need to be taken. The calculation of the risk prediction probability helps to identify potential earthquake risks in advance, so as to take corresponding preventive measures to ensure mining safety.

[0028] Furthermore, step one of this application includes:

[0029] In mining operations, original in-mining seismic signals at multiple locations and multiple times are collected through a sensor array arranged in the mining area; feature extraction is performed on multiple original in-mining seismic signal sets to obtain multiple in-mining seismic signal frequency sets and multiple in-mining seismic signal magnitude sets; multiple in-mining seismic signal frequency sets and multiple in-mining seismic signal magnitude sets are arranged according to timestamps of multiple times to obtain multiple in-mining seismic signal sequences.

[0030] Specifically, sensor arrays are deployed at different locations in the mining area to ensure that mining seismic activities can be fully monitored. The sensor array may include various types of sensors, such as seismic detectors, accelerometers, etc., to record seismic waves generated by underground rock deformation and stress changes. The layout of the sensor array needs to be optimized according to the geological conditions of the mining area and the characteristics of the mining activities to ensure that mining seismic signals can be effectively monitored. The original mining seismic signals generated during mining operations at different times are collected, including the original data of magnitude and signal frequency. The original mining seismic signal refers to the unprocessed seismic signal data collected by the sensor array at different locations and times during the mining operation, which contains a variety of information, such as amplitude, frequency, vibration waveform, etc., which can reflect the real-time dynamics of the strata during the mining process.

[0031] The original in-situ seismic signals collected at multiple locations at multiple times are integrated to form multiple sets of original in-situ seismic signals. Feature extraction is performed on multiple sets of original in-situ seismic signals to retain the most useful information for analysis (such as frequency and magnitude), and multiple sets of in-situ seismic signal frequencies and multiple sets of in-situ seismic signal magnitudes are obtained, which are sets of signal frequencies and magnitude data extracted from the original in-situ seismic signals, respectively. Feature extraction is a data processing method used to extract key features from raw data. The time domain signal is converted into a frequency domain signal through frequency domain analysis methods such as Fourier transform, that is, the seismic signal in the time domain is converted into a frequency distribution in the frequency domain, thereby extracting the signal frequency of the seismic wave and understanding the periodic characteristics of the vibration.

[0032] The magnitude reflects the energy released by an earthquake event, and the amplitude is directly related to the magnitude. The amplitude value in the collected raw signal can be converted into a magnitude value after processing, and each sampling point has an amplitude value. Generally speaking, the larger the amplitude, the higher the magnitude. The magnitude of the earthquake source can be estimated by combining the amplitude value recorded by the instrument with the distance of signal propagation. It is usually expressed in Richter magnitude or local magnitude, and the magnitude is calculated using amplitude and distance correction values. Since seismic waves attenuate as the distance increases during propagation, the amplitude needs to be corrected for distance. The distance correction is usually an attenuation function, expressed as A0(R), where R is the distance between the epicenter of the earthquake and the observation point. For example, if the source distance is 30 meters, the distance correction value is 0.3. The magnitude of each signal is calculated through amplitude analysis to quantify the energy release intensity of seismic activity.

[0033] According to multiple timestamps, that is, the time mark generated when recording data, it is used to identify the specific moment of each seismic signal acquisition. Multiple sets of on-site seismic signal frequencies and multiple sets of on-site seismic signal magnitudes are arranged to generate multiple on-site seismic signal sequences arranged in chronological order, reflecting the dynamic process of seismic activity. For example, if the magnitude sequence at a certain location continues to rise in a short period of time, it may indicate that the formation pressure accumulates and there is a risk of landslide or collapse. By deploying sensor arrays and feature extraction technology, the frequency and magnitude characteristics of on-site seismic signals at multiple locations can be obtained. After arranging them in chronological order to form a sequence, the changes in geological activities in the mining area can be monitored, helping to identify potential risks in a timely manner and improve the safety and prediction capabilities of the mining area.

[0034] Further, step 2 of this application includes:

[0035] According to the records of on-site earthquake risk events that occurred in historical time, the critical signal frequency and critical signal magnitude are obtained; the ratios of the on-site earthquake signal frequencies to the critical signal frequencies in the multiple on-site earthquake signal sequences are calculated respectively to obtain multiple signal frequency critical ratio sequences, and the averages are calculated respectively to obtain multiple frequency criticalities; the ratios of the on-site earthquake signal magnitudes to the critical signal magnitude in the multiple on-site earthquake signal sequences are calculated respectively to obtain multiple signal magnitude critical ratio sequences, and the averages are calculated respectively to obtain multiple magnitude criticalities; the averages of the multiple frequency criticalities and the multiple magnitude criticalities are calculated to obtain the average criticality.

[0036] Specifically, the records of mining seismic risk events that occurred in the historical period, that is, the historical data of geological risk events that occurred in mining operations, including the time, location, frequency, magnitude and consequences of the earthquake, are collected to set the critical frequency and magnitude of the current monitoring. The records of mining seismic risk events that occurred in the historical period are analyzed in detail to identify the frequency and magnitude characteristics of the seismic signal when the risk event occurred, and find out which frequencies and magnitudes are closely related to the occurrence of the risk event. Based on the results of data analysis, the critical signal frequency and critical signal magnitude are determined as important indicators to distinguish normal seismic signals from signals that may cause risk events. The critical signal frequency refers to the threshold of the seismic signal frequency associated with a significant increase in the probability of a mining seismic risk event; the critical signal magnitude refers to the threshold of the seismic signal magnitude associated with a significant increase in the probability of a mining seismic risk event. For example, suppose that by analyzing the mining seismic data of the past ten years, it is found that when the signal frequency exceeds 40Hz and the magnitude reaches level 2, the probability of a risk event increases significantly. Therefore, 40Hz is defined as the critical signal frequency and level 2 is defined as the critical signal magnitude.

[0037] Calculate the ratio of the frequency of the random seismic signal to the critical signal frequency in each random seismic signal sequence to obtain the critical signal frequency ratio. For example, if the signal frequency of a certain acquisition point is 35 Hz and the critical signal frequency is 40 Hz, the critical frequency ratio of the signal is 0.875. Repeat this operation to calculate the signal frequency at each acquisition point at each moment to obtain multiple critical frequency ratio sequences. For each critical frequency ratio sequence, calculate its average value, which is the frequency criticality of the sequence. The critical frequency is the average value of all critical frequency ratios in the sequence, representing the average degree of the signal frequency approaching the critical frequency in the entire sequence. Similarly, calculate the ratio of the magnitude of each random seismic signal to the critical signal magnitude, reflecting the degree of proximity of each signal magnitude to the critical magnitude. Repeat this operation to calculate the signal magnitude at each acquisition point at each moment to obtain multiple critical magnitude ratio sequences. For each critical magnitude ratio sequence, calculate its average value to obtain the critical magnitude of the sequence, representing the average degree of the signal magnitude approaching the critical magnitude in the entire sequence. Calculate the average of all frequency criticalities and magnitude criticalities to obtain the overall average criticality, which provides a comprehensive indicator to evaluate the overall risk level of mining seismic signals. The greater the criticality, the greater the probability that the current signal frequency or magnitude is close to the time of earthquake risk. By calculating the critical ratio of frequency and magnitude, the risk level of each signal sequence is accurately evaluated, and signals close to the critical value are identified, thereby achieving early warning. When the average criticality is high, a warning is issued in time to remind managers to take preventive measures, thereby effectively improving the safety of mining operations.

[0038] Further, step three of this application includes:

[0039] Extract and obtain multiple signal frequency sequences and multiple signal magnitude sequences from the multiple in-service seismic signal sequences; perform in-service seismic frequency fluctuation analysis based on the multiple signal frequency sequences and the critical signal frequency to obtain frequency fluctuation parameters; perform in-service seismic magnitude fluctuation analysis based on the multiple signal magnitude sequences and the critical signal magnitude to obtain magnitude fluctuation parameters; perform weighted calculation on the frequency fluctuation parameters and the magnitude fluctuation parameters to obtain in-service seismic fluctuation parameters.

[0040] Specifically, multiple signal frequency sequences and multiple signal magnitude sequences are extracted from multiple in-situ seismic signal sequences, that is, frequency sequences and magnitude sequences are extracted from the in-situ seismic signal sequences of each acquisition point. Each frequency value represents the frequency of the seismic signal at a certain moment in the mining process, and each magnitude value represents the magnitude of the seismic signal at a certain moment in the mining process. For each signal frequency sequence, its volatility with the critical signal frequency is calculated, including calculating statistics such as the standard deviation and mean deviation of the sequence to evaluate the degree of frequency fluctuation. Through these analyses, the frequency fluctuation parameters are obtained. For example, if the volatility of a frequency sequence is large, its frequency fluctuation parameters may be high.

[0041] Frequency volatility analysis refers to analyzing the frequency volatility by calculating the changes in the frequency sequence of the seismic signal, and measuring the degree of frequency fluctuation within a certain period of time through statistical methods. For example, one or more random signal frequencies are randomly selected from each signal frequency sequence, and the mean is calculated. Then, the frequency fluctuation parameter is obtained by calculating the ratio of the absolute value of the difference between the mean and the critical signal frequency to the critical signal frequency. Similarly, the calculation process is the same for multiple signal magnitude sequences. One or more random signal magnitudes are randomly selected from each signal magnitude sequence, the mean is calculated, and then the magnitude fluctuation parameter is obtained by calculating the ratio of the absolute value of the difference between the mean and the critical signal magnitude to the critical signal magnitude.

[0042] The frequency fluctuation parameter and the magnitude fluctuation parameter are weighted and calculated to obtain the final mining earthquake fluctuation parameter. The weight can be set according to actual needs or experience. If the frequency fluctuation has a greater impact on the risk in the current situation, a higher weight is given to the frequency fluctuation parameter. For example, assuming that the signal frequencies randomly extracted from multiple signal frequency sequences are 35 Hz, 38 Hz, and 42 Hz, and the critical signal frequency is 40 Hz, the calculated frequency fluctuation parameter is 0.041; the magnitudes randomly extracted from multiple signal magnitude sequences are 1.8, 2.1, and 1.9, and the critical signal magnitude is 2, and the calculated magnitude fluctuation parameter is 0.035. Assuming that the weight of the frequency fluctuation parameter is 0.6 and the weight of the magnitude fluctuation parameter is 0.4, the mining earthquake fluctuation parameter is 0.039. By quantifying the frequency and magnitude volatility of seismic signals and combining them with weighted fluctuation parameters, a comprehensive on-the-spot seismic fluctuation parameter is obtained, which reflects the overall fluctuation of signal frequency and magnitude. A larger fluctuation parameter indicates a stronger signal volatility, which represents a higher earthquake risk. This helps to timely identify potential geological disasters or other risks and support safety decisions in mining operations.

[0043] Furthermore, the present application also includes the following steps:

[0044] At least one random signal frequency is randomly selected from the multiple signal frequency sequences, and the mean is calculated to obtain an average random signal frequency; the ratio of the absolute value of the difference between the average random signal frequency and the critical signal frequency to the critical signal frequency is calculated to obtain a frequency fluctuation parameter.

[0045] Specifically, one or more random signal frequencies are randomly extracted from each signal frequency sequence. For each signal frequency sequence at each moment, random extraction is performed to obtain a set of signal frequency values ​​representing different time points. The mean of the frequency values ​​randomly extracted from all signal frequency sequences is calculated, all randomly extracted signal frequency values ​​are added, and then divided by the number of extracted frequencies to obtain the average random signal frequency. By calculating the absolute value of the difference between the average random signal frequency and the critical signal frequency, and calculating the ratio of the absolute value to the critical signal frequency, the frequency fluctuation parameter is obtained, which reflects the degree of deviation of the current signal frequency relative to the critical frequency, thereby evaluating the frequency volatility. The larger the value of the frequency fluctuation parameter, the more significant the fluctuation of the signal frequency, which means the higher the earthquake risk. Through the calculation of the frequency fluctuation parameter, the mining operation accurately evaluates the volatility of the seismic signal frequency and understands the deviation of the current signal frequency from the historical critical frequency. The larger the value of the frequency fluctuation parameter, the stronger the frequency volatility, and there may be a higher geological risk. Therefore, it can provide more timely and accurate risk warnings to ensure the safety of mining operations.

[0046] Further, step 4 of this application includes:

[0047] The variance of the multiple frequency criticalities is calculated to obtain the frequency critical concentrated parameter; the variance of the multiple magnitude criticalities is calculated to obtain the magnitude critical concentrated parameter; and the frequency critical concentrated parameter and the magnitude critical concentrated parameter are weightedly calculated to obtain the critical concentrated parameter.

[0048] Specifically, the frequency criticality is the value calculated from the ratio between the frequency of each random seismic signal and the critical signal frequency, reflecting the closeness of the signal frequency to the critical frequency. The variance of multiple frequency criticalities is calculated. Variance is a statistic that measures the degree of discreteness of a set of data. The mean of multiple frequency criticalities is calculated, and then the square of the variance of each frequency criticality and the mean is calculated. These square values ​​are added and divided by the number of frequency criticalities to obtain the variance, that is, the frequency criticality concentration parameter, which reflects the degree of concentration of frequency criticality. The larger the variance, the more concentrated the frequency criticality, and the probability of risk events occurring is relatively stable.

[0049] The magnitude criticality is calculated in the same way as the frequency criticality. The magnitude criticality is the ratio of the magnitude of each random seismic signal to the critical magnitude, which indicates the closeness between the magnitude and the critical magnitude. The magnitude critical concentration parameter also reflects the concentration of the magnitude criticality. The larger the variance, the more concentrated the magnitude is close to the critical value, indicating that the probability of risk occurrence is also more concentrated. The frequency critical concentration parameter and the magnitude critical concentration parameter are combined using a weighted calculation method to obtain a comprehensive critical concentration parameter. The concentration degree of earthquake risk can be evaluated by the level of the concentration parameter. The larger the variance, the more uneven the distribution of the criticality and the greater the concentration.

[0050] For example, assume that five frequency thresholds have been calculated: 0.91, 1.05, 1.01, 1.10, 0.90, the mean is 0.99, and then the variance is [(0.91-0.99) 2 +(1.05 -0.99) 2 +(1.00 -0.99) 2 +(1.10 -0.99) 2 +(0.90-0.99) 2 ] / 5=0.00612. Assuming that the five magnitude criticalities that have been calculated are 0.9, 1.05, 1.00, 1.15, and 0.95, the calculated mean is 1.01, and then the calculated variance is [(0.90-1.01) 2 +(1.05-1.01) 2 +(1.00-1.01) 2 +(1.15-1.01) 2 +(0.95-1.01) 2 ] / 5=0.0074. The frequency critical concentration parameter and the magnitude critical concentration parameter are weighted. Assuming that the frequency and magnitude are weighted as 0.6 and 0.4 respectively, the critical concentration parameter is 0.6*0.00612+0.4*0.0074=0.0066. By calculating the frequency critical concentration parameter and the magnitude critical concentration parameter and performing weighted calculations on them, a comprehensive indicator of earthquake risk, namely the critical concentration parameter, is obtained, which helps to accurately assess the earthquake risk in mining operations because the changes in frequency and magnitude are taken into account at the same time. The higher the critical concentration parameter, the more violent the fluctuation of the seismic signal, which may indicate a higher earthquake risk, which helps to identify potential earthquake risks in advance, so as to take corresponding preventive measures to ensure mining safety.

[0051] Furthermore, the present application also includes the following steps:

[0052] According to the recorded data of mining risk events in historical time, the sample mining seismic fluctuation parameter set, the sample average criticality set and the sample critical concentration parameter set are collected and processed, and the probability of the mining risk event occurring under different sample mining seismic fluctuation parameters, sample average criticality and sample critical concentration parameters is collected to obtain a sample risk probability set; the sample mining seismic fluctuation parameter set, the sample average criticality set, the sample critical concentration parameter set and the sample risk probability set are used to train a mining seismic risk predictor; the mining seismic fluctuation parameters, the average criticality and the critical concentration parameters are input into the mining seismic risk predictor, and the prediction output is used to obtain the risk prediction probability.

[0053] Specifically, the sample random earthquake fluctuation parameter set, sample average criticality set and sample critical concentration parameter set are obtained from historical records. The random earthquake fluctuation parameters refer to the parameters obtained by analyzing the frequency and magnitude volatility of random earthquake signals, reflecting the intensity of earthquake signal fluctuations; the sample average criticality set refers to the data set obtained by calculating the average values ​​of frequency criticality and magnitude criticality of each earthquake signal sequence in the historical samples, representing the relative distance between the signal and the critical state; the sample critical concentration parameter set refers to the data set obtained by calculating the variance of frequency criticality and magnitude criticality in each historical sample, reflecting the concentration and uniformity of the criticality distribution of different earthquake signals.

[0054] For each historical sample, the probability of a mining seismic risk event is calculated. The probability of the risk of the sample is calculated by matching the mining seismic fluctuation parameter, sample average criticality, and sample critical concentration parameter of each sample with the known historical risk data. The risk probability of each sample is estimated by statistical analysis, regression model, etc. Statistical analysis is to estimate the risk probability based on the characteristic value of the sample and the parameters of the distribution by assuming that the probability of the occurrence of a risk event conforms to a certain distribution (such as normal distribution or beta distribution). For example, suppose that historical data shows that the risk probability of samples with mining seismic fluctuation parameters greater than 0.3 is 0.8, and the risk probability of samples with mining seismic fluctuation parameters less than 0.3 is 0.2. For a new sample, if its mining seismic fluctuation parameter is 0.4, its risk probability is 0.8.

[0055] Select a regression model, such as logistic regression (because the risk probability is generally between 0 and 1), use historical data to train the regression model, input the random earthquake fluctuation parameters, average criticality and critical concentration parameters, and output whether an earthquake risk event occurred in the historical sample (usually a binary label, such as 0 for no risk event, 1 for a risk event). By minimizing the loss function, the logistic regression model is trained so that the model can find the regression coefficient that best fits the data. For new samples, input their random earthquake fluctuation parameters, average criticality and critical concentration parameters into the trained regression model, and output a probability value between 0 and 1, indicating the probability of an earthquake risk event. By calculating the risk probabilities of all samples, a sample risk probability set is finally formed, which contains the probability values ​​of random earthquake risk events occurring in all historical samples under different conditions.

[0056] Data processing is performed on the sample random earthquake fluctuation parameter set, sample average criticality set, sample critical concentration parameter set and sample risk probability set, and they are converted to the same scale. At the same time, the missing values ​​in the data are processed. Samples with missing values ​​can be deleted, or missing data can be filled with mean, median or interpolation. According to the nature of the problem, an appropriate machine learning algorithm is selected. For risk prediction, the goal is to predict the probability of an earthquake, which can be regarded as a regression problem (output a continuous probability value). A model suitable for regression problems is selected, such as a random forest regression model.

[0057] The sample data (including the seismic fluctuation parameters, criticality and concentration parameters) are used as input features and the risk probability is used as the target output. The model is trained using these data to form two parts: input (feature matrix) and output (target value). The data set is divided into a training set and a test set. Usually 80% of the data is used as the training set and the remaining 20% ​​is used as the test set. Random forest regression constructs multiple decision trees. Each tree is trained on a different random subset of the data, and the final prediction result is the average of the prediction results of all trees. Randomly select subsets of data and feature subsets to train multiple decision trees. Multiple trees can be trained in parallel to improve training efficiency.

[0058] The optimal hyperparameters (such as the number of trees, maximum depth, splitting criteria, etc.) are selected through cross-validation to improve the performance of the model. The splitting criteria of each tree are optimized through loss functions such as mean square error (the square of the average error between the predicted value and the true value), and finally a strong predictor is trained. The input features (fluctuation parameters, criticality, concentration parameters) in the test set are input into the trained model to obtain the prediction results, calculate the error between the prediction results and the actual risk probability, and compare the performance on the training set and the test set. If the training set performs very well but the test set performs poorly, it may mean that the model is overfitting, and the model complexity needs to be adjusted or other regularization techniques need to be used. According to the evaluation results, the model parameters are adjusted, such as the number of trees, maximum depth, minimum number of sample splits, etc. The model is optimized by adding new features or removing irrelevant features, and finally a seismic risk predictor is obtained.

[0059] The mining earthquake fluctuation parameters, average criticality and critical concentration parameters are preprocessed to ensure that the format of the input data is consistent with the format used when training the model. These data are input into the trained mining earthquake risk predictor. Based on the rules learned in the previous training, the random forest regressor is calculated through multiple decision trees. Each decision tree will give a prediction result. Finally, the random forest model will calculate the average of all trees as the final prediction result. Through the prediction process of the model, the output risk prediction probability is obtained. If the prediction probability is high (such as more than 0.8), take corresponding safety measures in advance, such as reducing the intensity of work and strengthening the structure of the mining area. By inputting the mining earthquake fluctuation parameters, average criticality and critical concentration parameters into the mining earthquake risk predictor, a real-time risk prediction probability is obtained, which helps mine managers make decisions in advance and take necessary safety measures to reduce the risk of mining earthquakes.

[0060] In summary, the intelligent analysis method of seismic signals during mining operations provided by the present application has the following technical effects:

[0061] During the mining operation, a sensor array is arranged in the mining area to collect in-mining seismic signals at multiple locations to obtain multiple in-mining seismic signal sequences, wherein each in-mining seismic signal includes a signal frequency and a signal magnitude; frequency criticality analysis is performed on the multiple in-mining seismic signal sequences to obtain multiple frequency criticalities, and magnitude criticality analysis is performed to obtain multiple magnitude criticalities, and the average criticality is calculated to obtain; based on the multiple in-mining seismic signal sequences, an in-mining seismic volatility analysis is performed to obtain in-mining seismic volatility parameters; based on the multiple frequency criticalities and multiple magnitude criticalities, a centralized analysis is performed to obtain critical centralized parameters; based on the in-mining seismic volatility parameters, the average criticality and the critical centralized parameters, an in-mining seismic risk prediction is performed to obtain a risk prediction probability as an in-mining seismic signal analysis result. That is to say, by deploying sensor arrays in the mining area, collecting sequences of earthquake signals from multiple locations, including signal frequency and magnitude, conducting criticality analysis on the signal frequency and magnitude, and using criticality indicators to evaluate the risk level of the signal; analyzing the degree of fluctuation in signal frequency and magnitude, calculating fluctuation parameters and conducting centralized analysis; training an earthquake risk prediction model through historical earthquake event data and risk probability sets, and applying it to real-time signal prediction, achieving accurate assessment of earthquake signals and real-time early warning of potential geological risks, and improving the accuracy of earthquake risk prediction during mining.

[0062] Embodiment 2: Based on the same inventive concept as the method for intelligent analysis of seismic signals during mining operations in the aforementioned embodiment 1, the present application also provides an intelligent analysis device for seismic signals during mining operations, see the attached Figure 2 , the intelligent analysis device for seismic signals during mining operations comprises:

[0063] The signal acquisition module 11 is used to collect mining seismic signals at multiple locations during mining operations through a sensor array arranged in the mining area to obtain multiple mining seismic signal sequences, wherein each mining seismic signal includes a signal frequency and a signal magnitude.

[0064] The critical analysis module 12 is used to perform frequency criticality analysis on the multiple random seismic signal sequences to obtain multiple frequency criticalities, and to perform magnitude criticality analysis to obtain multiple magnitude criticalities, and to calculate and obtain an average criticality.

[0065] The fluctuation analysis module 13 is used to perform fluctuation analysis of the mining seismic signals according to the plurality of mining seismic signal sequences to obtain the mining seismic fluctuation parameters.

[0066] The risk prediction module 14 is used to perform centralized analysis based on the multiple frequency criticalities and multiple magnitude criticalities to obtain critical centralized parameters, and to perform risk prediction of in-mining earthquakes based on the in-mining earthquake fluctuation parameters, average criticality and critical centralized parameters to obtain risk prediction probability as the in-mining earthquake signal analysis result.

[0067] Furthermore, the signal acquisition module 11 in the intelligent analysis device for seismic signals during mining operations is also used for:

[0068] In mining operations, original in-mining seismic signals at multiple locations and multiple times are collected through a sensor array arranged in the mining area; feature extraction is performed on multiple original in-mining seismic signal sets to obtain multiple in-mining seismic signal frequency sets and multiple in-mining seismic signal magnitude sets; multiple in-mining seismic signal frequency sets and multiple in-mining seismic signal magnitude sets are arranged according to timestamps of multiple times to obtain multiple in-mining seismic signal sequences.

[0069] Furthermore, the critical analysis module 12 in the intelligent analysis device for in-process seismic signals for mining operations is also used for:

[0070] According to the records of on-site earthquake risk events that occurred in historical time, the critical signal frequency and critical signal magnitude are obtained; the ratios of the on-site earthquake signal frequencies to the critical signal frequencies in the multiple on-site earthquake signal sequences are calculated respectively to obtain multiple signal frequency critical ratio sequences, and the averages are calculated respectively to obtain multiple frequency criticalities; the ratios of the on-site earthquake signal magnitudes to the critical signal magnitude in the multiple on-site earthquake signal sequences are calculated respectively to obtain multiple signal magnitude critical ratio sequences, and the averages are calculated respectively to obtain multiple magnitude criticalities; the averages of the multiple frequency criticalities and the multiple magnitude criticalities are calculated to obtain the average criticality.

[0071] Furthermore, the fluctuation analysis module 13 in the intelligent analysis device for seismic signals during mining operations is also used for:

[0072] Extract and obtain multiple signal frequency sequences and multiple signal magnitude sequences from the multiple in-service seismic signal sequences; perform in-service seismic frequency fluctuation analysis based on the multiple signal frequency sequences and the critical signal frequency to obtain frequency fluctuation parameters; perform in-service seismic magnitude fluctuation analysis based on the multiple signal magnitude sequences and the critical signal magnitude to obtain magnitude fluctuation parameters; perform weighted calculation on the frequency fluctuation parameters and the magnitude fluctuation parameters to obtain in-service seismic fluctuation parameters.

[0073] Furthermore, the fluctuation analysis module 13 in the intelligent analysis device for seismic signals during mining operations is also used for:

[0074] At least one random signal frequency is randomly selected from the multiple signal frequency sequences, and the mean is calculated to obtain an average random signal frequency; the ratio of the absolute value of the difference between the average random signal frequency and the critical signal frequency to the critical signal frequency is calculated to obtain a frequency fluctuation parameter.

[0075] Furthermore, the risk prediction module 14 in the intelligent analysis device for seismic signals during mining operations is also used for:

[0076] The variance of the multiple frequency criticalities is calculated to obtain the frequency critical concentrated parameter; the variance of the multiple magnitude criticalities is calculated to obtain the magnitude critical concentrated parameter; and the frequency critical concentrated parameter and the magnitude critical concentrated parameter are weightedly calculated to obtain the critical concentrated parameter.

[0077] Furthermore, the risk prediction module 14 in the intelligent analysis device for seismic signals during mining operations is also used for:

[0078] According to the recorded data of mining risk events in historical time, the sample mining seismic fluctuation parameter set, the sample average criticality set and the sample critical concentration parameter set are collected and processed, and the probability of the mining risk event occurring under different sample mining seismic fluctuation parameters, sample average criticality and sample critical concentration parameters is collected to obtain a sample risk probability set; the sample mining seismic fluctuation parameter set, the sample average criticality set, the sample critical concentration parameter set and the sample risk probability set are used to train a mining seismic risk predictor; the mining seismic fluctuation parameters, the average criticality and the critical concentration parameters are input into the mining seismic risk predictor, and the prediction output is used to obtain the risk prediction probability.

[0079] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The method and specific examples of intelligent analysis of seismic signals for mining operations in the first embodiment are also applicable to the intelligent analysis device for seismic signals for mining operations in the present embodiment. Through the detailed description of the intelligent analysis method of seismic signals for mining operations, those skilled in the art can clearly understand the intelligent analysis device for seismic signals for mining operations in the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0080] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0081] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent analysis method of seismic signals during mining operations, characterized in that: include: In mining operations, a sensor array is arranged in the mining area to collect mining seismic signals at multiple locations to obtain multiple mining seismic signal sequences, wherein each mining seismic signal includes a signal frequency and a signal magnitude; Performing frequency criticality analysis on the multiple random seismic signal sequences to obtain multiple frequency criticalities, and performing magnitude criticality analysis to obtain multiple magnitude criticalities, and calculating and obtaining an average criticality; Performing a mining seismic wave analysis based on the multiple mining seismic signal sequences to obtain mining seismic wave parameters; A concentrated analysis is performed based on the multiple frequency criticalities and multiple magnitude criticalities to obtain critical concentrated parameters, and a mining earthquake risk prediction is performed based on the mining earthquake fluctuation parameters, average criticality and critical concentrated parameters to obtain a risk prediction probability as the mining earthquake signal analysis result.

2. The method for intelligent analysis of seismic signals during mining operations according to claim 1, characterized in that: During mining operations, an array of sensors is deployed in the mining area to collect seismic signals at multiple locations, including: During mining operations, the original seismic signals at multiple locations and at multiple times are collected through a sensor array deployed in the mining area. Extracting features from a plurality of original in-situ seismic signal sets to obtain a plurality of in-situ seismic signal frequency sets and a plurality of in-situ seismic signal magnitude sets; According to the timestamps of multiple moments, multiple sets of in-flight seismic signal frequencies and multiple sets of in-flight seismic signal magnitudes are arranged to obtain multiple in-flight seismic signal sequences.

3. The method for intelligent analysis of seismic signals during mining operations according to claim 1, characterized in that: Performing frequency criticality analysis on the multiple random seismic signal sequences to obtain multiple frequency criticalities, and performing magnitude criticality analysis to obtain multiple magnitude criticalities, and calculating an average criticality, including: According to the records of mining-related earthquake risk events that occurred in the historical period, the critical signal frequency and critical signal magnitude are obtained; Calculating the ratios of the random-acquisition seismic signal frequencies in the multiple random-acquisition seismic signal sequences to the critical signal frequencies respectively, obtaining multiple signal frequency critical ratio sequences, and calculating the averages respectively, obtaining multiple frequency criticalities; Calculating the ratios of the magnitudes of the random-collected seismic signals in the multiple random-collected seismic signal sequences to the magnitude of the critical signals respectively, obtaining multiple signal magnitude critical ratio sequences, and calculating the averages respectively, obtaining multiple magnitude criticalities; The average of the multiple frequency criticalities and the multiple magnitude criticalities is calculated to obtain an average criticality.

4. The method for intelligent analysis of seismic signals during mining operations according to claim 3, characterized in that: According to the multiple mining seismic signal sequences, mining seismic fluctuation analysis is performed to obtain mining seismic fluctuation parameters, including: Extracting and obtaining a plurality of signal frequency sequences and a plurality of signal magnitude sequences from the plurality of random seismic signal sequences; According to the multiple signal frequency sequences and the critical signal frequency, a frequency fluctuation analysis of the earthquake frequency is performed to obtain a frequency fluctuation parameter; according to the multiple signal magnitude sequences and the critical signal magnitude, a magnitude fluctuation analysis of the earthquake magnitude is performed to obtain a magnitude fluctuation parameter; The frequency fluctuation parameter and the magnitude fluctuation parameter are weightedly calculated to obtain the mining seismic fluctuation parameter.

5. The method for intelligent analysis of seismic signals during mining operations according to claim 4, characterized in that: According to the multiple signal frequency sequences and the critical signal frequency, a seismic frequency fluctuation analysis is performed to obtain a frequency fluctuation parameter, including: Randomly extracting at least one random signal frequency from each of the plurality of signal frequency sequences, and calculating the mean to obtain an average random signal frequency; The ratio of the absolute value of the difference between the average random signal frequency and the critical signal frequency to the critical signal frequency is calculated to obtain a frequency fluctuation parameter.

6. The method for intelligent analysis of seismic signals during mining operations according to claim 1, characterized in that: According to the multiple frequency criticalities and multiple magnitude criticalities, a centralized analysis is performed to obtain critical centralized parameters, including: Calculating the variance of the multiple frequency criticalities to obtain a frequency critical concentration parameter; Calculating the variance of the multiple magnitude criticalities to obtain a magnitude critical concentration parameter; The frequency critical concentrated parameter and the magnitude critical concentrated parameter are weightedly calculated to obtain the critical concentrated parameter.

7. The method for intelligent analysis of seismic signals during mining operations according to claim 1, characterized in that: According to the mining seismic fluctuation parameters, average criticality and critical concentration parameters, mining seismic risk prediction is performed to obtain risk prediction probability, including: According to the historical data of mining risk events, the sample mining seismic fluctuation parameter set, sample average criticality set and sample critical concentration parameter set are collected and processed, and the probability of mining risk events occurring under different sample mining seismic fluctuation parameters, sample average criticality and sample critical concentration parameters is collected to obtain the sample risk probability set; The sample seismic fluctuation parameter set, the sample average criticality set, the sample critical concentration parameter set and the sample risk probability set are used to train a seismic risk predictor; The mining seismic fluctuation parameters, average criticality and critical concentration parameters are input into the mining seismic risk predictor, and the prediction output is used to obtain the risk prediction probability.

8. An intelligent analysis device for seismic signals during mining operations, characterized in that: The steps for implementing the method for intelligent analysis of seismic signals during mining operations according to any one of claims 1 to 7, wherein the intelligent analysis device for seismic signals during mining operations comprises: A signal acquisition module, wherein the signal acquisition module is used to collect mining seismic signals at multiple locations during mining operations through a sensor array arranged in a mining area to obtain multiple mining seismic signal sequences, wherein each mining seismic signal includes a signal frequency and a signal magnitude; A critical analysis module, the critical analysis module is used to perform frequency criticality analysis on the multiple random sampling seismic signal sequences to obtain multiple frequency criticalities, and to perform magnitude criticality analysis to obtain multiple magnitude criticalities, and to calculate and obtain an average criticality; A fluctuation analysis module, the fluctuation analysis module is used to perform fluctuation analysis of the mining seismic signal sequences to obtain fluctuation parameters of the mining seismic signal sequences; The risk prediction module is used to perform centralized analysis based on the multiple frequency criticalities and multiple magnitude criticalities to obtain critical centralized parameters. Seismic wave parameters, average criticality and critical concentration parameters are used to predict the seismic risk during mining. The risk prediction probability is obtained as the result of the analysis of the seismic signal during mining.

Images