Support safety monitoring system for tunneling rock burst

Abstract

The application discloses a supporting safety monitoring system for tunneling rock burst, relates to the technical field of tunneling rock burst supporting safety monitoring, and comprises a tunnel surveying module, a rock burst analysis module, a prevention treatment analysis module and a treatment execution module. In the tunneling process, the existing supporting safety monitoring system can evaluate the rock burst risk through stress, deformation, vibration, microseismic monitoring and other monitoring methods, but still has significant defects, including inaccurate identification of high-risk areas, insufficient monitoring accuracy, unreasonable allocation of supporting requirements, untimely response of the supporting system and other problems. The rock burst analysis module and the prevention treatment analysis module are used for analysis, and the treatment execution module is used for treatment. Balanced distribution of pressure is realized, and rapid response to pressure or displacement abnormal conditions is realized. The integrated analysis and automatic supporting adjustment mode greatly improves the efficiency and safety of tunnel stability maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel excavation rock burst support safety monitoring technology, in particular to a support safety monitoring system for tunnel excavation rock burst. Background Art

[0002] During tunnel excavation, existing support safety monitoring systems assess rockburst risks through a variety of monitoring methods, including stress, deformation, vibration, and microseismic monitoring. However, these systems still have significant flaws, including inaccurate identification of high-risk areas and a lack of comprehensive analytical tools. This makes it difficult to accurately identify and delineate high-risk areas, leading to uncertainty in safety assessments and insufficient monitoring accuracy. Traditional monitoring methods often rely on a single indicator, failing to comprehensively assess rockburst risks. This leads to inaccurate and unreliable monitoring data, irrational allocation of support requirements, and a lack of comprehensive analysis of initial stress and rock mass strength in each region. This leads to irrational allocation of support materials, impacting support effectiveness, slow support system response, and insufficient flexibility in manually adjusting the support system, making it impossible to quickly respond to sudden pressure or displacement anomalies, increasing operational complexity and risks. Summary of the Invention

[0003] The purpose of the present invention is to solve the above-mentioned problem and to provide a support safety monitoring system for rock burst in tunnel excavation.

[0004] The objectives of the present invention can be achieved through the following technical solutions: a support safety monitoring system for rock burst during tunneling, comprising a tunnel survey module, a rock burst analysis module, and a prevention and treatment analysis module; the tunnel survey module is used to collect data from tunnels that are about to be mined and tunnels that have been opened, and to distinguish the data, marking the data corresponding to the tunnels that are about to be mined as T1 and the data corresponding to the opened tunnels as T2;

[0005] The rockburst analysis module is used to perform rockburst analysis on tunnels before and after mining, specifically:

[0006] Analyze T1: Standardize stress, rock mass strength, and microseismic activity data to bring them to a uniform scale; extract features from the standardized data.

[0007] Extract features from stress data: peak stress and stress concentration coefficient; extract features from microseismic data: microseismic event frequency and energy release; then divide the extracted stress features and microseismic features into high stress areas and high microseismic activity areas; perform correlation analysis on stress features and microseismic features to obtain the Pearson correlation coefficient r;

[0008] Analyze T2: Statistically analyze the changes in displacement data over the time series to observe whether there is an abnormal increase trend in displacement. Calculate the average rate of displacement change, fit the displacement data series to a straight line, and use linear regression to calculate the trend coefficient of the displacement data. Then, set a safety threshold for the displacement change rate. If the set displacement change rate exceeds the corresponding threshold, the displacement change is considered abnormal, and processing signal 1 is generated. Then, analyze the changing trends of stress and strain data to identify concentrated areas of high stress or high strain. Calculate the stress change, perform linear regression on the stress data to obtain the trend coefficient of the strain structure data, compare the set safety threshold for the stress change rate with the stress change rate, and if the stress change rate exceeds the corresponding safety threshold, it indicates the risk of stress concentration or sudden increase, and processing signal 2 is generated.

[0009] The preventive processing and analysis module is used to process and analyze the marked area, specifically:

[0010] The initial stress, rock strength and microseismic activity data collected in each area are obtained through comprehensive analysis to obtain the casting volume coefficient; the generated processed signal 1 and processed signal 2 are analyzed to obtain the support pressure.

[0011] As a preferred embodiment of the present invention, it also includes a processing execution module; during the support process, the processing execution module automatically adjusts the support force according to the real-time monitored pressure and displacement to maintain a balanced stress distribution in each area; the processing execution module is also responsible for the dynamic adjustment of material filling and pouring pressure; during the pouring process, the processing execution module is also used to calculate the actual pouring volume V of the pouring area, and perform a comprehensive calculation based on the pouring volume coefficient JZZ, the cross-sectional area A of the tunnel, and the pouring pressure P1 of the pouring area, through the formula: Output the actual pouring volume V of the pouring area, where P1 = β0 × P2, P1 is the required pouring pressure, P2 is the collected actual pressure of the area, β0 is the pouring adjustment coefficient, and P0 is the reference pressure.

[0012] As a preferred embodiment of the present invention, the specific process of normalizing the stress, rock mass strength and microseismic activity data to make their values ​​on a unified scale is as follows:

[0013] The mean μ and standard deviation σ of each data point are calculated by the formula: Where x is a data point, N is the total number of data points, i = 1, 2, ..., N; then each data point is normalized: Each data point x i Normalized to z i .

[0014] As a preferred embodiment of the present invention, the specific process of extracting the features of peak stress and stress concentration factor from stress data and extracting the features of microseismic event frequency and energy release from microseismic data is as follows:

[0015] The peak stress is obtained by finding the maximum value c in the stress data set c max =max(c), the stress concentration factor is calculated by the ratio of the maximum principal stress to the compressive strength of the material, and the formula is Output stress concentration factor SCF,c max is the calculated peak stress, C is the compressive strength of the material; the frequency of earthquake events is calculated by counting the number of microseismic events occurring in a certain period of time, using the formula: Output the microseismic event frequency WPL, H is the total number of microseismic events within the time interval Δt; energy release is calculated by calculating the energy release E of each microseismic event and summing it within a certain time period: from the formula: Output energy release ESF, s = 1, 2, ..., H, H is the total number of microseismic events.

[0016] As a preferred embodiment of the present invention, the specific process of dividing the extracted stress characteristics and microseismic characteristics into high stress areas and high microseismic activity areas is as follows:

[0017] In the model, the stress distribution map is determined to identify the area with high stress, which is divided into high stress area; the frequency and energy release of microseismic events are counted and compared to obtain the area with frequent microseismic activity, which is divided into high microseismic activity area; the high stress area and the high microseismic activity area are superimposed; if the two areas overlap highly, it indicates that the rock burst risk in this area is high, and it is divided into a key attention activity area, a general attention activity area, or an ultra-key attention activity area. The division is judged by the correlation between stress characteristics and microseismic characteristics, and the Pearson correlation coefficient r is calculated. When r = 1, it indicates a perfect positive correlation, and it is divided into an ultra-key attention activity area, indicating that the stress characteristics and microseismic characteristics increase and decrease synchronously under certain circumstances; when r = -1, it indicates a perfect negative correlation, and it is divided into a general attention activity area, indicating that when one characteristic increases, the other characteristic decreases; when r = 0, it indicates no correlation, and it is divided into a key attention activity area, indicating that there is no obvious relationship between the two.

[0018] As a preferred embodiment of the present invention, the specific process of obtaining the initially collected stress, rock mass strength and microseismic activity data in each area and performing comprehensive analysis to obtain the casting volume coefficient is as follows:

[0019] By formula: The output calculation results in the casting volume coefficient JZZ, where c' is the initial stress value, S is the acquired rock mass strength, f is the frequency of microseismic activity, E is the energy release, ω1, ω2 and ω3 are the preset weight coefficients. Indicates the relative pressure on the rock mass.

[0020] As a preferred embodiment of the present invention, the specific process of analyzing the generated processing signal 1 and the processed signal 2 to obtain the support pressure is:

[0021] Analyze the processing signal 1: obtain the initial position data of the marker, calculate the distance between the mobile support and the position corresponding to the processing signal 1; the processing execution module moves the support system to the specified position through the positioning module; when the support system is in place, apply initial pressure, according to the pressure demand and balance analysis of each area of ​​the support, according to the formula: P 支护 =α×P 监测 , output support pressure P 支护 , P 监测 is the monitored regional pressure, and α is the control coefficient. If the pressure or displacement is found to be beyond the target range during the support process, the support system controlled by the processing execution module will adjust the support force.

[0022] Analyze the processing signal 2: Same as processing signal 1, move the support system to the specified position; when the support system is in place, apply initial pressure first; based on the pressure demand and balance analysis of each support area, the hydraulic support system will adjust the support force.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. This invention uses standardized processing, feature extraction, and regional division within the rockburst analysis module to comprehensively analyze tunnel stress, rock mass strength, and microseismic activity, enabling precise identification of high-risk areas. This module not only assesses key indicators such as peak stress, stress concentration factor, microseismic frequency, and energy release, but also determines the rockburst risk level in different areas through correlation analysis, providing a scientific basis for tunnel safety assessments. Furthermore, by detecting and generating processing signals based on displacement and stress change trends, early warnings can be issued before risks escalate and treatment measures can be triggered, effectively ensuring the long-term stability and safety of tunnel structures.

[0025] 2. This invention uses a preventive treatment analysis module to calculate the casting volume coefficient JZZ, comprehensively analyzing the initial stress, rock mass strength, and microseismic activity in each area to provide support requirements tailored to the risk level and ensure the rational allocation of support materials. Simultaneously, this module automatically analyzes the generated processing signals and utilizes a positioning module to precisely move the support system into position and dynamically adjust the support force, achieving balanced pressure distribution and rapidly responding to abnormal pressure or displacement. This integrated analysis and automated support adjustment significantly improves the efficiency and safety of tunnel stability maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0027] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0028] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] It should be understood that the terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0030] It should also be understood that the terminology used in this disclosure is for the purpose of describing specific embodiments only and is not intended to limit the disclosure. As used in this disclosure and the claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should be further understood that the term "and / or" as used in this disclosure and the claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0031] See also Figure 1 As shown, a support safety monitoring system for rock burst in tunnel excavation includes a tunnel survey module, a rock burst analysis module, a prevention and treatment analysis module and a treatment execution module;

[0032] The tunnel survey module is used to collect data from tunnels that are about to be mined and those that have been opened, and to distinguish the data. Specifically:

[0033] For tunnels to be mined, the survey team first conducts a preliminary safety assessment and environmental inspection on-site. Drones can be used for aerial photography to obtain an overview and preliminary data of the area. Next, the terrain is measured, with multiple measurement points selected in front of the tunnel to be mined, covering the entire area. Laser rangefinders or total stations are used for measurement, and the coordinates, ground height, and relative position of each measurement point are recorded. The measured data is imported into a computer and processed using Geographic Information System (GIS) software to create a detailed topographic map. Important terrain features (such as mountains, rivers, and roads) and potential safety zones are marked, and the data corresponding to the mined tunnel is labeled T1.

[0034] For tunnels that have already been opened, displacement sensors are installed at key locations such as the vault, side walls, and floor to monitor possible structural displacement or deformation. Data are regularly recorded and trends observed to identify potential structural problems such as settlement, heave, or lateral displacement. Furthermore, stress and strain sensors are installed on the tunnel walls to monitor internal stress changes in real time. The data corresponding to the opened tunnel is marked as T2.

[0035] The rockburst analysis module is used to perform rockburst analysis on tunnels before and after mining. Specifically:

[0036] Analysis of T1: Standardize the stress, rock strength, and microseismic activity data (different features have different units and magnitudes, which lead to some features dominating the model training and thus affecting the prediction results; data standardization can convert all features to the same scale, so that the model can treat each feature more fairly). Make their values ​​on a unified scale, calculate the mean μ and standard deviation σ of each data point, and use the formula: Where x is a data point, N is the total number of data points, i = 1, 2, ..., N; then each data point is normalized: Each data point x i Normalized to z i ;(normalized value z i Indicates the degree of deviation of the data point from the mean. The mean of the transformed data is 0 and the standard deviation is 1).

[0037] Then extract features from the standardized data.

[0038] Extract features from stress data: peak stress and stress concentration factor, where peak stress is: find the maximum value in the stress data set c (peak stress is the maximum stress that the rock mass withstands during excavation and is an important indicator for evaluating rock mass stability), c max =max(c); The stress concentration factor is calculated by the ratio of the maximum principal stress to the compressive strength of the material, and is calculated by the formula Output stress concentration factor SCF (SCF is an important parameter for evaluating the potential rock burst risk in high stress areas. The larger the value, the lower the rock mass stability). max is the peak stress calculated previously, and C is the compressive strength of the material;

[0039] Extract from microseismic data: microseismic event frequency and energy release, where the frequency of microseismic events is calculated by counting the number of microseismic events occurring in a certain period of time, using the formula: Output the microseismic event frequency WPL (microseismic event frequency reflects the active degree of stress release inside the rock mass. When the frequency is high, it may indicate an increased risk of rock burst), H is the total number of microseismic events within the time interval Δt; energy release is calculated by calculating the energy release E of each microseismic event and summing it over a certain period of time: from the formula: Output energy release ESF (the total amount of energy release can reflect the energy accumulation inside the rock mass, and a large energy release may indicate a potential rock burst), H is the total number of microseismic events, s = 1, 2, ..., H;

[0040] The extracted stress characteristics and microseismic characteristics are then divided into regions: the stress distribution map is determined in the model to identify areas with high stress and divide them into "high stress areas"; the frequency and energy release of microseismic events are counted and compared to obtain areas with frequent microseismic activity, which are divided into "microseismic high activity areas"; the high stress areas and microseismic high activity areas are superimposed; if the two areas highly overlap, it indicates that the rock burst risk in this area is high, and it is divided into "key concern activity areas", "general concern activity areas" or "super key concern activity areas". The division is judged by the correlation between stress characteristics and microseismic characteristics;

[0041] Correlation analysis between stress characteristics and microseismic characteristics: by formula Output Pearson correlation coefficient r, x i and y i Represents a single data point of two features, x i Represents the stress concentration factor SCF of a certain area; y i represents the frequency of microseismic events in the area; and They represent the average values ​​of these characteristics and are used to calculate the degree of data deviation. The Pearson coefficient r reflects the correlation between the two characteristics: when r = 1, it indicates a complete positive correlation, which is classified as the "super-focused activity area", indicating that the stress characteristics and microseismic characteristics increase and decrease synchronously under certain circumstances; when r = -1, it indicates a complete negative correlation, which is classified as the "general attention activity area", indicating that when one characteristic increases, the other characteristic decreases; when r = 0, it indicates no correlation, which is classified as the "focused activity area", indicating that there is no obvious relationship between the two.

[0042] Analysis of T2: Displacement sensors are installed at key locations such as the tunnel vault, side walls, and floor, and are labeled as position data. Stress and strain sensors record changes in the tunnel structure's horizontal and vertical displacements to detect settlement, uplift, or lateral displacement, and are labeled as strain structure data. The first recorded data collected after the sensor installation is labeled as initial position data, and the first recorded data collected after the stress and strain sensor installation is labeled as initial strain structure data.

[0043] Then analyze the changes in displacement data in time series to observe whether there is an abnormal increase trend in displacement; calculate the average displacement by setting the displacement at time t j The displacement data collected is d j , and calculate the average displacement increment Δd in each time period: Where k is the number of observation time intervals, and j = 1, 2, ..., k, d j+1 -d j is the difference between two consecutive displacement data; then analyze the displacement change and calculate the average rate v of displacement change: Where Δt1 is the time interval between the two observation time points; finally, the displacement data series is fitted into a straight line, and linear regression is used to calculate the trend coefficient β of the displacement data; the regression equation of linear regression is: d(t1) = α + βt1, where d(t) is the displacement value at time t, and β is the rate of change of displacement over time, with a positive value indicating an increase in displacement and a negative value indicating a decrease in displacement; a safety threshold for the displacement change rate v is then set. If v exceeds the corresponding threshold, the displacement change is considered abnormal, and processing signal 1 is generated;

[0044] Then, by analyzing the changing trends of stress and strain data, we can identify concentrated areas of high stress or high strain. Let the stress data collected at time tj be cj, and calculate the average stress change Δc in each time period: Then calculate the stress change rate v c : Similarly, linear regression is performed on the stress data to calculate the trend coefficient β of the strain structure data. c , then the regression equation of linear regression is: c(t1)=αc+βct1 where β c Indicates the rate of change of stress over time. A positive value indicates an increase in stress, and a negative value indicates a decrease in stress. Set the stress change rate β c The safety threshold and stress change rate β c For comparison, if β c Exceeding the corresponding safety threshold indicates the risk of stress concentration or sudden increase, and generates processing signal 2;

[0045] The preventive treatment and analysis module is used to process and analyze the marked areas, which are collectively referred to as "high stress areas", "microseismic high activity areas", "key attention activity areas", "general attention activity areas", and "super key attention activity areas". Specifically:

[0046] The initially collected stress, rock mass strength and microseismic activity data in each area are obtained for comprehensive analysis, using the formula: The output calculation results in the casting volume coefficient JZZ, where c' is the initial stress value, S is the collected rock mass strength, f is the microseismic activity frequency, E is the energy release, and ω1, ω2, and ω3 are preset weight coefficients. The specific values ​​can be adjusted according to the risk level of the area. Among them, c' / S represents the relative pressure on the rock mass. The larger the value, the closer the rock mass is to a state of failure and requires a larger support casting volume. The microseismic activity frequency f reflects the activity level of rock mass fracture activity in the area. The higher the value, the more unstable the internal structure of the rock mass and the higher the support demand. ω3 reflects the casting volume requirement for foundation support. Even if the stress and microseismic activity in the area are low, a certain casting volume is still required to provide foundation support.

[0047] The preventive processing analysis module is also used to analyze the generated processing signal 1 and the processing signal 2, specifically:

[0048] Analyze the processing signal 1: obtain the initial position data of the marker, select the appropriate specifications of the control mobile support according to the initial position data, and calculate the distance between the mobile support and the position corresponding to the processing signal 1; the processing execution module moves the support system accurately to the specified position through the positioning module; when the support system is in place, it first applies initial pressure; according to the pressure demand and balance analysis of each support area, the hydraulic support system will automatically adjust the support force to ensure balanced stress distribution in each area. The specific adjustment process is: P 支护 =α×P 监测 , P 支护 is the support pressure, P 监测 is the monitored regional pressure, α is the control coefficient, and the support force is dynamically adjusted according to the preset threshold. If the pressure or displacement is found to exceed the target range during the support process, the support system controlled by the processing execution module will automatically adjust the support force.

[0049] Analyze the second processed signal: Similarly, move the support system precisely to the designated position. Once the support system is in place, apply initial pressure. Based on the pressure requirements and balance analysis of each support area, the hydraulic support system automatically adjusts the support force.

[0050] The processing execution module is also used to calculate the actual pouring volume V of the pouring area, which is calculated comprehensively based on the pouring volume coefficient JZZ, the cross-sectional area A of the tunnel, and the pouring pressure P1 of the pouring area, using the formula: Output the actual pouring volume V of the pouring area, where P1 = β0 × P2, P1 is the required pouring pressure, P2 is the actual pressure of the area collected, β0 is the pouring adjustment coefficient, which is determined according to the geological conditions of the area, rock strength and other factors; P0 is the reference pressure, which is used to convert the pouring pressure into a relative proportion (the reference pressure can be the on-site safety standard pressure or an empirical value); the processing execution module then fills the material according to the calculated actual pouring volume V. During the pouring process, the pressure, volume filling amount and support effect are monitored in real time. If any deviation is found, the pouring pressure or material filling amount is automatically adjusted to ensure that the support effect meets the requirements.

[0051] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A support safety monitoring system for rock burst during tunneling, comprising a tunnel survey module, a rock burst analysis module, a preventive treatment analysis module, and a treatment execution module; characterized in that: The tunnel survey module is used to collect data from tunnels that are about to be mined and those that have been opened, and to distinguish the data, marking the data corresponding to the tunnels that are about to be mined as T1 and the data corresponding to the opened tunnels as T2; The rockburst analysis module is used to perform rockburst analysis on tunnels before and after mining, specifically: Analyze T1: Standardize stress, rock mass strength, and microseismic activity data to bring them to a uniform scale; extract features from the standardized data. Extract features from stress data: peak stress and stress concentration coefficient; extract features from microseismic data: microseismic event frequency and energy release; then divide the extracted stress features and microseismic features into high stress areas and high microseismic activity areas; perform correlation analysis on stress features and microseismic features to obtain the Pearson correlation coefficient r; Analyze T2: Statistically analyze the changes in displacement data over the time series to observe whether there is an abnormal increase trend in displacement. Calculate the average rate of displacement change, fit the displacement data series to a straight line, and use linear regression to calculate the trend coefficient of the displacement data. Then, set a safety threshold for the displacement change rate. If the set displacement change rate exceeds the corresponding threshold, the displacement change is considered abnormal, and processing signal 1 is generated. Then, analyze the changing trends of stress and strain data to identify concentrated areas of high stress or high strain. Calculate the stress change, perform linear regression on the stress data to obtain the trend coefficient of the strain structure data, compare the set safety threshold for the stress change rate with the stress change rate, and if the stress change rate exceeds the corresponding safety threshold, it indicates the risk of stress concentration or sudden increase, and processing signal 2 is generated. The preventive processing and analysis module is used to process and analyze the marked area, specifically: The initial collected stress, rock mass strength and microseismic activity data in each area are obtained through comprehensive analysis to obtain the casting volume coefficient: Output the calculated pouring volume coefficient JZZ, is the initial stress value, S is the acquired rock mass strength, f is the frequency of microseismic activity, E is the energy release, ω1, ω2 and ω3 are the preset weight coefficients, Indicates the relative pressure borne by the rock mass; the generated processing signal 1 and processing signal 2 are analyzed to obtain the support pressure, specifically: Analyze processing signal 1: obtain the initial position data of the mark, calculate the distance between the mobile support and the position corresponding to processing signal 1; the processing execution module moves the support system to the specified position through the positioning module; when the support system is in place, apply preliminary pressure, according to the pressure demand and balance analysis of each support area, by formula: P 支护 =α×P 监测 , output support pressure P 支护 , P 监测 is the monitored regional pressure, and α is the control coefficient. If the pressure or displacement is found to be beyond the target range during the support process, the support system controlled by the processing execution module will adjust the support force. Analyze processing signal 2: As with processing signal 1, move the support system to the designated location. Once the support system is in place, apply initial pressure. Based on the pressure requirements and balance analysis of each support area, the hydraulic support system adjusts the support force. During the support process, the processing execution module automatically adjusts the support force according to the real-time monitored pressure and displacement to maintain a balanced stress distribution in each area. The processing execution module is also responsible for the dynamic adjustment of material filling and pouring pressure. During the pouring process, the processing execution module is also used to calculate the actual pouring volume V of the pouring area, and performs a comprehensive calculation based on the pouring volume coefficient JZZ, the cross-sectional area A of the tunnel, and the pouring pressure P1 of the pouring area, through the formula: Output the actual pouring volume V of the pouring area, where P1=β0×P2, P1 is the required pouring pressure, P2 is the collected actual pressure of the area, β0 is the pouring adjustment coefficient, and P0 is the base pressure.

2. A support safety monitoring system for rock burst in tunneling according to claim 1, characterized in that: The specific process of standardizing the stress, rock mass strength and microseismic activity data to make their values ​​on a unified scale is as follows: The mean μ and standard deviation σ of each data point are calculated by the formula: , where x is a data point, N is the total number of data points, i=1, 2, ..., N; then each data point is normalized: , each data point x i Normalized to z i .

3. A support safety monitoring system for rock burst in tunneling according to claim 2, characterized in that: The feature extraction from stress data: Peak stress and stress concentration factor are extracted from microseismic data: The specific process of microseismic event frequency and energy release is: The peak stress is obtained by finding the maximum value c in the stress data set c max =max(c), the stress concentration factor is calculated by the ratio of the maximum principal stress to the compressive strength of the material, and the formula is Output stress concentration factor SCF,c max is the calculated peak stress, C is the compressive strength of the material; the frequency of earthquake events is calculated by counting the number of microseismic events occurring in a certain period of time, using the formula: Output the microseismic event frequency WPL, H is the total number of microseismic events within the time interval Δt; energy release is calculated by calculating the energy release E of each microseismic event and summing it within a certain time period: from the formula: Output energy release ESF, s = 1, 2, ..., H, H is the total number of microseismic events.

4. A support safety monitoring system for rock burst in tunneling according to claim 1, characterized in that: The specific process of dividing the extracted stress characteristics and microseismic characteristics into high stress areas and high microseismic activity areas is as follows: In the model, the stress distribution map is determined to identify areas with high stress and classify them as high-stress areas. The frequency and energy release of microseismic events are statistically analyzed and compared to obtain areas with frequent microseismic activity, which are classified as high-microseismic activity areas. The high-stress area and the high-microseismic activity area are superimposed. If the two areas highly overlap, it indicates that the rockburst risk in this area is high, and they are classified as key attention activity areas, general attention activity areas, or super key attention activity areas. The classification is judged by the correlation between stress characteristics and microseismic characteristics. The Pearson correlation coefficient r is calculated. When r=1, it indicates a perfect positive correlation, and the area is classified as a super key attention activity area, indicating that the stress characteristics and microseismic characteristics increase and decrease synchronously under certain circumstances. When r=−1, it indicates a perfect negative correlation, and the area is classified as a general attention activity area, indicating that when one characteristic increases, the other decreases. When r=0, it indicates no correlation, and the area is classified as a key attention activity area, indicating that there is no obvious relationship between the two.

Images