Mine rock burst multi-parameter coupling real-time monitoring and early warning system

Abstract

The invention discloses a mine rock burst multi-parameter coupling real-time monitoring and early warning system, and relates to the technical field of mine safety monitoring. The system comprises a multi-parameter acquisition module, a data transmission module, a data preprocessing module, a multi-parameter coupling analysis module, an early warning decision module and a terminal display module. The multi-parameter acquisition module is used for cooperatively acquiring rock mass stress, surrounding rock displacement, rock mass vibration and other various parameters related to rock burst; the data transmission module adopts a wired and wireless mixed transmission mode to realize real-time data transmission; the early warning decision module generates a corresponding early warning instruction through comparison of multiple levels of early warning thresholds; and the terminal display module realizes information real-time display, sound-light alarm and remote monitoring. According to the invention, the limitation of single parameter monitoring is overcome, the accuracy and timeliness of rock burst early warning are improved, the adaptability is high, and the safety production of mines can be effectively guaranteed.

Description

Technical Field

[0001] This invention relates to the field of mine safety monitoring technology, and in particular to a real-time monitoring and early warning system for multi-parameter coupling of rockburst in mines. Background Technology

[0002] Rock bursts are a common and major geological hazard in mining operations. Essentially, they occur when the rock mass surrounding a mine shaft or stope experiences a sudden release of energy under high ground stress, resulting in rapid deformation, destruction, and violent vibrations. Rock bursts are characterized by their suddenness and destructiveness, easily causing serious consequences such as tunnel collapses, equipment damage, and casualties, severely hindering safe production and efficient mining operations.

[0003] To mitigate the hazards of rockbursts, extensive research has been conducted both domestically and internationally on rockburst monitoring and early warning systems, resulting in the development of a range of monitoring equipment and systems. Currently, existing methods for monitoring rockbursts in mines primarily include single-parameter monitoring, such as stress monitoring, displacement monitoring, and vibration monitoring. Stress monitoring typically utilizes stress sensors to acquire data on rock mass stress changes; displacement monitoring uses displacement gauges to monitor the deformation and displacement of the surrounding rock in tunnels; and vibration monitoring employs microseismic sensors or seismographs to capture rock mass vibration signals.

[0004] However, existing technologies have the following shortcomings: First, single-parameter monitoring cannot comprehensively reflect the complex gestation process of rockbursts. Rockbursts are the result of multiple factors, including rock mass stress, displacement, vibration, and water content. Relying solely on changes in a single parameter cannot accurately determine the gestation state and risk of rockbursts, easily leading to misjudgments or omissions. Second, existing monitoring systems have weak parameter coupling analysis capabilities. Most can only achieve independent acquisition and simple display of each parameter, failing to establish an intrinsic correlation model between multiple parameters, and thus cannot achieve accurate early warning of rockbursts through multi-parameter collaborative analysis. Third, some monitoring systems suffer from data transmission delays and untimely early warning responses, making it difficult to meet the needs of real-time monitoring and early warning of rockbursts, and failing to provide sufficient emergency response time for on-site personnel. Fourth, existing early warning models have poor adaptability. Different mines have significantly different geological conditions and mining methods, and universal early warning thresholds and models are difficult to adapt to different mining scenarios, resulting in low early warning accuracy.

[0005] Therefore, in view of the shortcomings of the existing technology, this invention proposes a mine rockburst monitoring and early warning system that can realize multi-parameter collaborative acquisition, accurate coupling analysis, real-time and efficient early warning, and has strong adaptability. Summary of the Invention

[0006] The purpose of this invention is to overcome the limitations of existing mine rockburst monitoring and early warning systems, such as the single-parameter monitoring limitation, weak multi-parameter coupling analysis capability, untimely early warning, and poor adaptability, and to provide a real-time monitoring and early warning system for mine rockburst with multi-parameter coupling.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] A real-time monitoring and early warning system for multi-parameter coupled rockburst in mines includes a multi-parameter acquisition module, a data transmission module, a data preprocessing module, a multi-parameter coupled analysis module, an early warning decision module, and a terminal display module.

[0009] The multi-parameter acquisition module is used to acquire various raw monitoring parameters related to rockburst in the target monitoring area of ​​the mine. The raw monitoring parameters include rock stress parameters, surrounding rock displacement parameters, rock vibration parameters, environmental temperature and humidity parameters, and rock water content parameters.

[0010] The data transmission module is used to transmit the raw monitoring parameters collected by the multi-parameter acquisition module to the data preprocessing module in real time;

[0011] The data preprocessing module is used to perform noise reduction, outlier removal, and data standardization on the original monitoring parameters to obtain standardized monitoring data.

[0012] The multi-parameter coupling analysis module is used to calculate the rockburst risk assessment value based on standardized monitoring data and through the constructed multi-parameter coupling analysis model.

[0013] The early warning decision module is used to compare the rockburst risk assessment value with the preset early warning threshold, and generate the corresponding early warning level and early warning instruction based on the comparison result;

[0014] The terminal display module is used to display standardized monitoring data, rockburst risk assessment values, early warning levels, and early warning instructions in real time, and supports audible and visual alarms for early warning information and historical data queries.

[0015] Furthermore, the multi-parameter acquisition module includes a stress monitoring unit, a displacement monitoring unit, a vibration monitoring unit, a temperature and humidity monitoring unit, and a moisture content monitoring unit;

[0016] The stress monitoring unit includes multiple fiber optic stress sensors distributed in the surrounding rock of the roadway in the target monitoring area, used to collect normal stress and shear stress data of the rock mass, with a sampling frequency set to 1-5Hz.

[0017] The displacement monitoring unit includes multiple laser displacement sensors arranged on the top and bottom plates and both sides of the roadway, used to collect vertical and horizontal displacement data of the surrounding rock, with a sampling frequency set to 0.5-2Hz.

[0018] The vibration monitoring unit includes multiple microseismic sensors distributed in the target monitoring area, used to collect data on the amplitude, frequency, duration and vibration energy of rock mass vibration, with the sampling frequency set to 100-500Hz.

[0019] The temperature and humidity monitoring unit includes multiple temperature and humidity sensors arranged in the tunnel to collect ambient temperature and relative humidity data of the monitoring area, with a sampling frequency set to 0.1-0.5Hz;

[0020] The moisture content monitoring unit includes multiple high-frequency capacitive moisture content sensors inserted into the surrounding rock to collect moisture content data of the rock mass, with a sampling frequency set to 0.1-0.5Hz.

[0021] Furthermore, the data transmission module adopts a hybrid transmission method of "wired transmission + wireless transmission", including an optical fiber transmission unit, a LoRa wireless transmission unit, and a data aggregation node;

[0022] The optical fiber transmission unit is used to connect sensors located in the same tunnel area to achieve high bandwidth and low latency data transmission.

[0023] The LoRa wireless transmission unit is used to connect sensors located in remote areas or areas where wiring is difficult, enabling long-distance, low-power data transmission;

[0024] The data aggregation node is used to receive the raw monitoring parameters transmitted by each sensor through the optical fiber transmission unit or the LoRa wireless transmission unit. After the data is initially aggregated and integrated, it is transmitted to the data preprocessing module through the industrial Ethernet.

[0025] Furthermore, the data preprocessing module's processing procedure includes the following steps:

[0026] S1. Noise Reduction Processing: The original monitoring parameters are denoised using a wavelet threshold noise reduction algorithm to remove environmental interference and sensor noise. The functional expression for wavelet threshold noise reduction is:

[0027]

[0028] Among them, w j,k The original wavelet coefficients, w′ j,k Here are the denoised wavelet coefficients, and λ is the wavelet threshold. σ is the noise standard deviation, and N is the data length;

[0029] S2. Outlier Removal: Outliers are removed from the noise-reduced monitoring data using the Grubbs criterion.

[0030] S3. Data Standardization: The monitoring data after outlier removal is standardized using the min-max standardization method. The standardization formula is as follows:

[0031]

[0032] Where, x′ i For standardized monitoring data, x i For the original monitoring data after removing outliers, x max x is the maximum value of this parameter. min This is the minimum value of the parameter.

[0033] Furthermore, the multi-parameter coupling analysis module includes a coupling model construction unit and a risk assessment value calculation unit;

[0034] The coupling model construction unit constructs a multi-parameter coupling analysis model based on the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method. The specific steps are as follows:

[0035] T1. Establish a hierarchical structure: take rock burst risk assessment as the target layer, rock mass stress, surrounding rock displacement, rock mass vibration, ambient temperature and humidity, and rock mass water content as the criteria layer, and take the specific monitoring indicators corresponding to each criteria layer as the indicator layer.

[0036] T2. Determine the weights: The weights of each parameter in the criterion layer and each indicator in the indicator layer are determined by using the analytic hierarchy process. By constructing a judgment matrix, the largest eigenvalue of the judgment matrix and its corresponding eigenvector are calculated. After normalizing the eigenvector, the weight vector is obtained. The weight allocation is verified to be reasonable by the consistency test.

[0037] T3. Constructing a fuzzy evaluation matrix: Based on standardized monitoring data, determine the membership function of each indicator and construct a fuzzy evaluation matrix;

[0038] T4. Fuzzy comprehensive evaluation: The comprehensive evaluation results of each criterion layer are calculated using fuzzy matrix multiplication, and then the risk assessment value of rockburst at the target layer is calculated by combining the weights of the criterion layers.

[0039] The risk assessment value calculation unit is used to call the constructed multi-parameter coupled analysis model, input standardized monitoring data, and calculate the rockburst risk assessment value S, where the value range of S is [0,10].

[0040] Furthermore, the early warning decision module includes an early warning threshold setting unit, a risk comparison unit, and an early warning instruction generation unit;

[0041] The early warning threshold setting unit supports customizing and setting multi-level early warning thresholds according to the geological conditions, mining methods, and historical rock burst data of different mines. By default, four-level early warning thresholds are set: risk-free threshold S ≤ 3, low-risk threshold 3 < S ≤ 5, medium-risk threshold 5 < S ≤ 8, and high-risk threshold S > 8;

[0042] The risk comparison unit is used to compare the rock burst risk assessment value S with the preset early warning threshold in real time to determine the corresponding early warning level;

[0043] The early warning instruction generation unit is used to generate corresponding early warning instructions according to the determined early warning level.

[0044] Furthermore, the terminal display module includes a monitoring center terminal, an on-site early warning terminal, and a mobile terminal;

[0045] The monitoring center terminal uses an industrial-grade monitoring host equipped with a large-screen display device to display information such as monitoring data, risk assessment values, and early warning levels in real time, and supports historical data query and report generation;

[0046] The on-site early warning terminal is arranged at key positions in the mine shaft and uses an audible and visual alarm and an LED display screen for audible and visual alarms and emergency prompt displays in case of medium and high risks;

[0047] The mobile terminal supports managers to receive early warning information and view monitoring data in real time through the mobile phone APP.

[0048] Furthermore, it also includes a power supply module. The power supply module adopts a hybrid power supply method of "mains electricity + backup battery + solar auxiliary power supply" to provide stable power supply for each module of the system.

[0049] The beneficial effects of the present invention are as follows:

[0050] 1. Through the multi-parameter acquisition module, the present invention realizes the collaborative acquisition of multiple parameters related to rock burst, such as rock mass stress, surrounding rock displacement, rock mass vibration, environmental temperature and humidity, and rock mass moisture content, which can comprehensively reflect the complex gestation process of rock burst occurrence, overcome the limitations of single-parameter monitoring in the prior art, and lay a data foundation for subsequent accurate coupling analysis.

[0051] 2. The present invention constructs a multi-parameter coupling analysis model based on the analytic hierarchy process and the fuzzy comprehensive evaluation method. By determining the weights of each parameter and index and combining the fuzzy comprehensive evaluation, it realizes the deep coupling analysis of multiple parameters, can accurately calculate the rock burst risk assessment value, and improves the accuracy of rock burst risk assessment.

[0052] 3. This invention adopts a hybrid data transmission method of "wired + wireless", which realizes real-time and efficient transmission of monitoring data. At the same time, through the real-time comparative analysis of the early warning decision module and the multi-level early warning mechanism, early warning instructions can be quickly generated and pushed to each terminal, ensuring the timeliness of the early warning and providing sufficient emergency response time for on-site personnel.

[0053] 4. This invention supports custom setting of early warning thresholds according to the actual conditions of different mines. It is also equipped with a system self-diagnosis module and a hybrid power supply module, which improves the adaptability, stability and reliability of the system and can be widely applied to mines with different geological conditions and mining methods. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a module interaction diagram of the present invention;

[0056] Figure 2 This is a diagram of the overall system architecture of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0058] A real-time monitoring and early warning system for multi-parameter coupled rockburst in mines includes a multi-parameter acquisition module, a data transmission module, a data preprocessing module, a multi-parameter coupled analysis module, an early warning decision module, and a terminal display module.

[0059] The multi-parameter acquisition module is used to collect various raw monitoring parameters related to rockburst in the target monitoring area of ​​the mine. The raw monitoring parameters include rock stress parameters, surrounding rock displacement parameters, rock vibration parameters, environmental temperature and humidity parameters, and rock water content parameters.

[0060] The data transmission module is used to transmit the raw monitoring parameters collected by the multi-parameter acquisition module to the data preprocessing module in real time;

[0061] The data transmission module adopts a hybrid transmission method of "wired transmission + wireless transmission", including an optical fiber transmission unit, a LoRa wireless transmission unit, and a data aggregation node;

[0062] The fiber optic transmission unit is used to connect sensors located in the same tunnel area to achieve high-bandwidth, low-latency data transmission;

[0063] LoRa wireless transmission units are used to connect sensors located in remote or difficult-to-wire areas, enabling long-distance, low-power data transmission.

[0064] The data aggregation node is used to receive the raw monitoring parameters transmitted by each sensor through the fiber optic transmission unit or the LoRa wireless transmission unit. After the data is initially aggregated and integrated, it is transmitted to the data preprocessing module via industrial Ethernet.

[0065] The multi-parameter acquisition module includes a stress monitoring unit, a displacement monitoring unit, a vibration monitoring unit, a temperature and humidity monitoring unit, and a moisture content monitoring unit;

[0066] The stress monitoring unit includes multiple fiber optic stress sensors distributed in the surrounding rock of the roadway in the target monitoring area, used to collect normal stress and shear stress data of the rock mass, with a sampling frequency set to 1-5Hz;

[0067] The displacement monitoring unit includes multiple laser displacement sensors arranged on the top and bottom plates and both sides of the roadway to collect vertical and horizontal displacement data of the surrounding rock, with a sampling frequency set to 0.5-2Hz.

[0068] The vibration monitoring unit includes multiple microseismic sensors distributed in the target monitoring area to collect data on the amplitude, frequency, duration, and energy of rock mass vibrations. The sampling frequency is set to 100-500Hz.

[0069] The temperature and humidity monitoring unit includes multiple temperature and humidity sensors arranged in the tunnel to collect ambient temperature and relative humidity data of the monitoring area, with a sampling frequency set to 0.1-0.5Hz;

[0070] The moisture content monitoring unit includes multiple high-frequency capacitive moisture content sensors inserted into the surrounding rock to collect moisture content data of the rock mass, with a sampling frequency set to 0.1-0.5Hz.

[0071] The data preprocessing module is used to reduce noise, remove outliers, and standardize the raw monitoring parameters to obtain standardized monitoring data.

[0072] The data preprocessing module includes the following steps:

[0073] S1. Noise Reduction Processing: The original monitoring parameters are denoised using a wavelet threshold noise reduction algorithm to remove environmental interference and sensor noise. The functional expression for wavelet threshold noise reduction is:

[0074]

[0075] Among them, w j,k The original wavelet coefficients, w′ j，k Here are the denoised wavelet coefficients, and λ is the wavelet threshold. σ is the noise standard deviation, and N is the data length;

[0076] S2. Outlier Removal: Outliers are removed from the noise-reduced monitoring data using the Grubbs criterion. The specific steps are as follows:

[0077] S21. Calculate the average value of the monitoring data after noise reduction. and standard deviation s;

[0078] S22. Calculate the absolute value of the deviation between each data point and the average value. And compare it with the Grubbs critical value G(α,n)×s, where α is the significance level and n is the amount of data;

[0079] S23, if The data point is then identified as an outlier and removed.

[0080] S3. Data Standardization: The min-max standardization method is used to standardize the monitoring data after removing outliers, converting monitoring parameters of different dimensions and orders of magnitude into dimensionless data of a unified standard. The standardization formula is:

[0081]

[0082] Where, x′ i For standardized monitoring data, x i For the original monitoring data after removing outliers, x max x is the maximum value of this parameter. min This is the minimum value of the parameter.

[0083] The multi-parameter coupling analysis module is used to calculate the risk assessment value of rockburst based on standardized monitoring data and through the constructed multi-parameter coupling analysis model;

[0084] The early warning decision module is used to compare the risk assessment value of rockburst with the preset early warning threshold, and generate the corresponding early warning level and early warning instruction based on the comparison result;

[0085] The terminal display module is used to display standardized monitoring data, rockburst risk assessment values, early warning levels, and early warning instructions in real time, and supports audible and visual alarms for early warning information and historical data queries.

[0086] The multi-parameter coupling analysis module includes a coupling model construction unit and a risk assessment value calculation unit;

[0087] The coupling model construction unit constructs a multi-parameter coupling analysis model based on the analytic hierarchy process and fuzzy comprehensive evaluation method. The specific steps are as follows:

[0088] T1. Establish a hierarchical structure: take rock burst risk assessment as the target layer, rock mass stress, surrounding rock displacement, rock mass vibration, ambient temperature and humidity, and rock mass water content as the criteria layer, and take the specific monitoring indicators corresponding to each criteria layer as the indicator layer.

[0089] T2. Determining Weights: The weights of each parameter in the criterion layer and each indicator in the indicator layer are determined using the analytic hierarchy process (AHP). This is achieved by constructing a judgment matrix, calculating its largest eigenvalue and corresponding eigenvector, and then normalizing the eigenvectors to obtain the weight vector W = [w1, w2, ..., w...]. m ], where m is the number of parameters or indicators; the consistency test formula for the judgment matrix is:

[0090]

[0091] Where, λ max To determine the largest eigenvalue of the judgment matrix, CI is the consistency index, and RI is the average random consistency index. When CR < 0.1, it is determined that the judgment matrix has satisfactory consistency and the weight allocation is reasonable.

[0092] T3. Constructing the fuzzy evaluation matrix: Based on standardized monitoring data, determine the membership function of each indicator and construct the fuzzy evaluation matrix R = (r ij ) m×n , where r ij This represents the membership degree of the i-th indicator to the j-th evaluation level, where n is the number of evaluation levels;

[0093] T4. Fuzzy Comprehensive Evaluation: The comprehensive evaluation results of each criterion layer are calculated using fuzzy matrix multiplication. Then, the risk assessment value of rockburst at the target layer is calculated by combining the weights of the criterion layers. The calculation formula is as follows:

[0094]

[0095] Where B is the fuzzy comprehensive evaluation vector, ο is the fuzzy matrix multiplication operator, and b j Let c be the overall membership degree of the j-th evaluation level. j Let S be the quantitative value of the j-th evaluation level, and S be the risk assessment value of rockburst.

[0096] The risk assessment value calculation unit is used to call the constructed multi-parameter coupling analysis model, input the standardized monitoring data, and calculate the rock burst risk assessment value S. The value range of S is [0, 10], and the larger the value, the higher the risk of rock burst occurrence.

[0097] The early warning decision-making module includes an early warning threshold setting unit, a risk comparison unit, and an early warning instruction generation unit;

[0098] The early warning threshold setting unit supports customizing and setting multi-level early warning thresholds according to the geological conditions, mining methods, and historical rock burst data of different mines. By default, four-level early warning thresholds are set: no-risk threshold S ≤ 3, low-risk threshold 3 < S ≤ 5, medium-risk threshold 5 < S ≤ 8, high-risk threshold S > 8;

[0099] The risk comparison unit is used to compare the rock burst risk assessment value S calculated by the multi-parameter coupling analysis module with the preset four-level early warning thresholds in real time to determine the corresponding early warning level;

[0100] The early warning instruction generation unit is used to generate corresponding early warning instructions according to the determined early warning level: when the early warning level is no risk, generate a normal monitoring instruction; when the early warning level is low risk, generate an enhanced monitoring instruction; when the early warning level is medium risk, generate a on-site investigation instruction; when the early warning level is high risk, generate an instruction for personnel evacuation and production suspension for rectification.

[0101] The above-mentioned terminal display module includes a monitoring center terminal, an on-site early warning terminal, and a mobile terminal;

[0102] The monitoring center terminal uses an industrial-grade monitoring host and is equipped with a large-screen display device, which is used to display the standardized monitoring data, rock burst risk assessment value, early warning level, sensor distribution location, and roadway layout diagram of each monitoring area in real time, and supports historical data query, data statistical analysis, and report generation;

[0103] The on-site early warning terminals are arranged at key positions such as each working face and roadway intersection in the mine. They use audible and visual alarms and LED displays. When receiving a medium-risk or high-risk early warning instruction, they immediately start the audible and visual alarm and display the early warning level and emergency disposal tips on the LED display;

[0104] The mobile terminal supports managers to receive early warning information in real time through the mobile phone APP, view the monitoring data and early warning instructions, and achieve remote monitoring and emergency command.

[0105] It also includes a power supply module, which adopts a hybrid power supply method of "mains power + backup battery + solar auxiliary power supply" to provide stable power supply for the multi-parameter acquisition module, data transmission module, data preprocessing module, multi-parameter coupling analysis module, early warning decision module and terminal display module; among them, the backup battery uses a lithium battery pack, which automatically switches to backup battery power supply when the mains power is interrupted, ensuring that the system can operate continuously for no less than 72 hours; the solar auxiliary power supply unit is used to provide auxiliary power supply for sensors and data aggregation nodes in remote areas, reducing system energy consumption.

[0106] In summary, this invention overcomes the limitations of single-parameter monitoring, improves the accuracy and timeliness of rockburst early warning, has strong adaptability, and can effectively ensure safe production in mines.

[0107] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-parameter coupled real-time monitoring and early warning system for rockburst in mines, characterized in that: It includes a multi-parameter acquisition module, a data transmission module, a data preprocessing module, a multi-parameter coupling analysis module, an early warning decision-making module, and a terminal display module; The multi-parameter acquisition module is used to acquire various raw monitoring parameters related to rockburst in the target monitoring area of ​​the mine. The raw monitoring parameters include rock stress parameters, surrounding rock displacement parameters, rock vibration parameters, environmental temperature and humidity parameters, and rock water content parameters. The data transmission module is used to transmit the raw monitoring parameters collected by the multi-parameter acquisition module to the data preprocessing module in real time; The data preprocessing module is used to perform noise reduction, outlier removal, and data standardization on the original monitoring parameters to obtain standardized monitoring data. The multi-parameter coupling analysis module is used to calculate the rockburst risk assessment value based on standardized monitoring data and through the constructed multi-parameter coupling analysis model. The early warning decision module is used to compare the rockburst risk assessment value with the preset early warning threshold, and generate the corresponding early warning level and early warning instruction based on the comparison result; The terminal display module is used to display standardized monitoring data, rockburst risk assessment values, early warning levels, and early warning instructions in real time, and supports audible and visual alarms for early warning information and historical data queries.

2. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, The multi-parameter acquisition module includes a stress monitoring unit, a displacement monitoring unit, a vibration monitoring unit, a temperature and humidity monitoring unit, and a moisture content monitoring unit. The stress monitoring unit includes multiple fiber optic stress sensors distributed in the surrounding rock of the roadway in the target monitoring area, used to collect normal stress and shear stress data of the rock mass, with a sampling frequency set to 1-5Hz. The displacement monitoring unit includes multiple laser displacement sensors arranged on the top and bottom plates and both sides of the roadway, used to collect vertical and horizontal displacement data of the surrounding rock, with a sampling frequency set to 0.5-2Hz. The vibration monitoring unit includes multiple microseismic sensors distributed in the target monitoring area, used to collect data on the amplitude, frequency, duration and vibration energy of rock mass vibration, with the sampling frequency set to 100-500Hz. The temperature and humidity monitoring unit includes multiple temperature and humidity sensors arranged in the tunnel to collect ambient temperature and relative humidity data of the monitoring area, with a sampling frequency set to 0.1-0.5Hz; The moisture content monitoring unit includes multiple high-frequency capacitive moisture content sensors inserted into the surrounding rock to collect moisture content data of the rock mass, with a sampling frequency set to 0.1-0.5Hz.

3. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, The data transmission module adopts a hybrid transmission method of "wired transmission + wireless transmission", including an optical fiber transmission unit, a LoRa wireless transmission unit, and a data aggregation node; The optical fiber transmission unit is used to connect sensors located in the same tunnel area to achieve high bandwidth and low latency data transmission. The LoRa wireless transmission unit is used to connect sensors located in remote areas or areas where wiring is difficult, enabling long-distance, low-power data transmission; The data aggregation node is used to receive the original monitoring parameters transmitted by each sensor through the optical fiber transmission unit or the LoRa wireless transmission unit. After preliminary aggregation and integration of the data, it is transmitted to the data preprocessing module through the industrial Ethernet.

4. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, The processing process of the data preprocessing module includes the following steps: S1. Noise reduction processing: The wavelet threshold denoising algorithm is used to perform noise reduction processing on the original monitoring parameters to remove environmental interference and sensor self-noise; the function expression of wavelet threshold denoising is: Among them, w j,k The original wavelet coefficients, w′ j k represents the denoised wavelet coefficients, and λ represents the wavelet threshold. σ is the noise standard deviation, and N is the data length; S2. Outlier rejection: The Grubbs criterion is used to reject outliers from the denoised monitoring data. S3. Data standardization: The min-max standardization method is used to standardize the monitoring data after outlier rejection. The standardization formula is: Where, x′ i For standardized monitoring data, x i For the original monitoring data after removing outliers, x max x is the maximum value of this parameter. min This is the minimum value of the parameter.

5. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, The multi-parameter coupling analysis module includes a coupling model construction unit and a risk assessment value calculation unit; The coupling model construction unit constructs a multi-parameter coupling analysis model based on the analytic hierarchy process and the fuzzy comprehensive evaluation method. The specific steps are as follows: T1. Establish a hierarchical structure: Take the rock burst risk assessment as the target layer, take rock mass stress, surrounding rock displacement, rock mass vibration, environmental temperature and humidity, and rock mass moisture content as the criterion layer, and take the specific monitoring indicators corresponding to each criterion layer as the indicator layer; T2. Determine weights: Use the analytic hierarchy process to determine the weights of each parameter in the criterion layer and each indicator in the indicator layer. By constructing a judgment matrix, calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector. After normalizing the eigenvector, the weight vector is obtained, and the rationality of the weight distribution is verified through consistency testing; T3. Construct a fuzzy evaluation matrix: According to the standardized monitoring data, determine the membership function of each indicator and construct a fuzzy evaluation matrix; T4. Fuzzy comprehensive evaluation: Use fuzzy matrix multiplication to calculate the comprehensive evaluation results of each criterion layer, and then combine the weights of the criterion layer to calculate the rock burst risk assessment value of the target layer; The risk assessment value calculation unit is used to call the constructed multi-parameter coupling analysis model, input the standardized monitoring data, and calculate the rock burst risk assessment value S. The value range of S is [0, 10].

6. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, The early warning decision-making module includes an early warning threshold setting unit, a risk comparison unit, and an early warning instruction generation unit; The early warning threshold setting unit supports customizing and setting multiple levels of early warning thresholds according to the geological conditions, mining methods, and historical rock burst data of different mines. By default, four levels of early warning thresholds are set: no-risk threshold S ≤ 3, low-risk threshold 3 < S ≤ 5, medium-risk threshold 5 < S ≤ 8, high-risk threshold S > 8; The risk comparison unit is used to compare the rock burst risk assessment value S with the preset early warning threshold in real time to determine the corresponding early warning level; The early warning instruction generation unit is used to generate corresponding early warning instructions according to the determined early warning level.

7. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, The terminal display module includes a monitoring center terminal, a on-site early warning terminal, and a mobile terminal; The monitoring center terminal uses an industrial-grade monitoring host and is equipped with a large-screen display device to be used for real-time display of information such as monitoring data, risk assessment values, and early warning levels, and supports historical data query and report generation; The on-site early warning terminal is deployed in key locations underground in the mine, and uses audible and visual alarms and LED displays for audible and visual alarms and emergency prompts during medium- and high-risk situations. The mobile terminal allows managers to receive early warning information and view monitoring data in real time via a mobile app.

8. The mine rockburst multi-parameter coupled real-time monitoring and early warning system according to claim 1, characterized in that, It also includes a power module, which adopts a hybrid power supply method of "mains power + backup battery + solar auxiliary power supply" to provide stable power supply for each module of the system.

Images