High-stress rock mass disturbance catastrophe real-time early warning method based on fracture comprehensive signal

Abstract

The invention provides a high-stress rock mass disturbance catastrophe real-time early warning method based on a fracture comprehensive signal, which belongs to the technical field of geotechnical engineering, and constructs a comprehensive acoustic parameter ASCP by fusing various parameters such as amplitude, dominant frequency, energy distribution, crack fractal characteristics, rock mass fracture event density and the like in an acoustic emission signal. The calculation process is combined with contribution weights of different parameters to the destruction stage, and weight values are jointly calibrated through data analysis. On the basis of a large amount of engineering field monitoring and indoor true triaxial test data, the evolution law of the ASCP in the rock mass damage process is analyzed, multiple early warning thresholds of an ASCP evolution curve starting early warning threshold and an ASCP catastrophe early warning threshold are provided, and the early warning accuracy and timeliness are improved. According to the early warning method, various parameters of sound signals are integrated, a multi-threshold early warning method is established, the contribution degrees of various main sensitive parameters of high-stress rock mass disturbance damage sound emission are integrated, and the early warning accuracy, timeliness, high efficiency and economical efficiency are improved.

Description

Technical Field

[0001] This invention belongs to the field of geotechnical engineering technology, and specifically relates to a real-time early warning method for high-stress rock mass disturbance disasters based on fracture integrated signals, which is applicable to safety monitoring and disaster prevention and control of various deep geotechnical engineering projects. Background Technology

[0002] In deep geotechnical engineering (such as deep mining and long tunnel construction), the rock mass is under high stress and is prone to sudden fracturing and instability when affected by dynamic disturbances such as excavation and blasting, leading to disasters such as rock bursts and collapses, which seriously threaten engineering safety and personnel safety. Currently, the industry mainly uses acoustic emission (AE) signals generated when rock mass fractures to achieve early warning, but existing technologies have obvious shortcomings: most methods rely on a single parameter (such as amplitude and energy) in the acoustic emission signal to judge the state of the rock mass, which cannot fully reflect the complex process of rock mass failure (such as different stages of crack initiation, propagation, and penetration), and are prone to false alarms or missed alarms due to one-sided parameters; the early warning thresholds are mostly based on experience and are not dynamically adjusted in combination with the characteristics of the rock mass at the engineering site (such as lithology and distribution of structural surfaces) and indoor test data, making it difficult to adapt to the disturbance conditions of different engineering scenarios; there is a lack of accurate identification of the precursors of rock mass failure, and early warnings are only issued when the rock mass is close to instability, leaving little time for on-site emergency response and failing to effectively avoid disaster risks.

[0003] Therefore, there is an urgent need for a high-stress rock mass disturbance disaster early warning method that can integrate multiple sensitive parameters, dynamically adjust thresholds, and accurately identify precursors, in order to solve the problems of "low accuracy, poor adaptability, and untimely response" of existing technologies. Summary of the Invention

[0004] The purpose of this invention is to provide a real-time early warning method for high-stress rock mass disturbance disasters based on fracture comprehensive signals, which can intuitively characterize the precursory laws of rock mass failure, provide accurate early warning time, and improve the accuracy and timeliness of early warning.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A real-time early warning method for high-stress rock mass disturbance disasters based on fracture integrated signals includes the following steps:

[0007] S1. Acoustic emission signals of rock mass fracture under dynamic disturbance at the engineering site are collected by acoustic signal sensor, acoustic signal characteristic parameters are extracted and sensitive characteristic parameters are screened. The acoustic signal characteristic parameters include waveform amplitude, fractal dimension, LgN / b value, dominant frequency, activity coefficient and real volume.

[0008] S2. Under true three-dimensional stress conditions, conduct rock mass dynamic disturbance failure tests under different test conditions, simultaneously collect acoustic emission signals from indoor tests and extract sensitive characteristic parameters consistent with those in step S1, and establish a database.

[0009] S3. Based on the multiple sensitive feature parameters obtained in steps S1 and S2, an ASCP function for comprehensive feature parameters is constructed using a weighted fusion method. The expression of the ASCP function is as follows: ,in These are the weighting coefficients for each sensitive feature parameter; This is a proportional function of each sensitive feature parameter;

[0010] S4. Compare the ASCP evolution curves at different stages of rock mass failure in engineering field and laboratory tests, analyze the changing trend and evolution law of ASCP through quantitative methods, and establish a one-to-one correspondence between ASCP and rock mass stress state and degree of failure.

[0011] S5. Based on the changing trend and evolution law of the ASCP evolution curve in step S4, determine the activation warning threshold by the vertical bisector method, and determine the disaster warning threshold by the critical damage data of the indoor test, thus forming multiple warning thresholds.

[0012] S6. Based on the failure results of the dynamic disturbance of the rock mass in the engineering site and indoor test in steps S1 and S2, the ASCP function is inverted, and the weight coefficients and threshold ranges are dynamically adjusted.

[0013] S7. Store the data and early warning results from steps S1 to S6 into a sample library, and construct an ASCP evolution-threshold criterion association model through MATLAB interpolation and neural network training.

[0014] S8. Embed the trained ASCP evolution-threshold criterion association model into the monitoring system, collect acoustic emission signals from the engineering site in real time and calculate ASCP. When ASCP reaches the activation threshold, an early warning is triggered. When ASCP reaches the catastrophic threshold, an emergency warning is triggered.

[0015] As a further description of the above technical solution: the different test conditions mentioned in step S2 include different stress conditions, different stress levels, different structural surfaces, and different types of surrounding rock units.

[0016] As a further description of the above technical solution, the weight coefficients mentioned in step S3 are determined using the Analytic Hierarchy Process (AHP). The specific process is as follows:

[0017] A hierarchical evaluation model is constructed based on the monitoring results, including the target layer, the criterion layer, and the scheme layer;

[0018] Construct the judgment matrix Each sensitive feature parameter is compared pairwise, and the weights of each criterion layer to the target layer are determined to form a judgment matrix. The elements in the middle satisfy , and ;

[0019] Perform hierarchical single sorting on the judgment matrix. All elements are compared pairwise and then ranked hierarchically to determine their order of importance. The specific calculations are as follows:

[0020] , ;

[0021] After obtaining the weight matrix, calculate the largest eigenvalue. The CI value was calculated, and the random consistency index RI was obtained through multiple Satty simulations. The CR value was then calculated to determine whether the consistency was satisfactory.

[0022] , , ;

[0023] If CR < 0.1, it indicates that the judgment matrix... Within the error range, its elements can be used as weighting coefficients. If CR ≥ 0.1, then the judgment matrix needs to be adjusted. Make corrections.

[0024] As a further description of the above technical solution: the scaling function mentioned in step S3 includes an amplitude scaling function. Fractal dimension scaling function ,LgN / b value proportional function and other sensitive characteristic parameters scaling functions;

[0025] Where x is the number of sensors, V i Let B1 be the waveform voltage value at the i-th time node, and B1 be the maximum waveform voltage value at that time node; D i Let B1 be the fractal dimension value at the i-th time node, and B2 be the maximum fractal dimension value at that time node; LgN i / b i B1 is the LgN / bb value at the i-th time node, and B2 is the maximum value of LgN / b at that time node.

[0026] As a further description of the above technical solution, step S4, which involves analyzing the changing trend and evolutionary pattern of ASCP using quantitative methods, specifically includes:

[0027] Normalize the ASCP time series;

[0028] ;

[0029] Noise is smoothed using a sliding window method (window length ≥ 10 sampling periods);

[0030] The slope k of the ASCP evolution curve is calculated based on linear regression. k ≥ 0.05 / min is defined as a significant upward trend (corresponding to a precursor to disaster), 0.01 ≤ k < 0.05 / min is a steady fluctuation (corresponding to gradual destruction), and k < 0.01 / min is a stable state.

[0031] Use the CUSUM algorithm to set the control limit L=3× When "the cumulative and excessive acoustic emission energy of a single event increases by ≥200% simultaneously", it is determined to be the catastrophic critical point. By comparing field and experimental data, the evolution law of ASCP under different disturbance intensities, rock mass characteristics and failure modes is studied, so as to provide theoretical basis and data support for the subsequent setting of early warning thresholds.

[0032] As a further description of the above technical solution, the determination of the activation warning threshold by the vertical bisector method in step S5 is as follows: the slopes of the upper and lower straight line segments of the ASCP evolution curve are extended to intersect at the first point, the vertical bisectors of the upper and lower straight line segments are drawn to intersect at the second point, the first point and the second point are connected and intersected at the ASCP evolution curve at the third point, and the ASCP value corresponding to the third point is the activation warning threshold.

[0033] As a further description of the above technical solution, the construction of the ASCP evolution-threshold criterion association model through MATLAB interpolation and neural network training in step S7 specifically involves: using the interp1 function in MATLAB to interpolate the data, fill in missing data or smooth the data, and storing the interpolation results in a database using MATLAB's database toolbox; then loading the data from the database for preprocessing and converting it into a format suitable for neural network training; and then using MATLAB's deep learning toolbox to construct the ASCP evolution law-threshold criterion association model and training the model by specifying training options.

[0034] As a further description of the above technical solution: after the ASCP evolution-threshold criterion association model is constructed, its performance is verified using test data.

[0035] For a further description of the above technical solution: Step S8 also continuously transmits the monitoring data and early warning results back to the database and iteratively optimizes the correlation model.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] This invention integrates multiple sensitive parameters of acoustic emission signals (amplitude, fractal dimension, LgN / b value, etc.), and comprehensively reflects the entire process of rock mass failure through AHP weighting and ASCP, avoiding the one-sidedness of a single parameter and reducing false alarm and missed alarm rates. It establishes a dual early warning threshold of initiation warning + disaster warning, identifying early signs of rock mass failure (such as inflection points in the ASCP evolution curve) in advance, allowing sufficient time for on-site emergency response. Through model inversion and machine learning, it dynamically adjusts parameter weights and thresholds to adapt to engineering scenarios with different lithologies and disturbance conditions. It does not require additional complex equipment and can be implemented based on existing acoustic emission monitoring systems, reducing engineering costs. Based on indoor experimental databases and engineering field data, the steps are clear, the parameters are quantifiable, and the use of MATLAB tools simplifies data processing and model training, making it easy for engineers to use. Attached Figure Description

[0038] Figure 1 This is a flowchart of the real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to the present invention.

[0039] Figure 2 This is a schematic diagram illustrating the establishment of the nonlinear starting point for the accelerated change of ASCP in this invention.

[0040] Figure 3 This is a diagram illustrating the ASCP evolution pattern of a true triaxial fractured granite on the eve of multi-stage disturbance shear failure in Application Example 1.

[0041] Figure 4 This is a diagram illustrating the ASCP evolution of intact granite prior to a rockburst under different perturbation frequencies in true triaxial conditions, as shown in Application Example 2. Detailed Implementation

[0042] The claims of the present invention will be further described in detail below with reference to specific embodiments, but this does not constitute any limitation on the present invention. Any limited modifications made by any person within the scope of protection of the claims of the present invention are still within the scope of protection of the claims of the present invention.

[0043] A real-time early warning method for high-stress rock mass disturbance disasters based on fracture comprehensive signals, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0044] S1. Deploy acoustic signal sensors at the engineering site (such as tunnel face or mining area) to collect acoustic emission signals of rock mass fracturing during dynamic surrounding rock disasters during excavation. Obtain acoustic signal characteristic parameters, including emission waveform amplitude V, fractal dimension D (reflecting crack complexity), LgN / b value (reflecting the relationship between signal frequency and intensity), dominant frequency, activity coefficient (reflecting signal occurrence frequency), and solid volume (reflecting the fracturing range). Analyze the response characteristics and evolution of the acoustic signal characteristic parameters, and select the acoustic signal characteristic parameter most sensitive to rock mass failure response as the sensitive characteristic parameter.

[0045] S2. Under true three-dimensional stress conditions, confirm the sample types for all indoor tests, conduct dynamic catastrophic failure tests of rock mass under different test conditions (different stress conditions, different stress levels, different structural planes and surrounding rock unit types), collect a large amount of acoustic signal information data (including acoustic signal parameters, stress conditions, failure results, etc.) using indoor monitoring equipment, extract sensitive characteristic parameters consistent with those in step S1, store them in the database, establish a total database, and analyze the response characteristics and evolution law of rock mass fracture sensitivity characteristic parameters.

[0046] S3. Combining multiple sensitive characteristic parameters of rock mass dynamic disturbance failure obtained from engineering site and laboratory tests, a weighted fusion method is used to construct the comprehensive acoustic parameter ASCP. The functional relationship between ASCP and rock failure is as follows:

[0047]

[0048] Where ASCP is the functional relationship between the weighted comprehensive characteristic value of the acoustic signal and rock failure, n1, n2, n3, n i The weight coefficients corresponding to different sensitive feature parameters, l1, l2, l3, l i The proportional function represents the waveform amplitude, fractal dimension, LgN / b, dominant frequency, activity coefficient, real volume, and other sensitive characteristic parameters.

[0049] Wherein, the weighting coefficient , , , , The values ​​were determined using the Analytic Hierarchy Process (AHP): First, a hierarchical evaluation model was constructed based on extensive monitoring results. The target layer represents the selection of optimal acoustic emission parameters for destruction; the criterion layer includes parameter variation patterns, numerical values, the severity of abrupt changes in acoustic emission parameters, the degree of rock mass failure response to changes in acoustic emission parameters, and the anti-interference level of acoustic emission parameters; the scheme layer includes emission waveform amplitude, fractal dimension, LgN / b value, dominant frequency, activity coefficient, and solid volume. Second, a judgment matrix A was constructed, and pairwise comparisons were performed between each element to determine the weight of each criterion layer on the target layer. The judgment matrix A is as follows:

[0050]

[0051] Determine if the elements in matrix A satisfy: , and ;

[0052] Then, a hierarchical single sort is performed. All elements in the above formula are compared pairwise and then hierarchically sorted to determine their order of importance. The specific calculation is as follows:

[0053]

[0054]

[0055] After obtaining the weight matrix, the largest eigenvalue and CI value are calculated. Then, the random consistency index RI is obtained through 2000 simulations using Satty. The CR value is calculated to determine whether the consistency is passed.

[0056]

[0057]

[0058]

[0059] If CR < 0.1, it indicates that the judgment matrix A is within the error range class, and its elements can be used as weight coefficients. To perform the calculation, if CR ≥ 0.1, then the judgment matrix A needs to be corrected, and the final weight coefficients will be... The value range is 0.15 to 0.30, and the weighting coefficient is... The value range is 0.10 to 0.25, and the weighting coefficient is... The value range is 0.20 to 0.35, and the remaining weight coefficients are adjusted according to the rock mass type. The sum of the weight coefficients is 1.

[0060] The proportional function relationships are as follows:

[0061]

[0062]

[0063] ;

[0064] Where x is the number of sensors; V i Let B1 be the waveform voltage value at the i-th time node, and B1 be the maximum waveform voltage value at that node; D i Let B1 be the fractal dimension value at the i-th time node, and B2 be the maximum fractal dimension value at that node; LgN i / b i B1 is the LgN / b value at the i-th time node, and B3 is the maximum LgN / b value at that node; the scaling functions of the other parameters are all normalized to the [0,1] interval, referring to the above form.

[0065] S4. Compare the ASCP evolution curves from field tests and laboratory tests at various stages of rock mass failure (stabilization period, crack initiation period, crack propagation period, and instability period), and analyze the changing trends and evolution patterns of ASCP using the following quantitative methods:

[0066] Normalize the ASCP time series: ;

[0067] Noise is smoothed using a sliding window method (window length ≥ 10 sampling periods);

[0068] The slope k of the ASCP evolution curve is calculated based on linear regression: k ≥ 0.05 / min is defined as a significant upward trend (corresponding to a precursor to disaster), 0.01 ≤ k < 0.05 / min is a steady fluctuation (corresponding to gradual destruction), and k < 0.01 / min is a stable state.

[0069] The control limit L = 3× is set using the CUSUM algorithm. When the accumulated energy exceeds the limit and the energy of a single acoustic emission event suddenly increases by ≥200%, it is determined to be a "catastrophic critical point";

[0070] Ultimately, a one-to-one correspondence was established between ASCP and the stress state and degree of damage of the rock mass.

[0071] S5. Based on the evolutionary pattern of ASCP in step S4, set two levels of early warning thresholds:

[0072] The trigger warning threshold is determined using the vertical bisector method: the slopes of the upper and lower straight segments of the ASCP evolution curve (corresponding to the crack propagation and stabilization phases) are extended to intersect at the first point A, such as... Figure 2 As shown, draw perpendicular bisectors for the upper and lower line segments respectively. Figure 2The dashed lines 1 and 2 intersect at the second point D. The dashed line 3 connects the first point A and the second point D and intersects the ASCP evolution curve at the third point E. The third point E is determined as the activation warning threshold. Based on the statistical data of the results in the database, the ASCP values ​​before the destruction under different conditions are obtained and used as the ASCP disaster warning threshold.

[0073] The steps for constructing the perpendicular bisectors of the upper and lower line segments include:

[0074] Determine the starting point for calculation, wherein the calculation formula for the starting point satisfies:

[0075]

[0076] In the formula, x1 is the point corresponding to the opening angle between the straight line segment and the fitted curve is 1 / 5000°, where 1 / 5000° makes the angle between the fitted curve and the straight line segment small enough to meet the accuracy requirements for the calculation of the starting point; x0 is the point of coincidence between the fitted line and the function; f1(x) is the ASCP evolution curve; and f2(x) is the slope function curve of the straight line segment.

[0077] Using the above formula, we determine that the starting point of the upward sloping line is point C and the starting point of the downward sloping line is point B. Starting from points B and C, we calculate and find the midpoints of the upward and downward line segments, and then draw the perpendicular bisectors.

[0078] The disaster warning threshold is determined by taking the combined value of ASCP values ​​of rock masses before critical failure from the statistical database and the test results of similar rock masses.

[0079] S6. Based on the results of rock mass dynamic disturbance and failure from engineering sites and laboratory tests, an ASCP calculation model is derived, and the weighting coefficient n is dynamically adjusted. i And threshold ranges to ensure that the model matches the actual working conditions.

[0080] S7. Store all data from steps S1 to S6 (including acoustic signal parameters, ASCP values, early warning results, and damage results) into the database as samples. Then, using MATLAB interpolation and neural network training, construct an ASCP evolution-threshold criterion association model, as detailed below:

[0081] Using the interp1 function in MATLAB, data is interpolated to fill in missing or smooth data, and the interpolation results are stored in a database using MATLAB's database toolbox.

[0082] Load data from the database, preprocess it, and convert it into a format suitable for neural network training;

[0083] A correlation model between ASCP evolution law and threshold criterion was built using MATLAB's Deep Learning Toolbox, and the model was trained by specifying training options.

[0084] Use test data to validate the trained association model, compare the predicted results with the actual values, thereby verifying the model performance and ensuring the model accuracy.

[0085] S8. Embed the trained ASCP evolution-threshold criterion association model into the monitoring system. Based on the acoustic emission response when rock mass fails at the engineering site, extract indoor tests that match the construction site from the database, set the AE equipment parameters, and use the AE precursor features of the indoor tests for rock failure monitoring at the construction site. Extract the start-up warning threshold and ASCP disaster warning threshold of the ASCP evolution curve.

[0086] The area where the rock mass may be damaged was determined by AE positioning test, and this area was set as the AE monitoring space area.

[0087] After completing all the preliminary preparations, turn on the AE device and start the alert;

[0088] Based on the new acoustic emission parameter ASCP, which is a precursor to rock failure, the rock mass at the construction site is monitored in real time during the construction process.

[0089] Analyze the changing trend and evolution law of the ASCP evolution curve during the monitoring process, and observe whether the ASCP reaches the activation warning threshold, that is, whether the ASCP value reaches the ASCP value corresponding to the peak point of the nonlinear curvature of the new parameter ASCP evolution curve. If the ASCP value reaches the ASCP value corresponding to the peak point of the nonlinear curvature of the new parameter ASCP evolution curve, that is, the activation warning threshold is reached, an activation warning signal is issued and the next step is initiated; if the curve slope k does not reach the ASCP parameter corresponding to the peak point of the nonlinear curvature of the ASCP evolution curve, monitoring continues.

[0090] After issuing the activation warning signal, observe whether the ASCP reaches the disaster warning threshold. If the combined value of the new parameters of the ASCP test results at the critical failure time of this type of test rock reaches the disaster warning threshold, it indicates that the rock mass is about to fail. Immediately issue a disaster warning signal and arrange for the evacuation of on-site personnel. If the disaster warning threshold is not reached, continue monitoring.

[0091] At the same time, monitoring data and early warning results are continuously transmitted back to the database to iteratively optimize the correlation model.

[0092] Application Example 1:

[0093] The following example, "Acoustic emission early warning process before multi-stage disturbance shear fracture in true triaxial fractured granite," illustrates the implementation steps of this invention in detail:

[0094] In step S2, the sample type for all indoor tests is confirmed. In this example, granite with a sample type of 100 mm × 100 mm × 100 mm and a crack width d = 25 mm is used. The exothermic stress loading rate in all three directions is 1 MPa / s, and the load is applied to σ1 = 5 MPa, σ2 = 30 MPa, and σ3 = 25 MPa. The static stage is maintained for 200 s. In the stress redistribution stage, σ2 rises to 35 MPa, σ3 falls to 11.8 MPa, and σ1 rises to 15 MPa. Then, the loading of each level of disturbance begins. Each level of disturbance load is applied for 50 cycles, and the loading and unloading rate of each level is 1 MPa / s. The AE monitoring equipment used is 5 nano30 sensors. A multi-level disturbance true triaxial shear fracture test of fractured rock is carried out. The relevant indoor monitoring equipment collects a large amount of acoustic signal information data. Sensitive feature data consistent with those in step S1 is extracted, stored in the database, and a total database is established.

[0095] In step S3, combining multiple sensitive characteristic parameters of rock mass dynamic disturbance failure from engineering site and laboratory tests, a comprehensive characteristic parameter with a strong response is selected, and a calculation method with a corresponding comprehensive parameter ASCP is constructed. For example, the results after substituting the test result at 2280s are as follows: ;

[0096] Where ASCP is the functional relationship between the weighted comprehensive characteristic value of acoustic signals and rock failure. , , Here, l1, l2, and l3 represent the weighting coefficients corresponding to different sensitive feature parameters, and represent the proportional functions corresponding to the waveform amplitude, fractal dimension, and LgN / b value of the sensitive feature parameters. , , The proportional function relationship after substitution is calculated as follows:

[0097]

[0098]

[0099]

[0100] Where x is the number of sensors, V i Let D be the waveform voltage value collected at the i-th time node. i Let N be the fractal dimension of acoustic emission at the i-th time node. i and b i Let f be the total number of acoustic emission signals at the i-th time point and the value of b. i With A iLet be the dominant frequency and amplitude of the acoustic emission at the i-th time node;

[0101] Among them, the weighting coefficient , , The values ​​were determined using the Analytic Hierarchy Process (AHP). Taking a granite sample as an example, a judgment matrix A was constructed. The criterion layer contains five elements (C1: parameter variation law; C2: numerical magnitude; C3: mutation sensitivity; C4: destructive response; C5: anti-interference capability), and the scheme layer contains six acoustic emission parameters (P1: waveform amplitude; P2: fractal dimension; P3: lgN / b value; P4: dominant frequency; P5: activity coefficient; P6: actual volume). The criterion layer judgment matrix A was constructed as follows:

[0102]

[0103] By calculating the maximum eigenvalue λ max =5.23, consistency ratio CR=0.04<0.1, passes the test. Weight allocation: Criterion layer weight: W C =[0.32,0.12,0.35,0.15,0.06], the judgment matrix shows that P1 (amplitude) is better at representing the destructive trend than other parameters. The final comprehensive weight of the scheme layer is:

[0104] Parameter weights: n1=0.25, n2=0.18, n3=0.30, n4=0.12, n5=0.10, n6=0.05.

[0105] Based on the acoustic emission response of rock mass failure at the engineering site, indoor tests matching the construction site were selected from the database, the AE equipment parameters were set, and the AE precursor characteristics of the indoor tests were used for rock failure monitoring at the construction site. The initiation warning threshold and ASCP disaster warning threshold of the ASCP evolution curve were extracted.

[0106] The area where the rock mass may be damaged was determined by AE positioning test, and this area was set as the AE monitoring space area.

[0107] After completing all the preliminary preparations, turn on the AE device and start the alert;

[0108] Based on the new acoustic emission parameter ASCP, which is a precursor to rock failure, the rock mass at the construction site is monitored in real time during the construction process.

[0109] Analysis of the ASCP evolution curve during the monitoring process ( Figure 3 The changing trend and evolution pattern of ASCP (as shown) are observed to determine whether it reaches the activation warning threshold. The numerical determination method is as described in steps S5 and... Figure 2As shown, in this example, the early warning threshold for the ASCP evolution curve is set to a curve slope k > 35°, and the emergency warning threshold for ASCP is set to ASCP > 2.0. That is, whether the ASCP value has reached the ASCP value corresponding to the peak point of the nonlinear curvature of the new parameter ASCP evolution curve. If the ASCP value has reached the ASCP value corresponding to the peak point of the nonlinear curvature of the new parameter ASCP evolution curve, that is, the warning threshold has been reached, a warning signal is issued and the process proceeds to the next step; if the curve slope k has not reached the ASCP parameter corresponding to the peak point of the nonlinear curvature of the ASCP evolution curve, monitoring continues.

[0110] After issuing the activation warning signal, observe whether ASCP reaches the disaster warning threshold. If the comprehensive value of the new parameter ASCP test results when the rock mass is critically damaged in this type of test reaches the disaster warning threshold, it indicates that the rock mass is about to be damaged. Immediately issue a disaster warning signal and arrange for the evacuation of on-site personnel. If the disaster warning threshold is not reached, continue monitoring and continuously transmit the monitoring data and warning results back to the database to iteratively optimize the correlation model.

[0111] Application Example 2:

[0112] The following example, "Acoustic emission early warning process of intact granite before rockburst under different perturbation frequencies in true triaxial motion," illustrates the implementation steps of this invention in detail:

[0113] Based on the monitoring results of acoustic signals of rock mass fracture during dynamic surrounding rock disasters during on-site excavation, the response characteristics and evolution laws of acoustic signal characteristic parameters are analyzed. The acoustic signal characteristic parameters include the amplitude of the emitted waveform, fractal dimension, LgN / b value, dominant frequency, activity coefficient, and solid volume. Acoustic signal characteristic parameters with strong sensitivity are selected.

[0114] The specimen type for all indoor tests was confirmed. In this example, a 100 mm × 100 mm × 200 mm granite specimen was used. The stress loading rate in three directions was 0.5 MPa / s, loaded to σ1 = 50 MPa, σ2 = 30 MPa, and σ3 = 25 MPa, with a static holding time of 20 min. The load control method was "single-sided open" loading to 0.4σ. c The disturbance-induced rockburst stage involves loading and unloading the main unit and applying disturbance loads. In the early stages, when the load is low, each applied load is 0.2σ. c As the load increases, each level increases by 0.1σ. c When the load is large in the later stages, each level is 0.05σ. cEach level of disturbance load is applied for 50 cycles, with a loading rate of 1 MPa / s for each level. The AE monitoring equipment consists of three nano30 sensors. True triaxial disturbance rockburst tests are conducted on complete granite under different disturbance frequencies. A large amount of acoustic signal information data is collected from relevant indoor monitoring equipment, stored in the database, and a database is established.

[0115] Combining various sensitive characteristic parameters of rock mass dynamic disturbance failure from engineering site and laboratory tests, a comprehensive characteristic parameter with a strong response was selected, and a corresponding calculation method with comprehensive parameter ASCP was constructed. For example, the results after substituting the parameters at 7400 s in the experiment are as follows:

[0116]

[0117] Where ASCP is the functional relationship between the weighted comprehensive characteristic value of acoustic signals and rock failure. , , For different acoustic signal parameters, l1, l2, and l3 represent the weighting coefficients, where l1, l2, and l3 are proportional functions corresponding to the acoustic emission parameters waveform amplitude, fractal dimension, and LgN / b in the acoustic signal. , , The ASCP proportional function relationship is calculated as follows after substituting the input:

[0118]

[0119]

[0120]

[0121] Where x is the number of sensors, V i Let D be the waveform voltage value collected at the i-th time node. i Let N be the fractal dimension of acoustic emission at the i-th time node. i and b i Let f be the total number of acoustic emission signals at the i-th time point and the value of b. i With A i Let be the dominant frequency and amplitude of the acoustic emission at the i-th time node;

[0122] The weighting coefficient , , The values ​​were determined using the Analytic Hierarchy Process (AHP). Taking a granite sample as an example, a judgment matrix A was constructed. The criterion layer contains five elements (C1: parameter variation law; C2: numerical magnitude; C3: mutation sensitivity; C4: destructive response; C5: anti-interference capability), and the scheme layer contains six acoustic emission parameters (P1: waveform amplitude; P2: fractal dimension; P3: lgN / b value; P4: dominant frequency; P5: activity coefficient; P6: actual volume). The judgment matrix for the criterion layer was constructed as follows:

[0123]

[0124] By calculating the maximum eigenvalue λ max =5.23, consistency ratio CR=0.051<0.1, passes the test. Weight allocation: Criterion layer weight: W C =[0.25,0.18,0.30,0.12,0.10,0.05]. The judgment matrix shows that P1 (waveform amplitude) is better at representing the destructive trend than other parameters. The final scheme layer comprehensive weight is:

[0125] Parameter weights: n1=0.22, n2=0.16, n3=0.30, n4=0.14, n5=0.10, n6=0.08.

[0126] Based on the acoustic emission response of rock mass failure at the engineering site, indoor tests matching the construction site were selected from the database, the AE equipment parameters were set, and the AE precursor characteristics of the indoor tests were used for rock failure monitoring at the construction site. The initiation warning threshold and ASCP disaster warning threshold of the ASCP evolution curve were extracted.

[0127] The area where the rock mass may be damaged was determined by AE positioning test, and this area was set as the AE monitoring space area.

[0128] After completing all the preliminary preparations, turn on the AE device and start the alert;

[0129] Based on the new acoustic emission parameter ASCP, which is a precursor to rock failure, the rock mass at the construction site is monitored in real time during the construction process.

[0130] Analysis of the ASCP evolution curve during the monitoring process ( Figure 4 The changing trend and evolution pattern of ASCP (as shown) are observed to determine whether it reaches the activation warning threshold. The numerical determination method is as follows: Figure 2As shown, in this example, the early warning threshold for the ASCP evolution curve is set to a curve slope k > 35°, and the emergency warning threshold for ASCP is set to ASCP > 2.0. That is, whether the ASCP value has reached the ASCP value corresponding to the peak point of the nonlinear curvature of the new parameter ASCP evolution curve. If the ASCP value has reached the ASCP value corresponding to the peak point of the nonlinear curvature of the new parameter ASCP evolution curve, that is, the warning threshold has been reached, a warning signal is issued and the process proceeds to the next step; if the curve slope k has not reached the ASCP parameter corresponding to the peak point of the nonlinear curvature of the ASCP evolution curve, monitoring continues.

[0131] After issuing the activation warning signal, observe whether ASCP reaches the disaster warning threshold. If the comprehensive value of the new parameter ASCP test results when the rock mass is critically damaged in this type of test reaches the disaster warning threshold, it indicates that the rock mass is about to be damaged. Immediately issue a disaster warning signal and arrange for the evacuation of on-site personnel. If the disaster warning threshold is not reached, continue monitoring and continuously transmit the monitoring data and warning results back to the database to iteratively optimize the correlation model.

[0132] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the present invention.

Claims

1. A real-time early warning method for high-stress rock mass disturbance disasters based on fracture comprehensive signals, comprising the following steps: S1. Acoustic emission signals of rock mass fracture under dynamic disturbance at the engineering site are collected by acoustic signal sensor, acoustic signal characteristic parameters are extracted and sensitive characteristic parameters are screened. The acoustic signal characteristic parameters include waveform amplitude, fractal dimension, LgN / b value, dominant frequency, activity coefficient and real volume. S2. Under true three-dimensional stress conditions, conduct rock mass dynamic disturbance failure tests under different test conditions, simultaneously collect acoustic emission signals from indoor tests and extract sensitive characteristic parameters consistent with those in step S1, and establish a database. S3. Based on the multiple sensitive feature parameters obtained in steps S1 and S2, an ASCP function for comprehensive feature parameters is constructed using a weighted fusion method. The expression of the ASCP function is as follows: ,in These are the weighting coefficients for each sensitive feature parameter; This is a proportional function of each sensitive feature parameter; S4. Compare the ASCP evolution curves at different stages of rock mass failure in engineering field and laboratory tests, analyze the changing trend and evolution law of ASCP through quantitative methods, and establish a one-to-one correspondence between ASCP and rock mass stress state and degree of failure. S5. Based on the changing trend and evolution law of the ASCP evolution curve in step S4, determine the activation warning threshold by the vertical bisector method, and determine the disaster warning threshold by the critical damage data of the indoor test, thus forming multiple warning thresholds. S6. Based on the failure results of the dynamic disturbance of the rock mass in the engineering site and indoor test in steps S1 and S2, the ASCP function is inverted, and the weight coefficients and threshold ranges are dynamically adjusted. S7. Store the data from steps S1 to S6 into the database as samples, and construct the ASCP evolution-threshold criterion association model through MATLAB interpolation and neural network training. S8. Embed the trained ASCP evolution-threshold criterion association model into the monitoring system, collect acoustic emission signals from the engineering site in real time and calculate ASCP. When ASCP reaches the activation threshold, an early warning is triggered. When ASCP reaches the catastrophic threshold, an emergency warning is triggered.

2. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to claim 1, characterized in that: The different test conditions mentioned in step S2 include different stress conditions, different stress levels, different structural surfaces, and different types of surrounding rock units.

3. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture comprehensive signal according to claim 1, characterized in that, The weighting coefficients mentioned in step S3 are determined using the Analytic Hierarchy Process (AHP). The specific process is as follows: A hierarchical evaluation model is constructed based on the monitoring results, including the target layer, the criterion layer, and the scheme layer; Construct the judgment matrix Each sensitive feature parameter is compared pairwise, and the weights of each criterion layer to the target layer are determined to form a judgment matrix. The elements in the middle satisfy , and ; Perform hierarchical single sorting on the judgment matrix. All elements are compared pairwise and then ranked hierarchically to determine their order of importance. The specific calculations are as follows: ， ； After obtaining the weight matrix, calculate the largest eigenvalue. The CI value was calculated, and the random consistency index RI was obtained through multiple Satty simulations. The CR value was then calculated to determine whether the consistency was satisfactory. ， ， ； If CR < 0.1, it indicates that the judgment matrix... Within the error range, its elements can be used as weighting coefficients. ; If CR ≥ 0.1, then the judgment matrix needs to be adjusted. Make corrections.

4. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to claim 1, characterized in that: The scaling function mentioned in step S3 includes the amplitude scaling function. Fractal dimension scaling function ,LgN / b value proportional function and other sensitive characteristic parameters scaling functions; Where x is the number of sensors. Let be the waveform amplitude, fractal dimension, and LgN / b value at time node i, respectively. These represent the maximum values ​​of the sensitive feature parameters corresponding to the i-th time node.

5. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to claim 1, characterized in that, Step S4, which involves analyzing the changing trends and evolutionary patterns of ASCP using quantitative methods, specifically includes: Normalize the ASCP time series: ; The sliding window method is used to smooth the noise; The slope k of the ASCP evolution curve is calculated based on linear regression: k ≥ 0.05 / min is defined as a significant upward trend, 0.01 ≤ k < 0.05 / min is a steady fluctuation, and k < 0.01 / min is a stable state. The control limit L = 3 × ASCP is set using the CUSUM algorithm. norm When the accumulated energy exceeds the limit and the energy of a single acoustic emission event suddenly increases by ≥200%, it is determined to be the catastrophic critical point.

6. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture comprehensive signal according to claim 1, characterized in that, The method of determining the activation warning threshold by perpendicular bisector in step S5 is as follows: extend the slopes of the upper and lower straight line segments of the ASCP evolution curve to intersect at the first point, draw perpendicular bisectors on the upper and lower straight line segments respectively to intersect at the second point, connect the first point and the second point and intersect the ASCP evolution curve at the third point, and the ASCP value corresponding to the third point is the activation warning threshold.

7. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to claim 1, characterized in that, The specific steps of constructing the ASCP evolution-threshold criterion association model through MATLAB interpolation and neural network training in step S7 are as follows: using the interp1 function in MATLAB to interpolate the data, fill in missing data or smooth the data, and using MATLAB's database toolbox to store the interpolation results in the database; then loading the data from the database for preprocessing and converting it into a format suitable for neural network training; then using MATLAB's deep learning toolbox to construct the ASCP evolution law-threshold criterion association model, and training the model by specifying training options.

8. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to claim 7, characterized in that: After the ASCP evolution-threshold criterion association model was constructed, its performance was verified using test data.

9. The real-time early warning method for high-stress rock mass disturbance disaster based on fracture integrated signals according to claim 1, characterized in that: Step S8 also continuously transmits monitoring data and early warning results back to the database to iteratively optimize the correlation model.

Images