A nonlinear dynamic disaster deep well ground pressure monitoring and early warning method and system

Abstract

The application provides a nonlinear dynamic disaster deep well ground pressure monitoring and early warning method and system, relates to the technical field of geological engineering and disaster early warning, and comprises the following steps: according to the mutation theory, the grey theory, the Verhulst model theory, the Verhulst inverse function mode theory and the nonlinear dynamics theory, selecting state variables and control variables, analyzing the variables and key parameters to obtain analysis results; according to the analysis results, predicting the rock mass instability time to obtain prediction results; according to the prediction results, simulating the process of deformation development of the rock mass to instability to obtain the predicted rock mass instability time; taking acoustic emission time series, stress time series and displacement time series as observation sequences, describing the dynamic relationship between the observation sequences, and using the inversion theory to determine the inversion parameters; according to the prediction results, the predicted rock mass instability time and the inversion parameters, evaluating the stability of the rock mass to obtain early warning results. The application can realize comprehensive evaluation and early warning of the stability state of the rock mass.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological engineering and disaster early warning, in particular to a nonlinear dynamic disaster deep well ground pressure monitoring and early warning method and system. BACKGROUND

[0002] With the continuous growth of global demand for mineral resources, mining activities are becoming more frequent and developing deeper, and deep well mining has become an important trend in the development of mineral resources. However, deep well mining faces complex geological environment and severe safety challenges, among which ground pressure disaster is one of the main threats to mine safety production. Ground pressure disaster not only causes roadway collapse and equipment damage, but also may cause serious personnel casualties, bringing huge economic losses and social impact to mining enterprises.

[0003] Traditional ground pressure monitoring methods often rely on single stress monitoring or displacement monitoring means, which is difficult to fully reflect the stability state of rock mass. At the same time, due to the high nonlinearity, fuzziness and uncertainty of rock mass stress deformation process, traditional linear analysis methods are not competent in dealing with complex ground pressure problems. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a nonlinear dynamic disaster deep well ground pressure monitoring and early warning method and system, which comprehensively uses nonlinear scientific theory, catastrophe theory, gray theory, Verhulst model and other advanced theories and technical means, and realizes comprehensive evaluation and early warning of rock mass stability state through real-time collection and comprehensive analysis of multi-dimensional monitoring data such as acoustic emission signal, stress change and displacement change.

[0005] To solve the above technical problems, the technical scheme of the present application is as follows:

[0006] In a first aspect, a nonlinear dynamic disaster deep well ground pressure monitoring and early warning method is provided, the method comprising:

[0007] Acoustic emission signal, stress change data and displacement change data are obtained;

[0008] The collected original data are preprocessed to obtain preprocessed data;

[0009] The acoustic emission event rate, acoustic emission amplitude, stress change amount and displacement change amount are extracted from the preprocessed data to obtain key parameters;

[0010] According to the catastrophe theory, state variables and control variables are selected, and the variables and key parameters are analyzed to obtain analysis results;

[0011] According to the analysis results, the rock mass instability time is predicted to obtain prediction results;

[0012] According to the prediction result, a process of deformation development of the rock mass to instability is simulated to obtain a predicted rock mass instability time;

[0013] The acoustic emission time sequence, the stress time sequence and the displacement time sequence are taken as observation sequences, a dynamic relationship between the observation sequences is described, and an inversion theory is used to determine inversion parameters;

[0014] According to the prediction result, the predicted rock mass instability time and the inversion parameters, the stability of the rock mass is evaluated to obtain a warning result.

[0015] Further, the acoustic emission signal, the stress change data and the displacement change data are acquired, including:

[0016] According to the installation of the acoustic emission sensor, the stress meter and the displacement sensor, data acquisition software is configured;

[0017] The acoustic emission signal, the stress change data and the displacement change data are acquired through the data acquisition software.

[0018] Further, the acoustic emission event rate, the acoustic emission amplitude, the stress change amount and the displacement change amount are extracted from the preprocessed data to obtain key parameters, including:

[0019] A threshold of the preprocessed acoustic emission signal is set, and the acoustic emission event is identified according to the threshold of the acoustic emission signal to obtain the acoustic emission event rate;

[0020] The preprocessed acoustic emission signal is segmented, and the peak amplitude of each signal segment is acquired to obtain the acoustic emission amplitude;

[0021] According to the preprocessed stress data, a reference value of the stress is determined, and the stress change amount of each time point is calculated according to the reference value to obtain the stress change amount;

[0022] According to the preprocessed displacement data, a reference value of the displacement is determined, and the displacement change amount of each time point is calculated through the reference value to obtain the displacement change amount.

[0023] Further, according to the catastrophe theory, state variables and control variables are selected, and the variables and the key parameters are analyzed to obtain analysis results, including:

[0024] According to the catastrophe theory, state variables and control variables are selected, and the state variables are the deformation degree of the rock mass or the stress state, and the control variables are external factors affecting the system behavior, such as loading conditions and material properties;

[0025] According to the state variables and the control variables, X=a0+a1t+a2t 2 +a3t 3 +a4t 4Represent the state variable as a function of time, where a i Here, t is the undetermined coefficient, t is time, and X is the state variable;

[0026] Based on a function of time, through Perform variable substitution and set... To obtain the equilibrium equation Z 3 +aZ+b=06;

[0027] Based on the equilibrium equation, the bifurcation set equation is calculated as 4a. 3 +27b 2 =0, so that the discriminant D = 4a is obtained. 3 +27b 2 a i b is a coefficient in Taylor's expansion. i The transformed coefficients are: q is the adjustment term used to simplify the Taylor expansion; a and b are control variables; D is the bifurcation discriminant; and ΔZ and Δt describe the abrupt changes of the state variables and their corresponding time changes.

[0028] The analytical stability is obtained based on the discriminant to obtain the analytical results.

[0029] Furthermore, based on the analysis results, the time of rock mass instability is predicted to obtain the prediction results, including:

[0030] Based on the analysis results, the original monitoring data of the rock mass is obtained, which is usually time series data, such as displacement, stress or deformation data of the rock mass.

[0031] pass The original data is accumulated once to generate X. (0) (i)>0, where i is the number of monitoring data points with the same time interval, X (0) (i) is the original monitoring data, and (i) is the data generated by one accumulation, which is used to reduce the randomness of the data.

[0032] Based on the data generated from a single accumulation, via Z (1) (i)=(X (1) (i)+X (1) Calculate the mean data using (i-1)÷2, Z (1) (i) is mean-generated data;

[0033] By defining differential equations Solving for the accumulated data X (1) The expression for (t) is When t takes the ordinal number, the above formula becomes: Where i = 1, 2, ..., n; the expressions for a^ and u are: By defining a matrix B and a vector Y, and according to the matrix B and the vector Y, by generating and parameters of u, is the attenuation coefficient of the system, and u is the external input or driving term;

[0034] According to the first accumulation, the data and the mean data are generated, and by X (0) (i) = X (1) (i) - X (1) (i-1) and obtaining the predicted value of the original data;

[0035] According to the predicted value, a critical value S is set, and by calculating the time t of the expected damage event to obtain the predicted rock mass instability time, wherein S is the critical value, and Δt is the time interval of the data.

[0036] Further, according to the prediction result, the process of the deformation development of the rock mass to instability is simulated to obtain the predicted rock mass instability time, including:

[0037] According to the prediction result, the original monitoring data sequence is transformed by the first accumulation to fit into the Verhulst first-order whitening nonlinear differential equation to obtain the rock mass instability geostress disaster Verhulst nonlinear differential dynamic prediction equation;

[0038] Solving the nonlinear differential dynamic prediction equation, predicting the instability time, and converting the predicted instability time into actual time to obtain the actual predicted instability time.

[0039] Further, the acoustic emission time sequence, the stress time sequence and the displacement time sequence are taken as the observation sequence, the dynamic relationship between the observation sequences is described, and the inversion theory is used to determine the inversion parameters, including:

[0040] Collecting the data of the acoustic emission time sequence, the stress time sequence and the displacement time sequence;

[0041] Analyzing the correlation between the acoustic emission, stress and displacement time sequences to obtain the analysis result;

[0042] According to the analysis result, the dynamic relationship between the observation sequences is established to obtain the characteristics of the parameter data;

[0043] According to the characteristics of the data, the observation data is compared with the model prediction result, and the model parameters are continuously adjusted through the iterative optimization process until a certain convergence criterion is met or a predetermined number of iterations is reached, to determine the inversion parameters.

[0044] In a second aspect, a nonlinear dynamic disaster deep well ground pressure monitoring and early warning system comprises:

[0045] An acquisition module is configured to acquire acoustic emission signals, stress change data and displacement change data, pre-process the collected original data to obtain pre-processed data, extract acoustic emission event rate, acoustic emission amplitude, stress change amount and displacement change amount from the pre-processed data to obtain key parameters, select state variables and control variables according to the catastrophe theory, analyze the variables and the key parameters to obtain analysis results.

[0046] A processing module is configured to predict rock mass instability time according to the analysis results to obtain prediction results, simulate the process of deformation development of the rock mass to instability according to the prediction results to obtain predicted rock mass instability time, take the acoustic emission time sequence, the stress time sequence and the displacement time sequence as observation sequences, describe the dynamic relationship between the observation sequences, and use the inversion theory to determine inversion parameters, and evaluate the stability of the rock mass according to the prediction results, the predicted rock mass instability time and the inversion parameters to obtain early warning results.

[0047] In a third aspect, a computing device comprises:

[0048] One or more processors;

[0049] A storage device is configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method.

[0050] In a fourth aspect, a computer readable storage medium stores a program, and when the program is executed by a processor, the method is implemented.

[0051] The above-mentioned scheme of the present application at least has the following beneficial effects:

[0052] By comprehensively using the nonlinear scientific theory, the nonlinear, fuzzy and uncertain characteristics of the rock mass can be more accurately described, thereby improving the accuracy of the ground pressure disaster early warning, and through real-time monitoring of the acoustic emission signals, stress changes and displacement changes and extraction of key parameters for analysis, early warning can be made before the rock mass instability, sufficient time is provided for the mining enterprises to take preventive measures, and the occurrence of disastrous accidents is avoided, a complementary advantage is formed by combining acoustic emission monitoring, stress monitoring and displacement monitoring and other technical means, through multi-parameter comprehensive analysis, the stability state of the rock mass can be more comprehensively reflected, and based on the nonlinear dynamics model, the catastrophe theory and other scientific methods, a systematic early warning mechanism is established, the monitoring data are scientifically analyzed, the limitations of a single method are avoided, and the scientificity and systematicness of the early warning are improved. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 is a flowchart of a nonlinear dynamic disaster deep well ground pressure monitoring and early warning method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0054] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood, and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0055] As Figure 1 shown, an embodiment of the present application proposes a nonlinear dynamic disaster deep well ground pressure monitoring and early warning method, which comprises the following steps:

[0056] Step 11, acquiring acoustic emission signals, stress change data and displacement change data;

[0057] Step 12, pre-processing the collected original data to obtain pre-processed data;

[0058] Step 13, extracting acoustic emission event rate, acoustic emission amplitude, stress change and displacement change from the pre-processed data to obtain key parameters;

[0059] Step 14, according to the catastrophe theory, selecting state variables and control variables, analyzing the variables and key parameters to obtain analysis results;

[0060] Step 15, according to the analysis results, predicting the rock mass instability time to obtain prediction results;

[0061] Step 16, according to the prediction results, simulating the process of deformation development to instability of the rock mass to obtain the predicted rock mass instability time;

[0062] Step 17, taking acoustic emission time sequence, stress time sequence and displacement time sequence as observation sequences, describing the dynamic relationship between the observation sequences, and using inversion theory to determine inversion parameters;

[0063] Step 18, according to the prediction results, the predicted rock mass instability time and the inversion parameters, evaluating the stability of the rock mass to obtain early warning results.

[0064] In the embodiment of the present application, the early warning system can capture the dynamic changes of the rock mass in real time, improve the data quality, and reduce the influence of noise and error: by extracting the acoustic emission event rate, acoustic emission amplitude, stress change and displacement change from the preprocessed data, the key indicators of the stability state of the rock mass are directly related, which helps to quickly identify the precursor information of rock mass instability; using the catastrophe theory can scientifically and systematically analyze the nonlinear change process of the rock mass, improve the accuracy and scientificity of the early warning analysis, provide timely and accurate early warning information for the mining enterprises, so that they have enough time to take preventive measures and reduce the possibility and loss of disasters; by simulating the deformation process of the rock mass, the mechanism and development trend of rock mass instability can be more intuitively understood, which provides a scientific basis for early warning and emergency response, the model parameters are optimized through the inversion theory, the adaptability and accuracy of the early warning model are improved, and the early warning result is closer to the actual situation; the stability state of the rock mass is comprehensively evaluated, and a comprehensive early warning report is provided for the mining enterprises to guide them to develop a scientific and reasonable safety production plan.

[0065] In a preferred embodiment of the present application, the above step 11 comprises:

[0066] According to the installation of the acoustic emission sensor, the stress meter and the displacement sensor, the data acquisition software is configured;

[0067] The changes of the acoustic emission signal, the stress change data and the displacement change data are monitored in real time through the data acquisition software, and the acoustic emission signal, the stress change data and the displacement change data are acquired.

[0068] In the embodiment of the present application, through the real-time monitoring function of the data acquisition software, the mining enterprises can immediately master the dynamic change of the rock mass. The professional data acquisition software can automatically process the original data, reduce the human error, and improve the accuracy and reliability of the data; the acoustic emission sensor, the stress meter and the displacement sensor are installed to realize the comprehensive monitoring of different physical quantities of the rock mass; the automatic characteristics of the data acquisition software greatly reduce the burden of manual monitoring and improve the monitoring efficiency. At the same time, through the integration of intelligent algorithms, the software can automatically analyze the data, identify abnormal patterns, and realize the intelligentization of early warning.

[0069] In a specific embodiment of the present application, the acoustic emission sensor, stress meter and displacement sensor are selected according to the monitoring requirements. The acoustic emission sensor should have high sensitivity to capture weak acoustic emission signals; the stress meter should be able to accurately measure the stress change of the rock mass; the displacement sensor should have high resolution and stability, and be able to accurately measure the displacement change of the rock mass. The mine site is surveyed to understand the geological structure, mining progress and potential dangerous areas, and the installation position of the sensor is determined according to the survey results, usually in the deformation sensitive area, stress concentration area or potential damage area of the rock mass, and the sensor is installed according to the sensor instruction manual. Select the data acquisition software to ensure that the software can support the access of multiple sensors and has the functions of real-time data acquisition, storage and analysis. Install the software on the monitoring center or designated computer. Connect the sensor to the data acquisition software through wired or wireless mode. According to the interface type of the sensor, configure the corresponding interface in the software, set the sampling rate, range, filter and other parameters of the sensor in the data acquisition software to ensure the accuracy and effectiveness of data acquisition. At the same time, set the data storage path and format for subsequent data processing and analysis, open the data acquisition software and start the real-time monitoring function. The software will automatically receive data from the sensor and perform preliminary processing, and display the acoustic emission signal, stress change data and displacement change data in real time on the software interface. At the same time, the software will automatically store these data in the format and path set for subsequent analysis.

[0070] In a preferred embodiment of the present application, step 12 comprises:

[0071] The collected raw data is cleaned to remove outliers, and the cleaned data is converted, standardized / nomalized and filtered to obtain processed data.

[0072] In an embodiment of the present application, the data cleaning process can remove noise, errors and outliers from the raw data, ensuring that subsequent analysis is based on accurate and reliable data sets; data standardization / nomalization processing enables features of different dimensions and orders of magnitude to be compared and calculated on the same scale, which is crucial for many machine learning algorithms; filtering processing can remove high-frequency noise and unnecessary fluctuations in the data, making the data smoother and conducive to subsequent data analysis. At the same time, reducing the redundancy in the data can reduce computational complexity and improve processing efficiency; the data cleaned, converted and filtered is closer to the actual situation and can more accurately reflect the actual state of the rock mass.

[0073] In a specific embodiment of the present application, each data point is compared with a defined standard to identify outliers, the identified outliers are directly deleted, the outliers are replaced with mean, median, mode or other reasonable values, all measurements are converted to the same unit to avoid calculation errors caused by inconsistent units, the data is converted from the original format to a numerical format suitable for analysis, for time series data, the accuracy and consistency of the time stamp need to be ensured, which may require time zone conversion or format adjustment. Scale the data to fall within a small specific interval: scale the data to fall within the [0, 1] interval, but do not necessarily change the shape of the data distribution; apply a selected standardization / normalization method to each feature to obtain new feature values. Filter the data to remove noise or unwanted frequency components.

[0074] In a preferred embodiment of the present application, step 13 is performed by extracting the acoustic emission event rate, acoustic emission amplitude, stress change amount and displacement change amount from the preprocessed data to obtain key parameters, including:

[0075] A threshold value of the preprocessed acoustic emission signal is set, and an acoustic emission event is identified according to the threshold value of the acoustic emission signal to obtain the acoustic emission event rate;

[0076] The preprocessed acoustic emission signal is segmented to obtain the peak amplitude of each signal segment to obtain the acoustic emission amplitude;

[0077] The reference value of the stress is determined according to the preprocessed stress data, and the stress change amount at each time point is calculated according to the reference value to obtain the stress change amount;

[0078] The reference value of the displacement is determined according to the preprocessed displacement data, and the displacement change amount at each time point is calculated according to the reference value to obtain the displacement change amount.

[0079] In an embodiment of the present application, the acoustic emission event is identified by setting a reasonable threshold value, which can accurately distinguish between background noise and real rock mass fracture signals. The peak amplitude of the acoustic emission signal is directly related to the energy release of the crack propagation in the rock mass. By calculating the peak amplitude of each signal segment, the strength of rock mass fracture can be quantified. The reference value of the stress is determined and the stress change amount at each time point is calculated, which can directly reflect the dynamic change of the stress on the rock mass. By calculating the reference value of the displacement and the displacement change amount at each time point, the overall deformation trend and local damage of the rock mass can be evaluated.

[0080] In a specific embodiment of the present application, a suitable threshold value is selected according to historical data or statistical analysis. The threshold value is used to distinguish background noise and meaningful acoustic emission signals. The pre-processed acoustic emission signals are traversed, and when the signal amplitude exceeds the set threshold value, it is considered that an acoustic emission event has occurred, and the starting time and ending time of the event and the signal characteristics during the event are recorded. The number of acoustic emission events occurring in a given time window is counted, and the event number is divided by the length of the time window to obtain the acoustic emission event rate. The pre-processed acoustic emission signals are divided into several equal-length signal segments, and for each signal segment, the maximum value, i.e. the peak amplitude, is found; the peak amplitude and time position of each signal segment are recorded. The average stress value in the time period is selected as the reference value, and the pre-processed stress data is traversed. For each time point, the difference between the current stress value and the reference value, i.e. the stress change, is calculated, and the stress change at each time point is recorded. The average displacement value in the time period is selected as the reference value, and the pre-processed displacement data is traversed. For each time point, the difference between the current displacement value and the reference value, i.e. the displacement change, is calculated. The displacement change at each time point is recorded.

[0081] In a preferred embodiment of the present application, step 14, according to the catastrophe theory, selects state variables and control variables, analyzes the variables and key parameters to obtain analysis results, including:

[0082] According to the catastrophe theory, state variables and control variables are selected, the state variables are the deformation degree or stress state of the rock mass, and the control variables are external factors affecting the system behavior, such as loading conditions and material properties;

[0083] According to the state variables and control variables, the state variable X is expressed as a function of time t, where a 2 , t is time, and X is the state variable; 3 , t is time, and X is the state variable; 4 , t is time, and X is the state variable; i is a coefficient to be determined, t is time, and X is the state variable;

[0084] According to the function of time, variable substitution is performed by , and is set to obtain the balance equation Z 3 +aZ+b=0;

[0085] According to the balance equation, the bifurcation set equation is calculated as 4a 3 +27b 2 =0, to obtain the discriminant D=4a 3 +27b 2 , a i is the coefficient in the Taylor expansion, and b iTransformed coefficients, q is an adjustment term for simplifying Taylor expansion, a, b are control variables, D is a bifurcation discriminant, and Delta Z and Delta t are state variable mutations and their corresponding time changes;

[0086] Obtaining analysis stability according to the discriminant to obtain analysis results.

[0087] In the embodiments of the present application, the catastrophe theory provides a systematic and physically-based method to predict the instability behavior of rock mass; the early warning results obtained by this method are more scientific and reliable. By monitoring the state variables and control variables in real time and applying the catastrophe theory for analysis, early warning signals can be found in time before the instability of the rock mass, thus providing valuable response time for the mine enterprises. The catastrophe theory is not only used for prediction, but also helps to understand the internal mechanism of the rock mass instability; according to the analysis results of the catastrophe theory, the arrangement of monitoring points and the monitoring frequency can be optimized, thus improving the monitoring efficiency and reducing the cost.

[0088] In a specific embodiment of the present application, physical quantities reflecting the current state of the rock mass, such as the deformation degree or stress state of the rock mass, are selected, and external factors affecting the stability of the rock mass, such as loading conditions, material properties and geological conditions, are identified and quantified. The displacement change, acoustic emission event number change and stress change in the deformation process of the rock have obvious time effectiveness, and the parameter variables (X, Y, Z) can be regarded as functions of time T, i.e. X=f(t), thus can be expressed by Taylor formula expansion as: X=f(t)=a0+a1t+a2t 2 +…+a n t n , wherein a0, a1, … a n are undetermined coefficients. In actual engineering research, it can be approximately written as: X=f(t)=a0+a1t+a2t 2 +a3t 3 +a4t 4 , the undetermined coefficients in the formula can be obtained by regression analysis, according to the function of time, variable substitution is performed, and t=Z t -q, is obtained: , wherein b0=a4q 4 -a3q 3 +a2q 2 -a1q+a0, b1=-4a4q 3 +3a3q 2 -2a2q+a1, b2=6a4q 2 -3a3q+2a2, b4=a4, when further variable substitution is performed, and or Assuming that b4>0, then Where: C is the shear term, which is meaningless for catastrophe analysis; a, b are respectively: When C is not considered, that is, the cusp catastrophe model with Z as the state variable and a, b as the control variables, according to the catastrophe theory principle, let The equilibrium surface equation is: Z 3 +aZ+b=0, which gives the relationship between the state variable Z and the control variables a, b, and can be represented as a surface graph. The folding or cusp point set of the surface graph is called the singularity set, and its projection on the a-b plane is called the bifurcation set. The bifurcation set equation is: 4a 3 +27b 2 =0, let D=4a 3 +27b 2 , the bifurcation set is a half cubic parabola with a cusp at (0, 0). The (a, b) point on the bifurcation set (D=0) corresponds to the unstable state (critical state) of the system, and the system can mutate from one equilibrium state to another. At the same time, the bifurcation set also divides the control variable plane into two regions: in the larger region, D>0, the system is in a stable state; in the smaller region, D<0, the system has three equilibrium states, two of which are stable and one of which is unstable. This means that when D<0, the rock mass may lose stability. The criterion for judging the unstable point is: From the above analysis, there are two cases for the rock mass system to undergo catastrophe: ① D=0; ② D<0 and 3Z 2 +a<0. The catastrophe referred to by the right branch of the bifurcation set (b>0) means that the mathematical structure of the system (the number of equilibrium states and stability) has changed, but the value of the state variable Z has not jumped. For mine rock mass instability and pressure disaster prediction, the situation of crossing the left branch of the bifurcation set (b<0) is meaningful, as the corresponding point is an unstable state and the value of Z jumps. Now determine the state variable value corresponding to each point on the left branch of the bifurcation set (b<0). Under the condition that equation (2.15) is established, when a=0, equation (2.15) has three zero roots, Z1=Z2=Z3=0; when a<0, equation (2.14) has three real roots, respectively: The state variable Z undergoes catastrophe when crossing the bifurcation set, According to the substitution described, the corresponding time difference between before and after the rock mass loses stability is: The time difference Δt between the critical state (D=0) and failure can be calculated, and the sum of Δt and the duration of the critical state is the rock mass instability time. When D<0 and 3Z 2 +a<0, the system is inside the bifurcation set, and the failure time calculated by the above method is generally greater than the actual failure time. Assuming b4<0, the state of the rock mass is exactly the opposite of the result discussed above.

[0089] In a preferred embodiment of the present application, the step 15 is to predict the time of rock mass instability according to the analysis result, to obtain a prediction result, comprising:

[0090] According to the analysis result, the original monitoring data of the rock mass, usually time series data, such as displacement, stress or deformation data of the rock mass, are obtained.

[0091] Through a first cumulative generation of the original data, wherein X (0) (i) > 0, i is the number of monitoring data of the same interval time, X (0) (i) is the original monitoring data, and (i) is the first cumulative generation data, used to reduce the randomness of the data.

[0092] According to the first cumulative generation data, mean value data are calculated through Z (1) (i) = (X (1) (i) + X (1) (i-1)) ÷ 2, Z (1) (i) is the mean value generation data.

[0093] By defining a differential equation, the expression of the first cumulative generation data X (1) (t) is obtained as wherein, when t takes the serial number, the above formula becomes: wherein, i = 1, 2, …, n; a^ and u are expressed as By defining a matrix B and a vector Y, and according to the matrix B and the vector Y, parameters of and u are generated through is the decay coefficient of the system, and u is the external input or driving term.

[0094] According to the first cumulative generation data and the mean value data, the prediction value of the original data is obtained through X (0) (i) = X (1) (i) - X (1) (i-1) and

[0095] According to the prediction value, a critical value S is set, and the time t of the expected damage event is calculated through to obtain the predicted time of rock mass instability, wherein S is the critical value, and Δt is the time interval of the data.

[0096] ​​In the embodiment of the present application, the randomness of data is reduced by cumulative generation, so that the prediction result is more accurate, a large amount of sample data is not required, the small sample and poor information system has good adaptability, the parameter solving process is relatively simple, the calculation amount is small, it is suitable for real-time online prediction, the principle is intuitive, through real-time monitoring and prediction, a warning signal can be sent before the rock mass instability, and valuable time is provided for the mine enterprise to take preventive measures.

[0097] In a specific embodiment of the present application, the original time series data of the rock mass are obtained from the monitoring system, and the data can be displacement, stress or deformation data. It is assumed that the data are arranged in time sequence, and each time point corresponds to a data point. A one-time cumulative data generation method is usually used to generate a certain transformation of the original data, and the formula can be expressed as: Wherein, i is the number of monitoring data of the same interval time, X (1) (i) is one-time cumulative generated data, and the number in the upper right corner of the bracket represents the number of accumulations; X (0) (i) is non-negative monitoring data before accumulation, and the mean generated data is calculated according to the following formula: Z (1) (i) = [X (1) (i) + X (1) (i-1)] / 2, and the differential equation is set as Then is called the derivative of x, and x is the background value of ; a and b are parameters, and X (1) (t) is obtained by a first-order linear differential equation: The equation is solved to obtain: When t takes the serial number, the above formula becomes: In the formula, the coefficients a and u can be obtained according to the following formula: Wherein: X (0) (i) = X (1) (i) - X (1) (i-1) and The critical value S can be substituted into the above formula to obtain the failure event t: Wherein, Δt is the time interval of the monitoring data. After the prediction result is obtained, the accuracy of the model is verified, and if the error is large, the residual error sequence can be established to correct the error.

[0098] In a preferred embodiment of the present application, the step 16 comprises:

[0099] Based on the prediction results, the original monitoring data sequence is subjected to a cumulative generation transformation and fitted into a Verhulst first-order whitening nonlinear differential equation to obtain the Verhulst nonlinear differential dynamic prediction equation for rock mass instability and ground pressure disaster.

[0100] The nonlinear differential dynamic prediction equation is solved to predict the instability time, and the predicted instability time is converted into the actual time to obtain the actual predicted instability time.

[0101] In this embodiment of the invention, the Verhulst model can effectively describe systems with saturated growth characteristics. The parameters in the model help to understand the physical mechanisms of rock mass instability, making it suitable for rock mass instability prediction. It can also be extended to the prediction of other systems with similar growth characteristics. Unlike some short-term prediction methods, the Verhulst model supports long-term prediction of rock mass stability, which helps mining companies formulate long-term safety production plans. Through feedback from real-time monitoring data and model prediction results, mining companies can make more scientific decisions, optimize mining plans, and improve production efficiency and safety.

[0102] In a specific embodiment of the present invention, based on the prediction result, the original monitoring data sequence is subjected to an accumulation generation transformation to obtain the original equally spaced monitoring data sequence X. (0) (t): X (0) (t)={X (0) (1),X (0) (2)…X (0) Applying an AGO transformation to X(0)(t) (n)}, we get: X (1) (t)={X (1) (1),X (1) (2)…X (1) (n)}. X(1)(t) is fitted with the Verhulst first-order whitening nonlinear differential equation: Where a and b are undetermined coefficients, which can be obtained using the least squares method: and Y N =[X (0) (2),X (0) (3),…X (0) (n)) T The solution to the nonlinear differential equation is obtained by solving the undetermined coefficients. This is the established Verhulst nonlinear differential dynamic prediction model for rock mass instability and ground pressure disasters, where: t0 = 0 is the initial time, if X (0)(t) is non-equidistant time series data, it should be converted into equidistant time series, and then the model is established. The rock mass instability process is similar to the biological process from reproduction to death. Therefore, the critical value a / 2b of the biological model can be used as the critical judgment value (displacement, acoustic emission, stress) of instability. According to a / 2b, That is, the instability time t is obtained: The initial moment t0=0, then: The true prediction time is: T=t*Δt, wherein t is the time series number; and Δt is the average interval time of monitoring data.

[0103] In a preferred embodiment of the present application, the step 17 described above, the acoustic emission time sequence, the stress time sequence and the displacement time sequence are used as observation sequences, the dynamic relationship between the observation sequences is described, and the inversion theory is used to determine the inversion parameters, including:

[0104] Collecting data of acoustic emission time sequence, stress time sequence and displacement time sequence;

[0105] Analyzing the correlation between acoustic emission, stress and displacement time sequence to obtain analysis results;

[0106] According to the analysis results, the dynamic relationship between the observation sequences is established to obtain the characteristics of the parameter data;

[0107] According to the characteristics of the data, the observation data is compared with the model prediction results, and the model parameters are continuously adjusted through the iterative optimization process until a certain convergence criterion is met or a predetermined number of iterations is reached, so as to determine the inversion parameters.

[0108] In the embodiment of the present application, by comprehensively considering the time sequence data of acoustic emission, stress and displacement and other physical quantities, the stability state of the rock mass can be more comprehensively reflected, the iterative optimization process enables the model parameters to be dynamically adjusted according to the actual observation data, based on the analysis of the data and the model prediction results, the mining enterprises can make more scientific and reasonable decisions, optimize the mining scheme, collect and analyze the time sequence data in real time, so that the early warning system can timely discover the abnormal changes of the rock mass, and provide timely early warning information for the mine; by establishing a more accurate and reliable early warning system, the mining enterprises can more effectively manage the ground pressure disaster risk and improve the overall safety management level.

[0109] In a specific embodiment of the present application, the data of acoustic emission time sequence, stress time sequence and displacement time sequence are collected, and the Verhulst inverse function model is established, which can improve the accuracy of the model early warning and prediction, and can reduce the influence of random fluctuations. The Verhulst model is: When t→0, there is That is, when time t tends to infinity, the displacement value of the characteristic curve of the Verhulst prediction model tends to a characteristic value a / b, therefore, after variable exchange, the characteristic curve of the inverse function model is symmetrical about the X axis with the Verhulst model curve. When the displacement amount tends to infinity, the time t tends to a certain value. In theory: the deformation amount of the rock mass or the number of acoustic emission events or the stress change value tends to infinity, which means that the rock mass is unstable and damaged. Therefore, the certain value of the time t can be used as the prediction time of the rock mass instability and damage, and the Verhulst first-order whitening nonlinear differential equation is: The solution of the differential equation is: The inverse function of the above formula is obtained, and variable exchange is performed to obtain: The above formula is the Verhulst inverse function model of the established ground pressure disaster early warning and prediction. Wherein, t is the time sequence number; a and b are to-be-determined coefficients. When , then: When the displacement amount tends to infinity, that is: at0-bt0·t→0. The initial time t0≠0, generally t0≥1, then: t→a / b. When the deformation amount of the rock tends to infinity, the time t tends to a certain value (a / b). Therefore, T=a / b can be used as the instability prediction time. According to the least square method, a and b are obtained from the following formula:

[0110] Wherein: d (k) =1 / (X (0) (k-t0+1)·k), after t0 is obtained, the prediction time from the starting point of the modeling data to the rock damage is: T=a / b-t0.

[0111] In a preferred embodiment of the present application, the above-mentioned step 18 comprises:

[0112] The prediction results obtained by the nonlinear dynamic disaster deep well ground pressure monitoring and early warning method are comprehensively analyzed to obtain analysis results, including but not limited to the prediction value of the rock mass instability time, the change trend of acoustic emission activity, the stress change characteristics and the displacement change rate;

[0113] The current analysis results are compared with the rock mass stability monitoring data under similar geological conditions and mining conditions in the past to obtain comparison results;

[0114] According to the comparison results, the stability of the rock mass is evaluated to obtain early warning results.

[0115] In the embodiment of the present application, by comprehensively analyzing the prediction result and comparing with the historical data, the stability state of the rock mass can be more accurately evaluated, the early warning result provides a scientific decision basis for the mining enterprises, and helps to reasonably arrange the mining plan, strengthen the supporting measures or take other necessary preventive measures; the rock mass instability risk can be found and warned in time, which helps to avoid or reduce the occurrence of ground pressure disaster and ensure the safe production of the mine.

[0116] In a specific embodiment of the present application, X 、 Y, Z are three different observation sequences, respectively representing stress time sequence, acoustic emission time sequence and displacement time sequence, which together constitute three observation sequences in the nonlinear dynamics model of rock mass damage instability ground pressure disaster. Considering that the dimensions and orders of magnitude of X, Y and Z are different, therefore, they should be standardized first, and the average value of the observation sequence can be generally used as the standardization factor. From the physical properties of the system, f i is a certain nonlinear function, for the ground pressure disaster prediction system, is the general form

[66] -

[68] , and the nonlinear dynamics mathematical model equation is as follows:

[0117]

[0118]

[0119] In the formula: a1, a2, … a9, b 1, b2…, b9 and c 1,C2…, C9 are constants to be determined by inversion, which can be determined by inversion theory. Then, the parameters are brought into the above formula, and the nonlinear dynamics prediction result of the ground pressure monitoring y early warning is obtained; the latest prediction result is derived from the nonlinear dynamic disaster deep well ground pressure monitoring and early warning system, including but not limited to the prediction value of the rock mass instability time, the change trend data of acoustic emission activity, the stress change data and the displacement change data; the specific time point or time period of the possible instability of the rock mass given in the prediction report is viewed, the urgency and accuracy thereof are evaluated, the change trend graph of the acoustic emission event rate and amplitude is drawn using charts or statistical software, the frequency, intensity and duration of the acoustic emission activity are analyzed, the development of the internal damage of the rock mass is judged, the stress change curve graph is drawn, the stress concentration, release and fluctuation are observed; the relationship between the stress change and the mining activity, geological structure and other factors is analyzed, and the possible stress abnormal area is identified. The displacement change rate graph is calculated and drawn, the overall deformation trend and local deformation characteristics of the rock mass are observed, the relationship between the displacement change rate and the rock mass stability is analyzed, and whether there is a sign of rapid deformation or sudden displacement is judged. The rock mass stability monitoring data under similar geological conditions and mining conditions in the past is retrieved from the database, and the historical data and the current prediction result are aligned in terms of time scale and monitoring parameters. The predicted value of the rock mass instability time and the historical instability record are compared, the change trend of the acoustic emission activity, the stress change characteristics and the displacement change rate and other key parameters are compared, and the difference and significance of the comparison result are quantified using statistical methods. According to the comparison result, the current stability state of the rock mass is comprehensively evaluated; whether the rock mass is in a high-risk state, that is, whether it is close to or has reached the critical condition before the historical instability is judged. According to the stability evaluation result, the warning level and warning information are determined, and a detailed warning report is made, including the warning area, warning level, predicted instability time range, possible influence range and recommended preventive measures.

[0120] Embodiments of the present application also provide a nonlinear dynamic disaster deep well ground pressure monitoring and early warning system, comprising:

[0121] The acquisition module is configured to acquire the acoustic emission signal, the stress change data and the displacement change data; pre-process the collected original data to obtain pre-processed data; extract the acoustic emission event rate, the acoustic emission amplitude, the stress change amount and the displacement change amount from the pre-processed data to obtain key parameters; select state variables and control variables according to the catastrophe theory, analyze the variables and the key parameters to obtain analysis results;

[0122] The processing module is configured to predict the rock mass instability time according to the analysis result to obtain a prediction result, simulate a process of deformation development of the rock mass to instability according to the prediction result to obtain a predicted rock mass instability time, use the acoustic emission time sequence, the stress time sequence and the displacement time sequence as observation sequences, describe a dynamic relationship between the observation sequences, and determine inversion parameters by using an inversion theory, and evaluate the stability of the rock mass according to the prediction result, the predicted rock mass instability time and the inversion parameters to obtain a pre-warning result.

[0123] It should be noted that the system corresponds to the method described above, and all implementation manners in the method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0124] Embodiments of the present application also provide a computing device, comprising a processor and a memory storing a computer program, wherein the computer program is executed by the processor to perform the method described above. All implementation manners in the method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0125] Embodiments of the present application also provide a computer readable storage medium storing instructions, wherein the instructions are executed on a computer to make the computer perform the method described above. All implementation manners in the method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0126] The above is the preferred embodiment of the present application, and it should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A nonlinear dynamic disaster deep well ground pressure monitoring and early warning method, characterized in that, The method comprises: acquiring acoustic emission signals, stress change data and displacement change data; preprocessing the collected original data to obtain preprocessed data; extracting acoustic emission event rates, acoustic emission amplitudes, stress change amounts and displacement change amounts from the preprocessed data to obtain key parameters; selecting state variables and control variables according to the catastrophe theory, analyzing the variables and the key parameters to obtain analysis results; predicting the rock mass instability time according to the analysis results to obtain prediction results, including: acquiring the original monitoring data of the rock mass, which is time series data, including the displacement, stress or deformation data of the rock mass, according to the analysis results; By The original data is accumulated once to generate, wherein, > 0, i is the number of monitoring data of the same interval time, is the original monitoring data, is the accumulated data once to generate, used to reduce the randomness of data; According to the once accumulated generation data, by calculating mean data, is the mean generation data; By defining the differential equation, , the expression of the first-order cumulative generating data is , where, when t takes the serial number, the above formula becomes: , where, ; the expressions of a^ and u are , by defining the matrix B and the vector Y, , , and according to the matrix B and the vector Y, the parameters of a^ and u are generated by , and , and u are generated, is the attenuation coefficient of the system, and u is the external input or driving term; According to the once accumulated generation data and the mean data, the predicted value of the original data is obtained by and ​ According to the predicted value, a critical value S is set by calculating the time t of the expected failure event to obtain the predicted rock mass instability time, wherein S is the critical value, is the time interval of the data; simulating the deformation development of the rock mass to instability according to the prediction results to obtain the predicted rock mass instability time; taking the acoustic emission time series, stress time series and displacement time series as observation sequences, describing the dynamic relationship between the observation sequences, and using the inversion theory to determine the inversion parameters; evaluating the stability of the rock mass according to the prediction results, the predicted rock mass instability time and the inversion parameters to obtain early warning results.

2. The method according to claim 1, wherein, Acquiring acoustic emission signals, stress change data and displacement change data comprises: configuring data acquisition software according to the installation of acoustic emission sensors, stress gauges and displacement sensors; acquiring acoustic emission signals, stress change data and displacement change data by monitoring the changes of the acoustic emission signals, stress change data and displacement change data in real time through the data acquisition software.

3. The nonlinear dynamic disaster deep mine pressure monitoring and early warning method according to claim 2, characterized in that, Extracting acoustic emission event rates, acoustic emission amplitudes, stress change amounts and displacement change amounts from the preprocessed data to obtain key parameters comprises: setting a threshold value of the preprocessed acoustic emission signals, and identifying acoustic emission events according to the threshold value of the acoustic emission signals to obtain acoustic emission event rates; segmenting the preprocessed acoustic emission signals to obtain the peak amplitudes of each signal segment to obtain acoustic emission amplitudes; determining a reference value of stress according to the preprocessed stress data, and calculating the stress change amount at each time point according to the reference value to obtain the stress change amount; determining a reference value of displacement according to the preprocessed displacement data, and calculating the displacement change amount at each time point through the reference value to obtain the displacement change amount.

4. The nonlinear dynamic disaster deep mine pressure monitoring and early warning method according to claim 3, characterized in that, Selecting state variables and control variables according to the catastrophe theory, analyzing the variables and the key parameters to obtain analysis results comprises: selecting state variables and control variables according to the catastrophe theory, the state variables being the deformation degree or stress state of the rock mass, and the control variables being external factors affecting the system behavior, loading conditions and material properties; According to the state variable and the control variable, by representing the state variable as a function of time, wherein a i is a pending coefficient, is time, is the state variable; According to a function of time, by variable substitution, and setting to obtain ; According to , , to obtain , a, b are control variables, and D is a bifurcation discriminant According to Obtain analytical stability to obtain analytical results.

5. The nonlinear dynamic disaster deep mine pressure monitoring and early warning method according to claim 4, characterized in that, Simulating the deformation development of the rock mass to instability according to the prediction results to obtain the predicted rock mass instability time comprises: generating a transformation by once accumulating the original monitoring data sequence according to the prediction results, fitting into a Verhulst first-order whitening nonlinear differential equation to obtain a rock mass instability geostress disaster Verhulst nonlinear differential dynamic prediction equation; solving the nonlinear differential dynamic prediction equation, predicting the instability time, and converting the predicted instability time into actual time to obtain the actual predicted instability time.

6. The nonlinear dynamic disaster deep mine pressure monitoring and early warning method according to claim 5, characterized in that, The acoustic emission time sequence, stress time sequence and displacement time sequence are taken as observation sequences, the dynamic relationship between the observation sequences is described, and the inversion theory is used to determine the inversion parameters, including: Collecting data of acoustic emission time sequence, stress time sequence and displacement time sequence; Analyzing the correlation between acoustic emission, stress and displacement time sequence to obtain analysis results; According to the analysis results, the dynamic relationship between the observation sequences is established to obtain the characteristics of the parameter data; According to the characteristics of the data, the observation data is compared with the model prediction results, and the model parameters are continuously adjusted through an iterative optimization process until a certain convergence criterion is met or a predetermined number of iterations is reached, to determine the inversion parameters.

7. A nonlinear dynamic disaster deep mine pressure monitoring and early warning system, characterized in that, Including: An acquisition module is configured to acquire acoustic emission signals, stress change data and displacement change data; The collected raw data is preprocessed to obtain preprocessed data; The acoustic emission event rate, acoustic emission amplitude, stress change and displacement change are extracted from the preprocessed data to obtain key parameters; According to the catastrophe theory, the state variables and control variables are selected, and the variables and key parameters are analyzed to obtain analysis results; A processing module is configured to predict the rock mass instability time according to the analysis results to obtain prediction results, including: According to the analysis results, the original monitoring data of the rock mass, which is time series data, is obtained, including the displacement, stress or deformation data of the rock mass; By a first accumulation generation is performed on the original data, wherein, > 0, i is the number of monitoring data of the same interval time, is the original monitoring data, is the first accumulation generation data, used to reduce the randomness of the data; According to the once accumulated generation data, by calculating mean data, is the mean generation data; By defining the differential equation, , the expression of the first-order cumulative generating data is , where, when t takes the serial number, the above formula becomes: , where, ; a^ and u expressions are , by defining the matrix B and the vector Y, , , and according to the matrix B and the vector Y, by , the parameters of and u are generated , is the attenuation coefficient of the system, and u is the external input or driving term; According to the once accumulated generation data and the mean data, the predicted value of the original data is obtained by and ​ According to the prediction value, a critical value S is set by a time t of an expected failure event is calculated to obtain a predicted rock mass instability time, wherein S is a critical value, is a time interval of data; a process of deformation development of the rock mass to instability is simulated according to a prediction result to obtain a predicted rock mass instability time; acoustic emission time series, stress time series and displacement time series are taken as observation sequences, dynamic relationships among the observation sequences are described, and inversion theory is used to determine inversion parameters; and stability of the rock mass is evaluated according to the prediction result, the predicted rock mass instability time and the inversion parameters to obtain a warning result.

8. A computing device, comprising: Including: One or more processors; A storage device is configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program, which is executed by the processor to implement the method of any one of claims 1 to 6.

Images