Goaf detection method based on joint inversion of transient electromagnetic and seismic wave fields

Abstract

The present invention provides a goaf detection method based on the joint inversion of transient electromagnetic and seismic wave fields. By jointly collecting data and jointly inverting the goaf through a transient electromagnetic detection system and a reflection seismic detection system, the complementary advantages of the two detection methods are brought into play, the bottlenecks of a single method in terms of resolution and signal-to-noise ratio are broken through, and the fine characterization of the structure, physical properties and stability of the goaf is achieved. A machine learning classification algorithm is introduced to analyze the multi-attribute feature data set of the goaf, so as to realize the intelligent discrimination of the type, scale and stability of the goaf under complex geological conditions. A quantitative response relationship between the physical property parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf is established, a numerical model of the joint transient electromagnetic and seismic wave fields of the goaf is constructed, and an electromagnetic-seismic joint inversion objective function is constructed. The three-dimensional distribution of the resistivity and seismic wave velocity of the goaf and the quantitative assessment results of their uncertainty are obtained by calculation, thereby reducing the blind spots in the judgment of the goaf.

Description

Technical Field

[0001] The invention belongs to the technical field of geological engineering and relates to a goaf detection method. Background Art

[0002] Goafs created by coal mining refer to hollow areas formed after coal seam extraction. They primarily consist of three components: coal seam goaf, roadway engineering, and chambers. The formation and evolution of goafs are directly linked to surface subsidence, karst collapse, water resource depletion, and ecological degradation in mining areas, constraining their sustainable development. Therefore, timely detection and identification of the spatial distribution and stability of goafs is crucial for ensuring coal mining safety, guiding ecological restoration in mining areas, and promoting economic transformation in mining areas.

[0003] Conventional methods for goaf detection primarily include drilling, geophysical exploration, and mine surveying. However, these methods suffer from high cost, low resolution, and poor real-time performance. In recent years, geophysical exploration has been widely used and rapidly developed for goaf detection. For example, transient electromagnetic (TEM) was used to investigate a coal mining subsidence area, revealing the three-dimensional electrical structure of the subsidence area; shallow seismic reflection was used to determine the depth and extent of the goaf's roof failure zone; and the density and resistivity distribution of the goaf were inverted using combined gravity and apparent resistivity data. However, current joint inversion methods for goaf detection are mostly limited to qualitative descriptions and lack a unified mathematical model and inversion framework, making it difficult to accurately characterize the fine structure of goafs under complex conditions. Summary of the Invention

[0004] In order to solve the problem that the joint inversion method for goaf detection described in the background technology is difficult to accurately depict the fine structure of the goaf under complex conditions, the present invention provides a goaf detection method based on joint inversion of transient electromagnetic and seismic wave fields.

[0005] The method of the present invention comprises the following steps:

[0006] According to the burial conditions of the goaf, a transient electromagnetic detection system and a reflection seismic detection system are deployed in the tunnel crossing area where the goaf is located;

[0007] Collect transient electromagnetic apparent resistivity and reflection seismic waveform data, and perform preprocessing including data registration, noise suppression, and synchronous imaging to extract characteristic parameters of electrical and elastic differences in the goaf;

[0008] Based on the electrical and elastic difference characteristic parameters of the goaf, a multi-attribute feature data set was extracted. A machine learning classification algorithm was used to train, verify, and test the multi-attribute feature data set, and a goaf classification model was established to identify the type, scale, and stability of the goaf.

[0009] Based on Maxwell's equations and the elastic wave equation, the finite difference and finite element methods are used for discrete solution. A quantitative response relationship between the physical parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf is established, and a joint forward numerical model of transient electromagnetic and seismic wave fields in the goaf is constructed.

[0010] Based on the forward numerical model of transient electromagnetic and seismic wave fields in the goaf, combined with prior information on the geometry of the goaf and the stress state of the surrounding rock, an electromagnetic-seismic joint inversion objective function is constructed.

[0011] Based on the electromagnetic-seismic joint inversion objective function, the Bayesian-Markov Chain Monte Carlo method was used to solve the inversion problem, and the three-dimensional distribution of the resistivity and seismic velocity in the goaf and the quantitative assessment results of their uncertainty were obtained.

[0012] Based on the identification results of goaf type, scale and stability, combined with the three-dimensional distribution of goaf resistivity and seismic wave velocity and the quantitative assessment results of their uncertainty, a three-dimensional fine structure and physical property model of the goaf is established.

[0013] Furthermore, in the transient electromagnetic numerical simulation of the goaf, the staggered grid finite difference method is used to discretely solve the above equations. First, the study area is divided into Nx×Ny×Nz cubic grids, and then the electric field and magnetic field components are arranged at the grid edges and the center points of the faces, respectively. Parameters such as conductivity and permeability are assigned at the grid center. The central difference format with second-order accuracy is used in the time direction, and the staggered grid difference operator with second-order accuracy is used in the spatial direction to establish the three-dimensional transient electromagnetic forward numerical equations.

[0014] The above equations are assembled on the entire spatial grid and time step to form a large sparse linear equation system, which can be solved using direct or iterative methods to obtain the three-dimensional electromagnetic field spatiotemporal distribution.

[0015] Furthermore, the numerical simulation of reflection earthquakes adopts elastic wave equation.

[0016] The stress-strain relationship satisfies Hooke's law.

[0017] In the numerical solution, the staggered grid finite difference method is adopted, with the stress component configured at the grid center and the velocity component configured at the midpoint of the corresponding edge; the central difference format of second-order accuracy is used in both time and space directions to establish the elastic wave equation difference format in the velocity-stress form.

[0018] A giant sparse matrix equation system is obtained by assembling all grids and time steps, which is solved using the explicit time-stepping method to obtain the spatiotemporal evolution information of the three-dimensional elastic wave field.

[0019] Furthermore, the electrical and elastic difference characteristic parameters of the goaf include transient electromagnetic multi-attribute characteristic parameters and reflected seismic multi-attribute characteristic parameters; the transient electromagnetic multi-attribute characteristic parameters include apparent resistivity, apparent conductivity, induced polarization coefficient, and transient electromagnetic waveform attenuation coefficient; the reflected seismic multi-attribute characteristic parameters include seismic wave first arrival travel time, amplitude, frequency, phase, reflection coefficient, and attenuation coefficient.

[0020] Furthermore, the method for establishing the goaf classification model includes:

[0021] S1. Extracting a multi-attribute feature data set based on electrical and elastic difference characteristic parameters of the goaf, wherein the electrical and elastic difference characteristic parameters of the goaf include transient electromagnetic multi-attribute characteristic parameters and reflection seismic multi-attribute characteristic parameters, wherein the transient electromagnetic multi-attribute characteristic parameters include apparent resistivity, apparent conductivity, induced polarization coefficient, and transient electromagnetic waveform attenuation coefficient, and the reflection seismic multi-attribute characteristic parameters include seismic wave first arrival travel time, amplitude, frequency, phase, reflection coefficient, and attenuation coefficient;

[0022] S2. The Pearson correlation coefficient and mutual information index are used to analyze the correlation between each feature in the multi-attribute feature data set and the goaf type. The recursive feature elimination and sequential feature selection methods are used to screen the best feature combination as the feature subset with the greatest contribution to goaf classification.

[0023] S3, using random stratified sampling to divide the feature subset into three parts: training set, validation set and test set;

[0024] S4. The machine learning classification algorithm uses a support vector machine to construct an optimal classification hyperplane in a high-dimensional feature space to maximize the sample intervals between different categories. The training set is input into the support vector machine for training.

[0025] During the training process, grid search and cross-validation methods are used to optimize the model hyperparameters including kernel function type, penalty factor, and kernel function parameters to obtain the trained model;

[0026] S5. Use the test set to evaluate the performance of the goaf classification model of the trained model, and use the precision, recall rate, F1 value, and ROC curve indicators to comprehensively evaluate the classification effect; at the same time, use the learning curve to analyze the trend of the accuracy of the training set and the validation set as the sample size to determine whether the trained model has overfitting or underfitting; for the trained model with poor performance, return to steps S2-S4, adjust the feature selection, and optimize the model parameters until a model with satisfactory classification performance is obtained, which is used as the goaf classification model.

[0027] Furthermore, the method for constructing the goaf area transient electromagnetic and seismic wave field joint forward numerical model includes:

[0028] S1. Based on prior geological information, use modeling software to construct an initial model of the goaf, including the spatial distribution of the goaf and the resistivity, density, and wave velocity physical properties of the surrounding rock;

[0029] S2. Setting the excitation parameters of the transient electromagnetic emission source including the emission current and waveform and the receiving system parameters including the number of receiving channels and sampling interval, and configuring the spatial positions of the emission source and receiving points in the initial model of the goaf;

[0030] S3. Based on the spatial and temporal distribution of the three-dimensional electromagnetic field and the spatial positions of the transmitting source and the receiving point, the three-dimensional transient electromagnetic response of the initial model of the goaf is forward calculated to obtain the electric field and magnetic field components at different time and spatial positions, and synthesize the apparent resistivity characterization parameters;

[0031] S4. Setting the reflection seismic source parameters including source type and main frequency and the receiving system parameters including the number of detector groups and trace spacing, and configuring the spatial positions of the shot points and receiver points in the initial model;

[0032] S5. Based on the spatiotemporal evolution of the 3D elastic wavefield and the spatial locations of the shot and receiver points, forward model the 3D seismic wavefield snapshots of the initial model of the goaf, extract seismic records from different gathers, and pick up attribute parameters including first arrival travel time, dispersion, and amplitude attenuation.

[0033] S6. By changing the geometric parameters of the initial model of the goaf, including the goaf range and thickness, and the physical parameters including the resistivity and density of the goaf filling, steps S2-S6 are repeated to conduct parameter sensitivity analysis of electromagnetic and seismic responses, and quantitatively characterize the quantitative response relationship between the physical parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf;

[0034] S7. Based on the electric and magnetic field components at different time and spatial positions, the apparent resistivity characterization parameters, the seismic records of different gathers, the attribute parameters including first arrival travel time, dispersion, and amplitude attenuation, and the quantitative response relationship between the physical properties of the goaf and the electrical and elastic difference characteristic parameters of the goaf, a joint forward numerical model of transient electromagnetic and seismic wave fields in the goaf is constructed.

[0035] Furthermore, the solution process of the electromagnetic-seismic joint inversion objective function is:

[0036] The Bayesian-Markov chain Monte Carlo method is used for inversion solution;

[0037] By constructing a Markov chain to achieve random sampling of the posterior probability distribution, the optimal estimate and confidence interval of the goaf model parameters are obtained. The process is as follows:

[0038] S1. Based on geological data and empirical judgment, an initial model of the goaf is constructed as the starting point of the Markov chain;

[0039] S2, based on the Metropolis-Hastings criterion, perturb the current model mi to the next state mi+1 according to probability p;

[0040] S3. Repeat step S2, continuously updating and adjusting the state of the Markov chain until the convergence condition is reached: the posterior probability does not change significantly;

[0041] S4. Based on the stationary distribution of the Markov chain, a series of inversion model samples were randomly selected and statistically analyzed to obtain the optimal estimates and confidence intervals of the goaf model parameters, and the three-dimensional distribution of the goaf resistivity and seismic wave velocity and their uncertainty quantitative assessment results were obtained.

[0042] The present invention uses a transient electromagnetic detection system and a reflection seismic detection system to jointly collect data and jointly invert the goaf, giving full play to the complementary advantages of the two detection methods, breaking through the bottlenecks of a single method in terms of resolution and signal-to-noise ratio, and realizing the fine characterization of the structure, physical properties and stability of the goaf; a machine learning classification algorithm is introduced to analyze the multi-attribute feature data set of the goaf, realizing intelligent discrimination of the type, scale and stability of the goaf under complex geological conditions, and expanding the universality of the method; a quantitative response relationship between the physical property parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf is established, a joint forward numerical model of transient electromagnetic and seismic wave fields of the goaf is constructed, an electromagnetic-seismic joint inversion objective function is constructed, and the Bayesian-Markov chain Monte Carlo method is used for inversion solution. The three-dimensional distribution of the resistivity and seismic wave velocity of the goaf and the quantitative evaluation results of their uncertainty are obtained by calculation, thereby reducing the blind spots in the judgment of the goaf.

[0043] Compared with the existing technology, the present invention has the following beneficial effects: First, through the joint inversion of transient electromagnetic and seismic wave fields, it effectively solves the problems of low resolution and insufficient reliability of a single geophysical method in goaf detection, and realizes meter-level fine characterization of goaf; Second, through the machine learning classification algorithm, the efficiency and accuracy of intelligent identification and classification of goaf are significantly improved; Third, the inversion solution process effectively reduces the uncertainty of goaf inversion, and the inversion results are in good agreement with actual verification. The three-dimensional morphological characterization of the three-dimensional fine structure and physical property model of the goaf finally established is more realistic and reliable, and can accurately characterize the fine structure of the goaf under complex geological conditions; Fourth, it is universal and scalable, and has broad application prospects in the fields of coal mine goaf investigation, karst collapse area detection, and underground engineering safety evaluation, providing key technical support for the safe construction of major projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 Flow chart of the method of the present invention.

[0045] Figure 2 This is a mapping relationship diagram between the development degree of the goaf and the physical property parameters of the embodiment.

[0046] Figure 3 It is a three-dimensional fine structure model diagram of the goaf in the embodiment.

[0047] Figure 4 This is a tunnel optimization route plan diagram for an embodiment. DETAILED DESCRIPTION

[0048] In order to make the technical problems, technical solutions and beneficial effects to be solved by this application more clearly understood, this application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] The goaf detection method based on the joint inversion of transient electromagnetic and seismic wave fields is shown in the flowchart. Figure 1 As shown, the details are as follows.

[0050] First, according to the burial conditions of the goaf, a transient electromagnetic detection system and a reflection seismic detection system are deployed in the tunnel crossing area where the goaf is located.

[0051] Specifically, the transient electromagnetic detection system has a detection frequency of 0.1-100 Hz and a transmission power of no less than 500W; the reflection seismic detection system has an excitation frequency of 20-200 Hz and uses a controllable vibroseis source. The spatial layout and survey line parameters of the two detection systems will be optimized based on the burial conditions of the goaf.

[0052] Then, transient electromagnetic apparent resistivity and reflection seismic waveform data are collected, and preprocessing including data alignment, noise suppression, and synchronous imaging is performed to extract the electrical and elastic difference characteristic parameters of the goaf.

[0053] Specifically, the electrical and elastic difference characteristic parameters of the goaf are composed of transient electromagnetic multi-attribute characteristic parameters and reflected seismic multi-attribute characteristic parameters. The transient electromagnetic multi-attribute characteristic parameters include: apparent resistivity, apparent conductivity, induced polarization coefficient, transient electromagnetic waveform attenuation coefficient; the reflected seismic multi-attribute characteristic parameters include: seismic wave first arrival travel time, amplitude, frequency, phase, reflection coefficient, and attenuation coefficient.

[0054] Then, based on the electrical and elastic difference characteristic parameters of the goaf, a multi-attribute feature data set was extracted. The multi-attribute feature data set was trained, verified and tested using a machine learning classification algorithm, and a goaf classification model was established to identify the type, scale and stability of the goaf.

[0055] Specifically, the method for establishing the goaf classification model includes:

[0056] S1. Based on the electrical and elastic difference characteristic parameters of the goaf, a multi-attribute feature data set is extracted;

[0057] S2. The Pearson correlation coefficient and mutual information index are used to analyze the correlation between each feature in the multi-attribute feature data set and the goaf type. The recursive feature elimination and sequential feature selection methods are used to screen the best feature combination as the feature subset with the greatest contribution to goaf classification.

[0058] S3, using random stratified sampling to divide the feature subset into three parts: training set, validation set and test set;

[0059] S4. The machine learning classification algorithm uses a support vector machine to construct an optimal classification hyperplane in a high-dimensional feature space to maximize the sample intervals between different categories. The training set is input into the support vector machine for training.

[0060] During the training process, grid search and cross-validation methods are used to optimize the model hyperparameters including kernel function type, penalty factor, and kernel function parameters to obtain the trained model;

[0061] S5. Use the test set to evaluate the performance of the goaf classification model of the trained model, and use the precision, recall rate, F1 value, and ROC curve indicators to comprehensively evaluate the classification effect; at the same time, use the learning curve to analyze the trend of the accuracy of the training set and the validation set as the sample size to determine whether the trained model has overfitting or underfitting; for the trained model with poor performance, return to steps S2-S4, adjust the feature selection, and optimize the model parameters until a model with satisfactory classification performance is obtained, which is used as the goaf classification model.

[0062] Then, based on Maxwell's equations and elastic wave equation, the finite difference and finite element methods were used for discrete solution, and a quantitative response relationship between the physical parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf was established, and a joint forward numerical model of transient electromagnetic and seismic wave fields in the goaf was constructed.

[0063] Considering the quasi-static approximation conditions and neglecting the displacement current, the above equations can be simplified.

[0064] In the numerical simulation of transient electromagnetic in goaf, the staggered grid finite difference method is used to discretely solve the above equations. First, the study area is divided into Nx×Ny×Nz cubic grids. Then, the electric field and magnetic field components are configured at the grid edges and the center points of the faces, respectively. Parameters such as conductivity and permeability are assigned at the grid center. The central difference format with second-order accuracy is used in the time direction, and the staggered grid difference operator with second-order accuracy is used in the spatial direction to establish the three-dimensional transient electromagnetic forward numerical equations.

[0065] The above equations are assembled on the entire spatial grid and time step to form a large sparse linear equation system, which can be solved using direct or iterative methods to obtain the three-dimensional electromagnetic field spatiotemporal distribution.

[0066] Specifically, the elastic wave equation is used in numerical simulation of reflection seismic.

[0067] The stress-strain relationship satisfies Hooke's law.

[0068] In the numerical solution, the staggered grid finite difference method is adopted, with the stress component configured at the grid center and the velocity component configured at the midpoint of the corresponding edge; the central difference format of second-order accuracy is used in both time and space directions to establish the elastic wave equation difference format in the velocity-stress form.

[0069] A giant sparse matrix equation system is obtained by assembling all grids and time steps, which is solved using the explicit time-stepping method to obtain the spatiotemporal evolution information of the three-dimensional elastic wave field.

[0070] More specifically, the method for constructing a forward numerical model of transient electromagnetic and seismic wave fields in goaf areas includes:

[0071] S1. Based on prior geological information, use modeling software to construct an initial model of the goaf, including the spatial distribution of the goaf and the resistivity, density, and wave velocity physical properties of the surrounding rock;

[0072] S2. Setting the excitation parameters of the transient electromagnetic emission source including the emission current and waveform and the receiving system parameters including the number of receiving channels and sampling interval, and configuring the spatial positions of the emission source and receiving points in the initial model of the goaf;

[0073] S3. Based on the spatial and temporal distribution of the three-dimensional electromagnetic field and the spatial positions of the transmitting source and the receiving point, the three-dimensional transient electromagnetic response of the initial model of the goaf is forward calculated to obtain the electric field and magnetic field components at different time and spatial positions, and synthesize the apparent resistivity characterization parameters;

[0074] S4. Setting the reflection seismic source parameters including source type and main frequency and the receiving system parameters including the number of detector groups and trace spacing, and configuring the spatial positions of the shot points and receiver points in the initial model;

[0075] S5. Based on the spatiotemporal evolution of the 3D elastic wavefield and the spatial locations of the shot and receiver points, forward model the 3D seismic wavefield snapshots of the initial model of the goaf, extract seismic records from different gathers, and pick up attribute parameters including first arrival travel time, dispersion, and amplitude attenuation.

[0076] S6. By changing the geometric parameters of the initial model of the goaf, including the goaf range and thickness, and the physical parameters including the resistivity and density of the goaf filling, steps S2-S5 are repeated to conduct parameter sensitivity analysis of electromagnetic and seismic responses, and quantitatively characterize the quantitative response relationship between the physical parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf;

[0077] S7. Based on the electric and magnetic field components at different time and spatial positions, the apparent resistivity characterization parameters, the seismic records of different gathers, the attribute parameters including first arrival travel time, dispersion, and amplitude attenuation, and the quantitative response relationship between the physical properties of the goaf and the electrical and elastic difference characteristic parameters of the goaf, a joint forward numerical model of transient electromagnetic and seismic wave fields in the goaf is constructed.

[0078] Then, based on the forward numerical model of transient electromagnetic and seismic wave fields in the goaf, combined with the prior information of the goaf including the geometric shape and surrounding rock stress state geology, the electromagnetic-seismic joint inversion objective function is constructed.

[0079] Then, based on the electromagnetic-seismic joint inversion objective function, the Bayesian-Markov Chain Monte Carlo method was used to perform inversion solution, and the three-dimensional distribution of resistivity and seismic wave velocity in the goaf and the quantitative evaluation results of their uncertainty were obtained.

[0080] Specifically, the solution process of the electromagnetic-seismic joint inversion objective function is:

[0081] The Bayesian-Markov chain Monte Carlo method is used for inversion solution.

[0082] By constructing a Markov chain to achieve random sampling of the posterior probability distribution, the optimal estimate and confidence interval of the goaf model parameters are obtained. The process is as follows:

[0083] S1. Based on geological data and empirical judgment, an initial model of the goaf is constructed as the starting point of the Markov chain;

[0084] S2, based on the Metropolis-Hastings criterion, perturb the current model mi to the next state mi+1 according to probability p;

[0085] S3. Repeat step S2, continuously updating and adjusting the state of the Markov chain until the convergence condition is reached: the posterior probability does not change significantly;

[0086] S4. Based on the stationary distribution of the Markov chain, a series of inversion model samples were randomly selected and statistically analyzed to obtain the optimal estimates and confidence intervals of the goaf model parameters, and the three-dimensional distribution of the goaf resistivity and seismic wave velocity and their uncertainty quantitative assessment results were obtained.

[0087] Finally, based on the identification results of goaf type, scale and stability, combined with the three-dimensional distribution of goaf resistivity and seismic wave velocity and the quantitative assessment results of their uncertainty, a three-dimensional fine structure and physical property model of the goaf was established.

[0088] Example

[0089] In view of the fact that a water diversion tunnel of a certain water conservancy project passes through an old goaf section, the present invention is used to detect the goaf.

[0090] Based on the known distribution of the goaf, eight transient electromagnetic (TEM) survey lines were designed, each 5 km long and 20 m apart. Four seismic lines were also laid out, each 5 km long and 5 m apart. The transient electromagnetic transmitter used an EMP-400T transmitter from EMIT (USA), with a maximum transmit power of 800 A·m² and a frequency of 0.3 Hz to 300 Hz. The seismic excitation source used an IDE (USA) BIS-SHD50 spark source, with a single-point excitation energy of 2000 J. The transient electromagnetic receiver used a Phoenix V8 multi-channel receiver with 150 receiving channels. Seismic data was acquired using the Inova ARIES-II system, with 1000 receivers.

[0091] After acquiring transient electromagnetic apparent resistivity and three-component seismic waveform data along the entire survey line, the electromagnetic data was preprocessed using instrument response correction, synchronous stacking, and three-dimensional spatial interpolation, increasing the signal-to-noise ratio by more than fivefold. Seismic data were preprocessed using static correction, amplitude recovery, and surface roll attenuation to effectively suppress high-frequency random noise, optimize event response, and obtain high-quality post-stack migration profiles. Twelve attributes, including seismic reflection wave dispersion, amplitude, and apparent velocity, were extracted to collaboratively characterize the electrical and elastic differences in the goaf.

[0092] A typical goaf area was selected to construct a three-layer seismic-electromagnetic wave field coupling model of the overburden, bedrock, and goaf. Based on geological data, the goaf filling types were set: fissure type, collapse type, and water-filled type, with thicknesses of 1m-20m and burial depths of 10m-100m. Full-response numerical simulations were carried out to obtain the response characteristics of the apparent resistivity of 5Ω·m-500Ω·m and seismic wave velocity of 300m / s-2500m / s for different types of goaf. A mapping relationship between the "development degree of the goaf and physical property parameters" was established, such as Figure 2 As shown, this provides constraints for the joint inversion.

[0093] Using forward modeling data as training samples, a goaf classification model was constructed by integrating eight multi-source attributes, including measured apparent resistivity and seismic wave dispersion. Constrained by wellbore data, intelligently calibrated goaf type, size, and stability classification labels, and classified and identified field data. The accuracy of goaf identification reached 85%, an improvement of over 20% compared to traditional empirical interpretation methods.

[0094] Taking transient electromagnetic apparent resistivity and seismic wave reflection velocity as constraints, and incorporating prior geological information such as the burial pattern of the goaf and the stress state of the surrounding rock, the electromagnetic-seismic joint inversion objective function was constructed:

[0095] ,

[0096] Where m represents the spatial distribution and physical properties of the goaf; dobs represents the measured geophysical data; F is the forward operator; Wd and Wm are the data and model weighting matrices, respectively; m0 is the prior model; L is the smoothness constraint operator; and α and β are the prior information and smoothness constraint weights. Using the Markov Chain Monte Carlo method, the goaf model is randomly perturbed to obtain the posterior distribution of the inversion results, generate confidence probability plots, and quantitatively assess the uncertainty of the inversion parameters.

[0097] By integrating the results of transient electromagnetic and seismic joint inversion and uncertainty analysis, combined with drilling exposure, a three-dimensional fine structure model of the goaf along a water diversion tunnel was established. Figure 3 As shown in the figure, seven high-risk goaf sections were identified, with an overall positioning accuracy of better than 5m and a scale estimation error of less than 10%. The maximum depth of the goaf is over 50 meters, and the volume is over 50,000 cubic meters. Based on the stability prediction of the goaf, an optimized tunnel route plan was proposed, such as Figure 4 As shown, two strongly coupled goaf areas were partially avoided, reducing the risk of goaf instability by over 80% and saving 30 million yuan in project investment. Guidance was provided on-site for targeted goaf grouting reinforcement, enabling safe and efficient construction of a water diversion tunnel, creating significant engineering and social benefits.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application may be implemented in various computer languages, such as object-oriented programming languages ​​Java, C++, Python, and interpreted scripting languages ​​like JavaScript.

[0099] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0102] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0103] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for detecting goaf areas based on the joint inversion of transient electromagnetic and seismic wave fields, characterized in that: The following steps are involved: According to the burial conditions of the goaf, a transient electromagnetic detection system and a reflection seismic detection system are deployed in the tunnel crossing area where the goaf is located; Collect transient electromagnetic apparent resistivity and reflection seismic waveform data, and perform preprocessing including data registration, noise suppression, and synchronous imaging to extract characteristic parameters of electrical and elastic differences in the goaf; Based on the electrical and elastic difference characteristic parameters of the goaf, a multi-attribute feature data set was extracted. A machine learning classification algorithm was used to train, verify, and test the multi-attribute feature data set, and a goaf classification model was established to identify the type, scale, and stability of the goaf. Based on Maxwell's equations and the elastic wave equation, the finite difference and finite element methods are used for discrete solution. A quantitative response relationship between the physical parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf is established, and a joint forward numerical model of transient electromagnetic and seismic wave fields in the goaf is constructed. Based on the forward numerical model of transient electromagnetic and seismic wave fields in the goaf, combined with prior information on the geometry of the goaf and the stress state of the surrounding rock, an electromagnetic-seismic joint inversion objective function is constructed. Based on the electromagnetic-seismic joint inversion objective function, the Bayesian-Markov Chain Monte Carlo method was used to solve the inversion problem, and the three-dimensional distribution of the resistivity and seismic velocity in the goaf and the quantitative assessment results of their uncertainty were obtained. Based on the identification results of goaf type, scale and stability, combined with the three-dimensional distribution of goaf resistivity and seismic wave velocity and the quantitative assessment results of their uncertainty, a three-dimensional fine structure and physical property model of the goaf is established.

2. The method for goaf detection based on joint inversion of transient electromagnetic and seismic wave fields according to claim 1 is characterized in that: The electrical and elastic difference characteristic parameters of the goaf include transient electromagnetic multi-attribute characteristic parameters and reflected seismic multi-attribute characteristic parameters; the transient electromagnetic multi-attribute characteristic parameters include apparent resistivity, apparent conductivity, induced polarization coefficient, and transient electromagnetic waveform attenuation coefficient; the reflected seismic multi-attribute characteristic parameters include seismic wave first arrival travel time, amplitude, frequency, phase, reflection coefficient, and attenuation coefficient.

3. The method for goaf detection based on joint inversion of transient electromagnetic and seismic wave fields according to claim 2 is characterized in that: The method for constructing the goaf area transient electromagnetic and seismic wave field joint forward numerical model includes: S1. Based on prior geological information, use modeling software to construct an initial model of the goaf, including the spatial distribution of the goaf and the resistivity, density, and wave velocity physical properties of the surrounding rock; S2. Setting the excitation parameters of the transient electromagnetic emission source including the emission current and waveform and the receiving system parameters including the number of receiving channels and sampling interval, and configuring the spatial positions of the emission source and receiving points in the initial model of the goaf; S3. Based on the spatial and temporal distribution of the three-dimensional electromagnetic field and the spatial positions of the transmitting source and the receiving point, the three-dimensional transient electromagnetic response of the initial model of the goaf is forward calculated to obtain the electric field and magnetic field components at different time and spatial positions, and synthesize the apparent resistivity characterization parameters; S4. Setting the reflection seismic source parameters including source type and main frequency and the receiving system parameters including the number of detector groups and trace spacing, and configuring the spatial positions of the shot points and receiver points in the initial model; S5. Based on the spatiotemporal evolution of the 3D elastic wavefield and the spatial locations of the shot and receiver points, forward model the 3D seismic wavefield snapshots of the initial model of the goaf, extract seismic records from different gathers, and pick up attribute parameters including first arrival travel time, dispersion, and amplitude attenuation. S6. By changing the geometric parameters of the initial model of the goaf, including the goaf range and thickness, and the physical parameters including the resistivity and density of the goaf filling, steps S2-S5 are repeated to conduct parameter sensitivity analysis of electromagnetic and seismic responses, and quantitatively characterize the quantitative response relationship between the physical parameters of the goaf and the electrical and elastic difference characteristic parameters of the goaf; S7. Based on the electric and magnetic field components at different time and spatial positions, the apparent resistivity characterization parameters, the seismic records of different gathers, the attribute parameters including first arrival travel time, dispersion, and amplitude attenuation, and the quantitative response relationship between the physical properties of the goaf and the electrical and elastic difference characteristic parameters of the goaf, a joint forward numerical model of transient electromagnetic and seismic wave fields in the goaf is constructed.

Images