Intelligent prediction method and system for large deformation of surrounding rock in deep tunnel soft rock area
By setting up sensors in the tunnel surrounding rock area to acquire displacement data, calculating strain energy density and energy dissipation, and performing spectrum analysis, the accuracy and adaptability issues of large deformation prediction in soft rock areas are solved, and real-time, quantifiable early warning and prediction are realized.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-04-10
AI Technical Summary
Existing technologies for predicting large deformations of surrounding rock in deep-buried tunnels in soft rock areas suffer from insufficient accuracy, poor adaptability, and strong lag. They are unable to identify the energy accumulation-abrupt release process during surrounding rock deformation, resulting in distorted prediction results and difficulty in achieving real-time early warning.
By setting up sensors in the surrounding rock area of the tunnel to acquire displacement vectors in real time, calculating strain energy density and energy divergence, performing Fourier transform and spectrum analysis, generating modulation spectrum, tracking the deformation evolution path of the surrounding rock, and constructing a three-dimensional model to mark the location of potential unstable deformation.
It enables real-time, quantifiable prediction of large deformations in surrounding rock, avoids parameter uncertainty errors, reveals the direction and frequency response of deformation energy flow, and provides rolling early warning capability.
Smart Images
Figure CN121829435A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of tunnel construction risk monitoring, and more particularly, relates to an intelligent prediction method and system for large deformation of surrounding rock in soft rock area of deep-buried tunnel. BACKGROUND
[0002] In deep-buried tunnel engineering in soft rock area, large deformation of surrounding rock is a core risk factor affecting construction safety and operation stability. Current engineering industry mainly relies on three types of technical systems for prediction methods of large deformation of surrounding rock: theoretical criterion type, empirical formula type, and numerical simulation type. These methods have achieved certain results in specific scenarios, but when faced with complex geological structures and nonlinear evolution mechanisms, they generally have problems such as insufficient precision, poor adaptability, and strong lag.
[0003] Firstly, the theoretical criterion type method (such as elastic-plastic limit analysis, deformation modulus-stress ratio criterion, etc.) is usually based on simplified mechanical models and ideal material assumptions, which cannot truly reflect the time-dependent, creep, and structural joint effects of soft rock, resulting in sensitive and distorted prediction results. In addition, these methods rely on prior knowledge to build models, making it difficult to adapt to the complex behavior differences between different strata.
[0004] Secondly, the empirical formula type method (such as Q system, RMR, SRMR, deformation classification method, etc.) is based on a large amount of historical engineering data to extract statistical correlations, but lacks dynamicity and causal analysis, and cannot capture the evolution path of surrounding rock deformation under individualized working conditions. At the same time, its prediction ability is limited by the completeness of the database and regional representativeness, and it is difficult to generalize to new types of strata or structural anomaly areas.
[0005] Thirdly, the numerical simulation type method (FLAC3D, UDEC, ABAQUS, etc.) can simulate nonlinear failure processes, but it is highly dependent on initial boundary conditions, constitutive parameters, and fracture surface descriptions. In actual application, the results often do not match due to the lack of real underground parameters; more seriously, this type of method has high computational cost and large inversion space, making it difficult to achieve real-time early warning and rolling update.
[0006] Therefore, most current technical solutions lack the involvement of energy mechanisms, and cannot identify the physical driving process of "energy accumulation-mutation release" in surrounding rock deformation. Since soft rock large deformation often has obvious stage characteristics and spectral evolution characteristics, traditional methods are difficult to identify the gradual accumulation or frequency modulation effect under weak disturbance, so it is often too late when displacement anomalies are seen, missing the golden window of precursor identification. SUMMARY
[0007] To solve the above technical problems, the application provides an intelligent prediction method for large deformation of surrounding rock in soft rock area of deep-buried tunnel, comprising: By using sensors installed at various monitoring points in the tunnel surrounding rock area, the displacement vector of each monitoring point is acquired in real time. The second derivative of the displacement vector is used as the dynamic response intensity of the monitoring point under construction disturbance. The Fourier transform of the dynamic response intensity is performed to generate the modulation spectrum of the surrounding rock disturbance. Based on the displacement vector of the current monitoring point, the strain energy density of the current monitoring point is calculated, and combined with the rate of change of the displacement vector, the energy divergence of the current monitoring point is calculated. The energy divergence is then subjected to spectral analysis to obtain the spectral energy density of the current monitoring point at each frequency. A spatial maximum search is performed on the rate of change of spectral energy density and the rate of change of modulation spectrum over time for all monitoring points, and the corresponding monitoring points are taken as the locations most likely to experience unstable deformation.
[0008] Furthermore, the calculation of the strain energy density at the current monitoring point includes: , in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
[0009] Furthermore, the calculation of the energy dissipation at the current monitoring point includes: , in, For time Time Energy dissipation at each monitoring point For divergence operators, For time Time The rate of change of the displacement vector at each monitoring point, time Time Energy dissipation at each monitoring point Used to describe the Each monitoring point is in a state of energy convergence or energy dissipation.
[0010] Furthermore, time Time Energy dissipation at each monitoring point The gradient direction serves as the trend direction for the deformation development of the surrounding rock.
[0011] Furthermore, obtaining the spectral energy density at each frequency for the current monitoring point includes: , in, For time Time The angular frequency of the monitoring points in the Fourier transform The spectral energy density below, The starting time of the integration. The end time for integration. The imaginary unit is time. Time The angular frequency of the monitoring points in the Fourier transform Spectral energy density at the following This is used to describe the deformation mode of the surrounding rock, wherein the deformation mode is a gradual mode or a sudden mode.
[0012] Furthermore, when time Time Energy dissipation at each monitoring point When less than 0, the first Each monitoring point is in a state of energy convergence; When time Time Energy dissipation at each monitoring point When greater than 0, the first The monitoring points are in a state of energy dissipation.
[0013] Furthermore, when time Time Energy dissipation at each monitoring point When less than 0, according to the first The gradient direction of energy divergence at each monitoring point is used to construct deformation streamlines using path integral methods (such as the Runge-Kutta algorithm) to track possible deformation evolution paths of the surrounding rock.
[0014] Furthermore, a three-dimensional model of the surrounding rock is generated, and the deformation evolution path and the location most likely to be unstable deformation are marked on the three-dimensional model.
[0015] This invention also proposes an intelligent prediction system for large deformation of surrounding rock in soft rock areas of deep-buried tunnels, comprising: The data processing module is used to acquire the displacement vector of each monitoring point in real time through sensors set at each monitoring point in the tunnel surrounding rock area, take the second derivative of the displacement vector as the dynamic response intensity of the monitoring point under construction disturbance, perform Fourier transform on the dynamic response intensity, and generate the modulation spectrum of the surrounding rock disturbance. The spectral energy density acquisition module is used to calculate the strain energy density of the current monitoring point based on the displacement vector of the current monitoring point, and to calculate the energy divergence of the current monitoring point in combination with the rate of change of the displacement vector. The energy divergence is then subjected to spectral analysis to obtain the spectral energy density of the current monitoring point at each frequency. The prediction module is used to perform a spatial maximum search for the rate of change of spectral energy density and the rate of change of modulation spectrum over time at all monitoring points, and to identify the corresponding monitoring points as the locations most likely to experience unstable deformation.
[0016] Furthermore, the calculation of the strain energy density at the current monitoring point includes: , in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
[0017] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art: 1. The potential energy field is directly constructed from displacement data, skipping the traditional stress-strain inversion and avoiding the amplification of errors caused by parameter uncertainty.
[0018] 2. By characterizing the direction of energy flow and the frequency response of disturbance by energy divergence and modulation spectrum, the microscopic dynamic trend before the mutation is revealed.
[0019] 3. Rolling prediction is achieved by searching the maximum value of the rate of change of spectral energy density and the rate of change of modulation spectrum with time for all monitoring points, which does not rely on historical templates or static classification.
[0020] 4. The spectral energy density is introduced to distinguish between slow and sudden changes, and has a quantifiable and adjustable stability judgment index. BRIEF DESCRIPTION OF DRAWINGS
[0021] Figure 1 is a method flowchart of embodiment 1 of the present application; Figure 2 is a system structure diagram of embodiment 2 of the present application. DETAILED DESCRIPTION
[0022] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments.
[0023] The method provided by the present application can be implemented in a terminal environment, which can include one or more of the following components: a processor, a storage medium and a display screen. Among them, the storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.
[0024] The processor can include one or more processing cores. The processor connects various parts in the entire terminal through various interfaces and lines, executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.
[0025] The storage medium can include random access memory (RAM) and read-only memory (ROM). The storage medium can be used to store instructions, programs, codes, code sets or instructions.
[0026] The display screen is used to display the user interface of each application program.
[0027] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal can include more or fewer components, or combine certain components, or different component arrangements. For example, the terminal also includes radio frequency circuit, input unit, sensor, audio circuit, power supply and other components, which will not be described here.
[0028] Embodiment 1 As Figure 1 , the present embodiment proposes an intelligent prediction method for large deformation of soft rock in deep buried tunnel, which includes: Step 101: Using sensors installed at each monitoring point in the tunnel surrounding rock area, the displacement vector of each monitoring point is acquired in real time. The second derivative of the displacement vector is used as the dynamic response intensity of the monitoring point under construction disturbance. Fourier transform is performed on the dynamic response intensity to generate the modulation spectrum of the surrounding rock disturbance. Step 102: Calculate the strain energy density of the current monitoring point based on the displacement vector of the current monitoring point, and calculate the energy divergence of the current monitoring point in combination with the rate of change of the displacement vector. Perform spectral analysis on the energy divergence to obtain the spectral energy density of the current monitoring point at each frequency. Specifically, calculating the strain energy density at the current monitoring point includes: , in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
[0029] Preferably, this implementation provides the following example for obtaining the first... Unit fitting coefficient As shown below: Take data from monitoring points within a certain time period and calculate the data for that monitoring point. (This can be obtained through differential calculus), obtain the true strain energy density at the monitoring point, and divide by... Fitting Its function is to map the displacement gradient into a physical quantity (strain energy per unit volume).
[0030] Specifically, calculating the energy dissipation at the current monitoring point includes: , in, For time Time Energy dissipation at each monitoring point For divergence operators, For time Time The rate of change of the displacement vector at each monitoring point, time Time Energy dissipation at each monitoring point Used to describe the Each monitoring point is in a state of energy convergence or energy dissipation.
[0031] Specifically, obtaining the spectral energy density at each frequency for the current monitoring point includes: , in, For time Time The angular frequency of the monitoring points in the Fourier transform The spectral energy density below, The starting time of the integration. The end time for integration. The imaginary unit is time. Time The angular frequency of the monitoring points in the Fourier transform Spectral energy density at the following This is used to describe the deformation mode of the surrounding rock, wherein the deformation mode is a gradual mode or a sudden mode.
[0032] Preferably, in this embodiment, the deformation mode is determined to be a gradual change mode or a sudden change mode in the following way: , in, For time Time The proportion of high-frequency energy at each monitoring point For the maximum angular frequency, when time Time High-frequency energy percentage at each monitoring point When the proportion is less than the preset threshold, the deformation mode is a gradual change mode. Time High-frequency energy percentage at each monitoring point When the proportion is greater than or equal to the preset threshold, the deformation mode is the mutation mode.
[0033] Step 103: Perform a spatial maximum search for the rate of change of spectral energy density and the rate of change of modulation spectrum over time for all monitoring points, and take the corresponding monitoring point as the location most likely to be unstable deformation.
[0034] Specifically, time Time Energy dissipation at each monitoring point The gradient direction serves as the trend direction for the deformation development of the surrounding rock.
[0035] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, the first Each monitoring point is in a state of energy convergence; When time Time Energy dissipation at each monitoring point When greater than 0, the first The monitoring points are in a state of energy dissipation.
[0036] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, according to the first The gradient direction of energy divergence at each monitoring point is used to construct deformation streamlines using path integral methods (such as the Runge-Kutta algorithm) to track possible deformation evolution paths of the surrounding rock.
[0037] Specifically, a three-dimensional model of the surrounding rock of the track is generated, and the deformation evolution path and the location where unstable deformation is most likely to occur are marked on the three-dimensional model.
[0038] Example 2 like Figure 2 As shown in the figure, this embodiment proposes an intelligent prediction system for large deformation of surrounding rock in soft rock areas of deep-buried tunnels, including: The data processing module is used to acquire the displacement vector of each monitoring point in real time through sensors set at each monitoring point in the tunnel surrounding rock area, take the second derivative of the displacement vector as the dynamic response intensity of the monitoring point under construction disturbance, perform Fourier transform on the dynamic response intensity, and generate the modulation spectrum of the surrounding rock disturbance. The spectral energy density acquisition module is used to calculate the strain energy density of the current monitoring point based on the displacement vector of the current monitoring point, and to calculate the energy divergence of the current monitoring point in combination with the rate of change of the displacement vector. The energy divergence is then subjected to spectral analysis to obtain the spectral energy density of the current monitoring point at each frequency. Specifically, calculating the strain energy density at the current monitoring point includes: , in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
[0039] Specifically, calculating the energy dissipation at the current monitoring point includes: , in, For time Time Energy dissipation at each monitoring point For divergence operators, For time Time The rate of change of the displacement vector at each monitoring point (why is direction included?), and time. Time Energy dissipation at each monitoring point Used to describe the Each monitoring point is in a state of energy convergence or energy dissipation.
[0040] Specifically, obtaining the spectral energy density at each frequency for the current monitoring point includes: , in, For time Time The angular frequency of the monitoring points in the Fourier transform The spectral energy density below, The starting time of the integration. The end time for integration. The imaginary unit is time. Time The angular frequency of the monitoring points in the Fourier transform Spectral energy density at the following This is used to describe the deformation mode of the surrounding rock, wherein the deformation mode is a gradual mode or a sudden mode.
[0041] Preferably, in this embodiment, the deformation mode is determined to be a gradual change mode or a sudden change mode in the following way: , in, For time Time The proportion of high-frequency energy at each monitoring point For the maximum angular frequency, when time Time High-frequency energy percentage at each monitoring point When the proportion is less than the preset threshold, the deformation mode is a gradual change mode. Time High-frequency energy percentage at each monitoring point When the proportion is greater than or equal to the preset threshold, the deformation mode is the mutation mode.
[0042] The prediction module is used to perform a spatial maximum search for the rate of change of spectral energy density and the rate of change of modulation spectrum over time at all monitoring points, and to identify the corresponding monitoring points as the locations most likely to experience unstable deformation.
[0043] Specifically, time Time Energy dissipation at each monitoring point The gradient direction serves as the trend direction for the deformation development of the surrounding rock.
[0044] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, the first Each monitoring point is in a state of energy convergence; When time Time Energy dissipation at each monitoring point When greater than 0, the first The monitoring points are in a state of energy dissipation.
[0045] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, according to the first The gradient direction of energy divergence at each monitoring point is used to construct deformation streamlines using path integral methods (such as the Runge-Kutta algorithm) to track possible deformation evolution paths of the surrounding rock.
[0046] Specifically, a three-dimensional model of the surrounding rock of the track is generated, and the deformation evolution path and the location where unstable deformation is most likely to occur are marked on the three-dimensional model.
[0047] Example 3 This invention also proposes a storage medium storing multiple instructions, which are used to implement the intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels.
[0048] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.
[0049] Optionally, in this embodiment, the storage medium is configured to store program code for performing the above method steps: Step 101, by using sensors set at each monitoring point in the tunnel surrounding rock area, the displacement vector of each monitoring point is obtained in real time, the second derivative of the displacement vector is used as the dynamic response intensity of the monitoring point under construction disturbance, and Fourier transform is performed on the dynamic response intensity to generate the modulation spectrum of the surrounding rock disturbance. Step 102: Calculate the strain energy density of the current monitoring point based on the displacement vector of the current monitoring point, and calculate the energy divergence of the current monitoring point in combination with the rate of change of the displacement vector. Perform spectral analysis on the energy divergence to obtain the spectral energy density of the current monitoring point at each frequency. Specifically, calculating the strain energy density at the current monitoring point includes: , in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
[0050] Specifically, calculating the energy dissipation at the current monitoring point includes: , in, For time Time Energy dissipation at each monitoring point For divergence operators, For time Time The rate of change of the displacement vector at each monitoring point, time Time Energy dissipation at each monitoring point Used to describe the Each monitoring point is in a state of energy convergence or energy dissipation.
[0051] Specifically, obtaining the spectral energy density at each frequency for the current monitoring point includes: , in, For time Time The angular frequency of the monitoring points in the Fourier transform The spectral energy density below, The starting time of the integration. The end time for integration. The imaginary unit is time. Time The angular frequency of the monitoring points in the Fourier transform Spectral energy density at the following This is used to describe the deformation mode of the surrounding rock, wherein the deformation mode is a gradual mode or a sudden mode.
[0052] Step 103: Perform a spatial maximum search for the rate of change of spectral energy density and the rate of change of modulation spectrum over time for all monitoring points, and take the corresponding monitoring point as the location most likely to be unstable deformation.
[0053] Specifically, time Time Energy dissipation at each monitoring point The gradient direction serves as the trend direction for the deformation development of the surrounding rock.
[0054] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, the first Each monitoring point is in a state of energy convergence; When time Time Energy dissipation at each monitoring point When greater than 0, the first The monitoring points are in a state of energy dissipation.
[0055] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, according to the first The gradient direction of energy divergence at each monitoring point is used to construct deformation streamlines using path integral methods (such as the Runge-Kutta algorithm) to track possible deformation evolution paths of the surrounding rock.
[0056] Specifically, a three-dimensional model of the surrounding rock of the track is generated, and the deformation evolution path and the location where unstable deformation is most likely to occur are marked on the three-dimensional model.
[0057] Example 4 This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels.
[0058] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.
[0059] The storage medium can be used to store software programs and modules, such as the intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels in this embodiment of the invention. The processor executes the software programs and modules stored in the storage medium to perform various functional applications and data processing, thus realizing the aforementioned intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0060] The processor can call the information and application stored in the storage medium through the transmission system to execute the above method steps: Step 101, by using sensors set at each monitoring point in the tunnel surrounding rock area, the displacement vector of each monitoring point is obtained in real time, the second derivative of the displacement vector is used as the dynamic response intensity of the monitoring point under construction disturbance, and Fourier transform is performed on the dynamic response intensity to generate the modulation spectrum of the surrounding rock disturbance. Step 102: Calculate the strain energy density of the current monitoring point based on the displacement vector of the current monitoring point, and calculate the energy divergence of the current monitoring point in combination with the rate of change of the displacement vector. Perform spectral analysis on the energy divergence to obtain the spectral energy density of the current monitoring point at each frequency. Specifically, calculating the strain energy density at the current monitoring point includes: , in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
[0061] Specifically, calculating the energy dissipation at the current monitoring point includes: , in, For time Time Energy dissipation at each monitoring point For divergence operators, For time Time The rate of change of the displacement vector at each monitoring point, time Time Energy dissipation at each monitoring point Used to describe the Each monitoring point is in a state of energy convergence or energy dissipation.
[0062] Specifically, obtaining the spectral energy density at each frequency for the current monitoring point includes: , in, For time Time The angular frequency of the monitoring points in the Fourier transform The spectral energy density below, The starting time of the integration. The end time for integration. The imaginary unit is time. Time The angular frequency of the monitoring points in the Fourier transform Spectral energy density at the following This is used to describe the deformation mode of the surrounding rock, wherein the deformation mode is a gradual mode or a sudden mode.
[0063] Step 103: Perform a spatial maximum search for the rate of change of spectral energy density and the rate of change of modulation spectrum over time for all monitoring points, and take the corresponding monitoring point as the location most likely to be unstable deformation.
[0064] Specifically, time Time Energy dissipation at each monitoring point The gradient direction serves as the trend direction for the deformation development of the surrounding rock.
[0065] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, the first Each monitoring point is in a state of energy convergence; When time Time Energy dissipation at each monitoring point When greater than 0, the first The monitoring points are in a state of energy dissipation.
[0066] Specifically, when time Time Energy dissipation at each monitoring point When less than 0, according to the first The gradient direction of energy divergence at each monitoring point is used to construct deformation streamlines using path integral methods (such as the Runge-Kutta algorithm) to track possible deformation evolution paths of the surrounding rock.
[0067] Specifically, a three-dimensional model of the surrounding rock of the track is generated, and the deformation evolution path and the location where unstable deformation is most likely to occur are marked on the three-dimensional model.
[0068] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0069] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0070] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.
[0071] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0072] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0073] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.
[0074] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.
Claims
1. An intelligent prediction method for large deformation of surrounding rock in soft rock areas of deeply buried tunnels, characterized in that, include: By using sensors installed at various monitoring points in the tunnel surrounding rock area, the displacement vector of each monitoring point is acquired in real time. The second derivative of the displacement vector is used as the dynamic response intensity of the monitoring point under construction disturbance. The Fourier transform of the dynamic response intensity is performed to generate the modulation spectrum of the surrounding rock disturbance. Based on the displacement vector of the current monitoring point, the strain energy density of the current monitoring point is calculated, and combined with the rate of change of the displacement vector, the energy divergence of the current monitoring point is calculated. The energy divergence is then subjected to spectral analysis to obtain the spectral energy density of the current monitoring point at each frequency. A spatial maximum search is performed on the rate of change of spectral energy density and the rate of change of modulation spectrum over time for all monitoring points, and the corresponding monitoring points are taken as the locations most likely to experience unstable deformation.
2. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 1, characterized in that, The calculation of strain energy density at the current monitoring point includes: ， in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.
3. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 2, characterized in that, The calculation of the energy dissipation at the current monitoring point includes: ， in, For time Time Energy dissipation at each monitoring point For divergence operators, For time Time The rate of change of the displacement vector at each monitoring point, time Time Energy dissipation at each monitoring point Used to describe the Each monitoring point is in a state of energy convergence or energy dissipation.
4. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 3, characterized in that, Time Time Energy dissipation at each monitoring point The gradient direction serves as the trend direction for the deformation development of the surrounding rock.
5. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 3, characterized in that, Obtaining the spectral energy density at each frequency for the current monitoring point includes: ， in, For time Time The angular frequency of the monitoring points in the Fourier transform The spectral energy density below, The starting time of the integration. The end time for integration. The imaginary unit is time. Time The angular frequency of the monitoring points in the Fourier transform Spectral energy density at the following This is used to describe the deformation mode of the surrounding rock, wherein the deformation mode is a gradual mode or a sudden mode.
6. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 4, characterized in that, When time Time Energy dissipation at each monitoring point When less than 0, the first Each monitoring point is in a state of energy convergence; When time Time Energy dissipation at each monitoring point When greater than 0, the first The monitoring points are in a state of energy dissipation.
7. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 6, characterized in that, When time Time Energy dissipation at each monitoring point When less than 0, according to the first The gradient direction of energy divergence at each monitoring point is used to construct deformation streamlines using the path integral method, which are then used to track the possible deformation evolution paths of the surrounding rock.
8. The intelligent prediction method for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 7, characterized in that, A three-dimensional model of the surrounding rock of the track is generated, and the deformation evolution path and the location where unstable deformation is most likely to occur are marked on the three-dimensional model.
9. An intelligent prediction system for large deformation of surrounding rock in soft rock areas of deeply buried tunnels, characterized in that, include: The data processing module is used to acquire the displacement vector of each monitoring point in real time through sensors set at each monitoring point in the tunnel surrounding rock area, take the second derivative of the displacement vector as the dynamic response intensity of the monitoring point under construction disturbance, perform Fourier transform on the dynamic response intensity, and generate the modulation spectrum of the surrounding rock disturbance. The spectral energy density acquisition module is used to calculate the strain energy density of the current monitoring point based on the displacement vector of the current monitoring point, and to calculate the energy divergence of the current monitoring point in combination with the rate of change of the displacement vector. The energy divergence is then subjected to spectral analysis to obtain the spectral energy density of the current monitoring point at each frequency. The prediction module is used to perform a spatial maximum search for the rate of change of spectral energy density and the rate of change of modulation spectrum over time at all monitoring points, and to identify the corresponding monitoring points as the locations most likely to experience unstable deformation.
10. The intelligent prediction system for large deformation of surrounding rock in soft rock areas of deep-buried tunnels as described in claim 9, characterized in that, The calculation of strain energy density at the current monitoring point includes: ， in, For time Time Strain energy density at each monitoring point For the first Unit fitting coefficient, For time Time Displacement vector of each monitoring point For time Time The gradient of the displacement vector of each monitoring point. For time Time The square of the norm of the gradient of the displacement vector at each monitoring point, time Time Strain energy density at each monitoring point Used to describe the first on the surrounding rock The potential deformation energy accumulation at each monitoring point.