Non-contact multi-field coupling test method and system for surrounding rock stability of end slope mining mining tunnel

Abstract

The present application belongs to the technical field of end slope mining surrounding rock stability monitoring, aiming to solve the problems of great difficulty in laying optical fiber in the mining tunnel and single evaluation data of surrounding rock stability. A kind of end slope mining surrounding rock stability non-access multi-field coupling test method and system is provided, the method comprises: in the process of end slope coal mining machine exiting the mining tunnel, using the on-board high-pressure gas source to launch the composite sensor probe to the deep part of the mining tunnel;Microcrack acoustic emission events are obtained by the composite sensor probe;Macroscopic displacement field data are obtained by the ground remote sensing equipment;The macroscopic displacement field data and the microcrack acoustic emission events are mapped, fused, and the surrounding rock damage variable is obtained by inversion;Based on the surrounding rock damage variable, the equivalent safety factor is obtained, and the stability of the mining tunnel surrounding rock is evaluated. The composite sensor probe can effectively solve the problem of optical fiber wall coupling in the long and narrow mining tunnel, and realize continuous and quantitative evaluation of the stability of the mining tunnel surrounding rock through multi-data fusion.

Description

Technical Field

[0001] This invention belongs to the field of end-face mining surrounding rock stability monitoring technology, specifically relating to a non-accessible multi-field coupling test method and system for end-face mining surrounding rock stability. Background Technology

[0002] The current methods for monitoring the stability of surrounding rock in open-pit coal mine end-face mining have the following problems:

[0003] 1) Currently, most mining areas use manual coring methods, which are limited to the area around the mining chamber. The problem with this method is that it cannot dynamically reflect the unloading-creep-fracture propagation process. Unloading, creep, and fracture propagation are a continuous and interconnected process, crucial for assessing the stability of the mining area. However, manual coring around the mining chamber can only obtain localized, static information, failing to fully demonstrate the changes in this dynamic process.

[0004] 2) Existing global navigation satellite systems, radars, or optical instruments primarily focus on slope surface displacement. However, changes in the state of the surrounding rock inside the mining tunnel have a significant impact on the overall slope stability. Monitoring only the slope surface displacement cannot provide a thorough understanding of the actual situation of the surrounding rock inside the mining tunnel, resulting in certain limitations in the assessment of slope stability.

[0005] 3) Regarding theoretical calculations of slope stability, taking Chinese patent CN112287578A as an example, this theoretical calculation only provides a framework for calculating yield zone parameters and lacks in-situ measured data input. In-situ measured data can truly reflect the geological conditions and mechanical properties of the actual site. Without this data, the calculation results may deviate significantly from the actual situation, thus affecting the accurate judgment of slope stability.

[0006] 4) Distributed fiber optic strain sensing and distributed fiber optic acoustic sensing technologies have been applied in tunnels and oil and gas wells, but in scenarios involving narrow and elongated mining tunnels on slopes, challenges remain regarding rapid deployment and multi-field fusion. Narrow and elongated mining tunnels on slopes have unique structural characteristics, such as small cross-sections and lengths reaching 150-300m, and personnel entry is prohibited for safety reasons, making rapid fiber optic deployment in such environments difficult. Simultaneously, the fusion monitoring of multiple physical fields must be comprehensively considered to obtain more comprehensive and accurate information; currently, this technology still has shortcomings in this regard. Summary of the Invention

[0007] In order to solve at least one of the above-mentioned technical problems in the prior art, the present invention provides a non-accessible multi-field coupling test method and system for the stability of the surrounding rock in end-face mining tunnels.

[0008] This invention is achieved using the following technical solution: a non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels, comprising the following steps:

[0009] A prefabricated composite sensor probe for the depth of the end-face mining tunnel is constructed. The composite sensor probe includes an anchoring drill bit, M-section micro-airbags, and an optical fiber sensing module embedded within the micro-airbags. The composite sensor probe is mounted on the end-face mining machine. During the machine's withdrawal from the tunnel, an onboard high-pressure air source propels the probe along the bottom plate of the tunnel sidewall towards the depth of the tunnel, causing the anchoring drill bit to penetrate the deepest coal and rock within the tunnel. The M-section micro-airbags are then laid along the depth direction of the tunnel as the machine withdraws. The M-section micro-airbags are then inflated and fitted against the tunnel sidewall, and then inflated in sections to couple the optical fiber sensing module within the micro-airbags to the surface of the tunnel sidewall. The composite sensor probe is then used for sensing. The instrument probe acquires acoustic emission events from micro-fractures distributed throughout the mining tunnel, triggered by excitation. The excitation includes passive and active sources. Macroscopic displacement field data of the slope area above the mining tunnel are acquired using surface remote sensing equipment. A digital twin model of the end-slope mining area is constructed, and the macroscopic displacement field data and micro-fracture acoustic emission events are mapped and fused in the digital twin model to output a multi-field fused feature tensor. A multimodal deep neural network model is constructed, and the multi-field fused feature tensor is input into the multimodal deep neural network model to invert and obtain the surrounding rock damage variables. Based on the surrounding rock damage variables, an equivalent safety factor is obtained to characterize the stability of the surrounding rock of the mining tunnel, thereby assessing the stability of the surrounding rock of the mining tunnel.

[0010] Preferably, the composite sensor probe also has an aramid core built in as a load-bearing core wire. By applying tension to the aramid core at the mine entrance, the M-section micro-airbag is made to fit with the side wall of the mine. The tail of the composite sensor probe is connected to a nitrogen cylinder, which is controlled by a PLC controller to realize the sequential inflation of the M-section micro-airbag, so that the coupling coefficient between the fiber optic sensing module inside the micro-airbag and the surface of the mine side wall is greater than or equal to 0.85.

[0011] Preferably, after the fiber optic sensing module inside the micro-airbag is coupled to the sidewall surface of the mining tunnel, a baseline self-test is performed. The baseline self-test includes: checking the wall adhesion status of the micro-airbag through a Kevlar tension sensor and a MEMS-IMU, and verifying the coupling quality by sending a 25Hz test sweep signal through the fiber optic sensing module. If the signal-to-noise ratio of a certain micro-airbag is lower than 15 dB, the PLC controller controls the nitrogen cylinder to replenish the micro-airbag.

[0012] Preferably, when monitoring ends or when the composite sensor probe needs to be retrieved, the micro-airbags of section M are first degassed sequentially to reduce the adhesion between the micro-airbags and the sidewall of the mining tunnel to a preset value. Then, the aramid core is dragged back at the entrance of the mining tunnel to retrieve the composite sensor probe.

[0013] Preferably, the periodic impact vibration of the cutting drum of the end-side coal mining machine is used as a passive source, and a three-dimensional force hammer or controllable source plate arranged on the slope surface is used as an active source; the active source is used to inject a 20Hz–2kHz sweep frequency signal into the mining tunnel wall; the surface remote sensing equipment is a ground-based interferometric synthetic aperture radar set in the slope area above the mining tunnel.

[0014] Preferably, macroscopic displacement field data is used as boundary conditions and mapped to the digital twin model of the end-side mining area. Kernel density estimation and spatiotemporal smoothing are performed on the point cloud of microcrack acoustic emission events to obtain the intensity of microseismic events and map it to the digital twin model of the end-side mining area. After the mapped data is fused, the digital twin model of the end-side mining area outputs the multi-field fused feature tensor.

[0015] Preferably, the step of obtaining the equivalent safety factor for characterizing the stability of the surrounding rock in the mining tunnel based on the surrounding rock damage variable includes: obtaining the volume-average damage variable based on the surrounding rock damage variable, and inverting the equivalent safety factor based on the volume-average damage variable.

[0016] The expression for the equivalent safety factor is:

[0017]

[0018] In the formula, This is the equivalent safety factor; The volume-average damage variable;

[0019] The expression for the volume-average damage variable is:

[0020]

[0021] In the formula, Let V be the volume of the integration region. For the surrounding rock damage variable, ∈[0,1], when A value of 0 indicates that the object is intact. A value of 1 indicates complete destruction.

[0022] In a second aspect, the present invention provides a non-accessible multi-field coupling testing system for the stability of the surrounding rock in end-face mining tunnels, comprising: a composite sensor probe deployment module for launching the composite sensor probe into the mining tunnel and coupling the composite sensor probe with the surface of the mining tunnel sidewall, and also for performing the retrieval operation of the composite sensor probe; a multi-source excitation module, including a passive source and an active source; a data acquisition module, including the composite sensor probe and its demodulation device, and a surface remote sensing device; a data processing module configured to run a digital twin model of the end-face mining area and a multimodal deep neural network model, inverting the surrounding rock damage variables based on macroscopic displacement field data and micro-crack acoustic emission events, and then obtaining an equivalent safety factor for characterizing the stability of the mining tunnel surrounding rock based on the surrounding rock damage variables; and an early warning output module for outputting early warning information based on the assessment results of the stability of the mining tunnel surrounding rock.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] This invention employs a composite sensor probe, effectively solving the challenge of fiber-optic coupling to the wall of narrow mining tunnels. During the withdrawal of the end-face coal mining machine from the tunnel, an onboard high-pressure air source propels the composite sensor probe into the tunnel. After initial deployment, micro-inflatable bladders are inflated, ensuring tight coupling between the fiber-optic sensing module and the surrounding rock surface. Kevlar tension sensors and a MEMS-IMU monitor the adhesion of the micro-inflatable bladders, guaranteeing the accuracy and completeness of acoustic emission event acquisition from micro-cracks. Simultaneously, macroscopic displacement field data of the slope area above the mining tunnel is acquired using surface remote sensing equipment, achieving the goal of obtaining information related to the stability of the surrounding rock from different dimensions.

[0025] This application utilizes a digital twin model of the end-face mining area for data mapping and fusion, and then employs a multimodal deep neural network model to invert and obtain surrounding rock damage variables. Based on these variables, an equivalent safety factor is derived to characterize the stability of the surrounding rock in the mining tunnel. This application enables continuous and quantitative assessment of the stability of the surrounding rock in the mining tunnel, allowing for real-time monitoring of the dynamic changes in surrounding rock stability over time and as mining activities progress. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is the overall process flowchart of this application;

[0028] Figure 2This is a schematic diagram showing the deployment location of the composite sensor probe of this application.

[0029] In the image: 1 - Micro-airbag. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationships, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should fall within the scope of the technical content disclosed in the present invention. It should be noted that in this specification, relational terms such as "first" and "second" are only used to distinguish one entity from several other entities, and do not necessarily require or imply any actual relationship or order between these entities.

[0032] This invention provides an embodiment:

[0033] like Figure 1 , Figure 2 As shown, a non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels includes the following steps:

[0034] S1: A prefabricated composite sensor probe is made according to the depth of the end-face mining tunnel. The composite sensor probe includes an anchoring drill bit, a micro-airbag 1 (M section), and an optical fiber sensing module embedded in the micro-airbag 1.

[0035] In this embodiment, the composite sensor probe is a disposable fiber-optic-micro-airbag composite probe. The fiber optic sensing module includes a distributed acoustic sensing (DAS) chip and a distributed strain sensing (DSS) chip. The composite sensor probe also has a built-in MEMS-IMU (Micro-Electro-Mechanical-Inertial Measurement Unit). The micro-airbag 1 is made of thermoplastic polyurethane material with a thickness of 0.6 mm and a burst pressure of 0.8 MPa. The composite sensor probe contains 120 micro-airbags 1. The tail of the composite sensor probe and the air cable interface are always kept at a positive pressure of 0.05 MPa to prevent dust backflow. A filter screen is set at the interface, and a PTFE (polytetrafluoroethylene) nanofilm is added to the surface of the filter screen to intercept coal dust.

[0036] S2: The composite sensor probe is mounted on the end-face coal mining machine. During the exit of the end-face coal mining machine from the mining chamber, the composite sensor probe is launched along the bottom plate of the side face of the mining chamber into the depth of the mining chamber using the onboard high-pressure air source. This causes the anchoring drill bit to penetrate into the coal and rock at the deepest point of the mining chamber. The anchoring drill bit is equipped with a spiral drill blade (approximately 15kg) and uses 0.3MPa pneumatic propulsion to drill into the coal wall to a depth of 0.2–0.3m, with a torque of approximately 350N. m, thus completing the anchoring and fixing position on the coal and rock at the deepest point of the mining tunnel. The M-section micro airbag 1 is laid along the depth direction of the mining tunnel as the end-side coal mining machine withdraws.

[0037] S3: Tighten the M-section micro-airbag 1 and attach it to the side wall of the mining tunnel, then inflate the M-section micro-airbag 1 in sections so that the fiber optic sensing module inside the micro-airbag 1 is coupled to the surface of the side wall of the mining tunnel.

[0038] Specifically, the composite sensor probe also has an aramid core built in as a load-bearing core. By applying a tension force of about 5kN to the aramid core at the mine entrance, the corrugated ridge of the micro-airbag 1 is straightened and attached to the wall, ensuring that the overall normal pressure reaches 3-5kPa, so as to provide the basic conditions for overall geometric wall attachment. On this basis, local concavity and convexity compensation is achieved by segmented inflation: the tail of the composite sensor probe is connected to a 0.4MPa nitrogen cylinder, and each micro-airbag 1 is inflated for about 1s by sequential pulse control of the PLC controller, so that the top pressure reaches 25kPa.

[0039] After the fiber optic sensing module inside the micro-airbag 1 is coupled to the sidewall surface of the mining tunnel, a baseline self-test is performed. This baseline self-test includes: checking the wall adhesion status of the micro-airbag 1 using a Kevlar (aramid) tension sensor and a MEMS-IMU, and verifying the coupling quality by sending a 25Hz test sweep signal from the fiber optic sensing module. If the signal-to-noise ratio corresponding to a certain section of the micro-airbag 1 is lower than 15 dB, the PLC controller controls a nitrogen cylinder to replenish the micro-airbag 1. When the composite sensing probe reaches the predetermined position, it can expand according to a set time sequence, forming a circumferential coupling and attaching the fiber optic sensing module to the surrounding rock surface, ensuring a coupling coefficient ≥ 0.85.

[0040] S4: Acquire the acoustic emission events of microcracks that are fully distributed along the mining tunnel caused by excitation through a composite sensor probe; the excitation includes a passive source and an active source; the periodic impact vibration of the end-side coal mining machine cutting drum is used as the passive source, and the three-dimensional force hammer or controllable source plate arranged on the slope surface is used as the active source; the active source is used to inject a 20Hz–2kHz sweep frequency signal into the mining tunnel wall.

[0041] Within 2–3 minutes after the end-side coal mining machine retreats, the composite sensor probe completes the inflation and adhesion to the wall; the passive vibration source continues to be provided by the periodic impact vibration of the end-side coal mining machine's cutting drum; the active vibration source is injected according to the preset frequency sweep table to form a wide spectrum coverage; the fiber optic sensing module samples at 25kHz, and the sliding window cross-correlation-wavelet packet energy spectrum fusion algorithm is used to separate the two types of wave fields and obtain the crack imaging.

[0042] Microcrack acoustic emission events The expression is: ;

[0043] In the formula, Indicates the first The location coordinates (three-dimensional spatial location) of the acoustic emission event occurring in the microcrack. This indicates the moment the event occurred, reflecting the time distribution of crack opening or frictional slippage; The "magnitude" or "moment" of the event is used to measure the amount of energy released from the fracture.

[0044] S5: Obtain macroscopic displacement field data of the slope area above the mining tunnel using surface remote sensing equipment.

[0045] The surface remote sensing equipment is a ground-based interferometric synthetic aperture radar installed on the slope area above the mining tunnel. By setting absolute coordinate control points, multiple point cloud registrations can be achieved, thus revealing the slope deformation.

[0046] The expression for macroscopic displacement field data is: ;

[0047] For a certain moment A certain point on the slope surface The displacement vector (generally contains three components: along the slope direction, perpendicular to the slope surface, and normal).

[0048] S6: Construct a digital twin model of the end-side mining area, map and fuse macroscopic displacement field data and micro-crack acoustic emission events in the digital twin model of the end-side mining area, and output a multi-field fused feature tensor.

[0049] Macroscopic displacement field data is used as boundary conditions and mapped onto the digital twin model of the end-face mining area to obtain the equivalent intrinsic strain energy. Kernel density estimation and spatiotemporal smoothing are performed on the point cloud of micro-fracture acoustic emission events to obtain the microseismic event intensity, which is then mapped onto the digital twin model of the end-face mining area. After fusion, the mapped data are used to output a multi-field fused feature tensor from the digital twin model of the end-face mining area. Data mapping and fusion are existing technologies and will not be elaborated upon here.

[0050] S7: Construct a multimodal deep neural network model, input the feature tensor of multi-field fusion into the multimodal deep neural network model, and invert to obtain the surrounding rock damage variables;

[0051] In this embodiment, the multimodal deep neural network model is a hybrid model of graph neural network and Transformer architecture; wherein, the graph neural network is used to process the topological relationship data of the mining tunnel and coal pillar, and the Transformer architecture is a deep learning model based on self-attention mechanism, used to process the time series data of sound waves, strain and displacement.

[0052] The specific steps for obtaining the surrounding rock damage variables from the feature tensor of multi-field fusion are existing technologies and will not be elaborated here.

[0053] S8: Obtain the equivalent safety factor to characterize the stability of the surrounding rock in the mining tunnel based on the surrounding rock damage variable, and then evaluate the stability of the surrounding rock in the mining tunnel.

[0054] The steps for obtaining the equivalent safety factor characterizing the stability of the mining tunnel based on surrounding rock damage variables include: obtaining a volume-average damage variable based on the surrounding rock damage variables; inverting the volume-average damage variable to obtain the equivalent safety factor; and the equivalent safety factor decaying over time. The expression for the equivalent safety factor is:

[0055]

[0056] In the formula, This is the equivalent safety factor; The volume-average damage variable;

[0057] The expression for the volume-average damage variable is:

[0058]

[0059] In the formula, Let V be the volume of the integration region. For the surrounding rock damage variable, ∈[0,1], when A value of 0 indicates that the object is intact. A value of 1 indicates complete destruction.

[0060] This embodiment also includes the prediction of the remaining life of the surrounding rock in the mining tunnel, calculated using the following formula:

[0061]

[0062] In the formula, It is the reciprocal of the equivalent safety factor, and can be understood as a proxy variable for the instability velocity; The growth rate is the reciprocal of the equivalent safety factor, i.e., the instability acceleration rate; This is an empirical constant, called the acceleration factor, which is obtained from measured data or numerical regression. The acceleration exponent describes the nonlinearity of the instability evolution (typically 1 < 0). <3); The remaining lifetime refers to the predicted time from the current moment until the moment of instability; This is the attenuation term corresponding to the current equivalent safety factor; The safety factor of the surrounding rock in the mining tunnel under critical instability conditions; To control the denominator term in the time scale, in this embodiment, ≈1.0, , All data were obtained by regression analysis of historical data on the collapse of mining tunnels.

[0063] When monitoring ends or when the composite sensor probe needs to be retrieved, the M-section micro-airbag 1 is first sequentially vented to reduce the adhesion between the micro-airbag 1 and the sidewall surface of the mining tunnel to a preset value. The aramid core is then dragged back at the mining tunnel entrance to retrieve the composite sensor probe. The aramid core, serving as the load-bearing core of the composite sensor probe, provides axial tension, geometric straightening, and a retrieval channel during non-accessible deployment, ensuring the fiber optic sensing module is stably attached to the surrounding rock surface of the mining tunnel under the expansion of the micro-airbag 1.

[0064] In a second aspect, the present invention also provides a non-accessible multi-field coupling testing system for the stability of the surrounding rock in end-face mining tunnels, comprising: a composite sensor probe deployment module for launching the composite sensor probe into the mining tunnel and coupling the composite sensor probe with the surface of the mining tunnel sidewall, and also for performing the retrieval operation of the composite sensor probe; a multi-source excitation module, including a passive source and an active source; a data acquisition module, including the composite sensor probe and its demodulation device, and a surface remote sensing device; a data processing module configured to run a digital twin model of the end-face mining area and a multimodal deep neural network model, inverting the surrounding rock damage variables based on macroscopic displacement field data and micro-crack acoustic emission events, and then obtaining an equivalent safety factor for characterizing the stability of the mining tunnel surrounding rock based on the surrounding rock damage variables; and an early warning output module for outputting early warning information based on the assessment results of the stability of the mining tunnel surrounding rock.

[0065] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels, characterized in that, Includes the following steps: According to the depth of the end-side mining tunnel, the prefabricated composite sensor probe includes an anchoring drill bit, an M-section micro-airbag (1) and an optical fiber sensing module embedded in the micro-airbag (1). The composite sensor probe is mounted on the end-side coal mining machine. During the process of the end-side coal mining machine withdrawing from the mining chamber, the composite sensor probe is launched along the bottom plate of the side wall of the mining chamber to the depth of the mining chamber using the on-board high-pressure air source, so that the anchoring drill bit is driven into the coal and rock at the deepest part of the mining chamber. The M-section micro airbag (1) is laid along the depth direction of the mining chamber as the end-side coal mining machine withdraws. The M-section micro-airbag (1) is stretched and attached to the side wall of the mining tunnel. Then the M-section micro-airbag (1) is inflated in sections so that the fiber optic sensing module inside the micro-airbag (1) is coupled to the surface of the side wall of the mining tunnel. Acoustic emission events from microcracks, induced by excitation and distributed throughout the mining tunnel, are acquired using a composite sensor probe; the excitation includes passive and active sources. Macroscopic displacement field data of the slope area above the mining tunnel were obtained using surface remote sensing equipment; A digital twin model of the end-side mining area is constructed, and macroscopic displacement field data and micro-crack acoustic emission events are mapped and fused in the digital twin model of the end-side mining area to output a multi-field fused feature tensor. A multimodal deep neural network model is constructed, and the feature tensor of multi-field fusion is input into the multimodal deep neural network model to obtain the surrounding rock damage variables through inversion. Based on the surrounding rock damage variables, an equivalent safety factor is obtained to characterize the stability of the surrounding rock in the mining tunnel, and then the stability of the surrounding rock in the mining tunnel is evaluated. The steps for obtaining the equivalent safety factor for characterizing the stability of the surrounding rock in the mining tunnel based on the surrounding rock damage variable include: obtaining the volume-average damage variable based on the surrounding rock damage variable, and inverting the equivalent safety factor based on the volume-average damage variable. The expression for the equivalent safety factor is: In the formula, This is the equivalent safety factor; The volume-average damage variable; The expression for the volume-average damage variable is: In the formula, Let V be the volume of the integration region. For the surrounding rock damage variable, ∈[0,1], when A value of 0 indicates that the object is intact. A value of 1 indicates complete destruction.

2. The non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels according to claim 1, characterized in that: The composite sensor probe also has an aramid core built in as a load-bearing core wire. By applying tension to the aramid core at the mine entrance, the M-section micro-airbag (1) is made to fit with the side wall of the mine. The tail of the composite sensor probe is connected to a nitrogen cylinder. The nitrogen cylinder is controlled by a PLC controller to realize the sequential inflation of the M-section micro-airbag (1), so that the coupling coefficient between the fiber optic sensing module in the micro-airbag (1) and the surface of the mine side wall is greater than or equal to 0.

85.

3. The non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels according to claim 2, characterized in that: After the fiber optic sensing module inside the micro-airbag (1) is coupled to the side wall surface of the mining tunnel, a baseline self-test is also performed. The baseline self-test includes: checking the wall-attachment status of the micro-airbag (1) through the Kevlar tension sensor and MEMS-IMU, and verifying the coupling quality by sending a 25Hz test sweep frequency signal by the fiber optic sensing module. If the signal-to-noise ratio of a certain section of the micro-airbag (1) is lower than 15 dB, the PLC controller controls the nitrogen cylinder to replenish the micro-airbag (1).

4. The non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels according to claim 3, characterized in that: When monitoring ends or when the composite sensor probe needs to be retrieved, the micro-airbag (1) of section M is first degassed sequentially to reduce the adhesion between the micro-airbag (1) and the side wall of the mining tunnel to a preset value. The aramid core is then dragged back at the entrance of the mining tunnel to retrieve the composite sensor probe.

5. The non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels according to claim 1, characterized in that: The periodic impact vibration of the cutting drum of the end-side coal mining machine is used as a passive source, and a three-dimensional force hammer or controllable source plate arranged on the slope surface is used as an active source. The active source is used to inject a 20Hz–2kHz sweep frequency signal into the mining wall. The surface remote sensing equipment is a ground-based interferometric synthetic aperture radar set up in the slope area above the mining tunnel.

6. The non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels according to claim 1, characterized in that: Macroscopic displacement field data is used as boundary conditions and mapped to the digital twin model of the end-face mining area. Kernel density estimation and spatiotemporal smoothing are performed on the point cloud of micro-crack acoustic emission events to obtain the intensity of microseismic events and map it to the digital twin model of the end-face mining area. After the mapped data is fused, the multi-field fused feature tensor is output by the digital twin model of the end-face mining area.

7. A non-accessible multi-field coupling test system for the stability of surrounding rock in end-face mining tunnels, used to implement the non-accessible multi-field coupling test method for the stability of surrounding rock in end-face mining tunnels as described in any one of claims 1-6, characterized in that, include: The composite sensor probe deployment module is used to launch the composite sensor probe into the mining tunnel and couple the composite sensor probe with the sidewall surface of the mining tunnel. It can also perform the retrieval operation of the composite sensor probe. Multi-source excitation module, including passive and active seismic sources; The data acquisition module includes a composite sensor probe and its demodulation equipment, as well as surface remote sensing equipment; The data processing module is configured to run the digital twin model of the mining area and the multimodal deep neural network model. Based on the macro displacement field data and the acoustic emission event of micro-cracks, the surrounding rock damage variables are obtained, and then the equivalent safety factor used to characterize the stability of the surrounding rock of the mining tunnel is obtained based on the surrounding rock damage variables. The early warning output module outputs early warning information based on the assessment results of the stability of the surrounding rock in the mining tunnel.

Images