Wading dangerous rock mass early warning method, device and equipment based on multi-source stress fusion

Abstract

The invention relates to the technical field of electronics, and discloses a wading dangerous rock mass early warning method, device and equipment based on multi-source stress fusion, a wading dangerous rock mass comprises a tensile stress concentration area and a compression-shear sensitive area, and the tensile stress concentration area and the compression-shear sensitive area are determined by conducting finite element stress simulation on a three-dimensional geologic model of the wading dangerous rock mass. A tension fracture stress sensor is arranged in the tension stress concentration area, a compression-shear stress sensor is arranged in the compression-shear sensitive area, and a microseismic acoustic emission sensor is arranged in a preset area of a main control structural plane in the wading dangerous rock body. The method comprises the following steps: acquiring first stress data acquired by a tension fracture stress sensor, second stress data acquired by a compression-shear stress sensor and acoustic emission energy data acquired by a microseismic acoustic emission sensor; performing data fusion processing on the first stress data, the second stress data and the acoustic emission energy data to obtain an early warning coefficient value; and early warning is performed on the wading dangerous rock mass based on the early warning coefficient value, so that the early warning precision is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of geological disaster monitoring, early warning and electronic technology, in particular to the stability monitoring and early warning of water-involved dangerous rock mass, and specifically to a water-involved dangerous rock mass early warning method, device and equipment based on multi-source stress fusion. BACKGROUND

[0002] The water-involved dangerous rock mass refers to the water-involved dangerous rock mass of the reservoir bank in the reservoir area of a hydropower project affected by the reservoir water drawdown. These dangerous rock masses are high and steep, difficult to approach, and mainly composed of brittle and hard rock, so the displacement during deformation and failure is relatively small, and the disaster occurs suddenly. In related technologies, the displacement of different positions of the water-involved dangerous rock mass is monitored by using displacement monitoring methods such as global navigation satellite system (GNSS) and total station, so as to perform danger early warning. However, the displacement-based damage signal is difficult to capture, resulting in great difficulty in disaster early warning. Because the damage forms of different parts of such brittle dangerous rock mass are different, the tensile stress and tensile crack displacement index of the deep part is important in the rear part of the dangerous rock mass, and the compression-shear stress is important in the lower part of the dangerous rock mass. The usual damage forms are dumping, falling, buckling, etc. The main control structural plane or weak zone of different positions is affected by the reservoir water drawdown and heavy rainfall. Using the traditional displacement monitoring methods such as GNSS and total station, it is difficult to effectively capture the instability signal of the dangerous rock mass, and the false alarm rate of the traditional GNSS monitoring method is as high as 30-40%, while the false alarm rate of the present application method can be reduced to below 5%.

[0003] In addition, the traditional contact sensor (such as stress meter) needs to be drilled and buried, but the traditional construction process will damage the original stress field of the rock mass, and cannot accurately locate the key stress area, resulting in low survival rate of the sensor. The existing early warning methods mostly use single-index threshold alarm (such as displacement acceleration), do not distinguish the stress types (such as rear edge tensile stress and front edge compression-shear stress) of different parts of the dangerous rock mass, lack fusion analysis of deep crack propagation acoustic emission signals, ignore the tensile-compression stress synergistic evolution mechanism, resulting in high false alarm rate. SUMMARY

[0004] Therefore, the present application provides a water-involved dangerous rock mass early warning method, device and equipment based on multi-source stress fusion, to solve the problem that the displacement monitoring method cannot accurately capture the instability signal when used for water-involved dangerous rock mass early warning, resulting in insufficient timeliness and accuracy of the early warning result.

[0005] In a first aspect, the present application provides a water-involved dangerous rock mass early warning method based on multi-source stress fusion, the water-involved dangerous rock mass comprising a tensile stress concentration area and a compression-shear sensitive area, the tensile stress concentration area and the compression-shear sensitive area being determined by finite element stress simulation on a three-dimensional geological model of the water-involved dangerous rock mass, the tensile stress concentration area being provided with at least one tensile stress sensor, the compression-shear sensitive area being provided with at least one compression-shear stress sensor, and a preset region of a main control structural plane in the water-involved dangerous rock mass being provided with at least one microseismic acoustic emission sensor, the method comprising: acquiring first stress data collected by the tensile stress sensor, second stress data collected by the compression-shear stress sensor, and acoustic emission energy data collected by the microseismic acoustic emission sensor; performing data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain an early warning coefficient value; and performing early warning on the water-involved dangerous rock mass based on the early warning coefficient value.

[0006] The water-involved dangerous rock mass early warning method based on multi-source stress fusion provided by the present application first locks the tensile stress concentration area and the compression-shear sensitive area through finite element simulation, then arranges tensile stress sensors, compression-shear stress sensors, and microseismic acoustic emission sensors in a targeted manner, fuses three types of core data to obtain a quantitative early warning coefficient, and finally performs early warning according to an early warning level threshold, thereby solving the problem of blind point arrangement and failure to grasp key signals in related technologies, focusing monitoring on stress and damage signals directly related to instability, making up for the defect of displacement monitoring lag, performing risk early warning based on the fusion result, leaving enough time for emergency disposal, and avoiding misjudgment caused by environmental interference such as reservoir water drawdown and heavy rainfall, because stress and acoustic emission are essential signals of internal instability of a rock mass and are less affected by the outside world. The use of a quantitative early warning coefficient for early warning makes early warning more objective and standard, is easy to implement, and completely improves the problem of difficult disaster early warning in displacement monitoring, greatly improving early warning accuracy.

[0007] In an optional implementation, the three-dimensional geological model is obtained by the following steps: obtaining surface point cloud data of the water-involved dangerous rock mass generated by unmanned aerial vehicle LiDAR scanning, underground structure data obtained by geological radar detection and interpretation, lithology and weathered area image data obtained by a multispectral camera, and geological attribute data obtained by data collection; importing the surface point cloud data into a preset geological modeling software to construct a model, thereby obtaining a surface model; importing the underground structure data into the geological modeling software to construct a model, thereby obtaining an underground model; determining a basic geometric model of the water-involved dangerous rock mass based on the surface model and the underground model; determining vector partition information based on the lithology and weathered area image data; and inputting the vector partition information and the geological attribute data into the basic geometric model for optimization, thereby obtaining the three-dimensional geological model.

[0008] In an alternative embodiment, the tensile stress concentration zone and the compression shear sensitive zone are determined by the following steps: importing the three-dimensional geological model into a preset finite element simulation software to simulate the stress state, obtaining the tensile stress concentration zone information and the compression shear sensitive zone information of the water-related dangerous rock mass, the tensile stress concentration zone information being used to represent the three-dimensional spatial coordinates and depth information of the tensile stress concentration zone, and the compression shear sensitive zone information being used to represent the three-dimensional spatial coordinates and depth information of the compression shear sensitive zone.

[0009] In an alternative embodiment, the step of performing data fusion processing on the first stress data, the second stress data and the acoustic emission energy data to obtain the early warning coefficient value includes: Solving the fusion equation constructed in advance by using the first stress data, the second stress data and the acoustic emission energy data to obtain the early warning coefficient value, the fusion equation being:

[0010] wherein K represents the early warning coefficient, represents the first stress, represents the tensile strength of the rock mass, represents the second stress, represents the shear strength of the rock mass, represents the acoustic emission energy, represents the critical energy threshold, represents the change amount of pore water pressure, represents the weight coefficient of the tensile stress index, represents the weight coefficient of the compression shear stress index, represents the weight coefficient of the acoustic emission index, represents the weight coefficient of the water pressure influence, and the weight coefficients , , , are determined by any one or more of the historical analysis method, the physical model test method and the numerical simulation test method.

[0011] In an alternative embodiment, the step of performing early warning on the water-related dangerous rock mass based on the early warning coefficient value includes: obtaining a pre-set early warning level threshold; comparing the early warning level threshold with the early warning coefficient value to obtain a comparison result; and performing early warning on the water-related dangerous rock mass based on the comparison result.

[0012] In a second aspect, the present application provides a water-involved dangerous rock mass early warning system based on multi-source stress fusion, which also comprises at least one tensile stress sensor, at least one compression-shear stress sensor, at least one microseismic acoustic emission sensor, and an early warning module; the early warning module is connected with the tensile stress sensor, the compression-shear stress sensor, and the microseismic acoustic emission sensor respectively, and is used for executing the water-involved dangerous rock mass early warning method based on multi-source stress fusion of the first aspect or any of the corresponding embodiments thereof.

[0013] The water-involved dangerous rock mass early warning system based on multi-source stress fusion provided by the present application comprises a tensile stress sensor arranged in a tensile stress concentration area, a compression-shear stress sensor arranged in a compression-shear sensitive area, and a microseismic acoustic emission sensor arranged in a main control structure surface, the monitoring range is focused from full-area general monitoring to core risk area precise monitoring, it is ensured that the stress or damage signal directly related to instability is captured by the sensor, rather than irrelevant displacement interference, the problems of related art such as wrong arrangement of points and signal leakage are solved. The early warning module collects core data by fusing the results of the three types of sensors to obtain a quantitative early warning coefficient, finally, early warning is performed according to an early warning level threshold, the early warning is more objective and standard, and is easy to implement, the problem of difficult disaster early warning existing in displacement monitoring is completely improved, and the early warning precision is greatly improved.

[0014] In a third aspect, the present application provides a water-involved dangerous rock mass early warning device based on multi-source stress fusion, which is used for executing the method of the first aspect, and comprises: an acquisition module, which is used for acquiring first stress data collected by a tensile stress sensor, second stress data collected by a compression-shear stress sensor, and acoustic emission energy data collected by a microseismic acoustic emission sensor; a fusion module, which is used for performing data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain an early warning coefficient value; and an early warning module, which is used for performing early warning on the water-involved dangerous rock mass based on the early warning coefficient value.

[0015] In a fourth aspect, the present application provides a computer device, which comprises a memory and a processor, the memory and the processor are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the water-involved dangerous rock mass early warning method based on multi-source stress fusion of the first aspect or any of the corresponding embodiments thereof.

[0016] In a fifth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used for making a computer execute the water-involved dangerous rock mass early warning method based on multi-source stress fusion of the first aspect or any of the corresponding embodiments thereof.

[0017] In a sixth aspect, the present application provides a computer program product comprising computer instructions for causing a computer to execute the multi-source stress fusion based early warning method for water-involved dangerous rock mass according to the first aspect or any possible implementation thereof. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments or prior art technical solutions in the present application, the drawings needed to be used in the specific embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0019] Figure 1 Fig. 1 is a flowchart of a multi-source stress fusion based early warning method for water-involved dangerous rock mass according to an embodiment of the present application; Figure 2 Fig. 2 is a flowchart of another multi-source stress fusion based early warning method for water-involved dangerous rock mass according to an embodiment of the present application; Figure 3 Fig. 3 is a principle block diagram of a multi-source stress fusion based early warning system for water-involved dangerous rock mass according to an embodiment of the present application; Figure 4 Fig. 4 is a structure block diagram of a multi-source stress fusion based early warning device for water-involved dangerous rock mass according to an embodiment of the present application; Figure 5 Fig. 5 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort belong to the protection scope of the present application.

[0021] In related technologies, displacement monitoring methods such as Global Navigation Satellite System (GNSS) and total station are used to monitor the displacement of unstable rock masses at different locations in water-prone areas, thereby providing early warning of potential hazards. However, displacement-based damage signals are difficult to capture, making early warning of impending disaster challenging. This is because the failure modes of these brittle rock masses differ in different parts. In the rear of the rock mass, tensile cracking is dominant, and the tensile stress and displacement indicators at the depth of the tensile cracks are important. In the lower part of the rock mass, compressive and shear stresses are dominant. The common failure modes include toppling, collapse, and buckling. The main control structural planes or weak zones at different locations are affected by reservoir water drawdown and heavy rainfall. Traditional displacement monitoring methods such as GNSS and total station are insufficient to effectively capture the instability signals of unstable rock masses.

[0022] In view of this, the present application provides an early warning method for water-prone unstable rock masses based on multi-source stress fusion, which can be applied to a single server to achieve early warning of dangerous conditions of water-prone unstable rock masses. The method provided in this application first identifies tensile stress concentration areas and compression-shear sensitive areas through finite element simulation, then strategically deploys tensile stress, compression-shear stress, and microseismic acoustic emission sensors. It fuses these three types of core data to obtain a quantified early warning coefficient, and finally issues an early warning based on the warning level threshold. This method solves the problems of blindly deploying monitoring points and failing to capture key signals in related technologies, allowing monitoring to focus on stress and damage signals directly related to instability. It also compensates for the lag in displacement monitoring. By fusing stress and acoustic emission energy, risk warnings are issued based on the fusion results, allowing sufficient time for emergency response. Furthermore, it avoids misjudgments caused by environmental interference such as reservoir water level drop and heavy rainfall, as stress and acoustic emission are essential signals of internal rock mass instability and are less affected by external factors. Using quantified early warning coefficients makes the warnings more objective and standardized, easier to implement, and completely improves the difficulty of providing early warnings before disasters in displacement monitoring, greatly improving the accuracy of early warnings.

[0023] The core improvement of this invention, addressing the shortcomings of the aforementioned related technologies, lies in: (1) Precise positioning technology in the region: By combining the three-dimensional model of the UAV with the detection of ground-penetrating radar, the stress-sensitive area is accurately located through finite element stress simulation, which solves the problem of blind sensor deployment.

[0024] (2) Low-disturbance sensor implantation device and process: a micro-casing reverse drilling tool is used, and drilling and grouting are completed simultaneously. A filling material with a modulus that matches the rock mass is used to avoid secondary construction disturbance and reduce rock mass disturbance.

[0025] (3) Zoned and graded monitoring array: FBG stress gauges are linearly arranged in the trailing tensile crack zone to capture the crack propagation gradient; MEMS sensor groups are triangularly arranged in the leading compressive shear zone to calculate the compressive shear resultant force vector; acoustic emission probes are arranged in a "cross array" in the deep part to locate the crack initiation point.

[0026] (4) Multi-source stress data fusion and hierarchical early warning model: a weighted equation is established by fusing tensile stress, compressive shear stress, acoustic emission energy and pore water pressure, and the weight coefficient is determined through physical test and numerical simulation, and multi-level precise early warning based on early warning coefficient K value is realized.

[0027] According to the embodiment of the present application, a water-related dangerous rock mass early warning method based on multi-source stress fusion is provided, and it should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0028] The construction of the three-dimensional geological model provided by the embodiment of the present application adopts a multi-source data fusion method, first, a LiDAR and a multispectral camera are carried on a UAV platform (such as DJI M300) to obtain surface data; second, underground data is obtained by combining geological radar detection and geological investigation; finally, these data are fused in a modeling software (such as Rhino) to generate a geomechanical model for stress simulation.

[0029] A water-involved dangerous rock mass early warning method based on multi-source stress fusion is provided in the embodiment, which can be used for the server described above. The water-involved dangerous rock mass includes a tensile stress concentration area and a compression-shear sensitive area. The tensile stress concentration area and the compression-shear sensitive area are determined by performing finite element stress simulation on a three-dimensional geological model of the water-involved dangerous rock mass. Specifically, the finite element stress simulation outputs three-dimensional coordinates (such as X, Y, and Z) of the tensile stress concentration area and the compression-shear sensitive area, and sensors are arranged based on the three-dimensional coordinates output by the simulation. At least one tensile stress sensor is arranged in the tensile stress concentration area, at least one compression-shear stress sensor is arranged in the compression-shear sensitive area, and at least one microseismic acoustic emission sensor is arranged in a preset region of a main control structural plane in the water-involved dangerous rock mass. In the embodiment of the present application, the tensile stress concentration area can be a trailing edge tensile crack area with a buried depth of 3.5-4.2 m. A Φ8 mm diamond thin-wall drill bit is used to drill a hole along the main control structural plane (dip angle 65°±5°) in the trailing edge tensile crack area, and the depth of the hole is 4.0 m. A mixed slurry of epoxy resin-quartz sand-nanometer montmorillonite (ratio 1:3:0.05, viscosity 1200 cP, and curing modulus 22.3 GPa) is injected into the hole synchronously. A tensile stress sensor is implanted before the initial setting of the slurry. The tensile stress sensor can include but is not limited to an FBG chain stress gauge (range 0-5 MPa, resolution 0.01 kPa), which is arranged in parallel cracks with a three-node spacing of 50 cm. The orifice is closed with an expanded rubber plug, and nitrogen gas is injected to maintain a micro-pressure of 0.2 MPa. The compression-shear sensitive area refers to a leading edge compression-shear area with a buried depth of 2.8-3.3 m. The leading edge compression-shear area is arranged in a triangular shape with a side length of 60 cm. A hole is drilled to a position 0.5 m below a weak zone, and a compression-shear stress sensor is implanted. The compression-shear stress sensor can include but is not limited to a double-layer titanium alloy shell MEMS compression-shear composite sensor (outer flexible shell thickness 0.5 mm, and silicon gel buffer layer thickness 2 mm). The original rock debris (particle size 1-5 mm, and compaction degree 95%) is backfilled to restore the continuity of the rock mass. A microseismic acoustic emission sensor is arranged on the deep main control structural plane. The microseismic acoustic emission sensor can use an acoustic emission probe (frequency response 0.1-10 kHz) in cooperation with a conical vibration needle (length 20 cm). The tip of the vibration needle is embedded in the stable rock mass by 1 cm, and the rear end is wrapped with a 5 mm silicone shock isolation sleeve. The vibration needle is arranged in a cross array (array point spacing 40 cm). Figure 1 is a flowchart of the water-involved dangerous rock mass early warning method based on multi-source stress fusion according to the embodiment of the present application, as shown in Figure 1 , the flowchart includes the following steps: Step S101, acquiring first stress data collected by a tensile stress sensor, second stress data collected by a compression-shear stress sensor, and acoustic emission energy data collected by a microseismic acoustic emission sensor.

[0030] For example, in the embodiments of this application, the first stress data can be the actual tensile stress in the tensile stress concentration area, the second stress data can be the actual shear stress in the compression-shear sensitive area, and the acoustic emission energy data refers to the elastic wave energy released when micro-fractures occur inside the rock mass (such as crack propagation or particle friction), which is monitored in real time by a micro-vibration acoustic emission sensor.

[0031] Step S102: Perform data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value.

[0032] For example, in the embodiments of this application, the first stress data, the second stress data, and the acoustic emission energy data can be fused using a preset data fusion method to obtain the warning coefficient value.

[0033] Specifically, the data fusion processing includes: performing Kalman filtering to denoise the first stress data and the second stress data; performing short-time Fourier transform on the acoustic emission energy data to extract the energy values ​​of the characteristic frequency bands; and inputting the processed data into the fusion equation for solution.

[0034] Step S103: Issue an early warning for water-related unstable rock masses based on the early warning coefficient value.

[0035] For example, in this embodiment of the application, when the warning coefficient value is greater than the preset warning threshold, a warning operation is performed. This embodiment of the application does not limit the specific content of the warning threshold, which can be determined by those skilled in the art according to their needs.

[0036] This embodiment provides a multi-source stress fusion-based early warning method for water-prone unstable rock masses. It first identifies tensile stress concentration zones and compression-shear sensitive zones through finite element simulation, then strategically deploys tensile stress, compression-shear stress, and microseismic acoustic emission sensors. By fusing these three core data sources, a quantified early warning coefficient is obtained, and finally, an early warning is issued based on the warning level threshold. This method solves the problems of blindly deploying monitoring points and failing to capture key signals in related technologies, allowing monitoring to focus on stress and damage signals directly related to instability. It also compensates for the lag in displacement monitoring. By fusing stress and acoustic emission energy, risk warnings are issued based on the fusion results, allowing sufficient time for emergency response. Furthermore, it avoids misjudgments caused by environmental interference such as reservoir water level drop and heavy rainfall, as stress and acoustic emission are essential signals of internal rock mass instability and are less affected by external factors. Using quantified early warning coefficients makes the warnings more objective, standardized, and easier to implement, fundamentally improving the difficulty of providing early warnings before disasters using displacement monitoring and significantly enhancing early warning accuracy.

[0037] This embodiment provides an early warning method for water-prone unstable rock masses based on multi-source stress fusion, which can be used in the aforementioned server. The water-prone unstable rock mass includes tensile stress concentration zones and compression-shear sensitive zones. These zones are determined by finite element stress simulation of a three-dimensional geological model of the water-prone unstable rock mass. At least one tensile stress sensor is installed in the tensile stress concentration zone, and at least one compression-shear stress sensor is installed in the compression-shear sensitive zone. At least one micro-vibration acoustic emission sensor is installed in a preset area of ​​the main control structural surface in the water-prone unstable rock mass. Figure 2 This is a flowchart of an early warning method for water-related unstable rock masses based on multi-source stress fusion according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Acquire the first stress data collected by the tensile stress sensor, the second stress data collected by the compression-shear stress sensor, and the acoustic emission energy data collected by the microseismic acoustic emission sensor. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0038] Step S202: Perform data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value.

[0039] Specifically, step S202 includes: Step S2021: Solve the pre-constructed fusion equation using the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value. The fusion equation is:

[0040] Where K represents the warning coefficient, Indicates the first stress. Indicates the tensile strength of the rock mass. Indicates the second stress. Indicates the shear strength of the rock mass. Indicates acoustic emission energy. This represents the critical energy threshold. Changes in pore water pressure The weighting coefficients representing the tensile stress index. The weighting coefficients represent the compressive-shear stress index. The weighting coefficients representing acoustic emission indicators. The weighting factor represents the influence of water pressure. , , , It can be determined by any one or more of the following methods: historical analysis, physical model testing, and numerical simulation testing.

[0041] For example, K is a warning coefficient; the larger the K value, the greater the risk. A value of 1 represents critical instability. Specifically, a value of 0.8 represents local instability, a value of 0.6 represents the beginning of crack propagation, and a value of 0.4 represents the beginning of stress concentration. In this embodiment, the weighting coefficient... , , , The determination of the risk level requires a specific approach for water-related unstable rock masses. This involves a core process of data collection through experiments or simulations, regression analysis, and on-site verification and calibration. There are two main methods: First, physical model testing. This involves constructing a model indoors that is similar to the rock mass in geometry and material properties, installing corresponding sensors, and simulating real-world conditions such as reservoir water level fluctuations and rainfall. Data on tensile stress, compressive and shear stress, acoustic emission energy, and pore water pressure are collected under different warning coefficient K values ​​(e.g., stable, warning levels). The relationship between the data and the K value is fitted using multiple regression (e.g., least squares method). After solving for the coefficients, adjustments are made based on on-site data verification. Second, numerical simulation testing. Based on a three-dimensional geological model of the site, a high-fidelity numerical model is established in finite element software. Measured rock mass parameters are input, and multiple simulation conditions (different water levels, rainfall intensities) are set. Index data corresponding to each K value are extracted, and sensitivity analysis clarifies the influence of the index on K. Regression algorithms (e.g., linear regression, machine learning) are then used to solve for the coefficients, and finally, calibration is performed using on-site monitoring data.

[0042] Among them, the weighting coefficient , , , The determination needs to be specific to the water-related unstable rock mass, and can be carried out through one or a combination of the following three methods: (1) Historical analysis method: Based on historical instability case data, principal component analysis (PCA) is used to determine the sensitivity of each indicator.

[0043] (2) Physical model test method: Construct a physical model in the room that is similar to the geometry and material properties of the dangerous rock mass on site, install a sensor array, simulate reservoir water level changes and rainfall conditions, collect index data under different warning coefficient K values, and solve the weight coefficients through multiple regression analysis.

[0044] (3) Numerical simulation test method: Based on the three-dimensional geological model, a high-fidelity numerical model is established in the finite element software, multi-condition simulation is set, index data under different K value states are extracted, and the weight coefficients are solved through sensitivity analysis and regression algorithm. The final weight coefficients need to be verified and calibrated through field monitoring data.

[0045] Specifically, the physical model testing method requires the construction of a full-scale physical model indoors that resembles the physical field of the rock mass to be observed. This model must be designed based on the characteristics of the rock mass at the site (such as elastic modulus, tensile strength, and shear strength), and uses equivalent materials (such as a similarly proportioned soil-rock mixture) to simulate the geometry and joint network. An array of sensors identical to those used in the field is precisely embedded in the model, including trailing edge FBG stress gauges (for monitoring tensile stress). Leading-edge MEMS compression-shear composite sensor (for capturing shear stress) ) and deep acoustic emission probes (used to record acoustic emission energy) ) and pore water pressure monitoring equipment (for tracking) (Changes). The experiment simulated a real-world scenario by controlling external conditions: a water pump system was used to precisely regulate the rise and fall of the reservoir water level (e.g., simulating rapid changes with a daily drop of >1m), and rainfall events were introduced using rainfall simulation equipment (e.g., a sprinkler system). The load was gradually increased until the model reached a critical instability state (e.g., K=1.0). Throughout the experiment, sensor data was collected in real time, and different K values ​​were labeled (e.g., K=0.4 corresponds to stress concentration, K=0.6 corresponds to crack propagation, and K=0.8 corresponds to local instability). Based on these data points, multiple regression analysis (e.g., least squares method) was used to fit the data. , , and The relationship between parameters and K value is determined to regress and calculate the weight factor equation; this process requires iterative optimization to ensure that the fitting error is minimized and to ultimately verify the accuracy of the weight factor in the early warning model.

[0046] Secondly, the numerical simulation test method relies on the previously constructed three-dimensional geological model (derived from centimeter-level models generated by UAV oblique photography and lidar scanning). A high-fidelity model is then established in numerical simulation software (such as ANSYS or equivalent finite element tools), and measured rock mass parameters (such as tensile strength) are input. Shear strength and critical acoustic emission energy threshold By setting up multi-condition simulation scenarios, including rapid reservoir water level drops (e.g., daily drop > 1m) and changes in rainfall intensity, the software simulates the rock mass response under different K-value conditions. After running the simulation, the software automatically calculates and outputs the results. , , and The dynamic changes of indicators are monitored, and data sequences at key nodes such as K=0.4, 0.6, 0.8, and 1.0 are extracted. Next, curve fitting or optimization algorithms (such as machine learning-based regression models) are used to analyze the correlation between parameter indicators and K values, and the weighting factors are calculated through regression. This process requires sensitivity analysis based on specific properties of the unstable rock mass (such as the distribution of fracture water enrichment areas) to ensure that the α, β, γ, and δ values ​​accurately reflect local stress differentiation and event correlation. Regardless of the method used, the weighting factors must be validated with field data (such as the sudden increase in tensile stress at the rear edge mentioned in the implementation results) to confirm the reliability of the model's early warning in real-world environments (e.g., reducing false alarm rates). Both methods emphasize customization, as the geological conditions (such as lithology and structural plane dip) of each unstable rock mass are different, requiring independent testing to avoid errors in the universal model. Finally, the weighting factors obtained from regression will be directly applied to the calculation of the early warning coefficient K, achieving dynamic fusion of multi-source data and improving timeliness and accuracy.

[0047] Step S203: Issue an early warning for water-related unstable rock masses based on the early warning coefficient value.

[0048] Specifically, step S203 includes: Step S2031: Obtain the pre-set warning level threshold.

[0049] For example, in the embodiments of this application, the warning level threshold can be determined according to requirements, and the embodiments of this application do not impose specific limitations.

[0050] Step S2032: Compare the warning level threshold with the warning coefficient value to obtain the comparison result.

[0051] For example, the embodiments of this application do not limit the specific comparison process, as long as it is reasonable.

[0052] Step S2033: Issue an early warning for water-related unstable rock masses based on the comparison results.

[0053] For example, in the embodiments of this application, when K≥0.6, a yellow warning is triggered (cracks accelerate propagation); when K≥0.8 and the initial motion of the acoustic emission P wave is tensile, a red warning is triggered.

[0054] Furthermore, the frequency of microseismic events increased by only 6.8% after construction. The system successfully detected a sudden increase in trailing edge tensile stress from 0.82 MPa to 1.18 MPa (critical value 1.3 MPa), and combined with the peak acoustic emission energy of 1520 mV·s (critical value 1000 mV·s), triggered a red alert in advance.

[0055] In some alternative implementations, the three-dimensional geological model is constructed through the following steps: Step a1: Obtain surface point cloud data of the water-prone unstable rock mass generated by UAV LiDAR scanning, underground structure data interpreted by ground-penetrating radar, lithology and weathering zone image data collected by multispectral camera, and geological attribute data collected from data collection.

[0056] For example, the surface point cloud data is obtained by scanning the water-prone unstable rock mass using a drone equipped with lidar, resulting in centimeter-level surface point cloud data. Lithology and weathering zone image data are acquired using a drone's multispectral camera, underground structure data is acquired using ground-based pulse ground-penetrating radar, and geological attribute data is determined through on-site geological surveys. Specifically, the underground structure data can be a three-dimensional anomaly model obtained by interpreting ground-based pulse ground-penetrating radar data. Since the three-dimensional geological model needs to divide geological units according to lithology and weathering degree (e.g., "strongly weathered limestone unit," "intact sandstone unit"), lithology and weathering zone imagery is an efficient tool for achieving this division. It transforms lithology and weathering differences that are difficult to distinguish with the naked eye into intuitive color partitions through spectral differences.

[0057] Step a2: Import the surface point cloud data into the preset geological modeling software to build the model and obtain the surface model.

[0058] For example, in the embodiments of this application, the preset geological modeling software may include, but is not limited to, full-process geological modeling software (Geological Object Computer-Aided Design, GOCAD) and cross-platform 3D modeling software (Rhinoceros). The embodiments of this application do not limit the specific construction process of the surface model, as long as it is reasonable.

[0059] Step a3: Import the underground structure data into the geological modeling software to build the model and obtain the underground model.

[0060] For example, in this embodiment of the application, a three-dimensional anomaly model interpreted by radar (such as bedrock buried at a depth of 10m) is imported, and an underground grid is constructed by extending downward from the surface model. If the sensitive area is buried at a depth of 0-5m, the grid of that area is refined (size 0.2m), and the 5-10m area uses a 0.5m grid to ensure that the underground model covers the stress-sensitive area and the deep stable rock mass.

[0061] Step a4: Determine the basic geometric model of the water-prone unstable rock mass based on the surface model and the underground model.

[0062] For example, in the embodiments of this application, the construction of the basic geometric model is essentially to eliminate spatial deviations between the surface model (geometric accuracy) and the underground model (geological boundary) through coordinate unification, achieve seamless connection through topological integration, and match simulation requirements through accuracy optimization, ultimately forming a three-dimensional contour skeleton that conforms to both actual geological conditions and engineering calculations.

[0063] Step a5: Determine vector zoning information based on lithology and weathering zone image data.

[0064] For example, vector partitioning is the core carrier for transforming pixel-level image information into structured, reusable spatial region definitions. The most basic function of vector partitioning is to transform pixel-level lithological / weathering differences in multispectral images into polygonal regions with clear boundaries and well-defined attributes.

[0065] Specifically, this application embodiment uses an unmanned aerial vehicle (UAV) platform equipped with a LiDAR and a multispectral camera for scanning. LiDAR data is used to generate a high-precision (centimeter-level) digital elevation model (DEM) and a three-dimensional surface mesh model, accurately depicting the geometry of the unstable rock mass. Multispectral data is used to identify areas of lithological differences and weathering degrees. On-site geological logging is performed to confirm information such as the attitude (dip, dip angle) of rock strata and the development of major joint and fracture groups. A pulsed ground-penetrating radar (PPR) is used to scan the target area, detecting the distribution of underground fissures and water-bearing weak zones. The PPR data is interpreted and converted into "anomaly" objects in three-dimensional space.

[0066] Import all the above data into professional geological modeling software (such as Rhino, GOCAD, or a self-developed platform). Using the laser point cloud model as the geometric framework, integrate the anomaly areas interpreted by ground-penetrating radar and the structural surface information obtained from geological surveys as constraints to construct a three-dimensional geological model that includes not only the geometric shape but also preliminary rock mass quality classification, fracture distribution, and aquifer inference, as well as other mechanical property information.

[0067] Step a6: Input the vector partitioning information and geological attribute data into the basic geometric model for optimization to obtain a three-dimensional geological model.

[0068] In some alternative implementations, the tensile stress concentration zone and the compression-shear sensitive zone are determined by the following steps: The three-dimensional geological model is imported into a preset finite element simulation software to simulate the stress state, thereby obtaining information on the tensile stress concentration zone and the compression-shear sensitive zone of the water-prone rock mass. The tensile stress concentration zone information is used to characterize the three-dimensional spatial coordinates and depth information of the tensile stress concentration zone, and the compression-shear sensitive zone information is used to characterize the three-dimensional spatial coordinates and depth information of the compression-shear sensitive zone.

[0069] For example, in this embodiment of the application, the aforementioned three-dimensional geological model is imported into finite element analysis software (such as ANSYS or Abaqus). Based on different rock mass properties (such as weathered zones, intact rock zones, and fracture zones), different material parameters (elastic modulus, Poisson's ratio, density, etc., which are obtained through field sampling tests or empirical formulas) are assigned. Actual engineering loads, such as gravity and water pressure (dynamic load) caused by reservoir water level changes, are applied, and finite element stress calculations are performed. The simulation result cloud map is analyzed to accurately identify the maximum tensile stress concentration area (corresponding to the potential tensile fracture zone at the rear edge) and the maximum shear stress concentration area (corresponding to the potential compressive-shear zone at the front edge) in the model. Based on the distribution of extreme points in the stress cloud map, the three-dimensional coordinates (X, Y, Z) and range of these key target points are directly output in the three-dimensional model, for example, "rear edge tensile stress concentration area, burial depth 3.5-4.2m". This completes the closed-loop process "from modeling to stress calculation to coordinate calibration".

[0070] This embodiment provides an early warning system for water-related unstable rock masses based on multi-source stress fusion, such as... Figure 3 As shown, the system includes: at least one tensile stress sensor 301, at least one compressive shear stress sensor 302, at least one micro-vibration acoustic emission sensor 303, and an early warning module 304; The early warning module 304 is connected to the tensile stress sensor 301, the compressive-shear stress sensor 302, and the microseismic acoustic emission sensor 303, respectively, and is used to execute the early warning method for water-prone dangerous rock masses based on multi-source stress fusion in the above embodiments. For details, please refer to the descriptions of the relevant content in the above embodiments, which will not be repeated here.

[0071] This invention provides a multi-source stress fusion-based early warning system for water-prone unstable rock masses. It includes tensile stress sensors deployed in areas of concentrated tensile stress, compressive-shear stress sensors deployed in areas of sensitive compressive-shear stress, and micro-vibration acoustic emission sensors deployed on the main control structural surfaces. This system focuses the monitoring range from general measurement across the entire area to precise measurement of core risk areas, ensuring that the sensors capture stress or damage signals directly related to instability, rather than irrelevant displacement interference. This solves the problems of incorrect sensor placement and signal loss in related technologies. The early warning module obtains a quantified early warning coefficient by fusing core data from the three types of sensors, and finally issues an early warning based on the warning level threshold. This makes the early warning more objective, standardized, and easier to implement, fundamentally improving the difficulty of providing early warnings for impending disasters in displacement monitoring and significantly enhancing early warning accuracy.

[0072] This embodiment also provides an early warning device for water-prone unstable rock masses based on multi-source stress fusion. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0073] This embodiment provides an early warning device for water-prone unstable rock masses based on multi-source stress fusion, used to execute the early warning method for water-prone unstable rock masses based on multi-source stress fusion in the above embodiment, such as... Figure 4 As shown, it includes: The acquisition module 401 is used to acquire the first stress data collected by the tensile stress sensor, the second stress data collected by the compression-shear stress sensor, and the acoustic emission energy data collected by the micro-vibration acoustic emission sensor. The fusion module 402 is used to perform data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value; The early warning module 403 is used to provide early warnings for water-related unstable rock masses based on early warning coefficient values.

[0074] In some alternative implementations, the three-dimensional geological model is constructed through the following steps: The data obtained includes surface point cloud data generated by UAV LiDAR scanning of water-prone unstable rock masses, underground structure data interpreted by ground-penetrating radar, lithological and weathering zone image data collected by multispectral cameras, and geological attribute data collected from data collection. Import the surface point cloud data into the preset geological modeling software to build the model and obtain the surface model. Subsurface structure data is imported into geological modeling software for model building to obtain a subsurface model; The basic geometric model of the water-related unstable rock mass was determined based on the surface model and the underground model. Vector zoning information is determined based on lithological and weathering zone image data; The vector partitioning information and geological attribute data are input into the basic geometric model for optimization to obtain a three-dimensional geological model.

[0075] In some alternative implementations, the tensile stress concentration zone and the compression-shear sensitive zone are determined by the following steps: The three-dimensional geological model is imported into a preset finite element simulation software to simulate the stress state, thereby obtaining information on the tensile stress concentration zone and the compression-shear sensitive zone of the water-prone rock mass. The tensile stress concentration zone information is used to characterize the three-dimensional spatial coordinates and depth information of the tensile stress concentration zone, and the compression-shear sensitive zone information is used to characterize the three-dimensional spatial coordinates and depth information of the compression-shear sensitive zone.

[0076] In some alternative implementations, the fusion module 402 includes: The fusion submodule is used to solve the pre-constructed fusion equation using the first stress data, the second stress data, and the acoustic emission energy data to obtain the warning coefficient value. The fusion equation is as follows:

[0077] Where K represents the warning coefficient, Indicates the first stress. Indicates the tensile strength of the rock mass. Indicates the second stress. Indicates the shear strength of the rock mass. Indicates acoustic emission energy. This represents the critical energy threshold. Changes in pore water pressure The weighting coefficients representing the tensile stress index. The weighting coefficients represent the compressive-shear stress index. The weighting coefficients representing acoustic emission indicators. The weighting factor represents the influence of water pressure. , , , It can be determined by any one or more of the following methods: historical analysis, physical model testing, and numerical simulation testing.

[0078] In some alternative implementations, the warning module 403 includes: The acquisition submodule is used to acquire the pre-set warning level threshold; The comparison submodule is used to compare the warning level threshold with the warning coefficient value to obtain the comparison result; The early warning submodule is used to issue early warnings for water-related unstable rock masses based on comparison results.

[0079] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0080] In this embodiment, the water-related dangerous rock mass early warning device based on multi-source stress fusion is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0081] This invention also provides a computer device having the above-described features. Figure 4 The device shown is an early warning device for water-related unstable rock masses based on multi-source stress fusion.

[0082] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.

[0083] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0084] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0085] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0086] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0087] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0088] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0089] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0090] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for early warning of water-related unstable rock masses based on multi-source stress fusion, characterized in that, The water-prone unstable rock mass includes a tensile stress concentration zone and a compression-shear sensitive zone. These zones are determined through finite element stress simulation of a three-dimensional geological model of the water-prone unstable rock mass. At least one tensile stress sensor is installed in the tensile stress concentration zone, and at least one compression-shear stress sensor is installed in the compression-shear sensitive zone. At least one micro-vibration acoustic emission sensor is installed in a predetermined area of ​​the main controlling structural surface within the water-prone unstable rock mass. The method includes: Acquire the first stress data collected by the tensile stress sensor, the second stress data collected by the compression-shear stress sensor, and the acoustic emission energy data collected by the micro-vibration acoustic emission sensor; The first stress data, the second stress data, and the acoustic emission energy data are fused together to obtain the early warning coefficient value. The warning coefficient value is used to issue an early warning for the water-related unstable rock mass.

2. The method according to claim 1, characterized in that, The three-dimensional geological model was constructed through the following steps: The data obtained includes surface point cloud data generated by UAV LiDAR scanning of water-prone unstable rock masses, underground structure data interpreted by ground-penetrating radar, lithological and weathering zone image data collected by multispectral cameras, and geological attribute data collected from data collection. The surface point cloud data is imported into a preset geological modeling software for model construction to obtain a surface model. The underground structure data is imported into the geological modeling software for model building to obtain the underground model; The basic geometric model of the water-related unstable rock mass is determined based on the surface model and the underground model. Vector zoning information is determined based on the aforementioned lithology and weathering zone image data; The vector partitioning information and the geological attribute data are input into the basic geometric model for optimization to obtain a three-dimensional geological model.

3. The method according to claim 1 or 2, characterized in that, The tensile stress concentration zone and the compression-shear sensitive zone are determined through the following steps: The three-dimensional geological model is imported into a preset finite element simulation software to simulate the stress state, thereby obtaining information on the tensile stress concentration zone and the compression-shear sensitive zone of the water-prone rock mass. The tensile stress concentration zone information is used to characterize the three-dimensional spatial coordinates and depth information of the tensile stress concentration zone, and the compression-shear sensitive zone information is used to characterize the three-dimensional spatial coordinates and depth information of the compression-shear sensitive zone.

4. The method according to claim 1 or 2, characterized in that, The step of performing data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value includes: The pre-constructed fusion equation is solved using the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value. The fusion equation is as follows: Where K represents the warning coefficient, Indicates the first stress. Indicates the tensile strength of the rock mass. Indicates the second stress. Indicates the shear strength of the rock mass. Indicates acoustic emission energy. This represents the critical energy threshold. Changes in pore water pressure The weighting coefficients representing the tensile stress index. The weighting coefficients represent the compressive-shear stress index. The weighting coefficients representing acoustic emission indicators. The weighting factor represents the influence of water pressure. , , , It can be determined by any one or more of the following methods: historical analysis, physical model testing, and numerical simulation testing.

5. The method according to claim 1 or 2, characterized in that, The steps for issuing an early warning for the water-prone unstable rock mass based on the aforementioned early warning coefficient value include: Obtain the pre-set warning level threshold; The warning level threshold is compared with the warning coefficient value to obtain the comparison result; Based on the comparison results, an early warning is issued for the water-related unstable rock mass.

6. A water-related unstable rock mass early warning system based on multi-source stress fusion, characterized in that, The system also includes: at least one tensile stress sensor, at least one compressive-shear stress sensor, at least one micro-vibration acoustic emission sensor, and an early warning module; The early warning module is connected to the tensile stress sensor, the compressive shear stress sensor and the micro-vibration acoustic emission sensor respectively, and is used to execute the early warning method for water-related dangerous rock masses based on multi-source stress fusion as described in any one of claims 1 to 5.

7. A water-related unstable rock mass early warning device based on multi-source stress fusion, characterized in that, The apparatus for performing the method of claim 1, comprising: The acquisition module is used to acquire the first stress data collected by the tensile stress sensor, the second stress data collected by the compression-shear stress sensor, and the acoustic emission energy data collected by the micro-vibration acoustic emission sensor. The fusion module is used to perform data fusion processing on the first stress data, the second stress data, and the acoustic emission energy data to obtain the early warning coefficient value; The early warning module is used to issue an early warning for the water-related unstable rock mass based on the early warning coefficient value.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the early warning method for water-related unstable rock masses based on multi-source stress fusion as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the water-related unstable rock mass early warning method based on multi-source stress fusion as described in any one of claims 1 to 5.

10. A computer program product, characterized in that, The method includes computer instructions for causing a computer to execute the water-related unstable rock mass early warning method based on multi-source stress fusion as described in any one of claims 1 to 5.

Images