Slope deformation and failure analysis method, device and equipment and storage medium

Abstract

The invention discloses a side slope deformation and damage analysis method, device and equipment and a storage medium, and relates to the technical field of geological disaster prevention and control, the method adopts an SBAS-I nSAR technology to analyze the deformation characteristics of a side slope, and predicts the analyzed deformation characteristics at the same time, so that the prospective and prediction of potential deformation characteristics of the side slope are realized, and the analysis accuracy of the deformation and damage of the side slope is improved. And finally, the future deformation failure surface of the side slope is determined through the predicted future deformation characteristics, so that the prevention and control of the side slope have perspectiveness, certain prevention and control measures can be adopted when the side slope does not actually generate deformation failure, the long-term stability of the side slope is ensured, and the analysis result is more accurate as the deformation characteristics obtained through analysis are in a vector form. According to the method, good compatibility and adaptability of the extreme learning machine to vectors are utilized, so that data obtained by learning is more accurate than data obtained by a traditional machine learning machine.

Description

Technical Field

[0001] The present application relates to the technical field of geological disaster prevention and control, and particularly relates to a method, device, equipment and storage medium for analyzing the deformation and failure of slopes. Background Technique

[0002] In infrastructure construction such as water conservancy and hydropower, it is necessary to analyze the deformation and failure of rock and soil masses. The geological environment has complex geological structures such as deep and narrow river valleys and steep valley slopes, and the natural slope stability is poor. It is necessary to transform high-steep rock slopes.

[0003] Slope prevention and control refers to the prevention and control measures taken when it is impossible to avoid landslide areas or unstable slope areas for engineering construction. The analysis of slope stability deformation and failure is the basic work of slope prevention and control and the premise of subsequent prevention and control work. According to the characteristics of slope rock and soil masses, corresponding measures are taken to prevent slope instability to ensure the safety of production and personnel. The analysis of slope stability deformation and failure is the basic work of slope prevention and control and the premise of subsequent prevention and control work. The significance of studying slope stability lies in that it can not only provide a scientific theoretical basis for engineering construction, but also play an important guiding role in the early warning and prediction of the development trend of slopes.

[0004] The detection and analysis of slope instability and deformation failure usually adopt the kinematic deformation failure analysis method, model test method and numerical simulation method. The kinematic deformation failure analysis method is based on the equatorial orthographic projection map for deformation and failure analysis to determine the geometric probability of slope instability. This method cannot determine the mechanical probability of slope instability, and it can only identify simple basic instability modes and cannot compound instability modes; the model test method can identify the basic and compound instability modes of rock slopes, but it is necessary to make a physical model based on the rock slope. Making this physical model requires professional equipment and professional experimental techniques, resulting in a high experimental cost for this method, and the made physical model can only simulate simple slope instability types. Summary of the Invention

[0005] The main purpose of the present application is to provide a method, device, equipment and storage medium for analyzing the deformation and failure of slopes to solve the problem of low accuracy of the analysis of the deformation and failure of slope instability in the prior art.

[0006] To achieve the above object, the present application provides the following technical solutions:

[0007] A method for analyzing the deformation and failure of a slope, the slope has a cross-section and a number of cross-section monitoring points are set on the cross-section, and the deformation and failure analysis method includes:

[0008] Step S1, obtaining the observation data of all cross-section monitoring points based on a number of observation time intervals;

[0009] Step S2, analyze the deformation displacement vectors of all observed data;

[0010] Step S3, integrate all the deformation displacement vectors of an observation time interval into a vector data set;

[0011] Step S4, learn and train all the vector data sets through an extreme learning machine, and obtain a predicted vector data set based on a future time interval;

[0012] Step S5, respectively obtain the future displacement vectors of each cross-section monitoring point based on the current vector data set, and mark the cross-section monitoring points whose future displacement vectors exceed the preset displacement threshold as the potentially damaged monitoring points;

[0013] Step S6, respectively obtain the coordinate points of each potentially damaged monitoring point and obtain the projection vector lines of all the future displacement vectors based on the geological drawing of the slope;

[0014] Step S7, respectively obtain the perpendicular lines of each projection vector line and the intersection points of all the perpendicular lines, and slide the respective perpendicular lines on each projection vector line so that the minimum covering circle of all the intersection points reaches the minimum radius;

[0015] Step S8, obtain the center of the minimum covering circle corresponding to the minimum radius, which is the center of the deformation failure surface;

[0016] Step S9, define the distance between the center of the deformation failure surface and the leading edge of the cross-section as the radius of the deformation failure surface, and obtain the deformation failure surface.

[0017] As a further improvement of the present application, in Step S9, after defining the distance between the center of the deformation failure surface and the leading edge of the cross-section as the radius of the deformation failure surface to obtain the deformation failure surface, the following steps are included:

[0018] Step S10, obtain the finite element model of the slope, and import the finite element model and all the future displacement vectors into a preset geological simulation software to form a digital simulation model of the slope;

[0019] Step S20, obtain the leading edge line of the deformation failure surface in the preset geological simulation software;

[0020] Step S30, add a layer of support plates with a preset thickness along the leading edge line, and the normal line of the support plate is tangent to the deformation failure surface;

[0021] Step S40, through the preset geological simulation software, simulate the further deformation and failure of the slope under the condition of the support plate along the time process;

[0022] Step S50: Divide the time process into several simulation time lengths, and obtain the simulated displacement vectors of the further deformation and failure once for each simulation time length.

[0023] Step S60: Replace the future displacement vector with the simulated displacement vector as the execution entity, and repeat Steps S5 to S9. Obtain a simulated deformation and failure surface based on one simulation time length.

[0024] Step S70: Determine whether the radii of all simulated deformation and failure surfaces decrease along the time process. If so, execute Step S80.

[0025] Step S80: Determine that the support plate is an effective support plate.

[0026] Step S90: Send the installation position of the effective support plate to an external visual monitoring terminal.

[0027] As a further improvement of the present application, in Step S90, after sending the installation position of the effective support plate to an external visual monitoring terminal, it includes:

[0028] Step S100: Determine whether the radii of all simulated deformation and failure surfaces decrease and disappear along the time process. If not, execute Step S200.

[0029] Step S200: Determine that the deformation and failure risk of the slope has not been eliminated.

[0030] Step S300: Install an additional support plate above the elevation of the effective support plate.

[0031] Step S400: Repeat Steps S40 to S90 until all simulated deformation and failure surfaces disappear.

[0032] As a further improvement of the present application, after Step S400, repeat Steps S40 to S90 until all simulated deformation and failure surfaces disappear, it includes:

[0033] Step S1000: Add stabilizing members between the plates of all effective support plates to form a complete support surface.

[0034] Step S2000: Send the complete support surface to an external visual monitoring terminal.

[0035] As a further improvement of the present application, in Step S4, learn and train all vector data sets through an extreme learning machine, and obtain a predicted vector data set based on one future time interval, including:

[0036] Step S41: Perform vector normalization processing on all vector data sets, and obtain a normalized data set based on one vector data set.

[0037] Step S42: Divide the current normalized data set into a training set and a validation set according to a preset ratio;

[0038] Step S43: Define an extreme learning machine model according to the data dimension of the training set;

[0039] Step S44: Train and learn the extreme learning machine model through the training set to obtain a prediction model;

[0040] Step S45: Input the validation set into the prediction model to obtain a prediction data set based on a normalized data set;

[0041] Step S46: Respectively restore each prediction data set to a prediction vector data set through inverse vector normalization operation.

[0042] As a further improvement of the present application, in step S75, update the real-time positions of all moving points through a global optimization algorithm so that the minimum covering circle of all intersection points reaches the minimum radius, including:

[0043] Step S751: Define a number of random solutions for each moving point respectively;

[0044] Step S752: Define the optimization result of all random solutions as the minimum covering circle of all intersection points reaching the minimum radius;

[0045] Step S753: Initialize the positions of each random solution;

[0046] Step S754: Update the current position and current speed of each random solution respectively;

[0047] Step S755: Obtain the individual optimal solution and global optimal solution of each random solution respectively based on each update;

[0048] Step S756: Respectively judge whether the difference between each individual optimal solution and each individual optimal solution in the previous update is less than or equal to a first preset adaptation threshold. If all are less, execute step S757;

[0049] Step S757: Respectively judge whether the difference between each global optimal solution and each global optimal solution in the previous update is less than or equal to a second preset adaptation threshold. If all are less, execute step S758;

[0050] Step S758: Determine that the optimal solutions of all moving points have been obtained.

[0051] As a further improvement of the present application, in step S9, define the distance between the center of the deformation failure surface and the leading edge of the cross section as the radius of the deformation failure surface to obtain the deformation failure surface, and then, including:

[0052] Step S10, output the deformation failure surface to an external visualization terminal.

[0053] To achieve the above object, the present application also provides the following technical solutions:

[0054] A deformation failure analysis device for a slope, the deformation failure analysis device is applied to the deformation failure analysis method as described above, and the deformation failure analysis device includes:

[0055] An observation data acquisition module, configured to acquire observation data of all cross-section monitoring points based on a plurality of observation time intervals;

[0056] A deformation displacement vector acquisition module, configured to analyze the deformation displacement vectors of all the observation data;

[0057] A vector data set integration module, configured to integrate all the deformation displacement vectors of one observation time interval into a vector data set;

[0058] A predicted vector data set acquisition module, configured to learn and train all the vector data sets through an extreme learning machine, and obtain a predicted vector data set based on a future time interval;

[0059] A possible failure monitoring point marking module, configured to respectively obtain the future displacement vectors of each cross-section monitoring point based on the current vector data set, and mark the cross-section monitoring points whose future displacement vectors exceed a preset displacement threshold as possible failure monitoring points;

[0060] A projection vector line acquisition module, configured to respectively obtain the coordinate points of each possible failure monitoring point and obtain the projection vector lines of all the future displacement vectors based on the geological drawing of the slope;

[0061] A perpendicular intersection point update module, configured to respectively obtain the perpendiculars of each projection vector line and the intersection points of all the perpendiculars, and slide the respective perpendiculars on each projection vector line so that the minimum covering circle of all the intersection points reaches the minimum radius;

[0062] A deformation failure surface determination module, configured to obtain the center of the minimum covering circle corresponding to the minimum radius as the center of the deformation failure surface;

[0063] A deformation failure surface acquisition module, defining the distance between the center of the deformation failure surface and the leading edge of the cross-section as the radius of the deformation failure surface, and obtaining the deformation failure surface.

[0064] To achieve the above object, the present application also provides the following technical solutions:

[0065] An electronic device includes a processor and a memory coupled to the processor. The memory stores program instructions executable by the processor. When the processor executes the program instructions stored in the memory, it implements a method for analyzing the deformation and failure of a slope as described above.

[0066] To achieve the above object, the present application also provides the following technical solutions:

[0067] A storage medium stores program instructions that can implement a method for analyzing the deformation and failure of a slope as described above when executed by a processor.

[0068] The present application obtains the observation data of all cross-section monitoring points based on a number of observation time intervals; analyzes the deformation displacement vectors of all the observation data; integrates all the deformation displacement vectors of one observation time interval into a vector data set; learns and trains all the vector data sets through an extreme learning machine, and obtains a predicted vector data set based on a future time interval; obtains the future displacement vectors of each cross-section monitoring point based on the current vector data set, and marks the cross-section monitoring points whose future displacement vectors exceed the preset displacement threshold as potentially damaged monitoring points; respectively obtains the coordinate points of each potentially damaged monitoring point and obtains the projection vector lines of all the future displacement vectors based on the geological drawing of the slope; respectively obtains the perpendicular lines of each projection vector line and the intersection points of all the perpendicular lines, and slides the respective perpendicular lines on each projection vector line so that the minimum covering circle of all the intersection points reaches the minimum radius; obtains the center of the minimum covering circle corresponding to the minimum radius, which is the center of the deformation failure surface; defines the distance between the center of the deformation failure surface and the leading edge of the cross-section as the radius of the deformation failure surface, and obtains the deformation failure surface. The present application uses the SBAS-InSAR technology to analyze the deformation characteristics of the slope, and at the same time predicts the analyzed deformation characteristics, realizing the foresight and prediction of the potential deformation characteristics of the slope. Finally, the future deformation failure surface of the slope is confirmed through the predicted future deformation characteristics, making the prevention and control of the slope forward-looking. Certain prevention and control measures can be adopted when the slope has not actually undergone deformation and failure, ensuring the long-term stability of the slope. Since the analyzed deformation characteristics are in vector form, the method utilizes the good compatibility and adaptability of the extreme learning machine for vectors, making the learned data more accurate than that obtained by traditional machine learning machines. Description of the Drawings

[0069] Figure 1 It is a schematic flowchart of the steps of an embodiment of the method for analyzing the deformation and failure of the slope of the present application;

[0070] Figure 2 It is a schematic diagram of the functional modules of an embodiment of the device for analyzing the deformation and failure of the slope of the present application;

[0071] Figure 3 Schematic structural diagram of an embodiment of the electronic device of the present application;

[0072] Figure 4 Schematic structural diagram of an embodiment of the storage medium of the present application. Detailed implementation manners

[0073] Next, the present application will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0074] The terms "first", "second", and "third" in the present application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0075] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0076] As Figure 1 shown, this embodiment provides an embodiment of the slope deformation and failure analysis method. In this embodiment, the slope to be analyzed for deformation and failure has a cross-section, and a number of cross-section monitoring points are provided on the cross-section.

[0077] Preferably, a surface deformation monitoring point refers to a measurement point directly buried on the deformed body that can reflect its deformation characteristics, commonly known as an observation point. These monitoring points are usually used in total station and GNSS monitoring and are surface deformation monitoring points in the narrow sense. In the broad sense, monitoring points include all points installed at the monitoring site, which can be measurement marks or sensor components. Surface deformation monitoring points can be classified into the following categories:

[0078] Reference point: Usually buried on stable bedrock or outside the deformation area, preserved for a long time and stable without movement.

[0079] Working point: Buried near the object under study, required to be stable during the observation period, and its position is regularly detected by the reference point.

[0080] Observation point: Directly buried on the deformed body, can reflect the deformation characteristics of the building, and is generally buried inside the building.

[0081] Preferably, surface deformation monitoring points are widely used in various engineering and local deformation studies, such as monitoring the three-dimensional deformation of engineering buildings, the sliding of landslide bodies, the surface movement and subsidence caused by underground mining, etc. Specific application scenarios include:

[0082] Dam: Monitor the vertical displacement and horizontal displacement of the dam.

[0083] Subway tunnel structure: Monitor the deformation of the tunnel structure.

[0084] Slope geological disaster structure: Monitor the stability of the slope.

[0085] Bridge: Monitor the deformation of the bridge.

[0086] High-rise building: Monitor the inclination and settlement of the building.

[0087] Specifically, the deformation failure analysis method includes the following steps:

[0088] Step S1, obtain the observation data of all cross-section monitoring points based on several observation time intervals.

[0089] Preferably, the observation data can be obtained by the borehole inclinometer method or directly obtained.

[0090] Step S2, analyze the deformation displacement vectors of all the observation data.

[0091] Preferably, the Small Base line Subset InSAR (SBAS-InSAR) differential interferometric short baseline set time series deformation failure analysis technique is an InSAR time series method based on multiple master images. Based on the short baseline set principle, SBAS-InSAR has multiple master images, but one of the images still needs to be selected as the common master image for registration. After forming each interferometric subset, the external reference Digital Elevation Model (DEM) data is used to simulate and remove the topographic phase of each interferogram, and then a time series differential interferogram set is generated. After phase unwrapping, the phase information of each coherent target is obtained, including deformation phase, atmospheric delay phase, orbit error phase, etc. Each error phase can be removed by filtering methods or polynomial models in the time series.

[0092] Specifically, the processing flow of SBAS-InSAR is mainly data acquisition and presetting, SAR data preprocessing, generating a connection graph, an interferometric workflow, and connection graph editing.

[0093] Step S3, integrate all deformation displacement vectors in an observation time interval into a vector data set.

[0094] Preferably, the surface deformation information obtained by SBAS-InSAR analysis can be formed into vectors based on adjacent time series. The length of the vector is the surface deformation amplitude of adjacent time series, and the direction of the vector is the surface deformation direction of adjacent time series.

[0095] Step S4, learn and train all vector data sets through an extreme learning machine, and obtain a predicted vector data set based on a future time interval.

[0096] Preferably, the extreme learning model is a feedforward neural network that can be used to train a single hidden layer. Different from the traditional training algorithm of a single hidden layer feedforward neural network, the extreme learning machine randomly selects the input layer weights and hidden layer biases, and the output layer weights are calculated and analyzed based on the Moore-Penrose (MP) generalized inverse matrix theory by minimizing the loss function composed of the training error term and the regularization term of the output layer weight norm. And even if the hidden layer nodes are randomly generated by the extreme learning machine, the extreme learning machine still maintains the universal approximation ability of a single hidden layer feedforward neural network.

[0097] Step S5, obtain the future displacement vectors of each cross-section monitoring point based on the current vector data set, and mark the cross-section monitoring points whose future displacement vectors exceed the preset displacement threshold as potentially damaged monitoring points.

[0098] Preferably, the preset displacement threshold can be set to 2.5 m.

[0099] Step S6: Obtain the coordinate points of each potential failure monitoring point respectively and acquire the projection vector lines of all future displacement vectors based on the geological drawing of the slope.

[0100] Preferably, the geological drawing is the slope profile drawing generated during preliminary exploration, generally in the form of a software program rather than a real paper drawing.

[0101] Step S7: Obtain the perpendicular lines of each projection vector line and the intersection points of all perpendicular lines respectively, and slide the respective perpendicular lines on each projection vector line to minimize the radius of the minimum covering circle of all intersection points.

[0102] Preferably, the projection vector line is the line formed by projecting one vector onto another vector or plane. Specifically, the projection vector line is to map a vector (such as displacement, velocity, acceleration, force) onto another vector or plane to form a new vector with a perpendicular intersection point. This new vector is parallel to the projected vector and points in its direction. The projection vector line is determined by calculating the inner product and norm of two vectors. The specific calculation method involves the measurement or representation of a vector in a given direction. In two - dimensional or three - dimensional space, the projection vector line represents the projection of a vector in the direction of another vector, which helps to understand the relative position relationship between the two vectors.

[0103] Preferably, the projection vector line in this embodiment can be directly obtained through UG programming.

[0104] Step S8: The center of the minimum covering circle corresponding to the minimum radius is the center of the deformation failure surface.

[0105] Step S9: Define the distance between the center of the deformation failure surface and the leading edge of the cross - section as the radius of the deformation failure surface to obtain the deformation failure surface.

[0106] Preferably, the leading edge of the slope cross - section is usually located at the very front of the slope, that is, the intersection line between the front part of the landslide tongue and the original ground line, which is called the landslide front, and the most prominent point is called the tongue tip.

[0107] Preferably, steps S21 to S28 can be directly completed automatically in SARscape. The user only needs to select a small number of parameters and settings of SARscape, and the usage tutorial of SARscape can be directly obtained from public channels.

[0108] Furthermore, in step S9, after defining the distance between the center of the deformation failure surface and the leading edge of the cross - section as the radius of the deformation failure surface to obtain the deformation failure surface, the following steps are further included:

[0109] Step S10: Obtain the finite element model of the slope and import the finite element model and all future displacement vectors into the preset geological simulation software to form a digital simulation model of the slope.

[0110] Preferably, the preset geological simulation software can be implemented through general software such as Abaqus and FLAC3D, or can be implemented through software such as PLAXIS, 3DEC, GSMM, and EVS in the field of geotechnical engineering.

[0111] Step S20: Obtain the leading edge line of the deformation failure surface in the preset geological simulation software.

[0112] Step S30: Add a layer of support plates with a preset thickness along the leading edge line, and the normal line of the support plates is tangent to the deformation failure surface.

[0113] Preferably, the common diameter specifications of the arched frame slope protection formwork are 2.5 meters, 3 meters, 3.5 meters, 4 meters, etc., and the height ranges from 30 centimeters to 80 centimeters, including 30 centimeters, 40 centimeters, 50 centimeters, 60 centimeters, 70 centimeters, and 80 centimeters; the general specifications of the lattice beam slope protection formwork are 2m×2m, 3m×3m, 4m×4m, 5m×5m, 6m×6m, etc., and the dimensions are set according to actual needs.

[0114] Step S40: Through the preset geological simulation software, simulate the further deformation and failure of the slope under the condition of the support plates along the time process.

[0115] Step S50: Divide the time process into several simulation time lengths, and obtain a simulation displacement vector of the further deformation and failure once based on each simulation time length.

[0116] Preferably, the simulation time length can be the same as a preset time period, a preset prediction step number, etc.

[0117] Step S60: Replace the future displacement vector with the simulation displacement vector as the execution body, and repeat Steps S5 to S9 to obtain a simulated deformation failure surface based on one simulation time length.

[0118] Step S70: Judge whether the radii of all the simulated deformation failure surfaces decrease along the time process. If so, execute Step S80.

[0119] Step S80: Determine that the support plates are effective support plates.

[0120] Step S90: Send the installation positions of the effective support plates to an external visual monitoring terminal.

[0121] Furthermore, in Step S90, after sending the installation positions of the effective support plates to an external visual monitoring terminal, the following steps are further included:

[0122] Step S100: Judge whether the radii of all the simulated deformation failure surfaces decrease and disappear along the time process. If not, execute Step S200.

[0123] Step S200, determine that the risk of deformation and failure of the slope has not been eliminated.

[0124] Step S300, install an additional layer of support plates above the elevation of the effective support plates.

[0125] Step S400, repeatedly execute Steps S40 to S90 until all simulated deformation and failure surfaces disappear.

[0126] Preferably, perform a deformation and failure analysis once for each additional layer installed until the simulated deformation and failure surfaces disappear.

[0127] Furthermore, in Step S400, repeatedly execute Steps S40 to S90 until all simulated deformation and failure surfaces disappear. After that, it includes:

[0128] Step S1000, add stabilizing members between the plates of all effective support plates to form a complete support surface.

[0129] Step S2000, send the complete support surface to an external visual monitoring terminal.

[0130] Furthermore, in Step S4, learn and train all vector data sets through an extreme learning machine, and obtain a predicted vector data set based on a future time interval, including:

[0131] Step S41, perform vector normalization processing on all vector data sets to obtain a normalized data set based on a vector data set.

[0132] Preferably, vector normalization processing is a method of scaling a vector proportionally to a unit vector. The main purpose is to only consider the direction of the vector without affecting its magnitude. The mathematical principle of vector normalization is to divide the vector by its modulus length to obtain a unit vector.

[0133] Step S42, divide the current normalized data set into a training set and a validation set according to a preset ratio.

[0134] Preferably, the preset ratio usually adopts a ratio of 80%:20% to divide the image data into a training set and a validation set, that is, 80% of the data is the training set and 20% of the data is the validation set.

[0135] Step S43, define an extreme learning model according to the data dimension of the training set.

[0136] Step S44, train and learn the extreme learning model through the training set to obtain a prediction model.

[0137] Step S45, input the validation set into the prediction model to obtain a predicted data set based on a normalized data set.

[0138] Step S46, respectively restore each predicted data set to a predicted vector data set through the inverse operation of vector normalization.

[0139] Specifically, the extreme learning machine can be implemented for training and learning through the following process:

[0140] ① Define the i-th normalized coordinate data of the training set as (x i , t i ).

[0141] ② Define the training set x = (x i , t i ) as x = (x 1 , x 2 , …, x i , …, x m ) T , x i ∈ R m , where m is the number of normalized coordinate data in the training set and is also the dimension of the transposed matrix (x 1 , x 2 , …, x i , …, x m ) T , and R m is the set of m-dimensional vectors of the training set x.

[0142] ③ Define the training result t of the training set as t = (t i , t i ) as t = (t 1 , t 2 , …, t i , …, t n ) T , t i ∈ R n , where n is the number of training results in the training set and is also the dimension of the transposed matrix (t 1 , t 2 , …, t i , …, t n ) T , and R n is the set of n-dimensional vectors of the training result t.

[0143] ④ Based on the training set x = (x 1 , x 2 , …, x i , …, x m ) T , x i ∈ R m and the training result t = (t 1 , t 2 , …, t i , …, tn ) T ,t i ∈R n Define the extreme learning model according to the following formula:

[0144]

[0145] where β = [β 1 , β 2 , …, β j , … β L-1 , β L T , β is the first connection weight between the hidden layer and the output layer of the extreme learning model, β j is the j-th first connection weight, L is the number of nodes in the hidden layer, H(x) is the output value of the hidden layer, H(x) = [h 1 (x), h 2 (x), …, h j (x), …, h L-1 (x), h L (x)], h j (x) = g(w j ·x i + b j ), g(·) is the activation function, w j is the second connection weight between the input layer and the j-th node of the hidden layer of the extreme learning model, b j is the threshold of the j-th node of the hidden layer.

[0146] Preferably, g(·) can be set to activation functions such as the Sigmoid function, the Gaussian function, etc. If the Sigmoid function is selected, then g(a) can be expressed as where a = w j ·x i + b j .

[0147] It should be noted that the symbolic meanings of the above formulas are not interoperable with other parts of the embodiments.

[0148] Among them, according to the above specific process, step S44, training and learning the extreme learning model through the training set to obtain a prediction model, can be expanded as:

[0149] Step S441, randomly generate all the second connection weights and all the thresholds through a non-linear mapping function in the feature space based on the extreme learning model.

[0150] Step S442, calculate the output value of the hidden layer through the randomly generated second connection weights and thresholds.

[0151] ​Step S443, solve for the optimal solution of the first connection weights by minimizing the approximate squared difference according to the following formula:

[0152]

[0153] where H is the output matrix of the hidden layer, T is the target matrix of the output layer, β * is the optimal solution, H + is the Moore-Penrose generalized inverse matrix of the output matrix H, and H + =(H T H) -1 ·H T .

[0154] Step S444, obtain the optimal solution and the corresponding second connection weights and thresholds and substitute them into the extreme learning model to obtain the prediction model.

[0155] Preferably, the Moore-Penrose generalized inverse matrix H + can be calculated by singular value decomposition.

[0156] Furthermore, in step S7, obtain the perpendicular lines of each projection vector line and the intersection points of all perpendicular lines respectively, and slide the respective perpendicular lines on each projection vector line to minimize the radius of the minimum covering circle of all intersection points, including:

[0157] Step S71, define a moving point on each projection vector line respectively, and each moving point is respectively constrained on its own projection vector line.

[0158] Step S72, generate a perpendicular line perpendicular to the current projection vector line based on the moving point of the current projection vector line.

[0159] Step S73, obtain all intersection points between all perpendicular lines.

[0160] Step S74, obtain the minimum covering circle of all intersection points.

[0161] Step S75, update the real-time positions of all moving points through a global optimization algorithm to minimize the radius of the minimum covering circle of all intersection points.

[0162] Step S76, obtain the real-time positions of all moving points when the radius of the minimum covering circle of all intersection points reaches the minimum and define them as the final positions of all moving points.

[0163] Furthermore, in step S74, obtain the minimum covering circle of all intersection points, including:

[0164] Step S741, generate a rectangular coordinate system based on the geological drawing.

[0165] Step S742: Convert all intersection points into coordinate points according to the rectangular coordinate system.

[0166] Step S743: Obtain any two coordinate points p 1 and p 2 from all the coordinate points, and obtain the initial circle C 1 with the line segment p 2 p 2 as the diameter, where the subscript 2 represents the number of coordinate points inside the initial circle.

[0167] Step S744: Traverse each coordinate point in sequence, and determine whether the i-th coordinate point p i is located inside the first iterative circle C i-1 . If the i-th coordinate point p i is not located inside the first iterative circle C i-1 , then execute Step S745.

[0168] Step S745: Obtain the second iterative circle C 1 with the line segment p i p i as the diameter.

[0169] Step S746: Determine whether the j-th coordinate point p j is located inside the second iterative circle C i , where j < i. If the j-th coordinate point p j is not located inside the second iterative circle C i , then execute Step S247.

[0170] Step S747: Obtain the third iterative circle C 1 with the line segment p j p j as the diameter.

[0171] Step S748: Determine whether the k-th coordinate point p k is located inside the third iterative circle C j , where k < j < i. If the k-th coordinate point p k is not located inside the third iterative circle C j , then execute Step S249.

[0172] Step S749: Connect p i , p j , p k to form a triangle, and obtain the circumcircle of the triangle. The circumcircle is the minimum covering circle.

[0173] Furthermore, in Step S75, update the real-time positions of all moving points through a global optimization algorithm to minimize the radius of the minimum covering circle of all intersection points, including:

[0174] Step S751: Define a number of random solutions for each moving point respectively.

[0175] Step S752: Define the optimization result of all random solutions as the minimum radius of the minimum covering circle of all intersection points.

[0176] Step S753: Initialize the positions of each random solution.

[0177] Step S754: Update the current position and current speed of each random solution respectively.

[0178] Step S755: Obtain the individual optimal solution and the global optimal solution of each random solution respectively based on each update.

[0179] Step S756: Judge respectively whether the difference between each individual optimal solution and each individual optimal solution in the previous update is less than or equal to the first preset adaptation threshold. If all are less, execute Step S757.

[0180] Step S757: Judge respectively whether the difference between each global optimal solution and each global optimal solution in the previous update is less than or equal to the second preset adaptation threshold. If all are less, execute Step S758.

[0181] Preferably, the values of the first preset adaptation threshold and the second preset adaptation threshold need to be adjusted according to the specific problem, generally according to the calculation results. If the adaptation threshold is set too small, it may cause the algorithm to stop prematurely and the optimal solution cannot be obtained; if the adaptation threshold is set too large, it may cause the algorithm to be updated excessively and waste computing resources.

[0182] Preferably, the adaptation threshold can also be evaluated by one of the Griewank function, Rastrigin function, Schaffer function, Ackley function, and Rosenbrock function.

[0183] It should be noted that the symbol meanings in the above additional content are not interoperable with other parts of the embodiment.

[0184] Step S758: Determine that the optimal solutions of all moving points have been obtained.

[0185] Furthermore, in Step S9, define the distance between the center of the deformation failure surface and the leading edge of the section as the radius of the deformation failure surface to obtain the deformation failure surface. After that, it includes:

[0186] Step S10: Output the deformation failure surface to an external visualization terminal.

[0187] In this embodiment, the observed data of all cross-section monitoring points based on several observation time intervals are obtained; the deformation displacement vectors of all the observed data are analyzed; the deformation displacement vectors of one observation time interval are integrated into a vector data set; all the vector data sets are learned and trained by an extreme learning machine, and a predicted vector data set is obtained based on a future time interval; the future displacement vectors of each cross-section monitoring point are obtained based on the current vector data set, and the cross-section monitoring points whose future displacement vectors exceed the preset displacement threshold are marked as potential failure monitoring points; the coordinate points of each potential failure monitoring point are obtained respectively, and the projection vector lines of all the future displacement vectors are obtained based on the geological drawing of the slope; the perpendicular lines of each projection vector line and the intersection points of all the perpendicular lines are obtained respectively, and the perpendicular lines are slid on each projection vector line respectively, so that the minimum covering circle of all the intersection points reaches the minimum radius; the center of the minimum covering circle corresponding to the minimum radius is obtained, which is the center of the deformation failure surface; the distance between the center of the deformation failure surface and the leading edge of the cross-section is defined as the radius of the deformation failure surface, and the deformation failure surface is obtained. This embodiment uses the SBAS-InSAR technology to analyze the deformation characteristics of the slope, and at the same time predicts the analyzed deformation characteristics, realizing the foresight and prediction of the potential deformation characteristics of the slope. Finally, the future deformation failure surface of the slope is confirmed through the predicted future deformation characteristics, making the prevention and control of the slope forward-looking. Certain prevention and control measures can be adopted when the slope has not actually undergone deformation and failure, ensuring the long-term stability of the slope. Since the analyzed deformation characteristics are in vector form, the method utilizes the good compatibility and adaptability of the extreme learning machine to vectors, making the learned data more accurate than the data obtained by traditional machine learning machines.

[0188] As Figure 2 shown, this embodiment provides an embodiment of a device for analyzing the deformation and failure of a slope. In this embodiment, the device for analyzing the deformation and failure is applied to the method for analyzing the deformation and failure as described in the above embodiment.

[0189] Specifically, the device for analyzing the deformation and failure includes an observed data acquisition module 1, a deformation displacement vector acquisition module 2, a vector data set integration module 3, a predicted vector data set acquisition module 4, a potential failure monitoring point marking module 5, a projection vector line acquisition module 6, a perpendicular line intersection point update module 7, a deformation failure surface determination module 8, and a deformation failure surface acquisition module 9, which are electrically connected in sequence.

[0190] Among them, the observation data acquisition module 1 is used to acquire the observation data of all cross-section monitoring points based on a number of observation time intervals; the deformation displacement vector acquisition module 2 is used to analyze the deformation displacement vectors of all the observation data; the vector data set integration module 3 is used to integrate all the deformation displacement vectors of one observation time interval into a vector data set; the predicted vector data set acquisition module 4 is used to learn and train all the vector data sets through an extreme learning machine and obtain a predicted vector data set based on a future time interval; the possible failure monitoring point marking module 5 is used to respectively obtain the future displacement vectors of each cross-section monitoring point based on the current vector data set, and mark the cross-section monitoring points whose future displacement vectors exceed the preset displacement threshold as possible failure monitoring points; the projection vector line acquisition module 6 is used to respectively obtain the coordinate points of each possible failure monitoring point and obtain the projection vector lines of all the future displacement vectors based on the geological drawing of the slope; the perpendicular intersection point update module 7 is used to respectively obtain the perpendiculars of each projection vector line and the intersection points of all the perpendiculars, and slide the respective perpendiculars on each projection vector line so that the minimum covering circle of all the intersection points reaches the minimum radius; the deformation failure surface determination module 8 is used to obtain the center of the minimum covering circle corresponding to the minimum radius as the center of the deformation failure surface; the deformation failure surface acquisition module 9 defines the distance between the center of the deformation failure surface and the leading edge of the cross-section as the radius of the deformation failure surface to obtain the deformation failure surface.

[0191] Furthermore, the deformation failure analysis device further includes a slope digital simulation model acquisition module, a deformation failure surface leading edge line acquisition module, a support plate adding module, a support plate condition failure simulation module, a simulated displacement vector acquisition module, a simulated deformation failure surface acquisition module, a deformation failure surface radius judgment module, an effective support plate determination module, and an effective support plate installation position sending module that are electrically connected in sequence; the slope digital simulation model acquisition module is electrically connected to the deformation failure surface acquisition module 9.

[0192] Among them, the slope digital simulation model acquisition module is used to acquire the finite element model of the slope, and import the finite element model and all future displacement vectors into the preset geological simulation software to form the digital simulation model of the slope; the front edge line acquisition module of the deformation failure surface is used to acquire the front edge line of the deformation failure surface in the preset geological simulation software; the support plate adding module is used to add a layer of support plates with a preset thickness along the front edge line, and the normal line of the support plate is tangent to the deformation failure surface; the support plate condition failure simulation module is used to simulate the further deformation and failure of the slope under the condition of the support plate along the time process through the preset geological simulation software; the simulated displacement vector acquisition module is used to divide the time process into several simulated time lengths, and obtain the simulated displacement vector of the further deformation and failure once based on each simulated time length; the simulated deformation failure surface acquisition module is used to replace the future displacement vector with the simulated displacement vector as the execution main body, and repeatedly execute the failure possible monitoring point marking module 5 to the deformation failure surface acquisition module 9 to obtain a simulated deformation failure surface based on one simulated time length; the deformation failure surface radius judgment module is used to judge whether the radii of all simulated deformation failure surfaces decrease along the time process; the effective support plate determination module is used to determine that the support plate is an effective support plate if so; the effective support plate installation position sending module is used to send the installation position of the effective support plate to the external visual monitoring terminal.

[0193] Further, the deformation failure analysis device further includes a simulated deformation failure surface radius disappearance judgment module, a deformation failure risk non-elimination determination module, an additional support plate installation module, and a simulated deformation failure surface iteration module that are electrically connected in sequence; the simulated deformation failure surface radius disappearance judgment module is electrically connected to the effective support plate installation position sending module.

[0194] Among them, the simulated deformation failure surface radius disappearance judgment module is used to judge whether the radii of all simulated deformation failure surfaces decrease and disappear along the time process; the deformation failure risk non-elimination determination module is used to determine that the deformation failure risk of the slope is not eliminated if not; the additional support plate installation module is used to install an additional layer of support plates above the elevation of the effective support plate; the simulated deformation failure surface iteration module is used to repeatedly execute the support plate condition failure simulation module to the effective support plate installation position sending module until all simulated deformation failure surfaces disappear.

[0195] Further, the deformation failure analysis device further includes a complete support surface formation module and a complete support surface sending module that are electrically connected in sequence; the complete support surface formation module is electrically connected to the simulated deformation failure surface iteration module.

[0196] Among them, the complete support surface formation module is used to add stabilizing members between the plates of all effective support plates to form a complete support surface; the complete support surface sending module is used to send the complete support surface to the external visual monitoring terminal.

[0197] Further, the prediction vector dataset acquisition module 4 specifically includes a first prediction vector dataset acquisition sub-module, a second prediction vector dataset acquisition sub-module, a third prediction vector dataset acquisition sub-module, a fourth prediction vector dataset acquisition sub-module, a fifth prediction vector dataset acquisition sub-module, and a sixth prediction vector dataset acquisition sub-module that are electrically connected in sequence; the first prediction vector dataset acquisition sub-module is electrically connected to the vector dataset integration module 3, and the sixth prediction vector dataset acquisition sub-module is electrically connected to the damage possibility monitoring point marking module 5.

[0198] Among them, the first prediction vector dataset acquisition sub-module is used to perform vector normalization processing on all vector datasets to obtain a normalized dataset based on one vector dataset; the second prediction vector dataset acquisition sub-module is used to divide the current normalized dataset into a training set and a validation set according to a preset ratio; the third prediction vector dataset acquisition sub-module is used to define an extreme learning model according to the data dimension of the training set; the fourth prediction vector dataset acquisition sub-module is used to train and learn the extreme learning model through the training set to obtain a prediction model; the fifth prediction vector dataset acquisition sub-module is used to input the validation set into the prediction model to obtain a prediction dataset based on one normalized dataset; the sixth prediction vector dataset acquisition sub-module is used to restore each prediction dataset to a prediction vector dataset through inverse vector normalization operation.

[0199] Further, the fifth perpendicular intersection point update sub-module specifically includes a tenth perpendicular intersection point update unit, an eleventh perpendicular intersection point update unit, a twelfth perpendicular intersection point update unit, a thirteenth perpendicular intersection point update unit, a fourteenth perpendicular intersection point update unit, a fifteenth perpendicular intersection point update unit, a sixteenth perpendicular intersection point update unit, and a seventeenth perpendicular intersection point update unit that are electrically connected in sequence; the tenth perpendicular intersection point update unit is electrically connected to the ninth perpendicular intersection point update unit, and the seventeenth perpendicular intersection point update unit is electrically connected to the sixth perpendicular intersection point update sub-module.

[0200] Among them, the tenth perpendicular intersection point updating unit is used to define a number of random solutions for each moving point respectively; the eleventh perpendicular intersection point updating unit is used to define the optimization result of all random solutions as the minimum radius of the minimum covering circle of all intersection points; the twelfth perpendicular intersection point updating unit is used to initialize the positions of each random solution; the thirteenth perpendicular intersection point updating unit is used to update the current positions and current speeds of each random solution respectively; the fourteenth perpendicular intersection point updating unit is used to obtain the individual optimal solutions and global optimal solutions of each random solution respectively based on each update; the fifteenth perpendicular intersection point updating unit is used to judge whether the difference between each individual optimal solution and each individual optimal solution in the previous update is less than or equal to a first preset adaptation threshold respectively; the sixteenth perpendicular intersection point updating unit is used to judge whether the difference between each global optimal solution and each global optimal solution in the previous update is less than or equal to a second preset adaptation threshold respectively if they are all less; the seventeenth perpendicular intersection point updating unit is used to judge that the optimal solutions of all moving points have been obtained if they are all less.

[0201] Further, the deformation and failure analysis device further includes a deformation and failure surface output module electrically connected to the deformation and failure surface acquisition module 9, and this module is used to output the deformation and failure surface to an external visualization terminal.

[0202] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For the preferred, extended, limited, exemplified, and principle description parts of this embodiment, please refer to the above embodiment, and this embodiment will not be elaborated here.

[0203] In this embodiment, the observation data of all cross-section monitoring points based on several observation time intervals are obtained; the deformation displacement vectors of all the observation data are analyzed; all the deformation displacement vectors in one observation time interval are integrated into a vector data set; all the vector data sets are learned and trained by an extreme learning machine, and a predicted vector data set is obtained based on a future time interval; the future displacement vectors of each cross-section monitoring point are obtained respectively based on the current vector data set, and the cross-section monitoring points whose future displacement vectors exceed the preset displacement threshold are marked as the monitoring points with possible damage; the coordinate points of each monitoring point with possible damage are obtained respectively, and the projection vector lines of all the future displacement vectors are obtained based on the geological drawing of the slope; the perpendicular lines of each projection vector line and the intersection points of all the perpendicular lines are obtained respectively, and the perpendicular lines are slid on each projection vector line respectively to make the minimum covering circle of all the intersection points reach the minimum radius; the center of the minimum covering circle corresponding to the minimum radius is obtained, which is the center of the deformation failure surface; the distance between the center of the deformation failure surface and the leading edge of the cross-section is defined as the radius of the deformation failure surface, and the deformation failure surface is obtained. This embodiment uses the SBAS-InSAR technology to analyze the deformation characteristics of the slope, and at the same time predicts the analyzed deformation characteristics, realizing the foresight and prediction of the potential deformation characteristics of the slope. Finally, the future deformation failure surface of the slope is confirmed through the predicted future deformation characteristics, making the prevention and control of the slope have foresight. Certain prevention and control measures can be adopted when the slope has not actually undergone deformation and failure, ensuring the long-term stability of the slope. Since the analyzed deformation characteristics are in vector form, the method utilizes the good compatibility and adaptability of the extreme learning machine for vectors, making the learned data more accurate than that obtained by traditional machine learning machines.

[0204] Figure 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As Figure 3 shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0205] The memory 102 stores program instructions for implementing the fault detection method of an oil-immersed transformer according to any one of the above embodiments.

[0206] The processor 101 is configured to execute the program instructions stored in the memory 102 to perform fault detection on the oil-immersed transformer.

[0207] Among them, the processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with the ability to process signals. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0208] Furthermore, Figure 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application. Refer to Figure 4 , the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0209] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0210] In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. The above is only the implementation mode of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for analyzing deformation and failure of a slope, wherein the slope has a cross section and the cross section is provided with a plurality of cross section monitoring points, characterized in that: The deformation and failure analysis method comprises: Step S1, obtaining observation data of all cross-section monitoring points based on several observation time intervals; Step S2, analyzing the deformation displacement vectors of all observation data; Step S3, integrating all deformation displacement vectors in an observation time interval into a vector data set; Step S4, learning and training all vector data sets through an extreme learning machine, and obtaining a predicted vector data set based on a future time interval; Step S5, obtaining the future displacement vector of each cross-section monitoring point based on the current vector data set, and marking the cross-section monitoring point whose future displacement vector exceeds a preset displacement threshold as a possible damaged monitoring point; Step S6, respectively obtaining the coordinates of each possible damage monitoring point and obtaining the projection vector lines of all future displacement vectors based on the geological drawings of the slope; Step S7, respectively obtaining the perpendicular line of each projection vector line and the intersection point of all perpendicular lines, and sliding the perpendicular line on each projection vector line respectively so that the minimum covering circle of all intersection points reaches the minimum radius; Step S8, obtaining the center of the minimum covering circle corresponding to the minimum radius as the center of the deformation failure surface; Step S9, defining the distance between the center of the deformation failure surface and the front edge of the cross section as the radius of the deformation failure surface, to obtain the deformation failure surface.

2. The deformation and failure analysis method according to claim 1, characterized in that: Step S9, defining the distance between the center of the deformation failure surface and the front edge of the cross section as the radius of the deformation failure surface, and obtaining the deformation failure surface, and then comprising: Step S10, obtaining a finite element model of the slope, and importing the finite element model and all future displacement vectors into a preset geological simulation software to form a digital simulation model of the slope; Step S20, obtaining the front edge line of the deformation failure surface in the preset geological simulation software; Step S30, adding a layer of a support plate of a preset thickness along the front edge line, wherein the normal line of the support plate is tangent to the deformation failure surface; Step S40, simulating the further deformation and failure of the slope under the support plate condition along the time course by the preset geological simulation software; Step S50, dividing the time process into a plurality of simulation durations, and obtaining a simulation displacement vector of the further deformation and destruction based on each simulation duration; Step S60, replacing the future displacement vector with the simulated displacement vector as the execution subject, and repeatedly executing steps S5 to S9 to obtain a simulated deformation failure surface based on a simulation duration; Step S70, determining whether the radius of all simulated deformation failure surfaces decreases along the time course, if so, executing step S80; Step S80, determining that the support plate is a valid support plate; Step S90, sending the installation position of the effective support plate to an external visual monitoring terminal.

3. The deformation and failure analysis method according to claim 2, characterized in that: Step S90, sending the installation position of the effective support plate to an external visual monitoring terminal, and then comprising: Step S100, determining whether the radius of all simulated deformation failure surfaces decreases and disappears along the time course, if not, executing step S200; Step S200, determining that the deformation and damage risk of the slope has not been eliminated; Step S300, installing an additional support plate above the elevation of the effective support plate; Step S400, repeatedly executing steps S40 to S90 until all simulated deformation failure surfaces disappear.

4. The deformation and failure analysis method according to claim 3, characterized in that: Step S400, repeatedly executing steps S40 to S90 until all simulated deformation failure surfaces disappear, and then comprising: Step S1000, adding stabilizing members between all effective support plates to form a complete support surface; Step S2000, sending the complete support surface to an external visual monitoring terminal.

5. The deformation and failure analysis method according to claim 1, characterized in that: Step S4, learning and training all vector data sets through an extreme learning machine, and obtaining a predicted vector data set based on a future time interval, including: Step S41, performing vector normalization processing on all vector data sets, and obtaining a normalized data set based on a vector data set; Step S42, dividing the current normalized data set into a training set and a validation set according to a preset ratio; Step S43, defining an extreme learning model according to the data dimension of the training set; Step S44, training and learning the extreme learning model through the training set to obtain a prediction model; Step S45, inputting the verification set into the prediction model to obtain a prediction data set based on a normalized data set; Step S46, restore each prediction data set to a prediction vector data set through vector normalization inverse operation.

6. The deformation and failure analysis method according to claim 1, characterized in that: Step S9, defining the distance between the center of the deformation failure surface and the front edge of the cross section as the radius of the deformation failure surface, and obtaining the deformation failure surface, and then comprising: Step S10: outputting the deformation failure surface to an external visualization terminal.

7. A slope deformation and failure analysis device, the deformation and failure analysis device is applied to the deformation and failure analysis method according to any one of claims 1 to 6, characterized in that: The deformation and failure analysis device comprises: An observation data acquisition module is used to obtain observation data of all cross-section monitoring points based on several observation time intervals; A deformation displacement vector acquisition module is used to analyze the deformation displacement vectors of all observation data; A vector data set integration module is used to integrate all deformation displacement vectors of an observation time interval into a vector data set; A prediction vector data set acquisition module is used to learn and train all vector data sets through an extreme learning machine, and obtain a prediction vector data set based on a future time interval; A possible damage monitoring point marking module is used to obtain the future displacement vector of each cross-section monitoring point based on the current vector data set, and mark the cross-section monitoring point whose future displacement vector exceeds a preset displacement threshold as a possible damage monitoring point; A projection vector line acquisition module, used to respectively acquire the coordinate points of each possible damage monitoring point and acquire the projection vector lines of all future displacement vectors based on the geological drawings of the slope; A perpendicular line intersection point updating module is used to obtain the perpendicular line of each projection vector line and the intersection point of all perpendicular lines respectively, and slide the respective perpendicular line on each projection vector line respectively so that the minimum covering circle of all intersection points reaches the minimum radius; A deformation failure surface determination module, used to obtain the center of the minimum covering circle corresponding to the minimum radius as the center of the deformation failure surface; The deformation failure surface acquisition module defines the distance between the center of the deformation failure surface and the front edge of the cross section as the radius of the deformation failure surface to obtain the deformation failure surface.

8. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the deformation and failure analysis method as described in any one of claims 1 to 6 is implemented.

9. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the deformation and failure analysis method according to any one of claims 1 to 6 can be implemented.

Images