A method, device, equipment and storage medium for searching a slope sliding surface

Abstract

The present application discloses a search method, device, equipment and storage medium for a slope sliding surface, and relates to the technical field of electrical digital data processing. The method draws the projection vector line of each coordinate point on the monitoring section by mutating the coordinate point of the monitoring point; and obtains the perpendicular line of each projection vector line and all the intersection points between all the perpendicular lines; finally, defines a random point on the geological drawing, and iterates the position of the random point through a global optimization algorithm until the sum of the distances between the random point and all the intersection points reaches the minimum value, and the position of the random point is the center of the slope sliding surface; the distance between the center of the circle and the front edge of the monitoring section is defined as the radius, and the slope sliding surface is drawn by the center of the circle and the radius. The present application comprehensively considers all the perpendicular lines and the intersection points of all the perpendicular lines, so that when drawing the sliding surface, every sudden change point can be taken into account as much as possible, and compared with the strength reduction method and the limit equilibrium method, the sliding surface is more in line with reality.

Description

Technical Field

[0001] The present application relates to the technical field of electronic digital data processing, and in particular to a method, device, equipment and storage medium for searching a slope sliding surface. Background Art

[0002] Landslide prevention and control refers to the prevention and control measures taken when engineering construction is carried out in areas where landslides cannot be avoided or where the slopes are unstable. Landslide stability analysis is the basic work of landslide prevention and control and the prerequisite for subsequent prevention and control work. According to the characteristics of the slope rock and soil, take corresponding measures to prevent the slope from becoming unstable to ensure the safety of production and personnel. Landslide stability analysis is the basic work of landslide prevention and control and the prerequisite for subsequent prevention and control work. The significance of conducting stability research on landslides is that it not only provides a scientific theoretical basis for engineering construction, but also plays an important guiding role in the early warning and forecast of landslide development trends.

[0003] my country's hydropower projects are mainly concentrated in the southwest region, where the geological conditions are complex. Landslide geological disasters often occur on the slopes of the reservoir banks during the construction and water storage process, and the safety risk issues are prominent, which brings great safety hazards to the construction and operation and maintenance of hydropower projects. Traditional landslide geological disaster sliding surface searches mostly use limit equilibrium method or finite element method for analysis, but these methods are very sensitive to material parameters and solution methods, resulting in a certain error between the searched landslide sliding surface and the actual result. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device, equipment and storage medium for searching a slope sliding surface, so as to solve the problem that there is a certain error between the sliding surface of the landslide searched by the prior art and the actual result.

[0005] In order to achieve the above objectives, this application provides the following technical solutions:

[0006] A method for searching a slope sliding surface, the method being based on surface deformation monitoring points of the slope sliding surface, the method comprising:

[0007] Step S1, respectively obtaining monitoring data of each surface deformation monitoring point based on a number of natural moments, and respectively obtaining a displacement vector of each monitoring data by means of a borehole inclinometer method;

[0008] Step S2, marking the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and obtaining the coordinate point of each mutation monitoring point respectively;

[0009] Step S3, outputting each coordinate point to the geological drawing of the monitoring section respectively;

[0010] Step S4, drawing the projection vector line of each coordinate point on the monitoring section based on the geological drawing;

[0011] Step S5, respectively obtaining the perpendicular line of each projection vector line and obtaining all the intersection points between all the perpendicular lines;

[0012] Step S6, defining a random point on the geological drawing;

[0013] Step S7, iterating the position of the random point by a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum value;

[0014] Step S8, obtaining the position of the random point matching the minimum value as the center of the slope sliding surface;

[0015] Step S9: define the distance between the center of the circle and the front edge of the monitoring section as a radius, and draw the slope sliding surface through the center of the circle and the radius.

[0016] As a further improvement of the present application, in step S1, monitoring data of each surface deformation monitoring point based on several natural moments are obtained respectively, and the displacement vector of each monitoring data is obtained respectively by the borehole inclinometer method, and then, in step S2, the surface deformation monitoring point whose displacement vector exceeds the preset displacement threshold is marked as a mutation monitoring point, and the coordinate point of each mutation monitoring point is obtained respectively, before that, it also includes:

[0017] Step S10, marking the surface deformation monitoring point whose historical displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and obtaining the historical coordinate point of each mutation monitoring point respectively;

[0018] Step S20, learning and training all historical coordinate points of all historical moments through a machine learning algorithm to obtain a coordinate point prediction model;

[0019] Step S30, predicting possible mutation coordinate points of each mutation monitoring point based on a preset number of steps by using the coordinate point prediction model;

[0020] Step S40, obtaining the future displacement vectors of all possible sudden change coordinate points by the borehole inclinometer method;

[0021] Step S50, substituting the future displacement vector into step S2 to replace the displacement vector.

[0022] As a further improvement of the present application, step S20, learning and training all historical coordinate points of all historical moments through a machine learning algorithm to obtain a coordinate point prediction model, including:

[0023] Step S201, packing all historical coordinate points of the same mutation monitoring point into a coordinate data set;

[0024] Step S202, normalizing all coordinate data sets respectively to obtain a normalized data set based on one coordinate data set;

[0025] Step S203, dividing the current normalized data set into a training set and a validation set according to a preset ratio;

[0026] Step S204, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected;

[0027] Step S205, outputting the training set to the input layer, and performing several trainings through the neural network model;

[0028] Step S206, obtaining a root mean square error between the verification set and the current training result based on each training;

[0029] Step S207, obtaining the minimum value of the root mean square error among all training results, and obtaining the training result corresponding to the minimum value as the coordinate point prediction model.

[0030] As a further improvement of the present application, in step S202, all coordinate data sets are normalized respectively to obtain a normalized data set based on a coordinate data set, including:

[0031] Step S2021, perform standard normalization on each historical coordinate point in the current coordinate data set according to formula (1):

[0032] (1);

[0033] in, is the normalized horizontal coordinate obtained after the normalization of the current historical coordinate point. is the horizontal coordinate of the current historical coordinate point, is the average value of the horizontal coordinates of all historical coordinate points in the current coordinate data set. is the horizontal coordinate standard deviation of all historical coordinate points in the current coordinate data set, is the normalized ordinate obtained after normalization of the current historical coordinate point. is the ordinate of the current historical coordinate point, is the average ordinate of all historical coordinate points in the current coordinate data set. It is the standard deviation of the ordinate of all historical coordinate points in the current coordinate dataset.

[0034] As a further improvement of the present application, the neural network model is characterized by formula (2):

[0035] (2);

[0036] in, is the neural network model; is the first input nodes, each input node corresponds to a normalized data set in the training set, is the first The input nodes to the hidden layer The weights of the input nodes; is the first The bias of the input node; is the bias of the output layer; is the activation function; the number in the bracket of the symbol subscript is the number of layers, the subscript (1) is the first layer, that is, the input layer, and the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer.

[0037] As a further improvement of the present application, step S7, iterating the position of the random point by a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum, includes:

[0038] Step S71, defining a plurality of random solutions for the random point according to formula (3), and defining the optimization result of all random solutions as the sum of the distances between the random point and all intersection points reaching the minimum value;

[0039] (3);

[0040] in, is the set of all random solutions, For each random solution, is the label of the random solution, is the number of all random solutions; is the set of velocities of all random solutions, are the speeds of each random solution respectively;

[0041] Step S72, initialize the position of each random solution, and update the current position and current speed respectively based on the same random solution according to equation (4):

[0042] (4);

[0043] in, For the The random solution is The speed of the step, For the The random solution is The speed inertia of the step, is the inertia coefficient, For the The self-perception representation of a random solution, For the social cognitive representation of a random solution; and are learning factors, for A random number, For the The individual optimal solution obtained by random solutions is For the The global optimal solution obtained by random solutions is For the Step 1 A random solution, For the Step 1 A random solution;

[0044] Step S73, iterate each random solution according to formula (4) to update each and each ;

[0045] Step S74, determine each Compared with the previous iteration, whether the difference is less than or equal to the first preset adaptation threshold, if each If the difference between the values ​​in the previous iteration and the values ​​in the previous iteration are all less than or equal to the first preset adaptation threshold, step S75 is executed;

[0046] Step S75, determine each Compared with the difference of the previous iteration, whether it is less than or equal to the second preset adaptation threshold, if each If the difference between the values ​​in the previous iteration and the values ​​in the previous iteration are all less than or equal to the second preset adaptation threshold, step S76 is executed;

[0047] Step S76, determining whether the optimal solution of the random point has been obtained.

[0048] As a further improvement of the present application, in step S73, each random solution is iterated according to the formula (4) to update each and each ,include:

[0049] Step S731, based on each iteration, the inertia coefficient is linearly reduced once according to formula (5):

[0050] (5);

[0051] in, For the The random solution is The inertia coefficient after step optimization, is the initial inertia coefficient, is the current iteration number, is the maximum number of iteration steps.

[0052] In order to achieve the above objectives, this application also provides the following technical solutions:

[0053] A device for searching a slope sliding surface, the device being applied to the above-mentioned search method, the device comprising:

[0054] The monitoring data and displacement vector acquisition module is used to respectively acquire the monitoring data of each surface deformation monitoring point based on a number of natural moments, and respectively acquire the displacement vector of each monitoring data by means of a borehole inclinometer method;

[0055] A mutation monitoring point coordinate point acquisition module is used to mark the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and to respectively acquire the coordinate point of each mutation monitoring point;

[0056] A coordinate point output module, used for outputting each coordinate point to the geological drawing of the monitoring section;

[0057] A projection vector line drawing module, used for drawing the projection vector line of each coordinate point on the monitoring section based on the geological drawing;

[0058] A projection vector line perpendicular line intersection point acquisition module is used to respectively acquire the perpendicular line of each projection vector line and acquire all the intersection points between all the perpendicular lines;

[0059] A random point definition module, used to define a random point on the geological drawing;

[0060] A random point optimization module, used for iterating the position of the random point through a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum value;

[0061] A slope sliding surface circle center acquisition module is used to acquire the position of a random point matching the minimum value as the circle center of the slope sliding surface;

[0062] The slope sliding surface drawing module is used to define the distance between the center of the circle and the front edge of the monitoring section as a radius, and draw the slope sliding surface through the center of the circle and the radius.

[0063] In order to achieve the above objectives, this application also provides the following technical solutions:

[0064] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the above-mentioned method for searching for a slope sliding surface is implemented.

[0065] In order to achieve the above objectives, this application also provides the following technical solutions:

[0066] A storage medium stores program instructions, which, when executed by a processor, can implement the above-mentioned method for searching a slope sliding surface.

[0067] The present application obtains the monitoring data of each surface deformation monitoring point based on several natural moments, and obtains the displacement vector of each monitoring data by the borehole inclinometer method; marks the surface deformation monitoring point whose displacement vector exceeds the preset displacement threshold as a mutation monitoring point, and obtains the coordinate point of each mutation monitoring point; outputs each coordinate point to the geological drawing of the monitoring section; draws the projection vector line of each coordinate point on the monitoring section based on the geological drawing; obtains the perpendicular line of each projection vector line and obtains all the intersection points between all the perpendicular lines; defines a random point on the geological drawing; iterates the position of the random point by the global optimization algorithm until the sum of the distances between the random point and all the intersection points reaches the minimum; obtains the position of the random point that matches the minimum value as the center of the slope sliding surface; defines the distance between the center of the circle and the front edge of the monitoring section as the radius, and draws the slope sliding surface by the center of the circle and the radius. The present application comprehensively considers all the perpendicular lines and the intersection points of all the perpendicular lines, so that when drawing the sliding surface, every mutation point can be taken into account as much as possible. Compared with the traditional strength reduction method and limit equilibrium method, the sliding surface searched by the present application is closer to or consistent with reality. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A schematic diagram of the process steps of an embodiment of the method for searching the sliding surface of a slope of the present application;

[0069] Figure 2 A schematic diagram of the functional modules of an embodiment of a device for searching a slope sliding surface of the present application;

[0070] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0071] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0073] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. 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 also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0074] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0075] like Figure 1 As shown, this embodiment provides an embodiment of a method for searching a slope sliding surface. In this embodiment, the search method is based on surface deformation monitoring points of the slope sliding surface.

[0076] Preferably, the surface deformation monitoring point refers to a measurement point directly buried on the deformable 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 a narrow sense. In a 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 divided into the following categories:

[0077] ‌Benchmark point‌: Usually buried on stable bedrock or outside the deformation area, preserved for a long time and stable.

[0078] Working point: It is buried near the object being studied and is required to remain stable during the observation period. Its position is regularly checked by the reference point.

[0079] Observation point: directly buried on the deformed body, can reflect the deformation characteristics of the building, generally buried inside the building.

[0080] 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 landslides, and the surface movement and subsidence caused by underground mining. Specific application scenarios include:

[0081] ‌Dam‌: Monitors the vertical and horizontal displacement of the dam.

[0082] ‌Subway tunnel structure‌: monitor the deformation of the tunnel structure.

[0083] ‌Slope Hazard Structure‌: monitors the stability of slopes.

[0084] ‌Bridges‌: Monitor the deformation of bridges.

[0085] ‌High-rise buildings‌: Monitor the tilt and settlement of buildings.

[0086] Specifically, the search method includes the following steps:

[0087] Step S1, respectively obtaining monitoring data of each surface deformation monitoring point based on a number of natural moments, and respectively obtaining the displacement vector of each monitoring data by means of a borehole inclinometer method.

[0088] Preferably, the borehole inclinometer method can measure the vertical and horizontal displacements of the soil body, and then convert the vertical and horizontal displacement lengths into vectors.

[0089] Step S2: Mark the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and obtain the coordinate point of each mutation monitoring point respectively.

[0090] Preferably, the preset displacement threshold may be set to 10 mm, that is, the length of the historical displacement vector does not exceed 10 mm.

[0091] Step S3, output each coordinate point to the geological drawing of the monitoring section respectively.

[0092] Preferably, the address drawing is a slope profile drawing generated during preliminary exploration.

[0093] Step S4, drawing the projection vector line of each coordinate point on the monitoring section based on the geological drawing.

[0094] Step S5, respectively obtain the perpendicular line of each projection vector line and obtain all the intersection points between all the perpendicular lines.

[0095] Step S6, defining a random point on the geological drawing.

[0096] It is worth noting that step S6 is generally carried out using a software program rather than a real paper drawing.

[0097] Step S7, iterating the position of the random point through a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum value.

[0098] Step S8, obtaining the position of the random point that matches the minimum value as the center of the slope sliding surface.

[0099] Step S9, defining the distance between the center of the circle and the front edge of the monitoring section as the radius, and drawing the slope sliding surface through the center of the circle and the radius.

[0100] Preferably, the design of this embodiment is intended to avoid outliers between vertical lines, as outliers are likely to cause large errors when searching for the minimum enclosing circle.

[0101] Further, in step S1, monitoring data of each surface deformation monitoring point based on several natural moments are obtained respectively, and the displacement vector of each monitoring data is obtained respectively by the borehole inclinometer method, and then, in step S2, the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold is marked as a mutation monitoring point, and the coordinate point of each mutation monitoring point is obtained respectively, before that, it also includes:

[0102] Step S10, marking the surface deformation monitoring point whose historical displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and obtaining the historical coordinate point of each mutation monitoring point respectively;

[0103] Step S20, learning and training all historical coordinate points of all historical moments through a machine learning algorithm to obtain a coordinate point prediction model;

[0104] Step S30, predicting possible mutation coordinate points of each mutation monitoring point based on a preset number of steps by using the coordinate point prediction model;

[0105] Step S40, obtaining the future displacement vectors of all possible sudden change coordinate points by the borehole inclinometer method;

[0106] Step S50, substituting the future displacement vector into step S2 to replace the displacement vector.

[0107] Preferably, the borehole inclinometer method is a technique for determining the spatial position and trajectory of a borehole by measuring the inclination angle and azimuth of the borehole. Its principle is based on the effects of the earth's gravity field and magnetic field, and the specific steps are as follows:

[0108] ‌Measure the inclination angle‌: Install an inclinometer tube in the borehole. The inclinometer tube has four slots that match the pulley of the inclinometer probe. The probe is connected to the data acquisition instrument through a cable. By measuring the vertical inclination of the inclinometer tube, the inclination and hole quality caused by stratum movement are detected. The inclinometer probe has two sets of small pulleys, which are 0.5 meters apart. The angle of each section is measured in units of 0.5 meters. The offset of each section can be calculated by the inclination angle of each section. The relative offset of all measurement sections can be integrated to obtain the displacement of any point in the borehole relative to the reference point (bottom or top of the hole).

[0109] ‌Measure azimuth‌: Using the earth's magnetic field as a reference, the spatial position and attitude of the borehole are determined by measuring the changes in the magnetic field strength inside the borehole.

[0110] From the above principle, it can be known that the borehole inclinometer method can calculate the offset of each section through the inclination angle of each section. By integrating the relative offsets of all measuring sections, the displacement vector of any point in the borehole relative to the reference point (bottom or top of the hole) can be obtained. That is, the displacement vector of any point relative to the reference point (bottom or top of the hole) is differentiated to obtain the relative offset of all measuring sections.

[0111] It is worth noting that the borehole inclinometer method is a mature existing technology. The borehole inclinometer method in this embodiment is a conventional application. For the detailed measurement and calculation steps of the borehole inclinometer method, please refer to the existing technology, which will not be repeated in this embodiment.

[0112] Preferably, the natural moment, historical natural moment, and preset number of steps can all be set to be one step per second, one step per minute, or other different durations and the same number of steps.

[0113] Furthermore, in step S20, all historical coordinate points of all historical moments are learned and trained by a machine learning algorithm to obtain a coordinate point prediction model, including:

[0114] Step S201: Pack all historical coordinate points of the same mutation monitoring point into a coordinate data set.

[0115] Step S202 , normalizing all coordinate data sets respectively to obtain a normalized data set based on one coordinate data set.

[0116] Preferably, this embodiment prefers the normalization method of zero-mean normalization (Z-score normalization), which gives the mean and standard deviation of the original data to standardize the data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. For the normalization method, this embodiment can also use batch normalization. Compared with simple normalization, in the previous neural network training, only the input layer data is normalized, but not normalized in the middle layer. Although the data set of the input node is normalized, the data distribution of the input data after matrix multiplication is likely to change greatly, and as the number of hidden layer network layers continues to deepen, the change in data distribution will become greater and greater. Therefore, the normalization processing performed by batch normalization in the middle layer of the neural network makes the training effect better.

[0117] Step S203, dividing the current normalized data set into a training set and a validation set according to a preset ratio.

[0118] Preferably, the preset ratio is usually 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.

[0119] Step S204, defining a neural network model in which an input layer, a hidden layer, and an output layer are sequentially signal-connected.

[0120] Step S205, output the training set to the input layer and perform several trainings through the neural network model.

[0121] Step S206, obtaining a root mean square error between the validation set and the current training result based on each training.

[0122] Step S207, obtaining the minimum value of the root mean square error among all training results, and obtaining the training result corresponding to the minimum value as the coordinate point prediction model.

[0123] Furthermore, in step S202, all coordinate data sets are normalized respectively to obtain a normalized data set based on one coordinate data set, including:

[0124] Step S2021, perform standard normalization on each historical coordinate point in the current coordinate data set according to formula (1):

[0125] (1).

[0126] in, is the normalized horizontal coordinate obtained after the normalization of the current historical coordinate point. is the horizontal coordinate of the current historical coordinate point, is the average value of the horizontal coordinates of all historical coordinate points in the current coordinate data set. is the horizontal coordinate standard deviation of all historical coordinate points in the current coordinate data set, is the normalized ordinate obtained after normalization of the current historical coordinate point. is the ordinate of the current historical coordinate point, is the average ordinate of all historical coordinate points in the current coordinate data set. It is the standard deviation of the ordinate of all historical coordinate points in the current coordinate dataset.

[0127] Furthermore, the neural network model is represented by formula (2):

[0128] (2).

[0129] in, is a neural network model; The input layer input nodes, each of which corresponds to a normalized data set in the training set. The input layer The first input node to the hidden layer The weights of the input nodes; is connected to the hidden layer The bias of the input node; is the bias of the output layer; is the activation function; the number in the brackets of the symbol subscript is the number of layers, the subscript (1) is the first layer, that is, the input layer, and the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer.

[0130] Preferably, the training model training a neural network usually requires providing a large amount of data, namely a data set; the data set is generally divided into three categories, namely the above-mentioned training set (training set), validation set (validation set) and test set (test set).

[0131] Among them, one epoch is the process of training once with all the samples in the training set. The so-called training once refers to one forward pass and one back pass. When the number of samples in an epoch (i.e., training set) is too large, training once may consume too much time, and it is not necessary to use all the data in the training set for each training. In this case, the entire training set needs to be divided into multiple small blocks, that is, divided into multiple batches for training. An epoch consists of one or more batches, where a batch is a part of the training set. Each training process only uses a part of the data, i.e., a batch. The process of training a batch is an iteration.

[0132] Preferably, the neural network training specifically includes a perceptron, which is composed of two layers of neurons. The input layer receives external input signals and transmits them to the output layer. The output layer is MP neurons, and the step function is .

[0133] Preferably, given a training data set, the weights And training bias It can be obtained through learning, It can be understood as a fixed value with input of -1,0.

[0134] It should be noted that the above formula is not interchangeable with the symbolic meaning of other formulas in the embodiment, and this step function is only used for principle explanation and does not participate in the calculation of other formulas.

[0135] Preferably, in this embodiment, the number of neural network training times can be set to 1000 times.

[0136] Preferably, the learning rate from the 1st to the 500th epoch can be set to 0.01, the learning rate from the 501st to the 750th epoch can be set to 0.001, and the learning rate from the 751st to the 1000th epoch can be set to 0.0001.

[0137] It can be understood that the neural network training of this embodiment mainly includes the following ideas:

[0138] ① Initialize the weights and bias items in the network.

[0139] Initializing parameter values ​​(output unit weights, bias terms and hidden unit weights, bias terms are all model parameters) is to activate forward propagation, obtain the output value of each layer element, and then obtain the value of the loss function.

[0140] ②Activate forward propagation to obtain the output value of each layer and the expected value of the loss function of each layer.

[0141] ③According to the loss function, calculate the error term of the output unit and the error term of the hidden unit.

[0142] Calculate various errors, calculate the gradient of the parameters with respect to the loss function, or calculate partial derivatives according to the chain rule of calculus. For partial derivatives of vectors or matrices in a composite function, the partial derivative of the function inside the composite function is always multiplied on the left; for partial derivatives of scalars in a composite function, the partial derivative of the function inside the composite function can be multiplied on the left or on the right.

[0143] ④Update the weights and bias items in the neural network.

[0144] ⑤ Repeat ②~④ until the loss function is less than the preset bias or the number of iterations is used up, and the parameters output at this time are the current optimal parameters.

[0145] Further, step S7, iterating the position of the random point by a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum, includes:

[0146] Step S71, define several random solutions for the random point according to formula (3), and define the optimization result of all random solutions as the sum of the distances between the random point and all intersection points reaching the minimum value.

[0147] (3).

[0148] in, is the set of all random solutions, For each random solution, is the label of the random solution, is the number of all random solutions; is the set of velocities of all random solutions, are the speeds of each random solution respectively.

[0149] Step S72, initialize the position of each random solution, and update the current position and current speed respectively based on the same random solution according to equation (4):

[0150] (4).

[0151] in, For the The random solution is The speed of the step, For the The random solution is The speed inertia of the step, is the inertia coefficient, For the The self-perception representation of a random solution, For the social cognitive representation of a random solution; and are learning factors, for A random number, For the The individual optimal solution obtained by random solutions is For the The global optimal solution obtained by random solutions is For the Step 1 A random solution, For the Step 1 A random solution.

[0152] Preferably, The value range is , preferably ; The value range is , preferably .

[0153] Step S73, iterate each random solution according to formula (4) to update each and each .

[0154] Step S74, determine each Compared with the previous iteration, whether the difference is less than or equal to the first preset adaptation threshold, if each If the difference compared with the previous iteration is less than or equal to the first preset adaptation threshold, step S75 is executed.

[0155] Step S75, determine each Compared with the difference of the previous iteration, whether it is less than or equal to the second preset adaptation threshold, if each If the difference compared with the previous iteration is less than or equal to the second preset adaptation threshold, step S76 is executed.

[0156] Step S76, determining whether the optimal solution of the random point has been obtained.

[0157] Preferably, the values ​​of the first preset adaptation threshold and the second preset adaptation threshold need to be adjusted according to the specific problem, and generally need to be adjusted according to the calculation results. If the adaptation threshold is set too small, the algorithm may stop prematurely and fail to obtain the optimal solution; if the adaptation threshold is set too large, the algorithm may be over-iterated, wasting computing resources.

[0158] Preferably, the adaptation threshold may also be evaluated by one of the Griewank function, the Rastrigin function, the Schaffer function, the Ackley function, and the Rosenbrock function.

[0159] Further, in step S73, each random solution is iterated according to equation (4) to update each and each ,include:

[0160] Step S731, based on each iteration, the inertia coefficient is linearly reduced once according to formula (5):

[0161] (5).

[0162] in, For the The random solution is The inertia coefficient after step optimization, is the initial inertia coefficient, is the current iteration number, is the maximum number of iteration steps.

[0163] Preferably, the initial inertia coefficient is generally set to 0.5, and the maximum number of iteration steps is generally set according to actual needs, and in this embodiment can be set to 1000 times.

[0164] This embodiment obtains the monitoring data of each surface deformation monitoring point based on several natural moments, and obtains the displacement vector of each monitoring data by the borehole inclinometer method; marks the surface deformation monitoring point whose displacement vector exceeds the preset displacement threshold as a mutation monitoring point, and obtains the coordinate point of each mutation monitoring point; outputs each coordinate point to the geological drawing of the monitoring section; draws the projection vector line of each coordinate point on the monitoring section based on the geological drawing; obtains the vertical line of each projection vector line and obtains all the intersection points between all the vertical lines; defines a random point on the geological drawing; iterates the position of the random point by the global optimization algorithm until the sum of the distances between the random point and all the intersection points reaches the minimum; obtains the position of the random point that matches the minimum value as the center of the slope sliding surface; defines the distance between the center of the circle and the front edge of the monitoring section as the radius, and draws the slope sliding surface by the center of the circle and the radius. This embodiment comprehensively considers all the vertical lines and the intersection points of all the vertical lines, so that when drawing the sliding surface, each mutation point can be taken into account as much as possible. Compared with the traditional strength reduction method and limit equilibrium method, the sliding surface searched by this embodiment is closer to or consistent with reality.

[0165] like Figure 2As shown, this embodiment provides an embodiment of a search device for a slope sliding surface. In this embodiment, the search device is applied to the search method as in the above embodiment.

[0166] Specifically, the search device includes a monitoring data and displacement vector acquisition module 1, a mutation monitoring point coordinate point acquisition module 2, a coordinate point output module 3, a projection vector line drawing module 4, a projection vector line perpendicular intersection acquisition module 5, a random point definition module 6, a random point optimization module 7, a slope sliding surface center acquisition module 8, and a slope sliding surface drawing module 9, which are electrically connected in sequence.

[0167] Among them, the monitoring data and displacement vector acquisition module 1 is used to respectively obtain the monitoring data of each surface deformation monitoring point based on several natural moments, and obtain the displacement vector of each monitoring data by the borehole inclinometer method; the mutation monitoring point coordinate point acquisition module 2 is used to mark the surface deformation monitoring point whose displacement vector exceeds the preset displacement threshold as a mutation monitoring point, and obtain the coordinate point of each mutation monitoring point respectively; the coordinate point output module 3 is used to output each coordinate point to the geological drawing of the monitoring section respectively; the projection vector line drawing module 4 is used to draw the projection vector line of each coordinate point on the monitoring section based on the geological drawing; the projection The vector line perpendicular intersection acquisition module 5 is used to obtain the perpendicular of each projection vector line respectively and obtain all the intersection points between all the perpendicular lines; the random point definition module 6 is used to define a random point on the geological drawing; the random point optimization module 7 is used to iterate the position of the random point through the global optimization algorithm until the sum of the distances between the random point and all the intersection points reaches the minimum value; the slope sliding surface center acquisition module 8 is used to obtain the position of the random point that matches the minimum value, which is the center of the slope sliding surface; the slope sliding surface drawing module 9 is used to define the distance between the center of the circle and the front edge of the monitoring section as the radius, and draw the slope sliding surface through the center of the circle and the radius.

[0168] Furthermore, the search device also includes a mutation monitoring point historical coordinate point acquisition module, a coordinate point prediction model acquisition module, a mutation possible coordinate point prediction module, a future displacement vector acquisition module, and a future displacement vector substitution module, which are electrically connected in sequence; the mutation monitoring point historical coordinate point acquisition module is electrically connected to the monitoring data and displacement vector acquisition module 1, and the future displacement vector substitution module is electrically connected to the mutation monitoring point coordinate point acquisition module 2.

[0169] Among them, the mutation monitoring point historical coordinate point acquisition module is used to mark the surface deformation monitoring point whose historical displacement vector exceeds the preset displacement threshold as a mutation monitoring point, and obtain the historical coordinate points of each mutation monitoring point respectively; the coordinate point prediction model acquisition module is used to learn and train all historical coordinate points of all historical moments through a machine learning algorithm to obtain a coordinate point prediction model; the mutation possible coordinate point prediction module is used to predict the mutation possible coordinate points of each mutation monitoring point based on a preset number of steps through the coordinate point prediction model; the future displacement vector acquisition module is used to obtain the future displacement vectors of all possible mutation coordinate points through the borehole inclinometer method; the future displacement vector substitution module is used to substitute the future displacement vector into the mutation monitoring point coordinate point acquisition module 2 to replace the displacement vector.

[0170] Furthermore, the coordinate point prediction model acquisition module specifically includes a first coordinate point prediction model acquisition unit, a second coordinate point prediction model acquisition unit, a third coordinate point prediction model acquisition unit, a fourth coordinate point prediction model acquisition unit, a fifth coordinate point prediction model acquisition unit, a sixth coordinate point prediction model acquisition unit, and a seventh coordinate point prediction model acquisition unit, which are electrically connected in sequence; the first coordinate point prediction model acquisition unit is electrically connected to the mutation monitoring point historical coordinate point acquisition module, and the seventh coordinate point prediction model acquisition unit is electrically connected to the mutation possible coordinate point prediction module.

[0171] Among them, the first coordinate point prediction model acquisition unit is used to package all historical coordinate points of the same mutation monitoring point into a coordinate data set; the second coordinate point prediction model acquisition unit is used to normalize all coordinate data sets respectively, and obtain a normalized data set based on a coordinate data set; the third coordinate point prediction model acquisition unit is used to divide the current normalized data set into a training set and a verification set according to a preset ratio; the fourth coordinate point prediction model acquisition unit is used to define a neural network model in which the input layer, hidden layer, and output layer are signal-connected in sequence; the fifth coordinate point prediction model acquisition unit is used to output the training set to the input layer, and perform several trainings through the neural network model; the sixth coordinate point prediction model acquisition unit is used to obtain the root mean square error between the verification set and the current training result based on each training; the seventh coordinate point prediction model acquisition unit is used to obtain the minimum value of the root mean square error among all training results, and obtain the training result corresponding to the minimum value as the coordinate point prediction model.

[0172] Furthermore, the second coordinate point prediction model acquisition unit is specifically used to perform standard normalization on each historical coordinate point in the current coordinate data set according to formula (1):

[0173] (1).

[0174] in, is the normalized horizontal coordinate obtained after the normalization of the current historical coordinate point. is the horizontal coordinate of the current historical coordinate point, is the average value of the horizontal coordinates of all historical coordinate points in the current coordinate data set. is the horizontal coordinate standard deviation of all historical coordinate points in the current coordinate data set, is the normalized ordinate obtained after normalization of the current historical coordinate point. is the ordinate of the current historical coordinate point, is the average ordinate of all historical coordinate points in the current coordinate data set. It is the standard deviation of the ordinate of all historical coordinate points in the current coordinate dataset.

[0175] Furthermore, the fourth coordinate point prediction model acquisition unit is equipped with a neural network model represented by formula (2):

[0176] (2).

[0177] in, is a neural network model; The input layer input nodes, each of which corresponds to a normalized data set in the training set. The input layer The first input node to the hidden layer The weights of the input nodes; is connected to the hidden layer The bias of the input node; is the bias of the output layer; is the activation function; the number in the brackets of the symbol subscript is the number of layers, the subscript (1) is the first layer, that is, the input layer, and the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer.

[0178] Furthermore, the random point optimization module 7 specifically includes a first random point optimization submodule, a second random point optimization submodule, a third random point optimization submodule, a fourth random point optimization submodule, a fifth random point optimization submodule, and a sixth random point optimization submodule, which are electrically connected in sequence; the first random point optimization submodule is electrically connected to the random point definition module 6, and the sixth random point optimization submodule is electrically connected to the slope sliding surface center acquisition module 8.

[0179] The first random point optimization submodule is used to define several random solutions for the random point according to formula (3), and define the optimization result of all random solutions as the sum of the distances between the random point and all intersection points reaching the minimum value.

[0180] (3).

[0181] in, is the set of all random solutions, For each random solution, is the label of the random solution, is the number of all random solutions; is the set of velocities of all random solutions, are the speeds of each random solution respectively.

[0182] The second random point optimization submodule is used to initialize the position of each random solution and update the current position and current speed based on the same random solution according to formula (4):

[0183] (4).

[0184] in, For the The random solution is The speed of the step, For the The random solution is The speed inertia of the step, is the inertia coefficient, For the The self-perception representation of a random solution, For the social cognitive representation of a random solution; and are learning factors, for A random number, For the The individual optimal solution obtained by random solutions is For the The global optimal solution obtained by random solutions is For the Step 1 A random solution, For the Step 1 A random solution.

[0185] The third random point optimization submodule is used to iterate each random solution according to formula (4) to update each and each .

[0186] The fourth random point optimization submodule is used to determine each Whether the difference compared with the previous iteration is less than or equal to the first preset adaptation threshold.

[0187] The fifth random point optimization submodule is used if each Compared with the difference of the previous iteration, if the difference is less than or equal to the first preset adaptation threshold, then each Whether the difference compared with the previous iteration is less than or equal to the second preset adaptation threshold.

[0188] The sixth random point optimization submodule is used if each If the difference compared to the previous iteration is less than or equal to the second preset adaptation threshold, it is determined that the optimal solution of the random point has been obtained.

[0189] Furthermore, the third random point optimization submodule is specifically used to linearly decrease the inertia coefficient once according to formula (5) based on each iteration step:

[0190] (5).

[0191] in, For the The random solution is The inertia coefficient after step optimization, is the initial inertia coefficient, is the current iteration number, is the maximum number of iteration steps.

[0192] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The optimization, expansion, limitation, example, and principle description of this embodiment can be referred to the above embodiment, and this embodiment will not be repeated.

[0193] This embodiment obtains the monitoring data of each surface deformation monitoring point based on several natural moments, and obtains the displacement vector of each monitoring data by the borehole inclinometer method; marks the surface deformation monitoring point whose displacement vector exceeds the preset displacement threshold as a mutation monitoring point, and obtains the coordinate point of each mutation monitoring point; outputs each coordinate point to the geological drawing of the monitoring section; draws the projection vector line of each coordinate point on the monitoring section based on the geological drawing; obtains the vertical line of each projection vector line and obtains all the intersection points between all the vertical lines; defines a random point on the geological drawing; iterates the position of the random point by the global optimization algorithm until the sum of the distances between the random point and all the intersection points reaches the minimum; obtains the position of the random point that matches the minimum value as the center of the slope sliding surface; defines the distance between the center of the circle and the front edge of the monitoring section as the radius, and draws the slope sliding surface by the center of the circle and the radius. This embodiment comprehensively considers all the vertical lines and the intersection points of all the vertical lines, so that when drawing the sliding surface, each mutation point can be taken into account as much as possible. Compared with the traditional strength reduction method and limit equilibrium method, the sliding surface searched by this embodiment is closer to or consistent with reality.

[0194] Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 As shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0195] The memory 102 stores program instructions for implementing the method for searching the slope sliding surface of any of the above embodiments.

[0196] The processor 101 is used to execute the program instructions stored in the memory 102 to search for the sliding surface of the slope.

[0197] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having a signal processing capability. The processor 101 may 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 may be a microprocessor or the processor may also be any conventional processor, etc.

[0198] Further, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of the present application. Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, tablets, etc.

[0199] In the 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 only schematic. For example, the division of units is only a logical function division. There may 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 mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0200] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the content of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0201] The specific implementation methods of the present application are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the present application is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A method for searching a slope sliding surface, the method being based on surface deformation monitoring points of the slope sliding surface, characterized in that: The search method comprises: Step S1, respectively obtaining monitoring data of each surface deformation monitoring point based on a number of natural moments, and respectively obtaining a displacement vector of each monitoring data by means of a borehole inclinometer method; Step S2, marking the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and obtaining the coordinate point of each mutation monitoring point respectively; Step S3, outputting each coordinate point to the geological drawing of the monitoring section; Step S4, drawing the projection vector line of each coordinate point on the monitoring section based on the geological drawing; Step S5, respectively obtaining the perpendicular line of each projection vector line and obtaining all the intersection points between all the perpendicular lines; Step S6, defining a random point on the geological drawing; Step S7, iterating the position of the random point by a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum value; Step S8, obtaining the position of the random point matching the minimum value as the center of the slope sliding surface; Step S9: define the distance between the center of the circle and the front edge of the monitoring section as a radius, and draw the slope sliding surface through the center of the circle and the radius.

2. The search method according to claim 1, characterized in that: Step S1, respectively obtain monitoring data of each surface deformation monitoring point based on several natural moments, and respectively obtain the displacement vector of each monitoring data by means of the borehole inclinometer method, then, step S2, mark the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and respectively obtain the coordinate point of each mutation monitoring point, before that, it also includes: Step S10, marking the surface deformation monitoring point whose historical displacement vector exceeds the preset displacement threshold as a mutation monitoring point, and obtaining the historical coordinate point of each mutation monitoring point respectively; Step S20, learning and training all historical coordinate points of all historical moments through a machine learning algorithm to obtain a coordinate point prediction model; Step S30, predicting possible mutation coordinate points of each mutation monitoring point based on a preset number of steps by using the coordinate point prediction model; Step S40, obtaining the future displacement vectors of all possible sudden change coordinate points by the borehole inclinometer method; Step S50, substituting the future displacement vector into step S2 to replace the displacement vector.

3. The search method according to claim 2, characterized in that: Step S20, learning and training all historical coordinate points of all historical moments through a machine learning algorithm to obtain a coordinate point prediction model, including: Step S201, packing all historical coordinate points of the same mutation monitoring point into a coordinate data set; Step S202, normalizing all coordinate data sets respectively to obtain a normalized data set based on one coordinate data set; Step S203, dividing the current normalized data set into a training set and a validation set according to a preset ratio; Step S204, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected; Step S205, outputting the training set to the input layer, and performing several trainings through the neural network model; Step S206, obtaining a root mean square error between the verification set and the current training result based on each training; Step S207, obtaining the minimum value of the root mean square error among all training results, and obtaining the training result corresponding to the minimum value as the coordinate point prediction model.

4. The search method according to claim 3, characterized in that: Step S202, normalizing all coordinate data sets respectively to obtain a normalized data set based on one coordinate data set, including: Step S2021, perform standard normalization on each historical coordinate point in the current coordinate data set according to formula (1): （1）； in, is the normalized horizontal coordinate obtained after the normalization of the current historical coordinate point. is the horizontal coordinate of the current historical coordinate point, is the average value of the horizontal coordinates of all historical coordinate points in the current coordinate data set. is the horizontal coordinate standard deviation of all historical coordinate points in the current coordinate data set, is the normalized ordinate obtained after normalization of the current historical coordinate point. is the ordinate of the current historical coordinate point, is the average ordinate of all historical coordinate points in the current coordinate data set. It is the standard deviation of the ordinate of all historical coordinate points in the current coordinate dataset.

5. The search method according to claim 3, characterized in that: The neural network model is represented by formula (2): （2）； in, is the neural network model; is the first input nodes, each input node corresponds to a normalized data set in the training set, is the first The first input node to the hidden layer The weights of the input nodes; is the first The bias of the input node; is the bias of the output layer; is the activation function; the number in the bracket of the symbol subscript is the number of layers, the subscript (1) is the first layer, that is, the input layer, and the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer.

6. The search method according to claim 1, characterized in that: Step S7, iterating the position of the random point by a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum, including: Step S71, defining a plurality of random solutions for the random point according to formula (3), and defining the optimization result of all random solutions as the sum of the distances between the random point and all intersection points reaching the minimum value; （3）； in, is the set of all random solutions, For each random solution, is the label of the random solution, is the number of all random solutions; is the set of velocities of all random solutions, are the speeds of each random solution respectively; Step S72, initialize the position of each random solution, and update the current position and current speed respectively based on the same random solution according to equation (4): （4）； in, For the The random solution is The speed of the step, For the The random solution is The speed inertia of the step, is the inertia coefficient, For the The self-perception representation of a random solution, For the social cognitive representation of a random solution; and are learning factors, for A random number, For the The individual optimal solution has been obtained by random solutions. For the The global optimal solution obtained by random solutions is For the Step 1 A random solution, For the Step 1 A random solution; Step S73, iterate each random solution according to formula (4) to update each and each ; Step S74, determine each Compared with the previous iteration, whether the difference is less than or equal to the first preset adaptation threshold, if each If the difference between the values ​​in the previous iteration and the values ​​in the previous iteration are all less than or equal to the first preset adaptation threshold, step S75 is executed; Step S75, determine each Compared with the previous iteration, whether the difference is less than or equal to the second preset adaptation threshold, if each If the difference between the values ​​in the previous iteration and the values ​​in the previous iteration are all less than or equal to the second preset adaptation threshold, step S76 is executed; Step S76, determining whether the optimal solution of the random point has been obtained.

7. The search method according to claim 6, characterized in that: Step S73, iterate each random solution according to formula (4) to update each and each ,include: Step S731, based on each iteration, the inertia coefficient is linearly reduced once according to formula (5): （5）； in, For the The random solution is The inertia coefficient after step optimization, is the initial inertia coefficient, is the current iteration number, is the maximum number of iteration steps.

8. A device for searching a slope sliding surface, the device being applied to the search method according to any one of claims 1 to 7, characterized in that: The search device comprises: The monitoring data and displacement vector acquisition module is used to respectively acquire the monitoring data of each surface deformation monitoring point based on a number of natural moments, and respectively acquire the displacement vector of each monitoring data by means of a borehole inclinometer method; A mutation monitoring point coordinate point acquisition module is used to mark the surface deformation monitoring point whose displacement vector exceeds a preset displacement threshold as a mutation monitoring point, and to respectively acquire the coordinate point of each mutation monitoring point; A coordinate point output module, used for outputting each coordinate point to the geological drawing of the monitoring section; A projection vector line drawing module, used for drawing the projection vector line of each coordinate point on the monitoring section based on the geological drawing; A projection vector line perpendicular line intersection point acquisition module is used to respectively acquire the perpendicular line of each projection vector line and acquire all the intersection points between all the perpendicular lines; A random point definition module, used to define a random point on the geological drawing; A random point optimization module, used for iterating the position of the random point through a global optimization algorithm until the sum of the distances between the random point and all intersection points reaches a minimum value; A slope sliding surface circle center acquisition module is used to acquire the position of a random point matching the minimum value as the circle center of the slope sliding surface; The slope sliding surface drawing module is used to define the distance between the center of the circle and the front edge of the monitoring section as a radius, and draw the slope sliding surface through the center of the circle and the radius.

9. An electronic device, characterized in that: It comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the search method as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the search method according to any one of claims 1 to 7 can be implemented.

Images