Slope stability state dynamic identification method, device and equipment

Abstract

The embodiment of the invention provides a side slope stability state dynamic identification method, device and equipment. The side slope stability state dynamic identification method comprises the following steps: obtaining monitoring data of a target side slope about inclination angle change; determining the slope damage type of the target slope according to the monitoring data and a preset slope damage type judgment standard; performing feature extraction on the monitoring data in response to the fact that the slope damage type of the target slope is an acceleration type; determining the current failure rate of the target slope based on the extracted features; and calling a pre-constructed prediction model to generate a time prediction value when the landslide phenomenon of the target slope occurs based on the damage rate.

Description

Technical Field

[0001] This invention relates to the field of dynamic identification technology of slope stability state, and particularly to a slope stability... Qualitative state dynamic identification methods, devices and equipment. Background Technology

[0002] In recent years, the stability failure of mountain slopes, highway and railway subgrades, and water conservancy dams has frequently occurred, leading to major safety accidents and economic losses. Therefore, it is increasingly necessary to monitor slope stability in real time and make dynamic assessments.

[0003] Traditional slope stability assessment methods mostly rely on instruments and equipment such as total stations, GPS, and displacement gauges to make judgments on slope stability based on displacement or deformation data. These methods have problems such as high cost, poor real-time performance, and insensitivity to small changes. Summary of the Invention

[0004] To address the aforementioned technical problems, embodiments of the present invention provide a method for dynamic identification of slope stability state, comprising: Obtain monitoring data on the target slope regarding changes in dip angle; The slope failure type of the target slope is determined based on the monitoring data and the preset criteria for judging slope failure types. In response to the target slope's slope failure type being accelerated, feature extraction is performed on the monitoring data; The current damage rate of the target slope is determined based on the extracted features; A pre-built prediction model is invoked to generate a time prediction value for when the target slope will experience a landslide, based on the damage rate.

[0005] In one embodiment, constructing the prediction model includes: Building the model framework:

[0006] The The absolute value of the reciprocal of the angular velocity of the target slope, the t The time for the target slope to tilt and deform, the B The angle coefficient, the t f The predicted time for the landslide to occur on the target slope; Quantify the observation error of the monitoring data; The prediction model is constructed based on the observation error and model framework.

[0007] In one embodiment, constructing the prediction model based on the observation error and model framework includes: The observation error is defined to have a mean of 0 and a standard deviation of . The prediction model is: (The model follows a normal distribution.)

[0008] The W u For standard Brownian motion functions, The constant is the stated The tilt angle change rate corresponds to the damage rate. It is the angle of inclination.

[0009] In one embodiment, invoking a pre-built prediction model to generate a time prediction value for when the target slope will experience a landslide based on the damage rate includes: A target vector is constructed based on the angle coefficient, time prediction value, and standard deviation. ; Based on the tilt angle change rate and the target vector, the following is determined: t i The probability of constantly observing the rate of change of the slope angle of the target slope. d i ; The prediction model is invoked to determine the maximum likelihood estimate of the target vector based on the probability. Based on the maximum likelihood estimate, a genetic algorithm is used for global search to obtain the mean of the angle coefficients, the mean of the time prediction values, and the mean of the standard deviations in the target vector. Based on the maximum likelihood estimate, the covariance matrix of the target vector is determined using the inverse of the second-order partial derivative matrix. The angle coefficient, time prediction value, and standard deviation are determined based on the covariance matrix and the mean, mean, and mean of the standard deviation of the angle coefficient.

[0010] In one embodiment, the method further includes: The monitoring data is then denoised. The denoised monitoring data is normalized so that it is mapped to the interval [0,1].

[0011] In one embodiment, the monitoring data includes the change in the dip angle of the target slope over time; The normalization process for the denoised monitoring data includes:

[0012]

[0013] The T For time, the stated T’ The time after normalization. T min This is the minimum time value for the monitoring period. T max The maximum time value for the monitoring period, the D The change in inclination angle. D min To monitor the minimum rate of change of the tilt angle within a given time period, D max To monitor the minimum rate of change of the tilt angle within a given time period, D’ This represents the rate of change of tilt angle after normalization.

[0014] In one embodiment, the method further includes: Obtain historical monitoring data for each slope during historical periods; Based on the historical monitoring data, the normalized change status of the dip angle of each slope and the monitoring time are determined. Based on the normalized change state and monitoring time of each slope, a drawing is obtained to serve as the criterion for judging the slope failure type. Each area in the drawing corresponds to a slope change type, and different areas correspond to different slope change types.

[0015] In one embodiment, determining the slope failure type of the target slope based on the monitoring data and a preset criterion for judging slope failure types includes: The monitoring data is matched with regions on the drawing to determine the region where the monitoring data is located on the drawing. The slope failure type of the target slope is determined based on the area where it is located in the drawing, according to the monitoring data.

[0016] Another embodiment of the present invention also provides a dynamic identification device for slope stability, comprising: The first acquisition module is used to acquire monitoring data on the target slope regarding the change in dip angle; The first determining module is used to determine the slope failure type of the target slope based on the monitoring data and the preset judgment criteria for slope failure type. The response module is used to extract features from the monitoring data in response to the target slope's slope failure type being accelerated. The second determining module is used to determine the current damage rate of the target slope based on the extracted features; The calling module is used to call a pre-built prediction model to generate a time prediction value for when the target slope will experience a landslide based on the damage rate.

[0017] Another embodiment of the present invention also provides an electronic device, comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the slope stability state dynamic identification method as described above.

[0018] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0019] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the dynamic identification method for slope stability status in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram illustrating the application process of the dynamic identification method for slope stability status in this embodiment of the invention.

[0023] Figure 3 This is a schematic diagram of the criteria for determining the type of slope failure in an embodiment of the present invention.

[0024] Figure 4 This is a field test diagram from an application embodiment.

[0025] Figure 5 This is a graph showing the curve changes in one application example.

[0026] Figure 6 This is a graph showing the slope angle-time history relationship of a natural slope in an application example.

[0027] Figure 7This is a graph showing the probability prediction results in one application example.

[0028] Figure 8 This is a structural block diagram of the slope stability dynamic identification device in an embodiment of the present invention. Detailed Implementation

[0029] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but these are not intended to limit the scope of the invention.

[0030] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the following description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope of this disclosure will be apparent to those skilled in the art.

[0031] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.

[0032] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0033] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention, which have the features described in the claims and are therefore all within the scope of protection defined herein.

[0034] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0035] Specific embodiments of the present disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure and can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the present disclosure. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely to serve as the basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of substantially any suitable detailed structures.

[0036] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0037] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0038] like Figure 1 As shown, this embodiment of the invention provides a method for dynamic identification of slope stability, including: S1: Obtain monitoring data on the target slope regarding the change in dip angle; S2: Determine the slope failure type of the target slope based on the monitoring data and the preset slope failure type judgment criteria; S3: In response to the target slope failure type being accelerated, feature extraction is performed on the monitoring data; S4: Determine the current damage rate of the target slope based on the extracted features; S5: Invoke the pre-built prediction model to generate a time prediction value for when the target slope will experience a landslide based on the damage rate.

[0039] This embodiment focuses on slope dip angle monitoring and proposes a novel monitoring method that combines sensor monitoring technology, data extraction and analysis, and slope mechanics theory analysis. It is mainly used to identify the slope stability status in real time and provide timely warnings of potential landslide risks, thereby reducing casualties and economic property losses caused by slope instability and other disasters.

[0040] As described in the above embodiments, Figure 2 As shown, this embodiment first conducts a site survey of the entire area, using tilt sensors to perceive and extract site data, and then transmits the extracted site data using wireless communication technology. The monitoring data in this embodiment includes the change in the slope angle of the target slope over time; that is, the monitoring data includes both time and the change in slope angle. After obtaining the monitoring data, the system calls a preset slope failure type judgment standard to judge the monitoring data and determine the current failure type of the target slope. The failure types in this embodiment include non-destructive type, primary failure type, and secondary failure type. When the current failure type of the target slope is primary or secondary, it indicates that the target slope is currently in an accelerating failure type. In response to this judgment result, the system extracts features from the monitoring data, including the change in slope angle and time, and determines the current failure rate of the target slope based on the extracted features. After obtaining the damage rate, the system can call a pre-built prediction model, which is used to predict the time when a landslide occurs on the target slope. Therefore, by calling the prediction model and inputting parameters such as the damage rate into the model, the system can obtain at least the predicted time when a landslide occurs on the target slope.

[0041] The solution presented in this embodiment boasts higher sensitivity compared to traditional monitoring methods, capable of detecting millimeter-level tilt angle changes. Its accuracy far surpasses that of displacements visible to the naked eye. Based on tilt angle monitoring and certain tilt angle identification criteria, it issues corresponding early warnings. Furthermore, this slope stability assessment method based on tilt angle monitoring possesses real-time dynamic capabilities. Combined with sensor technology, it can support online monitoring platforms, achieving data updates at the minute or even second level. Additionally, this method has lower deployment costs compared to traditional methods, and the miniaturization and wireless nature of the sensors make it more suitable for large-scale deployment in complex terrain. Moreover, this method, combined with intelligent identification using computer programs, can reduce human error to a certain extent and is more adaptable to interference from complex environments.

[0042] In one embodiment, the obtained monitoring data needs to be preprocessed due to certain interference factors. Furthermore, the method also includes: S6: Denoise the monitoring data; S7: Normalize the noise-reduced monitoring data so that the monitoring data is mapped to the [0,1] interval.

[0043] Normalization can eliminate the influence of dimensions between data features, making different indicators comparable, and also avoiding problems such as numerical overflow or underestimation during calculation. In this embodiment, the data normalization process scales the time and deformed data proportionally, mapping the data to the [0,1] interval. Specifically, the normalization process for the denoised monitoring data includes:

[0044]

[0045] The T For time, the stated T’ The time after normalization. T min This is the minimum time value for the monitoring period. T max The maximum time value for the monitoring period, the D The change in inclination angle. D min To monitor the minimum rate of change of the tilt angle within a given time period, D max To monitor the minimum rate of change of the tilt angle within a given time period, D’ This represents the rate of change of tilt angle after normalization.

[0046] The criteria for determining the slope failure type described in this embodiment need to be pre-constructed; therefore, the method further includes: S8: Obtain historical monitoring data for each slope during historical periods; S9: Determine the normalized rate of change and monitoring time of the dip angle of each slope based on the historical monitoring data; S10: Based on the normalized change state and monitoring time of each slope, a drawing is generated to obtain a drawing used as a criterion for judging the slope failure type. Each area in the drawing corresponds to a slope change type. Different areas correspond to different slope change types. The slope change type is related to the slope failure rate.

[0047] The slope change type is related to the slope failure rate. Specifically, for example, a drawing can be created based on the determined data, using the normalized rate of change of the slope's dip angle as the ordinate and the normalized monitoring time as the abscissa. The structure of the drawing can be referenced... Figure 3 As shown in the figure, the olive-shaped area in the middle represents the slope angle changing at a constant rate with time, which is a non-accelerating type, while the areas on both sides of this area are the decelerating type and the accelerating type, respectively.

[0048] Furthermore, the slope failure type of the target slope is determined based on the monitoring data and the preset slope failure type judgment criteria, including: S101: Perform regional matching on the drawing to determine the region where the monitoring data is located in the drawing; S102: Determine the slope failure type of the target slope based on the monitoring data and the area where it is located in the drawing.

[0049] For example, after the monitoring data of the target slope is denoised and normalized, the data can be matched with the map that serves as the criterion for judging the slope damage type, the location of the data in the map can be determined, and the current damage type of the target slope can be determined based on the area where the location is located. Specifically, it is determined whether the current damage type is an accelerated type, i.e., an accelerated damage type.

[0050] The prediction model described in this embodiment also needs to be pre-built. Building the prediction model includes: S11: Building the model framework:

[0051] The The absolute value of the reciprocal of the angular velocity of the target slope, the t The time for the target slope to tilt and deform, the B The angle coefficient, the t f The predicted time for the landslide to occur on the target slope; S12: Quantify the observation error regarding the monitoring data; S13: Construct the prediction model based on the observation error and model framework.

[0052] The predicted failure time of the target slope is affected by observation errors. Observation errors refer to the fact that, due to factors such as measurement errors and environmental noise, the observed values ​​of inverse velocity and time are not entirely on the same straight line; that is, the intercept of the regression line is uncertain, leading to a difference between the predicted and actual landslide failure time. To take observation errors into account and achieve more accurate predictions, this embodiment proposes constructing a prediction model based on the aforementioned observation errors and model framework, including: S131: Define the observation error as having a mean of 0 and a standard deviation of . The prediction model is: (The model follows a normal distribution.)

[0053] The W u For standard Brownian motion functions, The constant is the stated The tilt angle change rate corresponds to the damage rate. It is the angle of inclination.

[0054] In this embodiment, the predicted failure time of a single landslide is assumed. t f Satisfying the mean is The standard deviation is The normal distribution is given by the observation error. For example, the prediction model can be simplified to:

[0055] The observation error The formula is expressed as follows:

[0056] Furthermore, the step of invoking a pre-built prediction model to generate a time prediction value for the occurrence of a landslide on the target slope based on the damage rate includes: S501: Construct a target vector based on the aforementioned angle coefficient, time prediction value, and standard deviation. ; S502: Based on the tilt angle change rate and the target vector, determine in... t i The probability of constantly observing the rate of change of the slope angle of the target slope. d i ; S503: Invoke the prediction model and determine the maximum likelihood estimate of the target vector based on the probability; S504: Based on the maximum likelihood estimate, a genetic algorithm is used to perform a global search to obtain the mean of the angle coefficients, the mean of the time prediction values, and the mean of the standard deviations in the target vector. S505: Based on the maximum likelihood estimate, the covariance matrix of the target vector is determined using the inverse of the second-order partial derivative matrix; S506: Determine the angle coefficient, time prediction value, and standard deviation based on the covariance matrix and the mean, mean, and mean of the standard deviation of the angle coefficient.

[0057] For example, due to the formula above and Since all parameters are unknown, a target vector is defined in this embodiment for ease of solution. When a landslide is in an accelerated deformation stage, there are n When there are 1 data point, set d i Indicates time as t i ( i =1,2,..., n Let the absolute value of the reciprocal of the dip angle deformation rate observed at time ) be... .when When the value is known, in t i Constant observation d i The probabilities are as follows:

[0058] Assuming when When the value is known, n The observations of each data point are statistically independent. Therefore, when When the value is known, observe D The probability, i.e. The likelihood function is as follows:

[0059] The maximum likelihood function estimate obtained based on the above formula is expressed as follows: That is The mean value is calculated using a genetic algorithm for global search in practical applications. The specific calculation process is shown in the program code below: % Define the likelihood function likelihood likelihood = @(theta) -sum(log(normpdf(di, theta(1)) (theta(2) - ti), theta(3)))); % Define the scope and constraints of variables lb = [0, min(ti), 0]; % Lower bound ub = [10, max(ti), 10]; % Upper bound %Set genetic algorithm parameters options = optimoptions(@ga, 'MaxGenerations', 2000, 'PlotFcn', 'gaplotbestf', 'MaxStallGenerations', 500, 'MaxTime', Inf); %Use a genetic algorithm to perform maximum likelihood estimation theta_hat = ga(likelihood, 3, [], [], [], [], lb, ub, [], options).

[0060] By employing a genetic algorithm, it is possible to calculate The specific value of . For its standard deviation, based on the maximum likelihood principle, it can be approximated by its covariance matrix. The covariance matrix is ​​equal to the inverse of the second-order partial derivative matrix (Hessian matrix), therefore the covariance matrix . satisfy:

[0061] t f yes The second element, in obtaining After obtaining the mean and covariance matrix, we can get The mean and standard deviation of each element. Then, using these mean and standard deviation, the following can be calculated: The values ​​of each element, including the time prediction value.

[0062] The methods for finding the covariance matrix include: firstly, using the second-order central difference formula (as shown below), and specifically, but not limited to, using the MATLAB program to calculate its numerical solution, thus obtaining the Hessian matrix. H ij In this embodiment, the Hessian matrix is ​​a 3×3 matrix:

[0063] in e i and e j It is a standard unit vector, with a difference step size. dx and dh 1×10 -6 Calculate H ij Then, based on the fact that the covariance matrix is ​​equal to the inverse of the Hessian matrix, it can be calculated that... , The standard deviation of each element is The square root of the diagonal element of a matrix.

[0064] The application effects of this solution are illustrated below with specific application examples: Field tests were conducted on a natural slope in a certain city. For example, the natural slope consisted of weakly expansive clay, with a toe angle of approximately 40°. At such a large angle, the high stability of the slope was related to the strong structure of the expansive clay. A trench 0.2m deep was artificially excavated at the toe of the slope to make it more prone to collapse. Six tilt sensors of different lengths were installed on the slope. (See reference for details.) Figure 4 As shown. After installing the tilt sensor, artificial rainfall was conducted with a constant rainfall intensity of 21 mm / h. The data sampling frequency for the field test was 1 Hz.

[0065] The field test used artificial rainfall at an intensity of 21 mm / h, causing slope failure. The main failure occurred in the middle of the natural slope, where a tilt sensor T3 and a 7 cm rod were installed. The sliding depth at the instability point was 25 cm. Figure 5 As shown. Images of the slope before and after damage are as follows. Figure 4 As shown, Figure 6 The tilt angle time history curves are obtained from six tilt angle sensors.

[0066] Furthermore, the slope instability point is located in the middle of the slope, and the tilt angle-time history variation curve measured by the tilt sensor T3 at this failure point shows a similar pattern to the results of the indoor model test. Figure 5 As shown in (a), the slope angle fluctuated before 3.75h but remained within a relatively stable range. Subsequently, the slope angle measured at T3 increased rapidly and entered the accelerated deformation stage. After this stage, the slope immediately failed.

[0067] A probabilistic predictive analysis considering observation errors was performed on the accelerated deformation stage, and the results were compared with the quantitative prediction results of the inverse dip rate method. The change in the absolute value of the inverse dip rate during the accelerated deformation stage is shown in the figure. Figure 5 As shown in (b) of the diagram.

[0068] Similar to indoor model tests, a probabilistic prediction analysis considering observation errors was performed on the accelerated deformation stage of the field test. The first 30%, 60%, 70%, 80%, and 90% of the data were used as prediction data. The prediction results of this method are as follows: Figure 7 As shown, as the data is gradually updated, the mean and range of the predicted failure time are constantly approaching the actual failure time, with the actual failure time of the slope being 4.047 hours.

[0069] As shown in the table below, unlike the results of indoor model tests, when the first 30% of the data is used as the prediction data, the quantitative prediction results are not within the 95% confidence interval of the probabilistic prediction method. However, when the first 60% or more (including 60%) of the data is used for prediction, the quantitative prediction results are all within the 95% confidence interval of the probabilistic prediction method. This indicates that as the monitoring data is continuously updated and improved, the results of the two methods are becoming increasingly similar. When using the probabilistic prediction method and taking the first 80% of the data as the prediction data, the actual failure time is already included within the 95% confidence interval. In contrast, when using the quantitative prediction method and taking the first 90% of the data as the prediction data, the predicted result differs from the actual slope failure time by nearly 0.03 hours. Compared to the quantitative prediction method, the probabilistic prediction method can predict the landslide failure time earlier and more accurately.

[0070]

[0071] like Figure 8 As shown, another embodiment of the present invention also provides a dynamic identification device for slope stability, comprising: The first acquisition module is used to acquire monitoring data on the target slope regarding the change in dip angle; The first determining module is used to determine the slope failure type of the target slope based on the monitoring data and the preset judgment criteria for slope failure type. The response module is used to extract features from the monitoring data in response to the target slope's slope failure type being accelerated. The second determining module is used to determine the current damage rate of the target slope based on the extracted features; The calling module is used to call a pre-built prediction model to generate a time prediction value for when the target slope will experience a landslide based on the damage rate.

[0072] In one embodiment, constructing the prediction model includes: Building the model framework:

[0073] The The absolute value of the reciprocal of the angular velocity of the target slope, the t The time for the target slope to tilt and deform, theB The angle coefficient, the t f The predicted time for the landslide to occur on the target slope; Quantify the observation error of the monitoring data; The prediction model is constructed based on the observation error and model framework.

[0074] In one embodiment, constructing the prediction model based on the observation error and model framework includes: The observation error is defined to have a mean of 0 and a standard deviation of . The prediction model is: (The model follows a normal distribution.)

[0075] The W u For standard Brownian motion functions, The constant is the stated The tilt angle change rate corresponds to the damage rate. It is the angle of inclination.

[0076] In one embodiment, invoking a pre-built prediction model to generate a time prediction value for when the target slope will experience a landslide based on the damage rate includes: A target vector is constructed based on the angle coefficient, time prediction value, and standard deviation. ; Based on the tilt angle change rate and the target vector, the following is determined: t i The probability of constantly observing the rate of change of the slope angle of the target slope. d i ; The prediction model is invoked to determine the maximum likelihood estimate of the target vector based on the probability. Based on the maximum likelihood estimate, a genetic algorithm is used for global search to obtain the mean of the angle coefficients, the mean of the time prediction values, and the mean of the standard deviations in the target vector. Based on the maximum likelihood estimate, the covariance matrix of the target vector is determined using the inverse of the second-order partial derivative matrix. The angle coefficient, time prediction value, and standard deviation are determined based on the covariance matrix and the mean, mean, and mean of the standard deviation of the angle coefficient.

[0077] In one embodiment, the method further includes: A noise reduction module is used to denoise the monitoring data; The normalization module is used to normalize the denoised monitoring data so that the monitoring data is mapped to the [0,1] interval.

[0078] In one embodiment, the monitoring data includes the change in the dip angle of the target slope over time; The normalization process for the denoised monitoring data includes:

[0079]

[0080] The T For time, the stated T’ The time after normalization. T min This is the minimum time value for the monitoring period. T max The maximum time value for the monitoring period, the D The change in inclination angle. D min To monitor the minimum rate of change of the tilt angle within a given time period, D max To monitor the minimum rate of change of the tilt angle within a given time period, D’ This represents the rate of change of tilt angle after normalization.

[0081] In one embodiment, the device further includes: The second acquisition module is used to acquire historical monitoring data of each slope during the historical period; The third determining module is used to determine the normalized change state of the dip angle of each slope and the monitoring time based on the historical monitoring data. The drawing module is used to draw a map based on the normalized change state and monitoring time of each slope to obtain a map that serves as a criterion for judging the slope failure type. Each area in the map corresponds to a slope change type, and different areas correspond to different slope change types. The slope change type is related to the slope failure rate.

[0082] In one embodiment, determining the slope failure type of the target slope based on the monitoring data and a preset criterion for judging slope failure types includes: The monitoring data is matched with regions on the drawing to determine the region where the monitoring data is located on the drawing. The slope failure type of the target slope is determined based on the area where it is located in the drawing, according to the monitoring data.

[0083] Another embodiment of the present invention also provides an electronic device, comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the slope stability state dynamic identification method as described above.

[0084] Furthermore, one embodiment of the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the dynamic identification method for slope stability state as described above. It should be understood that the various solutions in this embodiment have the corresponding technical effects in the above-described method embodiments, and will not be repeated here.

[0085] Furthermore, embodiments of the present invention also provide a computer program product, which is tangibly stored on a computer-readable medium and includes computer-readable instructions that, when executed, cause at least one processor to perform a slope stability state dynamic identification method such as the one described in the embodiments above.

[0086] It should be noted that the computer storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access storage medium (RAM), a read-only storage medium (ROM), an erasable programmable read-only storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only storage medium (CD-ROM), an optical storage medium, a magnetic storage medium, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program configured for use by or in connection with an instruction execution system, system, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, antenna, optical fiber, RF, etc., or any suitable combination thereof.

[0087] Furthermore, those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0088] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.

Claims

1. A method for dynamic identification of slope stability state, characterized in that, include: Obtain monitoring data on the target slope regarding changes in dip angle; The slope failure type of the target slope is determined based on the monitoring data and the preset criteria for judging slope failure types. In response to the target slope's slope failure type being accelerated, feature extraction is performed on the monitoring data; The current damage rate of the target slope is determined based on the extracted features; A pre-built prediction model is invoked to generate a time prediction value for when the target slope will experience a landslide, based on the damage rate.

2. The method for dynamic identification of slope stability state according to claim 1, characterized in that, Constructing the prediction model includes: Building the model framework: dt / |dθ| is the absolute reciprocal of the angular velocity of the target slope, t is the time of the slope's tilt deformation, B is the angle coefficient, and t f The predicted time for the landslide to occur on the target slope; Quantify the observation error of the monitoring data; The prediction model is constructed based on the observation error and model framework.

3. The method for dynamic identification of slope stability state according to claim 2, characterized in that, The construction of the prediction model based on the observation error and model framework includes: The observation error is defined as following a normal distribution with a mean of 0 and a standard deviation of σ0. The prediction model is: The W u Let τ be the standard Brownian motion function, and τ be a constant. The tilt angle change rate corresponds to the damage rate, and θ is the tilt angle.

4. The method for dynamic identification of slope stability state according to claim 3, characterized in that, The step of calling a pre-built prediction model to generate a time prediction value for the occurrence of a landslide on the target slope based on the damage rate includes: Construct a target vector λ based on the angle coefficient, time prediction value, and standard deviation; Based on the rate of change of tilt angle and the target vector, at t i The probability d of observing the rate of change of the slope angle of the target slope at any given time. i ; The prediction model is invoked to determine the maximum likelihood estimate of the target vector based on the probability. Based on the maximum likelihood estimate, a genetic algorithm is used for global search to obtain the mean of the angle coefficients, the mean of the time prediction values, and the mean of the standard deviations in the target vector. Based on the maximum likelihood estimate, the covariance matrix of the target vector is determined using the inverse of the second-order partial derivative matrix. The angle coefficient, time prediction value, and standard deviation are determined based on the covariance matrix and the mean, mean, and mean of the standard deviation of the angle coefficient.

5. The method for dynamic identification of slope stability state according to claim 1, characterized in that, The method further includes: The monitoring data is then denoised. The denoised monitoring data is normalized so that it is mapped to the interval [0,1].

6. The method for dynamic identification of slope stability state according to claim 5, characterized in that, The monitoring data includes the change in the slope angle of the target slope over time; The normalization process for the denoised monitoring data includes: Where T is time, and T' is the normalized time, T min T is the minimum time value for the monitoring period. max The maximum time value during the monitoring period, where D is the change in tilt angle. min To monitor the minimum rate of change of the dip angle within a given time period, D max To monitor the minimum rate of change of the dip angle within the monitoring period, D' is the normalized rate of change of the dip angle.

7. The method for dynamic identification of slope stability state according to claim 1, characterized in that, The method further includes: Obtain historical monitoring data for each slope during historical periods; Based on the historical monitoring data, the normalized change status of the dip angle of each slope and the monitoring time are determined. Based on the normalized change state and monitoring time of each slope, a drawing is obtained to serve as the criterion for judging the slope failure type. Each region in the drawing corresponds to a slope change type, and different regions correspond to different slope change types. The slope change type is related to the slope failure rate.

8. The method for dynamic identification of slope stability state according to claim 7, characterized in that, The slope failure type of the target slope is determined based on the monitoring data and the preset criteria for judging slope failure types, including: The monitoring data is matched with regions on the drawing to determine the region where the monitoring data is located on the drawing. The slope failure type of the target slope is determined based on the area where it is located in the drawing, according to the monitoring data.

9. A dynamic identification device for slope stability, characterized in that, include: The first acquisition module is used to acquire monitoring data on the target slope regarding the change in dip angle; The first determining module is used to determine the slope failure type of the target slope based on the monitoring data and the preset judgment criteria for slope failure type. The response module is used to extract features from the monitoring data in response to the target slope's slope failure type being accelerated. The second determining module is used to determine the current damage rate of the target slope based on the extracted features; The calling module is used to call a pre-built prediction model to generate a time prediction value for when the target slope will experience a landslide based on the damage rate.

10. An electronic device, comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the slope stability state dynamic identification method as described in any one of claims 1-8.

Images