Slope stability evaluation method and system based on displacement curve feature recognition

Abstract

The invention provides a slope stability evaluation method and system based on displacement curve feature recognition, and relates to the technical field of geological monitoring, and the method comprises the steps: obtaining the parameter information of a target slope and a potential sliding surface; constructing a slope discrete element model about a potential sliding surface based on the parameter information; parameter reduction is carried out based on the slope discrete element model, first information is obtained, and the first information is displacement scalar increment of a potential sliding surface at a monitoring point under different reduction coefficients; performing normalization processing on the first information to obtain second information; feature extraction is carried out based on the second information, and a plurality of distortion features are obtained by drawing a slope displacement increment space distribution curve; and evaluating the stability of the target slope through the distortion features to obtain the critical unstable state of the target slope. According to the method, the problem that key information is lost and misjudged during slope stability evaluation due to limitation of data processing dimensions in an existing method is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological monitoring, in particular to a slope stability evaluation method and system based on displacement curve feature recognition. BACKGROUND

[0002] The slope stability evaluation has long relied on the threshold judgment mechanism of displacement monitoring data. The traditional monitoring methods mainly include the deformation monitoring network based on the global navigation satellite system (GNSS), the array of inclination sensors and the interferometric synthetic aperture radar (InSAR) technology. These technologies continuously collect the displacement data of the slope surface, establish the displacement-time relationship curve, and then trigger the early warning according to the preset threshold of the single-point displacement accumulation or the rate of sudden change.

[0003] However, the root cause of the defects of the prior art lies in the limitation of the data processing dimension, which directly leads to the loss of key information and misjudgment. Taking the widely used GNSS as an example, limited by the sampling frequency of ≤1 Hz, it cannot capture the millisecond-level displacement transient signals (such as 0.5-2 second sharp pulses) caused by the micro-fracture of rock mass at the physical level. These high-frequency transients are exactly the early mechanical response of the sliding surface. When the transient peak signals filtered out by the sampling frequency accumulate to a certain spatial density, the traditional method will inevitably miss the judgment due to the lack of data. The deeper defect lies in the one-way simplification of the analysis model, that is, the prior art regards the displacement curve as an isolated scalar sequence, neither establishes the phase correlation of the displacement fluctuations of different monitoring points in the spatial dimension, nor constructs the normalized mapping of the displacement amplitude and the slope position. This makes the system only detect the oscillation peak value of each single-point curve when the most dangerous anti-phase oscillation (for example, the displacement wave of the slope shoulder and the slope foot forms a 180° phase difference) occurs in the slope body, but it cannot identify the structure surface shear locking state represented by this specific spatial phase relationship.

[0004] Therefore, it is urgently needed to provide a method capable of penetrating noise interference, accurately capturing the shape features of the displacement curve, and evaluating the slope stability by establishing the quantitative mapping of the feature peak pattern and the distortion type of the slope body, so as to fundamentally solve the problem of the identification failure of the early instability precursor of the prior art. SUMMARY

[0005] The present application relates to the technical field of geological monitoring, in particular to a slope stability evaluation method and system based on displacement curve feature recognition.

[0006] In a first aspect, the present application provides a slope stability evaluation method based on displacement curve feature recognition, comprising:

[0007] obtaining the parameter information and the potential sliding surface of the target slope;

[0008] construct a slope discrete element model about the potential sliding surface based on the parameter information;

[0009] perform parameter reduction based on the slope discrete element model, combine double-parameter coordinated reduction calculation to obtain first information, and the first information is displacement scalar increment of the potential sliding surface at a monitoring point under different reduction coefficients;

[0010] perform normalization processing on the first information to obtain second information, and the second information is normalized displacement scalar increment corresponding to the displacement scalar increment;

[0011] perform feature extraction based on the second information, and obtain multiple distortion features by drawing a spatial distribution curve of slope displacement increment;

[0012] evaluate the stability of the target slope through the distortion features to obtain a critical unstable state of the target slope.

[0013] In a second aspect, the application further provides a slope stability evaluation system based on displacement curve feature recognition, comprising:

[0014] an acquisition module configured to acquire parameter information and a potential sliding surface of a target slope;

[0015] a construction module configured to construct a slope discrete element model about the potential sliding surface based on the parameter information;

[0016] a reduction module configured to perform parameter reduction based on the slope discrete element model, combine double-parameter coordinated reduction calculation to obtain first information, and the first information is displacement scalar increment of the potential sliding surface at a monitoring point under different reduction coefficients;

[0017] a processing module configured to perform normalization processing on the first information to obtain second information, and the second information is normalized displacement scalar increment corresponding to the displacement scalar increment;

[0018] an extraction module configured to perform feature extraction based on the second information, and obtain multiple distortion features by drawing a spatial distribution curve of slope displacement increment;

[0019] an evaluation module configured to evaluate the stability of the target slope through the distortion features to obtain a critical unstable state of the target slope.

[0020] The application has the following beneficial effects:

[0021] (1) The present application determines the relationship of displacement scalar increment of each monitoring point under each reduction order by mining the spatial dimension dynamic evolution law, maps the overall deformation coordination of the slope surface under the current intensity condition through the spatial curve, captures the core representation of system stability, that is, when the slope tends to be critical instability, strain localization will inevitably lead to the collapse of spatial coordination of the slope displacement field, which presents as a sharp abnormal fluctuation of displacement scalar increment along the slope, local distortion or qualitative change of curve form in data level. The essence of this spatial distortion is the direct projection and precursor signal of the instability core mechanism such as the breakthrough of potential slip zone and the failure of stress-locked body in the slope surface deformation field, which has significant sensitivity and universality compared with the accumulation of single-point displacement to critical value (macroscopically visible).

[0022] (2) The present application avoids the interference of local accidental changes by obtaining the overall collapse of displacement field spatial correlation (i.e. non-single-point change), making the instability identification more robust, especially suitable for slopes with complex slip surface or obvious progressive damage.

[0023] (3) The present application can identify the suddenness of spatial distortion and has algorithm sensitivity through normalized amplification of differences and curve form analysis, which can early warn the instability trend and overcome the limitation of traditional criterion lagging behind the large deformation stage. And the spatial curve form and its distortion position naturally carry the instability mode information (such as superficial sliding and deep damage), forming a multi-dimensional criterion system with clear physical meaning. Using normalization processing to eliminate dimensional differences can be transplanted to different engineering backgrounds, and the double-parameter coordination principle is not restricted by numerical platform. Therefore, the present application has achieved substantial breakthroughs in the accuracy, timeliness, mechanism transparency and engineering adaptability of stability determination.

[0024] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application as described in the written description and claims hereof. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0026] Figure 1 The flow chart of the slope stability evaluation method based on displacement curve feature recognition described in the embodiments of the present application;

[0027] Figure 2A structural schematic diagram of a slope stability evaluation system based on displacement curve feature recognition in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings of the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0029] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Meanwhile, in the description of the present application, the terms “first”, “second”, and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0030] Embodiment 1

[0031] The present embodiment provides a slope stability evaluation method based on displacement curve feature recognition.

[0032] Referring to Figure 1 , the present method includes steps S1, S2, S3, S4, S5, and S6.

[0033] Step S1: obtaining parameter information of a target slope and a potential sliding surface;

[0034] In the present embodiment, geological survey is performed on the target slope, and the survey range is determined, which needs to cover the slope body, the slope top, and the slope foot influence area, to ensure that the survey data can reflect the overall geological structure of the slope. Then, through drilling core, geophysical interpretation, and in-situ testing, etc., the parameter information (such as rock-soil physical and mechanical parameters, engineering geological condition parameters) of the target slope and the spatial position and morphological characteristics of the potential sliding surface are obtained.

[0035] Step S2: constructing a slope discrete element model about the potential sliding surface based on the parameter information;

[0036] In this embodiment, the parameter information includes soil and rock mass parameters, potential sliding surface parameters, and slope geometric parameters. The soil and rock mass parameters include the density, initial cohesion, and initial internal friction angle of each layer of soil and rock mass. The potential sliding surface parameters include the spatial geometric parameters of the potential sliding surface (three-dimensional coordinate range, dip angle, direction, thickness, etc.) and the shear strength parameters of the potential sliding surface.

[0037] Understandably, when constructing a discrete element model of a slope, it is necessary to divide the soil and rock mass into layers and potential sliding surfaces, then assign mechanical parameters to the soil and rock mass and potential sliding surfaces, and set boundary conditions and initial geostress equilibrium.

[0038] Step S3: Based on the slope discrete element model, perform parameter reduction and combine it with two-parameter coordinated reduction calculation to obtain the first information, which is the scalar displacement increment of the potential sliding surface at the monitoring point under different reduction coefficients;

[0039] Step S3 includes:

[0040] Step S31: Set up multiple monitoring points on the potential slip surface of the discrete element model of the slope;

[0041] In this embodiment, the selection of monitoring points follows the principle of combining actual surveys with numerical simulation calculations. Points that are easy to install instruments, have a wide coverage area, and are also control points of the slope, such as shear exit points and trailing edge cracks.

[0042] Step S32: Obtain the initial shear strength parameters of the target slope, wherein the initial shear strength parameters include the initial cohesion and the initial internal friction angle;

[0043] Step S33: Gradually increase the reduction coefficient according to the preset gradient to obtain multi-level reduction coefficients;

[0044] Step S34: Based on the reduction factor, the initial shear strength parameter is reduced simultaneously, and the slope discrete element model is used for simulation calculation to obtain the displacement vector of each monitoring point under different reduction factors;

[0045] Step S35: Calculate the scalar displacement increment of each monitoring point under each reduction factor based on the displacement vector under each reduction factor and the displacement vector under the previous reduction factor.

[0046] In this embodiment, a dual-parameter coordinated reduction strategy is adopted to simultaneously reduce cohesion and internal friction angle, avoiding the distortion of physical meaning caused by reducing only a single parameter. Static equilibrium calculations are performed at each reduction factor level, recording the displacement vectors of multiple pre-set monitoring points on the potential sliding surface after the calculation, and calculating the scalar displacement increment relative to the previous reduction factor. The formula is as follows:

[0047] ΔD ij(F i ) = D ij (F i )-D ij (F i-1 )

[0048] In the formula, ΔD ij (F i ) indicates that monitoring point j is at the reduction factor F i Relative to the reduction factor F i-1 The displacement scalar increment, D ij (F i ) indicates that monitoring point j is at the reduction factor F i The displacement vector, D ij (F i-1 ) indicates that monitoring point j is at the reduction factor F i-1 The displacement vector, F i and F i-1 These represent the reduction coefficients for the i-th and (i-1)-th levels, respectively.

[0049] Step S4: Normalize the first information to obtain the second information, where the second information is the normalized displacement scalar increment corresponding to the displacement scalar increment;

[0050] Step S4 includes:

[0051] Step S41: Obtain the displacement scalar increment of all monitoring points corresponding to each reduction factor;

[0052] Step S42: For each reduction factor, iterate through the displacement scalar increments of all monitoring points and select the maximum value of the displacement scalar increment as the maximum value under the corresponding reduction factor;

[0053] Step S43: Normalize the displacement scalar increment of each level by using the maximum value under the reduction factor of each level to obtain the corresponding normalized displacement scalar increment.

[0054] In this embodiment, the reduction factor F is obtained. i Below, the maximum value ΔD of the displacement scalar increment of the monitoring point group. imax The displacement scalar increment value of each monitoring point is normalized by dividing by the maximum value to facilitate the extraction of curve change characteristics. The formula is as follows:

[0055] ΔD ijnorm (F i )=ΔD ij (F i ) / ΔD imax

[0056] In the formula, ΔD ijnorm (F i ) indicates that monitoring point j is at the reduction factor Fi Relative to the reduction factor F i-1 The normalized displacement scalar increment, ΔD ij (F i ) indicates that monitoring point j is at the reduction factor F i Relative to the reduction factor F i-1 The displacement scalar increment, ΔD imax The reduction factor F represents the reduction factor. i The maximum value below.

[0057] Step S5: Based on the second information, feature extraction is performed, and multiple distortion features are obtained by plotting the spatial distribution curve of slope displacement increment;

[0058] Step S5 includes:

[0059] Step S51: For each reduction factor, plot the spatial distribution curve of the slope displacement increment for each level, with the spatial location of the monitoring point along the potential slope as the abscissa and the normalized displacement scalar increment of the monitoring point as the ordinate.

[0060] Step S52: Obtain the set of spatial distribution curves of slope displacement increment under all reduction coefficients in ascending order;

[0061] Step S53: Based on the set of spatial distribution curves of slope displacement increment, distortion identification is performed. Combined with the identification of violent fluctuations and oscillations, the identification of local peak groups and trough groups, the identification of abrupt discontinuous regions, and the identification of abrupt changes in overall morphology, the corresponding distortion features are obtained. The distortion features include the first distortion feature, the second distortion feature, the third distortion feature, and the fourth distortion feature.

[0062] It should be noted that when the shear strength of the soil and rock mass is high (i.e., F... i When the stress is relatively small, the slope is in a stable or small deformation state. The spatial distribution curve is usually relatively smooth and continuous, showing characteristics that match the initial stress field or small deformation mode (such as gradually increasing or decreasing).

[0063] With F i When the slope increases, approaches or reaches the critical state: the plastic zone inside the slope expands and becomes continuous, and strain localization is significantly enhanced. This is reflected in the relationship between the monitoring point location and ΔD. ijnorm (F i On the curve, abnormal non-smoothness will appear, which is called distortion.

[0064] For example, there may be violent fluctuations and oscillations, with the curve exhibiting irregular sawtooth patterns and sharp alternations between high and low points, significantly deviating from the smooth / gradual trend under steady-state conditions. This oscillation reflects a disruption of the spatial continuity of slope displacement changes, i.e., the appearance of the first distortion characteristic.

[0065] If there are local peak clusters or trough clusters, and multiple spatially adjacent points exhibit disproportionately high or low increments, forming prominent spikes, peaks, or depressions, then the second distortion feature appears.

[0066] If a sudden, discontinuous region appears, and within a short spatial distance, the increment value of the displacement scalar experiences a sudden, non-gradual, sharp jump or drop, and its curve exhibits a step-like shape, then the third distortion characteristic appears.

[0067] If a morphological mutation is found, the overall distribution pattern changes significantly compared to the curve morphology at the previous level or with a lower reduction coefficient (e.g., from flat to violently oscillating, or from single-peak to multi-peak), which is the fourth distortion feature.

[0068] Step S53 includes:

[0069] Step S531: Obtain the third information under each reduction coefficient through the set of spatial distribution curves of slope displacement increments. The third information is the difference of the normalized displacement scalar increments corresponding to adjacent monitoring points.

[0070] In this embodiment, the formula for calculating the third information is:

[0071] ΔD ij ′=ΔD ijnorm (F i )-ΔD i(j-1)norm (F i )

[0072] In the formula, ΔD ij ′ represents the difference between monitoring point j and monitoring point j-1 at the reduction factor F i The difference in the normalized displacement scalar increments, ΔD ijnorm (F i ) indicates that monitoring point j is at the reduction factor F i Relative to the reduction factor F i-1 The normalized displacement scalar increment, ΔD i(j-1)norm (F i ) indicates that monitoring point j-1 is at the reduction factor F i Relative to the reduction factor F i-1 The normalized displacement scalar increment.

[0073] Step S532: Input all the third information into the differential symbol function to obtain the symbol results output in the order of monitoring points;

[0074] In this embodiment, the formula for calculating the symbol result is:

[0075] s ij =sgn(ΔD) ij ′)

[0076] In the formula, s ij This indicates that monitoring point j and monitoring point j-1 are at the reduction factor F i The symbolic result, s ij ∈{-1, 0, 1}, sgn(·) denotes the difference sign function, ΔD ij ′ represents the difference between monitoring point j and monitoring point j-1 at the reduction factor F i The difference in the increments of the normalized displacement scalar.

[0077] Step S533: Calculate the proportion parameter through the symbol result. If the proportion parameter is greater than the preset proportion, it is identified as the first distortion feature.

[0078] In this embodiment, if the proportion of alternating non-zero terms in the sign results output according to the monitoring point order is high, then the change is considered to be jagged, i.e., satisfying the following:

[0079]

[0080] In the formula, # represents counting, S ij This indicates that monitoring point j and monitoring point j-1 are at the reduction factor F i The symbolic result, s i(j+1) Monitoring points j+1 and j are at the reduction factor F i The following symbolic results show that N represents the number of monitoring points and k represents the preset percentage, which can be 0.6.

[0081] Step S534: Perform window sliding based on the set of spatial distribution curves of slope displacement increment. If there are trough groups or peak groups within the window, they are identified as the second distortion feature.

[0082] In this embodiment, a local window is defined, with a window size w (e.g., w = 3), and the sliding window covers a set of points S. k ={ΔD ijnorm (F i )|j=k,k+1,...,k+w-1}, where ΔD ijnorm (F i ) indicates that monitoring point j is at the reduction factor F i Relative to the reduction factor F i-1 The normalized displacement scalar increment, where k represents the starting position index of the sliding window in the monitoring point sequence.

[0083] Calculate statistics within the window and globally:

[0084]

[0085] In the formula, μ k σ represents the mean within the window. k μ represents the standard deviation within the window. gσ represents the global mean. g Let w represent the global standard deviation, w represent the window size, and ΔD represent the global standard deviation. ijnorm (F i ) indicates that monitoring point j is at the reduction factor F i Relative to the reduction factor F i-1 The normalized displacement scalar increment, k represents the starting position index of the sliding window in the monitoring point sequence, and N represents the number of monitoring points.

[0086] The valley cluster within the window satisfies:

[0087]

[0088] The peak group within the window should satisfy:

[0089]

[0090] In the formula, min represents the minimum value, max represents the maximum value, and S k Let ΔD represent the set of points covered by the sliding window. ijnorm (F i ) indicates that monitoring point j is at the reduction factor F i Relative to the reduction factor F i-1 The normalized displacement scalar increment, μ g σ represents the global mean. g H represents the global standard deviation, and H represents the outlier threshold. When H is 2, the corresponding confidence interval is 95%.

[0091] Step S535: Calculate the steep change parameter under each level of reduction coefficient using the third information. If the steep change parameter is greater than the preset steep change, it is identified as the third distortion feature.

[0092] In this embodiment, when the absolute value of the third information is significantly greater than the average change, it is considered to have experienced a sharp jump or drop. The formula for calculating the steep change parameter is as follows:

[0093]

[0094] In the formula, J i The reduction factor F represents the reduction factor. i The steeply changing parameter, ΔD ij ′ represents the difference between monitoring point j and monitoring point j-1 at the reduction factor F i The difference between the normalized displacement scalar increments, |·| represents taking the absolute value, and N represents the number of monitoring points.

[0095] In this embodiment, the preset steep change is set to 2, that is, when J... i If the value is greater than 2, it is considered a sharp change and identified as the third distortion feature.

[0096] Step S536: Extract the corresponding overall morphological features based on the spatial distribution curves of slope displacement increments corresponding to two adjacent reduction coefficients;

[0097] Step S537: If there is a sudden change in the overall morphological characteristics of two adjacent reduction coefficients, it is identified as the fourth distortion feature.

[0098] In this embodiment, if the overall distribution pattern changes significantly compared to the curve shape at the previous level or with a lower reduction factor (e.g., from flat to violently oscillating, or from a single peak to multiple peaks), it is considered an overall aberration in the shape, namely the fourth distortion feature (which can be obtained through machine learning aberration classification and aberration detection of curve fitting residuals).

[0099] Step S6: Evaluate the stability of the target slope using the distortion characteristics to obtain the critical unstable state of the target slope.

[0100] Step S6 includes:

[0101] Step S61: Obtain the distortion features corresponding to each level of reduction coefficient in ascending order of reduction coefficient;

[0102] Step S62: Take the reduction factor at which the distortion feature first appears as the critical reduction factor;

[0103] Step S63: Take the slope strength level corresponding to the critical reduction coefficient as the critical unstable state of the target slope.

[0104] In this embodiment, when the reduction process first shows a significant change or a qualitative leap (such as from slight fluctuations to violent oscillations), that is, when any distortion feature appears for the first time, it is considered that the slope begins to enter a critically unstable state at this strength level, such as a significant accelerated deformation stage.

[0105] In summary, this invention has innovatively proposed and systematically constructed a quantitative evaluation mechanism for slope stability based on the spatial distortion evolution of slope displacement response. Its core is reflected in a method chain formed by three inseparable links.

[0106] First, by implementing a dual-parameter coordinated and synchronous reduction strategy of cohesion and internal friction angle, this invention ensures that the strength weakening process conforms to the actual physical and mechanical behavior of the soil and rock mass, fundamentally avoiding the mechanism distortion problem caused by traditional single-parameter reduction, and laying a physically reasonable foundation for subsequent analysis.

[0107] Secondly, for each independent reduction coefficient state, a distribution curve of displacement scalar increments (their normalized values) ordered along the spatial location of the slope is constructed and analyzed. By dynamically tracking this spatial curve, the significant spatial distortion characteristics exhibited when approaching instability are captured. This distortion is specifically characterized by: when the slope approaches critical instability, the displacement scalar increments show violent discontinuous fluctuations, abrupt changes in local values, or a qualitative change in the overall distribution pattern (compared to the smooth, gradual characteristics under low reduction coefficients). This spatial distortion phenomenon essentially reveals a direct mapping of instability precursors such as the formation of potential slip zones, intensified strain localization, or breakthrough of locked sections in the slope surface deformation response.

[0108] Finally, this invention establishes the appearance or abrupt change in the evolution of multi-point coordinated spatial distortion characteristics as the instability criterion. Specifically, when a significant and identifiable distortion characteristic is first observed in the displacement increment curve distributed along the slope at a specific reduction coefficient, or when this characteristic abruptly intensifies with increasing reduction, the reduction coefficient corresponding to this characteristic is directly determined as the critical value, thereby achieving an objective quantitative assessment of the slope safety factor. This invention reveals the essential correlation between the distortion phenomenon of displacement response in the spatial dimension of the slope and the overall instability state of the slope, and establishes a diagnostic standard that can be implemented in an engineering manner.

[0109] Example 2:

[0110] like Figure 2 As shown in the figure, this embodiment provides a slope stability evaluation system based on displacement curve feature recognition. The system includes:

[0111] The acquisition module is used to acquire parameter information and potential slip surfaces of the target slope;

[0112] A construction module is used to construct a discrete element model of the slope regarding the potential slip surface based on the parameter information;

[0113] The reduction module is used to reduce parameters based on the slope discrete element model and combine it with two-parameter coordinated reduction calculation to obtain first information, which is the scalar displacement increment of the potential sliding surface at the monitoring point under different reduction coefficients.

[0114] The processing module is used to normalize the first information to obtain the second information, wherein the second information is the normalized displacement scalar increment corresponding to the displacement scalar increment.

[0115] The extraction module is used to extract features based on the second information and obtain multiple distortion features by drawing the spatial distribution curve of the slope displacement increment;

[0116] The evaluation module is used to evaluate the stability of the target slope through the distortion characteristics and obtain the critical unstable state of the target slope.

[0117] The reduction module includes:

[0118] The setting unit is used to set multiple monitoring points on the potential slip surface of the discrete element model of the slope.

[0119] The first acquisition unit is used to acquire the initial shear strength parameters of the target slope, the initial shear strength parameters including the initial cohesion and the initial internal friction angle;

[0120] The first processing unit is used to gradually increase the reduction coefficient according to a preset gradient to obtain a multi-level reduction coefficient.

[0121] The reduction unit is used to reduce the initial shear strength parameter based on the reduction coefficient, and to perform simulation calculations in conjunction with the slope discrete element model to obtain the displacement vector of each monitoring point under different reduction coefficients.

[0122] The calculation unit is used to calculate the displacement scalar increment of each monitoring point under each reduction factor based on the displacement vector under each reduction factor and the displacement vector under the previous reduction factor.

[0123] The extraction module includes:

[0124] The plotting unit is used to plot the spatial distribution curve of the slope displacement increment for each level of reduction coefficient, with the spatial location of the monitoring point along the potential slope as the abscissa and the normalized displacement scalar increment of the monitoring point as the ordinate.

[0125] The second processing unit is used to obtain a set of spatial distribution curves of slope displacement increment under all reduction coefficients in ascending order of reduction coefficient;

[0126] The identification unit is used to identify distortion based on the set of spatial distribution curves of slope displacement increment. It combines the identification of violent fluctuations and oscillations, the identification of local peak groups and trough groups, the identification of abrupt discontinuous regions, and the identification of abrupt changes in overall morphology to obtain the corresponding distortion features. The distortion features include a first distortion feature, a second distortion feature, a third distortion feature, and a fourth distortion feature.

[0127] The evaluation module includes:

[0128] The second acquisition unit is used to acquire the distortion features corresponding to each level of reduction coefficient in ascending order of reduction coefficient;

[0129] The third processing unit is used to take the reduction factor that first appears the distortion feature as the critical reduction factor.

[0130] The fourth processing unit is used to take the slope strength level corresponding to the critical reduction coefficient as the critical unstable state of the target slope.

[0131] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0132] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0133] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A slope stability evaluation method based on displacement curve feature recognition, characterized in that, include: Obtain parameter information and potential slip surface of the target slope; Based on the parameter information, a discrete element model of the slope with respect to the potential slip surface is constructed; Based on the slope discrete element model, parameter reduction is performed, and combined with two-parameter coordinated reduction calculation, the first information is obtained. The first information is the scalar displacement increment of the potential sliding surface at the monitoring point under different reduction coefficients. The first information is normalized to obtain the second information, which is the normalized displacement scalar increment corresponding to the displacement scalar increment. Based on the second information, feature extraction is performed, and multiple distortion features are obtained by plotting the spatial distribution curve of slope displacement increment. The stability of the target slope is evaluated by the distortion characteristics, and the critical unstable state of the target slope is obtained.

2. The slope stability evaluation method based on displacement curve feature recognition according to claim 1, characterized in that... The parameter reduction based on the discrete element model of the slope, combined with the two-parameter coordinated reduction calculation, yields the first information, including: Multiple monitoring points were set on the potential slip surface of the discrete element model of the slope. Obtain the initial shear strength parameters of the target slope, including the initial cohesion and the initial internal friction angle; By gradually increasing the reduction coefficient according to a preset gradient, a multi-level reduction coefficient can be obtained. Based on the reduction factor, the initial shear strength parameter is simultaneously reduced, and the slope discrete element model is used for simulation calculation to obtain the displacement vector of each monitoring point under different reduction factors. The displacement scalar increment of each monitoring point under each reduction factor is calculated based on the displacement vector under each reduction factor and the displacement vector under the previous reduction factor.

3. The slope stability evaluation method based on displacement curve feature recognition according to claim 1, characterized in that... The step of normalizing the first information to obtain the second information includes: Obtain the displacement scalar increment of all monitoring points corresponding to each level of reduction factor; For each reduction factor, the displacement scalar increments of all monitoring points are traversed, and the maximum value of the displacement scalar increments is selected as the maximum value under the corresponding reduction factor. The displacement scalar increment at each level is normalized by using the maximum value under each reduction factor to obtain the corresponding normalized displacement scalar increment.

4. The slope stability evaluation method based on displacement curve feature recognition according to claim 1, characterized in that... The feature extraction based on the second information, and the obtaining of multiple distortion features by plotting the spatial distribution curve of slope displacement increment, include: For each reduction factor, the spatial distribution curve of the slope displacement increment for each level is plotted with the spatial location of the monitoring point along the potential slope as the abscissa and the normalized displacement scalar increment of the monitoring point as the ordinate. According to the reduction factor in ascending order, we obtain the set of spatial distribution curves of slope displacement increment under all reduction factors; Distortion identification is performed based on the set of spatial distribution curves of slope displacement increment. Combined with the identification of violent fluctuations and oscillations, the identification of local peak groups and trough groups, the identification of abrupt discontinuous regions, and the identification of abrupt changes in overall morphology, the corresponding distortion features are obtained. The distortion features include the first distortion feature, the second distortion feature, the third distortion feature, and the fourth distortion feature.

5. The slope stability evaluation method based on displacement curve feature recognition according to claim 4, characterized in that... The obtained corresponding distortion features include: The third information under each reduction coefficient is obtained by the set of spatial distribution curves of slope displacement increment. The third information is the difference of the normalized displacement scalar increment corresponding to adjacent monitoring points. Input all the third information into the differential symbol function to obtain the symbol results output in the order of the monitoring points; The percentage parameter is calculated based on the symbol result. If the percentage parameter is greater than the preset percentage, it is identified as the first distortion feature. Window sliding is performed based on the set of spatial distribution curves of slope displacement increment. If there are trough groups or peak groups within the window, they are identified as the second distortion feature. The steep change parameter under each level of reduction coefficient is calculated using the third information. If the steep change parameter is greater than the preset steep change, it is identified as the third distortion feature. Based on the spatial distribution curves of slope displacement increments corresponding to two adjacent reduction coefficients, extract the corresponding overall morphological features; If there is a sudden change in the overall morphological characteristics of two adjacent reduction coefficients, it is identified as the fourth distortion feature.

6. The slope stability evaluation method based on displacement curve feature recognition according to claim 1, characterized in that... The evaluation of the stability of the target slope based on the distortion characteristics, to obtain the critical unstable state of the target slope, includes: Obtain the distortion features corresponding to each level of reduction coefficient in ascending order of reduction coefficient; The reduction factor at which the first distortion feature appears is taken as the critical reduction factor; The slope strength level corresponding to the critical reduction factor is taken as the critical unstable state of the target slope.

7. A slope stability evaluation system based on displacement curve feature recognition, characterized in that, include: The acquisition module is used to acquire parameter information and potential slip surfaces of the target slope; A construction module is used to construct a discrete element model of the slope regarding the potential slip surface based on the parameter information; The reduction module is used to reduce parameters based on the slope discrete element model and combine it with two-parameter coordinated reduction calculation to obtain first information, which is the scalar displacement increment of the potential sliding surface at the monitoring point under different reduction coefficients. The processing module is used to normalize the first information to obtain the second information, wherein the second information is the normalized displacement scalar increment corresponding to the displacement scalar increment. The extraction module is used to extract features based on the second information and obtain multiple distortion features by drawing the spatial distribution curve of the slope displacement increment; The evaluation module is used to evaluate the stability of the target slope through the distortion characteristics and obtain the critical unstable state of the target slope.

8. The slope stability evaluation system based on displacement curve feature recognition according to claim 7, characterized in that, The reduction module includes: The setting unit is used to set multiple monitoring points on the potential slip surface of the discrete element model of the slope. The first acquisition unit is used to acquire the initial shear strength parameters of the target slope, the initial shear strength parameters including the initial cohesion and the initial internal friction angle; The first processing unit is used to gradually increase the reduction coefficient according to a preset gradient to obtain a multi-level reduction coefficient. The reduction unit is used to reduce the initial shear strength parameter based on the reduction coefficient, and to perform simulation calculations in conjunction with the slope discrete element model to obtain the displacement vector of each monitoring point under different reduction coefficients. The calculation unit is used to calculate the displacement scalar increment of each monitoring point under each reduction factor based on the displacement vector under each reduction factor and the displacement vector under the previous reduction factor.

9. The slope stability evaluation system based on displacement curve feature recognition according to claim 7, characterized in that, The extraction module includes: The plotting unit is used to plot the spatial distribution curve of the slope displacement increment for each level of reduction coefficient, with the spatial location of the monitoring point along the potential slope as the abscissa and the normalized displacement scalar increment of the monitoring point as the ordinate. The second processing unit is used to obtain a set of spatial distribution curves of slope displacement increment under all reduction coefficients in ascending order of reduction coefficient; The identification unit is used to identify distortion based on the set of spatial distribution curves of slope displacement increment. It combines the identification of violent fluctuations and oscillations, the identification of local peak groups and trough groups, the identification of abrupt discontinuous regions, and the identification of abrupt changes in overall morphology to obtain the corresponding distortion features. The distortion features include a first distortion feature, a second distortion feature, a third distortion feature, and a fourth distortion feature.

10. The slope stability evaluation system based on displacement curve feature recognition according to claim 7, characterized in that, The evaluation module includes: The second acquisition unit is used to acquire the distortion features corresponding to each level of reduction coefficient in ascending order of reduction coefficient; The third processing unit is used to take the reduction factor that first appears the distortion feature as the critical reduction factor. The fourth processing unit is used to take the slope strength level corresponding to the critical reduction coefficient as the critical unstable state of the target slope.

Images