A method for spatiotemporal collaborative inversion of slope mechanical parameter field

Abstract

The application aims to provide a slope mechanical parameter field space-time cooperative inversion method, an electronic device and a storage medium. Based on limited actual data, the space-time correlation characteristics and single-point evolution characteristics of a surface displacement field are extracted, and drilling prior constraints, same-layer parameter smoothing constraints and parameter range constraints are combined to iteratively invert the internal rock mechanical parameter field of the slope, so that the slope internal mechanical parameter distribution result more consistent with the geological layering rule and the true slope deformation response is obtained.

Description

Technical Field

[0001] This invention relates to the field of engineering design and construction, specifically to a spatiotemporal collaborative inversion method for slope mechanical parameter fields, electronic equipment, and storage medium. Background Technology

[0002] Slopes are widely used in transportation, water conservancy, mining, urban construction, and energy projects. Their stability directly affects project safety and the safety of people and property. To predict slope deformation data, it is necessary to build a slope model and simulate it. The accuracy of the mechanical parameters within the slope model is an important indicator of whether the slope model can make correct predictions.

[0003] In existing technologies, due to limitations in monitoring methods and natural environment, the acquisition of internal mechanical parameters of slope rock mass is usually based on drilling, sampling and laboratory test results to directly give the internal mechanical parameters of rock mass, or on numerical and machine learning methods to infer the internal mechanical parameters of rock mass based on the monitoring of displacement or stress response.

[0004] The above methods have certain limitations, resulting in inaccurate internal rock mass mechanical parameters. This makes it impossible to obtain slope internal mechanical parameter distribution results that are more consistent with geological stratification patterns and actual slope deformation responses. Specifically: existing methods rely solely on a small number of borehole parameters for local assignment, making it difficult to reflect the three-dimensional spatial distribution of internal rock mass mechanical parameters; insufficient utilization of prior borehole information and weak geological constraints cause the inverted internal rock mass mechanical parameters to deviate from the borehole findings; existing parameter inversion methods are prone to unreasonable spatial oscillations, insufficient parameter field continuity, and results lacking engineering geological significance. These inaccuracies in the internal rock mass mechanical parameters consequently lead to errors in subsequent predictions of overall slope deformation. Summary of the Invention

[0005] The purpose of this invention is to provide a spatiotemporal collaborative inversion method, electronic device and storage medium for slope mechanical parameter fields. Based on limited actual data, by extracting the spatiotemporal correlation characteristics and single-point evolution characteristics of the surface displacement field, and combining borehole prior constraints, same-layer parameter smoothing constraints and parameter range constraints, iterative inversion of the rock mechanical parameter field inside the slope is performed, thereby obtaining the distribution results of internal slope mechanical parameters that are more consistent with the geological stratification law and the actual slope deformation response.

[0006] To achieve the above objectives, the present invention provides a spatiotemporal collaborative inversion method for slope mechanical parameter fields, comprising the following steps: recording the initial state of the actual slope, collecting first spatiotemporal change information of multiple target points on the surface of the actual slope within a preset time period, and extracting first feature parameters from the first spatiotemporal change information;

[0007] A slope model is established based on the initial state of the actual slope. The slope model is discretized into multiple calculation units. Initial mechanical parameters are assigned to each calculation unit based on engineering data and empirical parameters.

[0008] Based on the initial mechanical parameters, the slope model is made to simulate the evolution within the preset time period, and the second time-space change information of the target point on the surface of the slope model corresponding to the actual slope is collected within the preset time period. Second feature parameters of the same type as the first feature parameters are extracted from the second time-space change information.

[0009] If the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted, and several iterative simulations are performed until the first feature parameter and the second feature parameter meet the preset conditions.

[0010] Optionally, the acquisition of first temporal and spatial change information of multiple points on the actual slope surface within a preset time period includes:

[0011] Location coordinates, detection time, and displacement;

[0012] The first feature parameter includes: the combination of correlation features of all monitoring points and the autocorrelation features of all monitoring points.

[0013] Optionally, the extraction of the associated feature combination features of all monitoring points from the first temporal and spatial change information adopts an attention mechanism algorithm.

[0014] Optionally, the initial mechanical parameters assigned to each calculation unit based on engineering data and empirical parameters include: cohesion, internal friction angle, elastic modulus, uniaxial compressive strength, Poisson's ratio, and tensile-compressive strength ratio.

[0015] Optionally, each computational unit can be preprocessed with initial mechanical parameters to handle pinch-outs, missing layers, and layer variations, so that the generated data has spatial continuity.

[0016] Optionally, the comparison of the first feature parameter and the second feature parameter includes multiple dimensions, specifically including: point-by-point displacement error term, similarity constraint term of cooperative response between monitoring points, single-point time series autocorrelation feature constraint term, prior constraint term of borehole mechanical parameters, smoothing constraint term of unit mechanical parameters, and range constraint term of mechanical parameters.

[0017] Optionally, if the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted. The preset conditions specifically include satisfying one of the following conditions: the point-by-point displacement error term, the similarity constraint term of the cooperative response between monitoring points, the single-point time-series autocorrelation feature constraint term, the prior constraint term of the borehole mechanical parameters, the smoothing constraint term of the unit mechanical parameters, and the range constraint term of the mechanical parameters all converge.

[0018] The first time-space change information includes the first displacement generated by the actual slope, and the second time-space change information includes the second displacement simulated by the slope model. The displacement error between the first displacement and the second displacement meets the engineering allowable accuracy requirements, and the spatiotemporal response correlation characteristics between monitoring points are less than the set tolerance.

[0019] The parameter changes are less than a given threshold for several consecutive iterations.

[0020] Optionally, if the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each computing unit are adjusted, and several iterative simulations are performed. The adjustment of the initial mechanical parameters of each computing unit specifically includes: calculation based on the point-by-point displacement error term, the similarity constraint term of the cooperative response between monitoring points, the single-point time-series autocorrelation feature constraint term, the prior constraint term of the borehole mechanical parameters, the smoothing constraint term of the unit mechanical parameters, the range constraint term of the mechanical parameters, and their respective constraint term weight coefficients.

[0021] The present invention also provides an electronic device, the electronic device comprising: a memory storing a computer program; a processor communicatively connected to the memory, which executes the spatiotemporal co-inversion method for slope mechanical parameter fields as described above when the computer program is invoked; and a display communicatively connected to the processor and the memory, used to display a GUI interactive interface related to the spatiotemporal co-inversion method for slope mechanical parameter fields.

[0022] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the spatiotemporal collaborative inversion method for slope mechanical parameter fields described in any of the preceding claims.

[0023] The spatiotemporal co-inversion method, electronic device, and storage medium for slope mechanical parameter fields provided by this invention have the following beneficial effects:

[0024] This invention provides a spatiotemporal collaborative inversion method for slope mechanical parameter fields, comprising the following steps: Based on limited actual data, by extracting the spatiotemporal correlation features and single-point evolution features of the surface displacement field, and combining borehole prior constraints, same-layer parameter smoothing constraints, and parameter range constraints, iterative inversion of the internal rock mechanical parameter field of the slope is performed to obtain the distribution results of the internal mechanical parameters of the slope. With this setup, this invention utilizes an attention mechanism algorithm to extract the spatiotemporal correlation features of the slope surface displacement field as an important comparison item, enabling the inverted internal slope mechanical parameters to not only locally fit displacement values ​​when predicting slope deformation, but also correctly characterize the overall collaborative deformation mode of the slope; and by combining borehole prior constraints, same-layer parameter smoothing constraints, and parameter range constraints to determine the inverted internal slope mechanical parameters, a distribution result of the internal slope mechanical parameters that is more consistent with the geological stratification patterns and the actual slope deformation response is obtained.

[0025] This invention also provides an electronic device. Since the electronic device and the spatiotemporal collaborative inversion method for slope mechanical parameter fields belong to the same inventive concept, the electronic device, based on limited actual data, extracts the spatiotemporal correlation features and single-point evolution features of the surface displacement field, and combines borehole prior constraints, same-layer parameter smoothing constraints, and parameter range constraints to iteratively invert the rock mechanical parameter field inside the slope, thereby obtaining the distribution results of the internal mechanical parameters of the slope. With this setup, this invention utilizes an attention mechanism algorithm to extract the spatiotemporal correlation features of the slope surface displacement field as an important comparison item, enabling the inverted internal mechanical parameters of the slope to not only locally fit displacement values ​​when predicting slope deformation, but also correctly characterize the overall collaborative deformation mode of the slope; and by combining borehole prior constraints, same-layer parameter smoothing constraints, and parameter range constraints to determine the inverted internal mechanical parameters of the slope, it obtains the distribution results of the internal mechanical parameters of the slope that are more consistent with the geological stratification laws and the actual slope deformation response.

[0026] This invention also provides a storage medium. Since the storage medium and the spatiotemporal collaborative inversion method for slope mechanical parameter fields belong to the same inventive concept, the storage medium, based on limited actual data, extracts the spatiotemporal correlation features and single-point evolution features of the surface displacement field, and combines borehole prior constraints, same-layer parameter smoothing constraints, and parameter range constraints to iteratively invert the rock mechanical parameter field inside the slope, thereby obtaining the distribution results of the internal mechanical parameters of the slope. With this setup, this invention utilizes an attention mechanism algorithm to extract the spatiotemporal correlation features of the slope surface displacement field as an important comparison item, enabling the inverted internal mechanical parameters of the slope to not only locally fit displacement values ​​when predicting slope deformation, but also correctly characterize the overall collaborative deformation mode of the slope; and by combining borehole prior constraints, same-layer parameter smoothing constraints, and parameter range constraints to determine the inverted internal mechanical parameters of the slope, it obtains the distribution results of the internal mechanical parameters of the slope that are more consistent with the geological stratification rules and the actual slope deformation response. Attached Figure Description

[0027] Figure 1 This is a schematic flowchart of a spatiotemporal collaborative inversion method for slope mechanical parameter fields provided in an embodiment of the present invention.

[0028] Figure 2 This is a block diagram of an electronic device provided in an embodiment of the present invention.

[0029] The attached figures are labeled as follows:

[0030] 101-Processor; 102-Communication interface; 103-Memory; 104-Communication bus; 105-Display. Detailed Implementation

[0031] To make the objectives, advantages, and features of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the drawings are all in a very simplified form and are not drawn to scale, and are only used to facilitate and clarify the explanation of the embodiments of this invention. Furthermore, the structures shown in the drawings are often part of the actual structures. In particular, different figures may emphasize different aspects and may sometimes use different scales.

[0032] It should be understood that when an element or layer is referred to as "on" or "connected to" other elements or layers, it may be directly on or connected to other elements or layers, or may include intervening elements or layers. Conversely, when an element is referred to as "directly on" or "directly connected to" other elements or layers, intervening elements or layers are not included. Although the terms first, second, third, etc., may be used to describe various elements, components, areas, layers, and / or portions, these elements, components, areas, layers, and / or portions should not be limited by these terms. These terms are only used to distinguish one element, component, area, layer, or portion from another element, component, area, layer, or portion. Therefore, without departing from the teachings of this invention, the first element, component, area, layer, or portion discussed below may be referred to as a second element, component, area, layer, or portion. Spatial relation terms such as "below," "under," "below," "above," "on top," "above," etc., may be used herein for convenience of description to describe the relationship between one element or feature shown in the figures and other elements or features. It should be understood that, in addition to the orientations shown in the figures, spatial relational terms are intended to also include different orientations of the devices in use and operation. For example, if the devices in the figures are flipped, then elements or features described as “below,” “under,” or “below” will be oriented “on” other elements or features. Devices may be oriented additionally (rotated 90 degrees or otherwise) and the spatial descriptive terms used herein will be interpreted accordingly. The terminology used herein is intended only to describe particular embodiments and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “comprising” is used to identify the inclusion of features, steps, operations, elements, and / or components, but does not exclude the inclusion or addition of one or more other features, steps, operations, elements, components, and / or groups. When used herein, the terms “and / or” include any and all combinations of the associated listed items.

[0033] The purpose of this invention is to provide a spatiotemporal collaborative inversion method, electronic device and storage medium for slope mechanical parameter fields. Based on limited actual data, by extracting the spatiotemporal correlation characteristics and single-point evolution characteristics of the surface displacement field, and combining borehole prior constraints, same-layer parameter smoothing constraints and parameter range constraints, iterative inversion of the rock mechanical parameter field inside the slope is performed, thereby obtaining the distribution results of internal slope mechanical parameters that are more consistent with the geological stratification law and the actual slope deformation response.

[0034] Please refer to Figure 1 , Figure 1 This is a schematic flowchart illustrating a spatiotemporal collaborative inversion method for slope mechanical parameter fields provided in an embodiment of the present invention. Figure 1As shown, to achieve the above objectives, this invention provides a spatiotemporal collaborative inversion method for slope rock mass mechanical parameter fields, comprising the following steps:

[0035] Record the initial state of the actual slope, collect the first time-space change information of multiple target points on the surface of the actual slope within a preset time period, and extract the first feature parameter from the first time-space change information;

[0036] A slope model is established based on the initial state of the actual slope. The slope model is discretized into multiple calculation units. Initial mechanical parameters are assigned to each calculation unit based on engineering data and empirical parameters.

[0037] Based on the initial mechanical parameters, the slope model is made to simulate the evolution within the preset time period, and the second time-space change information of the target point on the surface of the slope model corresponding to the actual slope is collected within the preset time period. Second feature parameters of the same type as the first feature parameters are extracted from the second time-space change information.

[0038] If the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted, and several iterative simulations are performed until the first feature parameter and the second feature parameter meet the preset conditions.

[0039] Existing technologies generally use drilling, sampling, and laboratory test results to directly determine the internal mechanical parameters of the rock mass, or use numerical and machine learning methods to infer these parameters from monitored displacement or stress responses. However, this approach of directly determining or inferring internal mechanical parameters based on limited data fails to fully utilize prior information such as drilling and geological surveys, and lacks cross-validation among multiple data sets, making it difficult to accurately, stably, and continuously invert the internal mechanical parameter field of the rock mass. The difference between this invention and existing technologies lies in that, after assuming internal mechanical parameters of the rock mass based on existing engineering data, this invention uses these assumed parameters to simulate the overall deformation of the slope. It then compares multiple parameters of the slope model and the actual slope within the same period, including the spatiotemporal characteristics of surface displacement at multiple monitoring points. If the parameters do not meet preset conditions, the assumed internal mechanical parameters are readjusted according to formulas, and the simulation is repeated until all parameters of the slope model and the actual slope meet the preset conditions. At this point, the assumed internal mechanical parameters represent a realistic, stable, and continuous internal mechanical parameter field of the rock mass.

[0040] Specifically, the first temporal and spatial change information of multiple points on the actual slope surface within a preset time period includes: point coordinate information p=[x,y,z], detection time t, and displacement u; the first feature parameter includes: the associated feature combination F of all monitoring points.att And the autocorrelation characteristics F of all monitoring points auto In simple terms, F is the combination of associated features of all monitoring points. att The autocorrelation characteristic F of the monitoring points reflects the overall deformation of the slope surface. auto This reflects the deformation of individual points on the slope surface. Specifically, spatiotemporal response characteristics are comprehensive features describing the coordinated deformation patterns of the slope in terms of spatial distribution and temporal evolution, and are key constraint information in slope stability analysis and parameter inversion. Spatially, it reflects the deformation correlation between different monitoring points on the slope surface, determining which points deform synchronously, belong to the same sliding zone, and which points are relatively independent and have better stability. Temporally, it reflects the trend, rate, acceleration characteristics, and autocorrelation of the displacement of a single monitoring point over time, characterizing the continuity and regularity of slope deformation. The extraction method is detailed later. Autocorrelation characteristics are important indicators for measuring the continuity and regularity of monitoring data in time or space, and in slope displacement analysis, they are mainly reflected in displacement autocorrelation characteristics. By calculating the correlation between the current displacement and historical displacement of the same monitoring point, it determines whether the deformation process is smooth, continuous, and regular. When the autocorrelation characteristic value is high, it indicates that the slope deformation trend is stable, the correlation between previous and subsequent changes is strong, and it belongs to uniform or gradual deformation; a low value indicates large deformation fluctuations, obvious abrupt changes, and poor stability. The displacement evolution features of a single point are extracted from the displacement sequence of the monitoring point itself, including the mean, first-order difference, second-order difference, and autocorrelation features, which constitute a single-point evolution feature vector. The calculation method is as follows:

[0041] At all monitoring times The displacement of the monitoring point at the corresponding time is:

[0042] Indicates the first j Each monitoring point is The displacement value at time t.

[0043] The displacement sequence matrix of all M monitoring points can then be represented as:

[0044]

[0045] First-order difference characteristics are used to characterize the rate of displacement change:

[0046]

[0047] Second-order difference features are used to characterize abrupt shifts in displacement trends.

[0048]

[0049] Displacement autocorrelation coefficient: Let the time window length for solving the autocorrelation coefficient be... The autocorrelation coefficient of the displacement sequence at the j-th monitoring point is defined as:

[0050]

[0051] in, Let be the average value of the displacement sequence at the j-th monitoring point.

[0052] The autocorrelation characteristic of the j-th monitoring point is denoted as:

[0053]

[0054] The set of autocorrelation features for all M monitoring points is:

[0055]

[0056] Furthermore, the associated feature combination F of all monitoring points is extracted from the first time-space change information. att The feature extraction employs an attention mechanism algorithm. To address the issue that existing technologies, while providing internal mechanical parameters of the slope rock mass, can reflect local slope deformation, they cannot accurately simulate the overall slope deformation. Therefore, it is necessary to extract the associated feature combinations of all monitoring points from the point change information. Previously, due to limitations in computing power and algorithms, accurately extracting the associated feature combinations of all monitoring points was difficult. However, the rapid development of artificial intelligence in recent years has made accurate calculation possible. The attention mechanism is an intelligent algorithm for mining data association features. This method uses the displacement curves of each monitoring point during the monitoring period as point features, calculates the degree of association between the displacement evolution processes of different monitoring points through normalized similarity, and further forms an inter-point association weight matrix. It automatically determines which points deform synchronously and belong to the same deformation area, and which points have weak association and are relatively independent. It can capture the spatial response relationship between points and extract the overall slope deformation features, rather than relying on single data points. Its calculation method is as follows:

[0057] Based on the displacement sequence matrix U, the displacement curves of all monitoring points are normalized. j Taking the displacement curve of a monitoring point as an example, normalization is performed to make the subsequent spatiotemporal response characteristics focus more on the displacement change trend:

[0058]

[0059] in, Indicates the first j Calculate the average displacement of each monitoring point. This represents a numerically stable term, used to prevent the denominator from being zero; its value is an extremely small positive number.

[0060] Then the first j The monitoring point and the firsti The attention weights among the monitoring points can be expressed as:

[0061]

[0062] in, The temperature coefficient is used to adjust the concentration of attention weights between points; it is a hyperparameter that is manually specified. express j The monitoring point for the first i The degree of attention paid to the displacement response characteristics of each monitoring point. A larger value indicates a higher degree of attention paid to the displacement response characteristics of the first monitoring point. i The displacement characteristics of the monitoring point for the first j The greater the contribution of each monitoring point to the response characterization.

[0063] The spatiotemporal correlation feature vector of the j-th monitoring point is then expressed as:

[0064]

[0065] By combining the associated feature vectors of all monitoring points, a set of spatiotemporal response features of the surface displacement field is obtained:

[0066]

[0067] Preferably, the initial mechanical parameters assigned to each calculation unit based on engineering data and empirical parameters include: cohesion c, internal friction angle φ, elastic modulus E, uniaxial compressive strength σ, Poisson's ratio μ, and tensile-compressive strength ratio η. Cohesion c is a strength index of resistance to shear failure generated by the mutual adsorption and cementation between rock particles. It reflects the bonding capacity of the soil or rock mass itself and is a key parameter determining the slope's anti-sliding capacity. The greater the cohesion, the less likely the rock mass is to be pulled apart or sheared, and the stronger the overall slope stability. In inversion analysis, cohesion directly affects the development of the shear failure surface and the slope deformation mode. The internal friction angle φ characterizes the ability of rock particles to rub and interlock under shear action, reflecting the material's frictional strength. The greater the internal friction angle, the stronger the rock mass's shear resistance and the less likely it is to slide. It, together with cohesion, constitutes the shear strength of the rock mass and is one of the most crucial parameters for judging whether a slope is unstable and calculating the stability safety factor. The elastic modulus E is a stiffness index that measures the resistance of rock mass to deformation, indicating the ease with which a material undergoes elastic deformation under stress. A larger elastic modulus indicates a "harder" rock mass, resulting in less deformation under the same load; a smaller modulus indicates a "softer" material, making it more prone to significant displacement. In slope numerical simulation, the elastic modulus directly determines the magnitude and distribution of surface settlement and displacement. Uniaxial compressive strength σ is the ultimate ability of rock mass to resist axial pressure failure under unconfined conditions, reflecting the rock's hardness and bearing capacity. A larger value indicates that the rock is less likely to be crushed or cracked, serving as an important basis for determining slope excavation and support schemes. Poisson's ratio μ is the ratio of lateral deformation to axial deformation of rock under axial stress, describing the material's deformation compatibility. A larger Poisson's ratio indicates a more pronounced lateral expansion effect in the rock mass, making it more prone to lateral expansion under stress; in three-dimensional numerical simulation, Poisson's ratio directly affects the stress distribution, lateral displacement, and failure mode of the rock mass. The tensile-compressive strength ratio η is the ratio of the tensile strength to the uniaxial compressive strength of a rock mass, reflecting the difference between the material's tensile and compressive strengths. Rock materials are typically strong in compressive strength but weak in tensile strength; the smaller this ratio, the worse the tensile performance and the more prone the material is to tensile cracking. In slope deformation inversion, the tensile-compressive strength ratio is used to control cracking and damage in the tensile zone of the rock mass, making the simulation more consistent with real failure patterns.

[0068] We will l The initial mechanical parameter vector for the i-th computational unit in a given formation is defined as follows:

[0069]

[0070] The rock mechanics parameters inside the model need to be continuously updated iteratively to construct the internal mechanical parameter field of the slope model. The rock mechanics parameter field to be inverted inside the entire slope can be represented as:

[0071]

[0072] Since borehole data reveals the mechanical parameters of each stratum before the numerical model is built, it is considered prior information. Therefore, the first... r The mechanical parameters of the strata revealed by each borehole are characterized as follows:

[0073]

[0074] It should be noted that when assigning initial mechanical parameters to each computational unit, the upper and lower limits of the internal mechanical parameter field of the slope model are derived from the regional empirical parameter range and corrected by indoor mechanical tests of rocks of various stratigraphic types revealed by boreholes. In subsequent inversion processes, the rock inversion mechanical parameters should also conform to these upper and lower limits. That is:

[0075]

[0076] The above equation can be expressed in vector form, which is used for subsequent mechanical parameter range constraint terms. L range The calculation.

[0077]

[0078] in , indicating the type of mechanical parameters that need to be inverted.

[0079] At this point, we input the initial mechanical parameters into the numerical simulation module to solve for the simulated displacement curves of the initial surface monitoring points of the slope model. Let the... j Each monitoring point is The simulated displacement calculated by the numerical model at time t is:

[0080]

[0081] in, In numerical simulation, C represents the adverse working conditions that cause changes in the slope surface displacement, such as rainfall, slope excavation, and underground mining at the bottom of the slope.

[0082] The simulated displacement matrix for all monitoring points is:

[0083]

[0084] At this point, the autocorrelation feature set F of M monitoring points at the same time intervals between the slope model simulation and the actual slope can be extracted according to the aforementioned steps. auto sim and the spatiotemporal response feature set F of the surface displacement field att sim .

[0085] Preferably, each computational unit is preprocessed with initial mechanical parameters to handle pinch-outs, missing layers, and stratigraphic variations, ensuring spatial continuity of the generated data. Accurately handling stratigraphic pinch-outs, missing layers, and stratigraphic variations is crucial for ensuring model realism, parameter rationality, and computational stability during 3D geological modeling and parameter inversion of slopes. Stratigraphic pinch-outs, missing layers, and abrupt stratigraphic changes are common geological phenomena in slope engineering, directly determining the spatial distribution structure of rock masses and the transmission path of mechanical parameters. Failure to properly handle these variations can lead to blurred stratigraphic interfaces, incorrect lithological attribution, and abnormal parameter transmission across layers, resulting in geologically meaningless abrupt changes and oscillations in the inversion results, significantly deviating from actual geological conditions. Identifying and properly processing these geological variations in advance during the modeling stage clarifies the spatial range and unit assignment of each rock stratum, providing a reliable layered constraint basis for subsequent parameter inversion. This ensures smooth and reasonable parameters within the same stratum and clear and independent boundaries between different strata, avoiding invalid calculations and spurious solutions, improving the engineering credibility and geological rationality of the inversion results, and providing a more realistic geological basis for slope stability evaluation.

[0086] Preferably, the comparison of the first feature parameter and the second feature parameter includes multiple dimensions, specifically including: point-by-point displacement error term L. disp L, a constraint term for the similarity of coordinated responses among monitoring points att Single-point time series autocorrelation feature constraint term L auto Prior constraints on borehole mechanical parameters L bore Element mechanical parameter smoothing constraint term L smooth and mechanical parameter range constraint term L range .

[0087] Point-by-point displacement error term L disp The point-by-point consistency between the displacement curves simulated in the constrained slope model and the measured displacement curves is expressed by the following formula:

[0088]

[0089] Similarity constraint terms for collaborative response among monitoring points F is used to compare the associated feature combination F of all monitoring points in the slope model simulation. att sim The association feature combination F with all monitoring points of the actual slope att It not only ensures the deformation correlation between all monitoring points simulated in the slope model and all monitoring points on the actual slope in the spatial dimension, determining which points deform synchronously and belong to the same sliding zone, and which points are relatively independent and have better stability; it also characterizes the continuity and regularity of slope deformation by showing the displacement trends, rates, acceleration characteristics, and autocorrelation patterns of each monitoring point over time between all monitoring points simulated in the slope model and all monitoring points on the actual slope. Its expression formula is:

[0090]

[0091] Single-point time series autocorrelation feature constraint term L auto The purpose is to ensure that the simulated displacement curve of the slope model is consistent with the actual slope displacement curve in terms of changing trends, stage transitions, acceleration characteristics, and time correlation. This constraint term is constructed based on the statistical characteristics, difference characteristics, and autocorrelation characteristics of the displacement sequence at each monitoring point, and is used to constrain the consistency between the simulated displacement curve and the measured displacement curve in the single-point time-series evolution law. Its expression formula is:

[0092]

[0093] Prior constraint term L for drilling mechanical parameters bore The purpose is to compare the inversion parameter field simulated by the slope model with the actual slope parameters to ensure that the parameters at the location revealed by the borehole do not deviate from the known facts. Its formula is:

[0094]

[0095] The set of known borehole locations is as follows: The r-th borehole control position is the first l The known parameters of the rock-like strata are: Its corresponding inversion value is At the same time .

[0096] Element mechanical parameter smoothing constraint term L smooth The purpose is to avoid unreasonable abrupt changes in the spatial distribution of the inverted parameter field from the slope model simulation, and to ensure reasonable spatial continuity of the internal parameter field constructed based on the established three-dimensional rock stratum structure model. This constraint term is only used to constrain the parameter continuity between adjacent units within the same rock stratum. Assumptions This represents the set of units adjacent to the i-th inversion unit within the model. This indicates the stratum number to which the i-th inversion unit belongs. This indicates the stratum number of the j-th adjacent unit of the i-th inversion unit; then when When this occurs, a smoothing constraint is applied to the corresponding parameter vector. Therefore, the intensity parameter smoothing constraint term is defined as:

[0097]

[0098] in, This is an indicator function that takes the value 1 when the internal condition is true, and 0 otherwise; For the first l Smoothing weights between adjacent units within a rock stratum; This represents the total number of valid terms participating in the smoothing constraint. This constraint only applies to the parameter continuity within the same rock layer; different rock layers are independent of each other.

[0099] Mechanical parameter range constraint term L range The purpose is to ensure that the inversion mechanical parameters simulated by the slope model fall within a limited range. Its expression formula is:

[0100]

[0101] in, This indicates that in the nth iteration, the... l The i-th element of a stratum needs to retrieve the p-th type of mechanical parameters; , Indicates the first l The first rock stratum p Upper and lower limits of mechanical parameters.

[0102] The above six indicators form a joint objective function L, which simultaneously ensures that the simulated displacement values, inter-point coordination relationships, and single-point time-series evolution patterns are consistent with the measured results. Its expression is:

[0103]

[0104] in, These are the weighting coefficients for each constraint term, which can be adjusted according to the inversion objective, data reliability, and the importance of the constraints. The larger the weighting coefficient, the higher the contribution of the corresponding constraint term to the joint objective function. During the inversion process, parameter updates will place greater emphasis on satisfying this constraint, thereby enhancing the guiding role of this type of feature in correcting the internal mechanical parameter field.

[0105] Because the joint objective function L compares the slope model simulation results with the actual slope response from six dimensions, it achieves a high degree of matching between model parameters and real-world parameters, significantly improving the rationality and engineering applicability of the inversion. The synergistic effect of the six constraints ensures that the model parameters not only closely match the monitoring response but also conform to the geological distribution patterns. Compared to traditional single constraints, this model more closely reflects the mechanical properties and deformation mechanisms of real slopes, resulting in more reliable and stable inversion results. This makes the numerical model suitable for subsequent engineering analyses such as slope stability assessment, identification of potential instability zones, optimization of reinforcement measures, and disaster risk early warning.

[0106] Preferably, if the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted. The preset conditions specifically include meeting one of the following conditions:

[0107] All the point-to-point displacement error terms, monitoring point co-response similarity constraints, single-point time-series autocorrelation feature constraints, borehole mechanical parameter prior constraints, unit mechanical parameter smoothing constraints, and mechanical parameter range constraints have converged; that is, the constructed joint objective function L satisfies the convergence condition.

[0108] The first time-space change information includes the first displacement generated by the actual slope, and the second time-space change information includes the second displacement simulated by the slope model. The displacement error between the first displacement and the second displacement meets the engineering allowable accuracy requirements and the spatiotemporal response correlation characteristics between monitoring points are less than the set tolerance; that is, the displacement error meets the engineering allowable accuracy requirements and the spatiotemporal response correlation characteristics between monitoring points are less than the set tolerance.

[0109] The parameter changes are less than a given threshold for several consecutive iterations.

[0110] Preferably, if the first and second feature parameters do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted, and several iterative simulations are performed. The adjustment of the initial mechanical parameters of each calculation unit specifically includes: calculation based on point-by-point displacement error terms, similarity constraints between monitoring points, single-point time-series autocorrelation feature constraints, prior constraints on borehole mechanical parameters, smoothing constraints on unit mechanical parameters, range constraints on mechanical parameters, and their respective constraint weight coefficients. It should be noted that the gradient term of the joint objective function L for the mechanical parameters to be inverted is not limited to the analytical gradient obtained directly from backpropagation by numerical simulation software. In actual calculations, the approximate gradient or equivalent descent direction of the joint objective function for each unit mechanical parameter can be obtained through finite difference sensitivity analysis, response surface approximation, or other parameter sensitivity calculation methods, and the internal mechanical parameters can be iteratively updated accordingly. Specifically, if the preset conditions are not met in the nth round of calculation, the formula for updating and adjusting the internal mechanical parameters to be inverted in the (n+1)th round is:

[0111]

[0112] in, Describe the joint objective function L For the first i The first unit l Approximate gradient or equivalent sensitivity of mechanical parameters;

[0113] The iteration rate or step size per iteration is manually set and used for model convergence.

[0114] Please refer to Figure 2 , Figure 2 This is a block diagram of an electronic device according to an embodiment of the present invention. Figure 2As shown, the present invention also provides an electronic device, the electronic device comprising:

[0115] Memory 103 stores computer programs;

[0116] The processor 101 is communicatively connected to the memory and executes the spatiotemporal collaborative inversion method for slope mechanical parameter fields described above when calling the computer program.

[0117] The display 105 is communicatively connected to the processor and the memory, and is used to display a GUI interactive interface related to the spatiotemporal co-inversion method of slope mechanical parameter field.

[0118] Since the electronic device and the spatiotemporal collaborative inversion method of slope mechanical parameter field belong to the same inventive concept, the electronic device uses a text detection algorithm to generate a recognition box and uses the geometric properties of the recognition box itself to adjust the image. It does not rely on the recognition of the geometric elements of the water meter. The recognition and adjustment process is completed at the algorithm level, which requires fewer resources and has higher recognition efficiency and accuracy.

[0119] Since the electronic device provided by this invention belongs to the same inventive concept as the spatiotemporal collaborative inversion method of slope mechanical parameter field described above, the electronic device provided by this invention has all the advantages of the spatiotemporal collaborative inversion method of slope rock mass mechanical parameter field described above. Therefore, the beneficial effects of the electronic device provided by this invention will not be described in detail here.

[0120] like Figure 2 As shown, the electronic device also includes a communication interface 102 and a communication bus 104, wherein the processor 101, the communication interface 102, and the memory 103 communicate with each other via the communication bus 104. The communication bus 104 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 104 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 102 is used for communication between the aforementioned electronic device and other devices.

[0121] The processor 101 referred to in this invention can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 101 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines.

[0122] The memory 103 can be used to store the computer program. The processor 101 implements various functions of the electronic device by running or executing the computer program stored in the memory 103 and calling the data stored in the memory 103.

[0123] The memory 103 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0124] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the spatiotemporal collaborative inversion method for slope mechanical parameter fields described in any of the preceding claims.

[0125] Since the storage medium and the slope mechanical parameter field spatiotemporal collaborative inversion method belong to the same inventive concept, the storage medium uses a text detection algorithm to generate a recognition box and uses the geometric properties of the recognition box itself to adjust the image. It does not rely on the recognition of the geometric elements of the water meter. The recognition and adjustment processes are completed at the algorithm level, requiring fewer resources and resulting in higher recognition efficiency and accuracy.

[0126] Since the storage medium provided by this invention belongs to the same inventive concept as the spatiotemporal collaborative inversion method of slope mechanical parameter field described above, the storage medium provided by this invention has all the advantages of the spatiotemporal collaborative inversion method of slope rock mass mechanical parameter field described above. Therefore, the beneficial effects of the storage medium provided by this invention will not be elaborated here.

[0127] The storage medium of embodiments of the present invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0128] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0129] It should also be noted that although the present invention has been disclosed above with reference to preferred embodiments, these embodiments are not intended to limit the present invention. For any person skilled in the art, many possible variations and modifications can be made to the technical solutions of the present invention based on the disclosed technical content, or equivalent embodiments can be modified accordingly, without departing from the scope of the present invention. Therefore, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the present invention shall still fall within the scope of protection of the present invention.

[0130] It should also be understood that, unless otherwise specified or indicated, the terms “first,” “second,” “third,” etc., in the specification are used only to distinguish the various components, elements, and steps in the specification, and not to indicate the logical or sequential relationships between the various components, elements, and steps.

[0131] Furthermore, it should be recognized that the terminology described herein is used only to describe particular embodiments and not to limit the scope of the invention. It must be noted that the singular forms “a” and “an” used herein and in the appended claims include plural bases unless the context clearly indicates otherwise. For example, a reference to “a step” or “an apparatus” means a reference to one or more steps or apparatuses, and may include secondary steps and secondary apparatuses. All conjunctions used should be understood in the broadest sense. And the word “or” should be understood to have the definition of logical “or” rather than logical “exclusive OR”, unless the context clearly indicates otherwise. Furthermore, implementation of embodiments of the invention may include performing selected tasks manually, automatically, or in combination.

Claims

1. A spatiotemporal collaborative inversion method for slope mechanical parameter fields, characterized in that, Includes the following steps: Record the initial state of the actual slope, collect the first time-space change information of multiple target points on the surface of the actual slope within a preset time period, and extract the first feature parameter from the first time-space change information; A slope model is established based on the initial state of the actual slope. The slope model is discretized into multiple calculation units. Initial mechanical parameters are assigned to each calculation unit based on engineering data and empirical parameters. Based on the initial mechanical parameters, the slope model simulates the evolution within the preset time period, and collects second temporal and spatial variation information of the target point location on the slope model surface corresponding to the actual slope within the preset time period. From the second temporal and spatial variation information... Extract a second feature parameter of the same type as the first feature parameter; If the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted, and several iterative simulations are performed until the first feature parameter and the second feature parameter meet the preset conditions.

2. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 1, characterized in that, The first temporal and spatial change information of the actual slope surface at multiple points within a preset time period includes: Location coordinates, detection time, and displacement; The first feature parameter includes: the combination of correlation features of all monitoring points and the autocorrelation features of all monitoring points.

3. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 1, characterized in that, The extraction of the associated feature combination features of all monitoring points from the first time-space change information adopts an attention mechanism algorithm.

4. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 1, characterized in that, The initial mechanical parameters assigned to each calculation unit based on engineering data and empirical parameters include: cohesion, internal friction angle, elastic modulus, uniaxial compressive strength, Poisson's ratio, and tensile-compressive strength ratio.

5. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 4, characterized in that, To ensure spatial continuity of the generated data, initial mechanical parameters are assigned to each computational unit before processing for rock layer pinch-outs, gaps, and stratigraphic variations.

6. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 1, characterized in that, The comparison of the first and second feature parameters includes multiple dimensions, specifically including: point-by-point displacement error term, similarity constraint term for collaborative response between monitoring points, single-point time-series autocorrelation feature constraint term, prior constraint term for borehole mechanical parameters, smoothing constraint term for unit mechanical parameters, and range constraint term for mechanical parameters.

7. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 1, characterized in that, If the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each calculation unit are adjusted. The preset conditions specifically include meeting one of the following conditions: All the following constraints converged: point-by-point displacement error, similarity of coordinating response between monitoring points, single-point time-series autocorrelation feature constraint, prior constraint of borehole mechanical parameters, smoothing constraint of unit mechanical parameters, and range constraint of mechanical parameters. The first time-space change information includes the first displacement generated by the actual slope, and the second time-space change information includes the second displacement simulated by the slope model. The displacement error between the first displacement and the second displacement meets the engineering allowable accuracy requirements, and the spatiotemporal response correlation characteristics between monitoring points are less than the set tolerance. The parameter changes are less than a given threshold for several consecutive iterations.

8. The spatiotemporal collaborative inversion method for slope mechanical parameter fields as described in claim 1, characterized in that, If the first feature parameter and the second feature parameter do not meet the preset conditions, the initial mechanical parameters of each computing unit are adjusted, and several iterative simulations are performed. The adjustment of the initial mechanical parameters of each computing unit specifically includes: calculation based on the point-by-point displacement error term, the similarity constraint term of the cooperative response between monitoring points, the single-point time-series autocorrelation feature constraint term, the prior constraint term of the borehole mechanical parameters, the smoothing constraint term of the unit mechanical parameters, the range constraint term of the mechanical parameters, and their respective constraint term weight coefficients.

9. An electronic device, characterized in that, include: Memory, which stores computer programs; The processor, which is communicatively connected to the memory, executes the spatiotemporal collaborative inversion method of slope mechanical parameter field as described in any one of claims 1-8 when calling the computer program. The display, which is communicatively connected to the processor and the memory, is used to display a GUI interactive interface related to the spatiotemporal co-inversion method of slope mechanical parameter field.

10. A storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the spatiotemporal co-inversion method for slope mechanical parameter fields as described in any one of claims 1-8.

Images