Method and device for generating dam surface settlement nephogram based on adaptive interpolation model

Abstract

The embodiment of the invention discloses a method and device for generating a dam surface settlement cloud picture based on a self-adaptive interpolation model. A specific embodiment of the method comprises the steps of performing feature extraction on multi-dimensional monitoring point data of a preset dam structure to generate a dam body scene portrait; according to the dam body scene portrait, generating an optimal interpolation algorithm; optimizing the optimal interpolation algorithm to generate an optimized interpolation algorithm; generating a non-oscillation cloud picture according to dam body physical attributes of a preset dam structure and an optimization interpolation algorithm; performing preset-size grid block division on the non-oscillation cloud picture to generate a cloud picture grid node set; performing parallel processing on each cloud picture grid node in the cloud picture grid node set to generate an accelerated interpolation result; and performing incremental updating on the accelerated interpolation result to generate an updated interpolation result. According to the implementation mode, the accuracy, efficiency and engineering applicability of dam settlement interpolation are improved.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and specifically to a method and apparatus for generating dam surface settlement cloud maps based on an adaptive interpolation model. Background Technology

[0002] Dam surface settlement monitoring is a core component of the safe operation and maintenance of water conservancy projects. Its core task is to extrapolate the overall deformation trend through displacement data from a limited number of monitoring points and generate high-precision settlement cloud maps to support risk decision-making. Traditional methods mainly rely on spatial interpolation algorithms, but these are limited by the complex structure of dams and the sparsity of monitoring data.

[0003] However, when using the above methods, the following technical problems often arise: mainstream algorithms (such as Inverse Distance Weighting (IDW) and Kriging) employ fixed parameter configurations, making it difficult to adapt to the differences in mechanical properties among different types of dams. For example, concrete dams, due to their high material homogeneity, use high-power IDW to capture local deformations, while earth-rock dams, due to significant material stratification, rely on the variogram function in Kriging to model spatial correlations. However, existing systems generally lack dynamic algorithm switching mechanisms, leading to significant errors in single models within heterogeneous dam bodies. Dam boundaries (such as abutments and toes), being in a state of free deformation, are easily affected by data truncation effects during interpolation and extrapolation, generating spurious settlement trends. Although this can be mitigated by manually setting virtual points, it relies on experience and cannot be dynamically updated. High-precision algorithms (such as Radial Basis Function Interpolation (RBF) and Co-Kriging) have high time complexity. When there are more than 200 monitoring points, the generation delay of a single frame cloud image exceeds 10 seconds, which is difficult to meet the needs of high-frequency monitoring. Existing acceleration schemes mostly use grid downsampling, but this leads to the loss of details and makes it impossible to identify millimeter-level cracks. Traditional weighting formulas do not consider the gradient changes caused by sudden changes in local loads (such as a sudden drop in reservoir water level), which weakens the ability to detect risks such as seepage damage. Summary of the Invention

[0004] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0005] Some embodiments of this disclosure propose a method and apparatus for generating dam surface settlement cloud maps based on an adaptive interpolation model to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide a method for generating a dam surface settlement cloud map based on an adaptive interpolation model. The method includes: extracting features from multi-dimensional monitoring point data of a preset dam structure to generate a dam scene profile, wherein the dam scene profile includes: monitoring point density, dam material type, geometric shape, and historical settlement pattern; generating an optimal interpolation algorithm based on the dam scene profile; optimizing the optimal interpolation algorithm to generate an optimized interpolation algorithm; generating a non-oscillating cloud map based on the dam's physical properties and the optimized interpolation algorithm; dividing the non-oscillating cloud map into grid blocks of a preset size to generate a cloud map grid node set; performing parallel processing on each cloud map grid node in the cloud map grid node set to generate an accelerated interpolation result; and incrementally updating the accelerated interpolation result to generate an updated interpolation result.

[0007] Secondly, some embodiments of this disclosure provide a device for generating dam surface settlement cloud maps based on an adaptive interpolation model. The device includes: a processing unit configured to extract features from multi-dimensional monitoring point data of a preset dam structure to generate a dam scene profile, wherein the dam scene profile includes: monitoring point density, dam material type, geometric shape, and historical settlement pattern; a first generation unit configured to generate an optimal interpolation algorithm based on the dam scene profile; an optimization unit configured to optimize the optimal interpolation algorithm to generate an optimized interpolation algorithm; a second generation unit configured to generate a non-oscillating cloud map based on the dam physical properties of the preset dam structure and the optimized interpolation algorithm; a partitioning unit configured to partition the non-oscillating cloud map into grid blocks of a preset size to generate a cloud map grid node set; a processing unit configured to perform parallel processing on each cloud map grid node in the cloud map grid node set to generate an accelerated interpolation result; and an update unit configured to incrementally update the accelerated interpolation result to generate an updated interpolation result.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] The various embodiments of this disclosure have the following beneficial effects: The method for generating dam surface settlement cloud maps based on an adaptive interpolation model, as described in some embodiments of this disclosure, specifically involves constructing a monitoring density-material stiffness dual-factor decision tree and matching the optimal interpolation algorithm (e.g., Inverse Distance Weighting (IDW), Kriging, or RBF) in real time to address the insufficient adaptability of a single model. Finite element simulation data and monitoring data are integrated to establish a stiffness gradient-sensitive weighting function, ensuring that the interpolation results conform to mechanical constitutive relations. Virtual boundary points are automatically generated based on the dam body contour and stress distribution, and an anti-oscillation filtering algorithm is used to eliminate edge extrapolation distortion. A GPU-parallelized interpolation kernel and an incremental mesh update strategy are developed to achieve sub-second real-time rendering of high-density meshes (1cm accuracy). The spatial correlation radius is dynamically adjusted according to the dam's functional zoning (e.g., core wall, rockfill, and filter layer) to suppress abnormal transmission errors across material regions. The adaptive interpolation model, based on real-time switching algorithms (e.g., IDW, Kriging, or RBF) for parameters such as monitoring density and material stiffness, solves the rigidity problem of traditional single models. Field measurements show that the interpolation error in the concrete dam core wall region has decreased from ±4.5mm to ±1.2mm. Gradient-sensitive weight adjustment enhances the ability to capture local deformation, improving the resolution of settlement gradient abrupt change zones (>5mm / m) by 40%. Dam stiffness parameters and finite element simulation data are introduced as interpolation constraints to avoid mechanical contradictions driven purely by data. Virtual anchor point generation and anti-oscillation filtering techniques effectively suppress boundary distortion and reduce errors in the dam toe region, while supporting dynamic anchor point updates to adapt to real-time changes in monitoring point data. GPU parallelization and incremental update strategies achieve sub-second response times, supporting single-node processing of 100,000 grid points per second, significantly accelerating compared to traditional Kriging. Level of Detail (LOD) rendering caters to both panoramic and local magnification needs, reducing memory usage by 70%. The solution is adaptable to various types of dams, including rigid / flexible dams and straight / arch dams, and is compatible with multiple sources of sensors such as Global Navigation Satellite System (GNSS) and hydrostatic leveling through a physical-data fusion mechanism, demonstrating outstanding engineering generalization capabilities. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1 This is a flowchart of some embodiments of the method for generating dam surface settlement cloud maps based on an adaptive interpolation model according to the present disclosure; Figure 2These are schematic diagrams of some embodiments of the device for generating dam surface settlement cloud maps based on an adaptive interpolation model according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0013] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0014] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0015] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0018] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] Figure 1 A flowchart 100 is shown, illustrating some embodiments of a method for generating dam surface settlement contour maps based on an adaptive interpolation model according to this disclosure. This method for generating dam surface settlement contour maps based on an adaptive interpolation model includes the following steps: Step 101: Extract features from the multi-dimensional monitoring point data of the preset dam structure to generate a dam scene profile.

[0020] In some embodiments, the execution entity (e.g., a computing device) of the method for generating dam surface settlement cloud maps based on an adaptive interpolation model can extract features from multi-dimensional monitoring point data of a preset dam structure to generate a dam scene profile. This dam scene profile includes: monitoring point density, dam material type, geometric shape, and historical settlement patterns.

[0021] Here, the monitoring point density can be the number of monitoring points per unit area. For example, a concrete dam surface with 10 points per 100 square meters has a density of 0.1 points / square meter. The dam material type can be a categorized dam material, such as "rigid" (concrete dam, masonry dam) or "flexible" (earth-rock dam, asphalt core dam). For example, the dam material type could be "earth-rock dam." The geometric shape can be the overall shape of the dam; for example, it could be "straight," "arch," or "gravity-type." The historical settlement pattern can be a settlement law derived from statistical analysis of historical data. For example, the historical settlement pattern could be "settlement in the dam heel area is consistently greater than that in the dam crest." The multidimensional monitoring point data can include, but is not limited to, at least one of the following: monitoring point geometry and historical settlement pattern of the monitoring points.

[0022] Optionally, the aforementioned implementing entity can extract features from the multi-dimensional monitoring point data of the preset dam structure through the following steps to generate a dam scene profile: The first step is to determine the monitoring point density based on the multi-dimensional monitoring point data of the aforementioned pre-set dam structure.

[0023] As an example, the aforementioned implementing entity can determine the monitoring point density by calculating the number of monitoring points per unit area (e.g., per 100 square meters) of the multi-dimensional monitoring point data of the aforementioned preset dam structure.

[0024] The second step is to identify the dam material type of the aforementioned preset dam structure in order to generate the dam material type.

[0025] As an example, the aforementioned executing entity can identify the dam material type of the preset dam structure by querying a pre-defined engineering database, thereby generating the dam material type. The engineering database is a database containing dam design data recorded during the dam construction process.

[0026] The third step is to extract the geometric shape of the pre-set dam structure to generate the geometric shape.

[0027] As an example, the aforementioned implementing entity can determine the geometry of the aforementioned pre-designed dam structure by calculating the curvature of the dam axis.

[0028] The fourth step is to statistically analyze the historical settlement patterns of the aforementioned pre-defined dam structure to generate a historical settlement pattern.

[0029] As an example, the aforementioned implementing entity can use statistical analysis methods (such as standard deviation) to statistically analyze the historical settlement patterns of the aforementioned preset dam structure in order to generate historical settlement patterns.

[0030] The fifth step is to determine the above-mentioned monitoring point density, dam material type, geometric shape, and historical settlement pattern as the dam scene profile.

[0031] As an example, the aforementioned implementing entity can integrate the aforementioned monitoring point density, dam material type, geometric shape, and historical settlement pattern into a dam scene profile.

[0032] Step 102: Generate the optimal interpolation algorithm based on the above dam scene profile.

[0033] In some embodiments, the aforementioned execution entity can generate an optimal interpolation algorithm based on the aforementioned dam scene profile.

[0034] Here, the optimal interpolation algorithm described above can be Inverse Distance Weighting (IDW). Alternatively, it can be the Kriging algorithm.

[0035] Optionally, the aforementioned execution entity can generate the optimal interpolation algorithm based on the aforementioned dam scene profile through the following steps: The first step is to select candidate algorithms for the above-mentioned dam scene profile to generate a candidate algorithm set.

[0036] Here, the aforementioned candidate algorithm set includes, but is not limited to, at least one of the following: Inverse Distance Weighted (IDW), Kriging, and Radial Basis Function (RBF). Inverse Distance Weighted (IDW) is suitable for scenarios where monitoring points are uniformly distributed and deformation is gradual. Kriging, based on variograms, models spatial correlation and is suitable for heterogeneous materials (e.g., earth-rock dams) and regions with trend changes. Radial Basis Function fits complex nonlinear relationships through global basis functions and is suitable for scenarios requiring high smoothness.

[0037] As an example, the aforementioned execution entity can select candidate algorithms based on decision tree logic for the aforementioned dam scene profile to generate a candidate algorithm set. Specifically: when the monitoring point density is ≥0.1 points / square meter and the dam is made of rigid material, IDW is selected, p=2, where p is a power parameter controlling the rate at which the influence of distance on the weight decays. The search radius is 1.2 times the average spacing. Otherwise, if the monitoring point density is less than 0.05 points / square meter and spatial autocorrelation exists (variance function R0), the algorithm is selected. 2When the variance is greater than 0.8, choose Kriging, and set the mutation function type to exponential. Otherwise, if a delay greater than 2 seconds is allowed and global smoothing is required, choose RBF, with the basis function being a Gaussian kernel function and a smoothing factor of 0.3.

[0038] The second step is to switch the candidate algorithm set in response to the determination that the multidimensional monitoring point data meets the preset algorithm switching conditions, so as to generate the optimal interpolation algorithm.

[0039] Here, the aforementioned preset algorithm switching conditions can be pre-defined conditions that can trigger algorithm switching. For example, the aforementioned preset algorithm switching conditions can be "monitoring point density change exceeds 20%, local settlement gradient abrupt change, user manually specifies accuracy / efficiency priority".

[0040] As an example, the aforementioned execution entity can recalculate the input parameters when the monitoring point data (e.g., displacement or settlement information collected by GNSS, hydrostatic level, etc., including point coordinates, timestamps, settlement values, etc.) is updated. Switching between the three candidate algorithms is triggered if any of the following conditions are met: monitoring point density change exceeds 20%, abrupt change in local settlement gradient, or the user manually specifies accuracy / efficiency priority. To avoid abrupt changes in the cloud map caused by algorithm switching, weighted hybrid interpolation is used (e.g., IDW and Kriging results are mixed at a ratio of 0.7:0.3), with a transition time ≤0.5 seconds.

[0041] Step 103: Optimize the above optimal interpolation algorithm to generate an optimized interpolation algorithm.

[0042] In some embodiments, the execution entity may optimize the optimal interpolation algorithm to generate an optimized interpolation algorithm.

[0043] Optionally, the aforementioned execution entity can optimize the optimal interpolation algorithm by performing the following steps to generate an optimized interpolation algorithm: The first step is to determine the local settlement gradient of the multidimensional monitoring point data based on the above optimal interpolation algorithm, so as to generate local settlement gradient values.

[0044] Here, the aforementioned local settlement gradient values ​​represent the degree of drastic settlement changes.

[0045] As an example, the aforementioned implementing entity can determine the local settlement gradient of the multi-dimensional monitoring point data by dividing the settlement difference between two adjacent points by the distance, based on the optimal interpolation algorithm described above, to generate a local settlement gradient value. For instance, if points A and B are 1 meter apart and their settlement differs by 5 millimeters, the gradient is 5 mm / m. The larger the gradient value, the more abnormal the deformation in that area, potentially indicating a crack or leakage risk zone.

[0046] As yet another example, the aforementioned implementing entity can monitor multi-dimensional data points. Calculate its nearest neighbor. gradient: .in Indicates the monitoring points currently being calculated; , Indicates monitoring point The plane position coordinates in the dam surface coordinate system.

[0047] , Indicates monitoring point The planar position coordinates. Indicates monitoring point The settlement value. Indicates monitoring point The settlement value.

[0048] The second step is to determine the density of monitoring points within a preset radius for the preset interpolation point data, so as to generate monitoring point density values.

[0049] Here, the interpolation point data mentioned above can be the grid point data for which settlement values ​​need to be calculated. The preset radius mentioned above can be a pre-set radius. R represents the preset radius.

[0050] As an example, the aforementioned execution entity can use the data to be interpolated as the center and count the number of monitoring points N within a circular area with a radius of R, with a density of... .

[0051] The third step involves expanding the preset radius and optimizing the preset power parameter in response to the determination that the density value of the monitoring points is less than the preset minimum density value, thereby obtaining the expanded radius and the optimized power parameter.

[0052] Here, the aforementioned preset minimum density value can be a pre-set minimum density value.

[0053] As an example, the aforementioned executing entity can respond to determining that the density value of the aforementioned monitoring points is less than a preset minimum density value, i.e. The search radius is expanded from R to 2R to avoid interpolation holes. The power factor is adjusted based on the monitoring point density values. Sparse regions reduce To smooth the results: .in, This represents the initial IDW exponentiation parameter. α is derived through training with historical data (typical value 0.05~0.2).

[0054] The fourth step is to optimize the optimal interpolation algorithm based on the local settlement gradient value, the expanded radius, and the optimized power parameter to generate an optimized interpolation algorithm.

[0055] As an example, the aforementioned execution entity can use the local settlement gradient value as a weight correction factor: .in, β represents the initial weights. β is the sensitivity coefficient (default 0.5). The larger the gradient, the greater the weight increase, enhancing the ability to express details in highly deformable regions. The absolute value of the local settlement gradient at the monitoring point is used to optimize the above optimal interpolation algorithm and generate an optimized interpolation algorithm.

[0056] Step 104: Generate an oscillation-free cloud map based on the preset physical properties of the dam structure and the above-mentioned optimized interpolation algorithm.

[0057] In some embodiments, the aforementioned execution entity can generate an oscillation-free cloud map based on the physical properties of the dam body of the preset dam structure and the aforementioned optimized interpolation algorithm.

[0058] Optionally, the aforementioned executing entity can generate an oscillation-free cloud map based on the preset physical properties of the dam structure and the aforementioned optimized interpolation algorithm through the following steps: The first step is to construct a co-kriging model of the physical properties of the dam body based on the above-mentioned preset dam structure in order to generate settlement values ​​of the data points to be interpolated.

[0059] As an example, the aforementioned implementing entity can introduce the elastic modulus E of the dam body partition as an auxiliary variable to construct a co-kriging model: .in, Indicates the point to be interpolated The settlement value. This represents the global offset. Indicates known monitoring points The settlement value. and The weighting coefficients are obtained through optimization using the cooperative mutation function. This represents the weighting coefficient related to the elastic modulus. This indicates the number of known monitoring points. This indicates the number of elastic modulus partitions.

[0060] The second step involves linearly weighting the settlement values ​​of the data points to be interpolated and the preset historical finite element simulation results based on the optimized interpolation algorithm described above, in order to generate the final settlement prior field.

[0061] As an example, the aforementioned implementing entity can generate a priori settlement field based on the finite element analysis results of historical load conditions. , and real-time interpolation results Linear weighting: The λ value is dynamically adjusted based on the residuals between the monitoring points and the simulation data: if the mean residual is <2mm, λ=0.8; otherwise, λ=0.5, thus obtaining the final settlement prior field.

[0062] The third step is to perform virtual detection anchor point fusion on the aforementioned final settlement test field to generate an anchor point fused settlement field.

[0063] As an example, the aforementioned execution entity can generate virtual points by extending 0.5L (where L is the average spacing between monitoring points) outside the dam outline. The virtual points are then assigned the average value of their nearest real monitoring points. The noise margin is 3σ (σ is the standard deviation of historical data). When the change in monitoring points near the contour line is >2mm, the virtual point values ​​are recalculated to generate the anchor point fusion settlement field.

[0064] The fourth step is to filter the above-mentioned anchor point fusion settlement field to generate an oscillation-free cloud map.

[0065] As an example, the above-mentioned execution entity can smooth the edge regions of the RBF interpolation result using Gaussian filtering, with the kernel function being: Parameter settings: kernel size = 5×5 pixels, σ = 1.5. Median filtering is used to detect abrupt changes in color patches in the cloud map caused by uneven distribution in the interpolation region. A 3×3 median filter is used in the gradient abrupt change region to generate an oscillating cloud map.

[0066] Step 105: Divide the above non-oscillating cloud map into grid blocks of a preset size to generate a cloud map grid node set.

[0067] In some embodiments, the execution entity may divide the non-oscillating cloud map into grid blocks of a preset size to generate a set of cloud map grid nodes.

[0068] Here, the aforementioned preset size grid block can be a pre-defined 256×256 grid block.

[0069] As an example, the aforementioned execution entity can divide the dam surface corresponding to the non-oscillating cloud map into 256×256 grid blocks.

[0070] Step 106: Perform parallel processing on each cloud map grid node in the above cloud map grid node set to generate accelerated interpolation results.

[0071] In some embodiments, the execution entity may perform parallel processing on each cloud map grid node in the cloud map grid node set to generate accelerated interpolation results.

[0072] As an example, the aforementioned execution entity can use multiple CUDA threads to process each cloud grid node in the cloud grid node set in parallel to generate accelerated interpolation results.

[0073] Step 107: Incrementally update the above accelerated interpolation results to generate updated interpolation results.

[0074] In some embodiments, the execution entity may incrementally update the accelerated interpolation results to generate updated interpolation results.

[0075] As an example, the aforementioned execution entity can calculate the displacement of the monitoring point. This represents the settlement value of the monitoring point at the current moment; This indicates the settlement value at the monitoring point at the previous moment. (Mark) The region containing points >1mm. By re-interpolating locally, only a circular region with a radius of 2m centered on the point of change is re-interpolated, reducing the amount of calculation by 60%~80% to generate updated interpolation results.

[0076] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a device for generating dam surface settlement cloud maps based on an adaptive interpolation model. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this device for generating dam surface settlement cloud maps based on an adaptive interpolation model can be specifically applied to various electronic devices.

[0077] like Figure 2 As shown, the device 200 for generating dam surface settlement cloud maps based on an adaptive interpolation model in some embodiments includes: a processing unit 201, a first generation unit 202, an optimization unit 203, a second generation unit 204, a partitioning unit 205, a processing unit 206, and an updating unit 207. The system includes the following components: a processing unit 201, configured to extract features from multi-dimensional monitoring point data of a preset dam structure to generate a dam scene profile, which includes monitoring point density, dam material type, geometric shape, and historical settlement pattern; a first generation unit 202, configured to generate an optimal interpolation algorithm based on the dam scene profile; an optimization unit 203, configured to optimize the optimal interpolation algorithm to generate an optimized interpolation algorithm; a second generation unit 204, configured to generate a non-oscillating cloud map based on the physical properties of the preset dam structure and the optimized interpolation algorithm; a partitioning unit 205, configured to partition the non-oscillating cloud map into grid blocks of a preset size to generate a cloud map grid node set; a processing unit 206, configured to perform parallel processing on each cloud map grid node in the cloud map grid node set to generate an accelerated interpolation result; and an update unit 207, configured to incrementally update the accelerated interpolation result to generate an updated interpolation result.

[0078] It is understandable that the elements and references recorded in the device 200 for generating dam surface settlement cloud maps based on the adaptive interpolation model are... Figure 1The steps described in the method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 for generating dam surface settlement cloud maps based on an adaptive interpolation model and the units contained therein, and will not be repeated here.

[0079] The following is for reference. Figure 3 It illustrates a schematic diagram of the structure of an electronic device (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 3 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0080] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be 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. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0081] In one embodiment, the processor is used to run a computer program stored in a memory to perform the following steps: extracting features from multi-dimensional monitoring point data of a preset dam structure to generate a dam scene profile, wherein the dam scene profile includes: monitoring point density, dam material type, geometric shape, and historical settlement pattern; generating an optimal interpolation algorithm based on the dam scene profile; optimizing the optimal interpolation algorithm to generate an optimized interpolation algorithm; generating a non-oscillating cloud map based on the dam physical properties of the preset dam structure and the optimized interpolation algorithm; dividing the non-oscillating cloud map into grid blocks of a preset size to generate a cloud map grid node set; performing parallel processing on each cloud map grid node in the cloud map grid node set to generate an accelerated interpolation result; and incrementally updating the accelerated interpolation result to generate an updated interpolation result.

[0082] This disclosure also provides a computer-readable storage medium storing a computer program, which includes program instructions. When the program instructions are executed, the method implemented can be referred to the various embodiments of the method for generating dam surface settlement cloud maps based on an adaptive interpolation model disclosed above.

[0083] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0084] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0085] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for generating settlement cloud maps of dam surfaces based on an adaptive interpolation model, characterized in that, include: Feature extraction is performed on the multi-dimensional monitoring point data of the preset dam structure to generate a dam scene profile, wherein the dam scene profile includes: monitoring point density, dam material type, geometric shape and historical settlement pattern; Based on the dam scene profile, generate the optimal interpolation algorithm; The optimal interpolation algorithm is optimized to generate an optimized interpolation algorithm; Based on the physical properties of the dam body of the preset dam structure and the optimized interpolation algorithm, an oscillation-free cloud map is generated; The non-oscillating cloud map is divided into grid blocks of a preset size to generate a cloud map grid node set; Parallel processing is performed on each cloud map grid node in the cloud map grid node set to generate accelerated interpolation results; The accelerated interpolation results are incrementally updated to generate updated interpolation results.

2. The method according to claim 1, characterized in that, The step of extracting features from multi-dimensional monitoring point data of the preset dam structure to generate a dam scene profile includes: The monitoring point density is determined by analyzing the multi-dimensional monitoring point data of the preset dam structure to generate the monitoring point density. The material type of the dam body in the preset dam structure is identified to generate the dam body material type; The geometric shape of the preset dam structure is extracted to generate the geometric shape; The historical settlement patterns of the preset dam structure are statistically analyzed to generate historical settlement patterns; The density of monitoring points, the type of dam material, the geometric shape, and the historical settlement pattern are used to create a dam scene profile.

3. The method according to claim 1, characterized in that, The step of generating the optimal interpolation algorithm based on the dam scene image includes: Candidate algorithms are selected from the dam scene profile to generate a candidate algorithm set; In response to determining that the multidimensional monitoring point data meets the preset algorithm switching conditions, the candidate algorithm set is switched to generate the optimal interpolation algorithm.

4. The method according to claim 1, characterized in that, The optimization of the optimal interpolation algorithm to generate an optimized interpolation algorithm includes: According to the optimal interpolation algorithm, the local settlement gradient of the multidimensional monitoring point data is determined to generate local settlement gradient values. The density of monitoring points within a preset radius is determined for the preset interpolation point data to generate monitoring point density values; In response to determining that the density value of the monitoring point is less than the preset minimum density value, the preset radius is expanded and the preset power parameter is optimized to obtain the expanded radius and the optimized power parameter; Based on the local settlement gradient value, the expanded radius, and the optimized power parameter, the optimal interpolation algorithm is optimized to generate an optimized interpolation algorithm.

5. The method according to claim 1, characterized in that, The step of generating an oscillation-free cloud map based on the pre-defined physical properties of the dam structure and the optimized interpolation algorithm includes: A co-kriging model is constructed for the physical properties of the dam body of the preset dam structure to generate settlement values ​​of the data points to be interpolated; Based on the optimized interpolation algorithm, the settlement values ​​of the data to be interpolated and the preset historical finite element simulation results are linearly weighted to generate the final settlement prior field. Virtual detection anchor point fusion is performed on the final settlement prior field to generate an anchor point fused settlement field; The anchor point fusion settlement field is filtered to generate an oscillation-free cloud map.

6. A device for generating dam surface settlement cloud maps based on an adaptive interpolation model, characterized in that, include: The processing unit is configured to extract features from multi-dimensional monitoring point data of a preset dam structure to generate a dam scene profile, wherein the dam scene profile includes: monitoring point density, dam material type, geometric shape and historical settlement pattern. The first generation unit is configured to generate the optimal interpolation algorithm based on the dam scene image; An optimization unit is configured to optimize the optimal interpolation algorithm to generate an optimized interpolation algorithm; The second generation unit is configured to generate an oscillation-free cloud map based on the physical properties of the dam body of the preset dam structure and the optimized interpolation algorithm. The partitioning unit is configured to divide the non-oscillating cloud map into grid blocks of a preset size to generate a set of cloud map grid nodes; The processing unit is configured to perform parallel processing on each cloud map grid node in the cloud map grid node set to generate accelerated interpolation results. The update unit is configured to incrementally update the accelerated interpolation result to generate an updated interpolation result.

7. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the computer program, when executed by a processor, implements the method as described in any one of claims 1 to 5.

Images