A method and system for evaluating soil-rock ratio of mountain airports based on progressive spatial interpolation

Abstract

The present invention belongs to the interdisciplinary field of civil engineering, geological engineering, and artificial intelligence. Specifically, it discloses a method and system for assessing the earth-rock ratio at mountain airports based on progressive spatial interpolation. The method comprises the following steps: S1, data acquisition; S2, boundary elevation prediction: constructing an initial Delaunay triangulation based on the acquired data, and using a regionally adapted spatial interpolation algorithm at the centroid of each triangle to predict the boundary elevation; S3, constructing a complete and highly accurate set of boundary points; S4, calculating the volume of each earthwork and the earth-rock ratio; and S5, dynamically updating interpolation model parameters through an online learning mechanism based on real-time sensor data changes. Dynamic Bayesian networks (DBNs) and evidence theory (DSTs) are introduced to model the uncertainty of terrain disturbances and lithologic changes, and Monte Carlo simulation is used to generate confidence intervals and predicted distributions for the earth-rock ratio. The present invention is suitable for efficiently and accurately determining the earth-rock interface and calculating the earth-rock ratio during engineering surveys, while also quantifying the uncertainty of the calculation results.

Description

Technical Field

[0001] The present invention relates to the interdisciplinary field of civil engineering, geological engineering and artificial intelligence, and in particular to a method and system for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation. Background Art

[0002] The soil-rock ratio, defined as the ratio of the natural volumes of various types of soil and rock used for cut and fill within a given area, is a key indicator in engineering surveys, directly impacting aspects such as material allocation, construction costs, project efficiency, and environmental protection. With the rapid advancement of infrastructure projects such as airports in mountainous areas across my country, the requirements for the accuracy and reliability of soil-rock ratio calculations are increasing.

[0003] Mountain airports are typically located on gently sloping hills or plateaus, characterized by significant topography and frequent changes in rock and soil types, requiring large-scale deep excavation and high-fill operations. In this context, traditional soil-rock ratio assessment faces numerous challenges. Firstly, limited and sparsely distributed drilling data makes it difficult to fully reflect the true morphology of the underground soil-rock interface. Secondly, existing methods generally lack the ability to respond to geological disturbances, data uncertainties, and real-time changes.

[0004] Currently, two-dimensional methods widely used in engineering (such as the average section method and the prism method) are simple to use and low-cost, but they ignore the complexity of geological spatial distribution and produce significant approximation errors. Three-dimensional methods are theoretically more accurate and can simulate actual stratigraphic fluctuations for volumetric calculations, but they rely heavily on high-density spatial data, limiting their application in mountainous engineering.

[0005] In recent years, some researchers have attempted to improve the three-dimensional capabilities of earthwork calculations by combining digital modeling tools such as GIS, TIN, and DEM. These methods have been initially applied in projects such as the new Baiyun Airport and a mine in Yunnan. However, most methods still focus solely on the elevation difference between the surface and the design surface, failing to achieve high-precision reconstruction and dynamic identification of the critical underground soil-rock interface. This error is particularly pronounced in areas with significant lithologic variation.

[0006] In addition, most existing methods are static modeling methods and lack the ability to integrate real-time sensor data to dynamically update the model. At the same time, the lack of a theoretical framework to quantify prediction uncertainty and model credibility also limits the value of the results in safety assessment in engineering design.

[0007] Therefore, there is an urgent need to develop a progressive spatial interpolation method based on limited survey data and sensor fusion, combined with an uncertainty quantification analysis mechanism, to break through the current bottlenecks in continuous identification, volume analysis, and dynamic updating of soil-rock interfaces, thereby significantly improving the accuracy and intelligence of soil-rock ratio assessment in complex engineering scenarios such as mountain airports. Summary of the Invention

[0008] In order to solve the problems existing in the prior art, the present invention provides a method and system for evaluating the earth-rock ratio of mountain airports based on progressive spatial interpolation, which solves the problems mentioned in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solution: a method for evaluating the earth-rock ratio of mountain airports based on progressive spatial interpolation, comprising the following steps:

[0010] S1, data collection;

[0011] S2. Boundary elevation prediction: Based on the collected data, the initial Delaunay triangulation is constructed, and the boundary elevation is predicted using a regionally adapted spatial interpolation algorithm at the center of each triangle;

[0012] S3. Construct a complete and high-precision demarcation point set: Add the new demarcation points predicted in step S2 to the point set, reconstruct the triangulation network, and determine whether to continue iterating; through multiple rounds of progressive encryption, optimize spatial coverage and prediction accuracy, and gradually construct a complete and high-precision demarcation point set;

[0013] S4. Calculate the volume of each earthwork and the ratio of earthwork to rockwork: Based on the final generated boundary point set, fit the earthwork boundary surface, merge it with the digital terrain model (DTM) and the design elevation surface, and construct a closed stratum 3D model. Calculate the volume of each earthwork and the ratio of earthwork to rockwork based on the model.

[0014] S5. Generate confidence intervals and predicted distributions of soil-rock ratios: Combined with real-time sensor data changes, the interpolation model parameters are dynamically updated through an online learning mechanism. Dynamic Bayesian networks (DBNs) and evidence theory (DSTs) are introduced to model the uncertainty of terrain disturbances and lithologic changes. Monte Carlo simulations are then used to generate confidence intervals and predicted distributions of soil-rock ratios.

[0015] Preferably, in step S1, the soil and rock classification standards are determined according to the project overview and relevant specifications, the drilling data is processed, and the three-dimensional coordinates of typical soil and rock boundary points are extracted; then, geological and topographic data are collected in real time using multi-source equipment, an initial spatial interpolation data set is established, and each point is assigned a dynamically updated timestamp and confidence weight.

[0016] Preferably, the data collection method includes drilling data extraction and real-time survey data fusion; the multi-source equipment includes geological sensors, elevation sensors and GNSS positioning equipment.

[0017] Preferably, in step S2, the following is specifically included:

[0018] S21. Use the drilling demarcation points to construct a Delaunay triangulation network, and increase the density of points or grids in areas with severe terrain fluctuations to improve the accuracy of interpolation prediction;

[0019] S22, automatically generate the centroid of the triangulation network and select the spatial interpolation method based on regional characteristics;

[0020] S23. Calculate the covariance or joint variance of the prediction results in combination with the selected interpolation model as an indicator for evaluating the interpolation accuracy and uncertainty.

[0021] Preferably, the selecting of the spatial interpolation method based on regional characteristics specifically includes:

[0022] For areas with drastic terrain changes, kernel regression (KR) or inverse distance weighted interpolation (IDW) methods are used.

[0023] For areas with flat terrain, choose Gaussian process regression (GPR) or Kriging interpolation method.

[0024] Multi-model ensemble learning is introduced in abnormal areas, including local regression combined with random forest to supplement the prediction method.

[0025] Preferably, in step S3, determining whether to continue iteration specifically includes: each round of interpolation results participates in a new round of triangulation network construction, and determining whether to terminate the iteration based on the prediction error convergence criterion, the spatial point density balance criterion and the uncertainty threshold criterion.

[0026] Preferably, in step S5, the following is specifically included:

[0027] S51. For each new data point, assign a dynamic confidence weight ω:

[0028]

[0029] Among them, λ and μ are adjustable parameters, δ is the sampling delay, and σ is the noise index;

[0030] Through dynamic weights, the data set is fused: D*=D∪{(x i ,y i ,z i ,ω i )},x i ,y i is the plane coordinate of the i-th data point, z i is the real-time observation value of the point, ω i is the dynamic weight of the i-th data point; D is the existing data set, D * The dataset after fusion update;

[0031] S52, construct dynamic Bayesian network DBN to model the soil-rock ratio change trend, assuming S t is the soil-rock ratio state at time t, indicating the soil-rock ratio information of the current area, O t is the observation value at time t, collected by the sensor, then the Bayesian update formula is as follows:

[0032]

[0033] P(S t-1 |O 1:t-1 ) is the posterior distribution of the state at the previous moment, P(S t |S t-1 ) is the state prediction model, P(O t |S t ) is the likelihood model of the current observation, P(O t |O 1:t-1 ) is used for normalization and does not participate in the final prediction, dS t-1 is the integration of the state variables, combined with the current observation P(O t |S t ) is updated to the new posterior P(S t |O 1:t ), dynamically adjust the soil and rock prediction surface;

[0034] S53, introduce evidence theory DST for joint inference, set the soil-rock ratio state of a certain area as θ, judge the rock property, and different models or sensors give different confidence values Among them, the conflict Among them, A and B are the possible state subsets proposed by different models, and m1(A)·m2(B) is the confidence level of each subset. Finally, by reasonably integrating data from different sources and combining Monte Carlo simulation, the soil-rock ratio confidence interval and joint prediction distribution are generated.

[0035] On the other hand, to achieve the above-mentioned purpose, the present invention further provides the following technical solution: a soil-rock ratio evaluation system for mountain airports based on progressive spatial interpolation, the system comprising the following modules:

[0036] Data acquisition module;

[0037] Boundary elevation prediction module: constructs the initial Delaunay triangulation based on the collected data, and uses the regional adaptive spatial interpolation algorithm at the center of each triangle to predict the boundary elevation;

[0038] A complete and high-precision demarcation point set construction module: This module incorporates the new demarcation points predicted by the demarcation elevation prediction module into the point set, reconstructs the triangulation network, and determines whether to continue iterating. Through multiple rounds of progressive encryption, the module optimizes spatial coverage and prediction accuracy, gradually constructing a complete and high-precision demarcation point set.

[0039] Module for calculating the volume of each earthwork and the ratio of earthwork to rockwork: Based on the final generated boundary point set, the earthwork boundary surface is fitted and integrated with the digital terrain model (DTM) and the designed elevation surface to construct a closed stratum 3D model. Based on the model, the volume of each earthwork and the ratio of earthwork to rockwork are calculated.

[0040] Soil-rock ratio confidence interval and prediction distribution generation module: Combined with real-time sensor data changes, the interpolation model parameters are dynamically updated through an online learning mechanism. Dynamic Bayesian network DBN and evidence theory DST are introduced to model the uncertainty of terrain disturbance and rock property changes, and Monte Carlo simulation is combined to generate soil-rock ratio confidence interval and prediction distribution.

[0041] On the other hand, to achieve the above-mentioned purpose, the present invention further provides the following technical solution: an electronic device, comprising: a processor; and a memory for storing one or more programs;

[0042] When the one or more programs are executed by a processor, the processor is enabled to execute the method for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation.

[0043] On the other hand, to achieve the above-mentioned purpose, the present invention also provides the following technical solution: a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation.

[0044] The beneficial effects of the present invention are:

[0045] 1) This paper proposes a new strategy using the centroid of the triangulated network as the interpolation prediction point, which effectively fills the spatial gaps between drilling points, improves the spatial data distribution balance and interpolation accuracy, and is particularly suitable for the problem of sparse and uneven distribution of survey points in complex mountainous terrain;

[0046] 2) This paper introduces a covariance structure to quantify interpolation uncertainty. Based on the uncertainty indicators output by models such as GPR and KR, it uses Monte Carlo simulation to achieve a diverse expression of soil-rock interface prediction results, thereby providing confidence intervals for soil-rock ratio estimation and enhancing risk perception capabilities for engineering design.

[0047] 3) This invention integrates intelligent uncertainty modeling technologies such as dynamic Bayesian networks and evidence theory for the first time, enabling real-time perception and response to geological disturbances and construction dynamics.

[0048] 4) This invention builds a dynamic update mechanism driven by real-time multi-source sensor data, which significantly improves the timeliness, stability and engineering adaptability of interpolation modeling;

[0049] 5) The present invention achieves continuous correction and self-enhancement of the interpolation model through real-time access to IoT sensor data and a dynamic update mechanism for model parameters, establishes a complete soil-rock ratio prediction confidence interval output system, and significantly enhances the system's response to geological disturbances and dynamic changes in construction. The method of the present invention has good versatility. In addition to mountain airports, it is also suitable for soil-rock ratio assessment in similar geological environments such as mountain roads, railways, and mines. It has significant engineering promotion value and practical prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of the method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation in Example 1;

[0051] FIG2( a ) is a schematic diagram of the spatial distribution of soil-rock boundary points extracted in CAD in Example 2;

[0052] FIG2( b ) is a Delaunay triangulation diagram initially constructed by extracting the soil-rock boundary point in Example 2;

[0053] FIG3( a ) is a triangulated mesh diagram reconstructed after interpolation at the centroid of each triangulated mesh in Example 2;

[0054] FIG3( b ) is a triangulated mesh diagram reconstructed after two interpolations at the centroid of each triangulated mesh in Example 2;

[0055] FIG4( a ) is a schematic diagram of three-dimensional solid modeling of the soil-rock interface and the design elevation surface in Example 2;

[0056] FIG4( b ) is a schematic diagram of three-dimensional solid modeling of the terrain surface and the design elevation surface in Example 1;

[0057] Figure 5 The distribution diagram of the soil-rock ratio calculation results in Example 2;

[0058] Figure 6 This is a dynamic response evaluation diagram of the soil-rock ratio result updated in real time in Example 2;

[0059] Figure 7 Schematic diagram of a system module for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation in an embodiment of the present invention;

[0060] Figure 8 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention;

[0061] In the figure, 110 is a data acquisition module; 120 is a boundary elevation prediction module; 130 is a complete and high-precision boundary point set construction module; 140 is a module for calculating the volume of each earthwork and the earth-rock ratio; 150 is a module for generating confidence intervals and predicted distributions of the earth-rock ratio; 210 is a processor; and 220 is a memory. DETAILED DESCRIPTION

[0062] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0063] Example 1

[0064] The method of the present invention first extracts the spatial coordinates of typical boundary points based on the drilling data and soil-rock classification rules of the engineering area, constructs a Delaunay triangulation based on the known point set, and applies an adaptive spatial interpolation algorithm to predict the boundary elevation at the centroid of each triangle. At the same time, the prediction error and covariance structure are evaluated to achieve basic uncertainty quantification. Subsequently, a progressive iterative strategy is adopted to gradually optimize the interface fitting accuracy and point density through interpolation prediction, point set encryption and triangulation reconstruction. To improve the real-time and dynamic response capabilities of the method, Internet of Things sensor technology is further introduced to collect regional geological and topographic change data in real time. By constructing a dynamic Bayesian network (DBN), the interpolation model and interface prediction results are dynamically updated based on historical status and the latest observation data. At the same time, a multi-source information fusion mechanism based on evidence theory is introduced to integrate the confidence assignment of soil-rock ratio from multiple models, multiple sensors, and data of different spatiotemporal scales, systematically modeling and inferring overall uncertainty. In addition, Bayesian learning and Monte Carlo simulation are combined to quantitatively evaluate multi-source uncertainty factors including measurement errors, geotechnical parameter disturbances, and model approximation errors, further improving the reliability and robustness of soil-rock ratio calculation results; Figure 1 As shown, the method steps are as follows:

[0065] S1. Data acquisition: Based on the project overview and relevant specifications, determine the soil and rock classification standards, process drilling data, and extract the three-dimensional coordinates of typical soil and rock boundary points. Then, use multi-source equipment to collect geological and topographic data in real time, establish an initial spatial interpolation dataset, and assign each point a dynamically updated timestamp and confidence weight.

[0066] Data collection methods include drilling data extraction and real-time survey data fusion; the multi-source equipment includes geological sensors, elevation sensors, and GNSS positioning equipment, and has unique identification and precise positioning capabilities.

[0067] S2. Boundary elevation prediction: Based on the collected data, an initial Delaunay triangulation is constructed, and a regionally adapted spatial interpolation algorithm is used at the centroid of each triangle to predict the boundary elevation. The details include the following:

[0068] S21. Use the drilling demarcation points to construct a Delaunay triangulation network, and increase the density of points or grids in areas with severe terrain fluctuations to improve the accuracy of interpolation prediction;

[0069] S22. Automatically generate the centroid points of the triangulated network and select a spatial interpolation method based on regional characteristics; the spatial interpolation method selected based on regional characteristics specifically includes: selecting kernel regression KR or inverse distance weighted interpolation method IDW method for areas with drastic terrain changes; selecting Gaussian process regression GPR or Kriging interpolation method Kriging method for areas with flat terrain; introducing multi-model ensemble learning in abnormal areas, including local regression combined with random forest supplementary prediction method.

[0070] S23. Calculate the covariance or joint variance of the prediction results based on the selected interpolation model as an indicator for evaluating interpolation accuracy and uncertainty, and to guide subsequent adaptive modeling and risk perception.

[0071] S3. Construct a complete and high-precision demarcation point set: Add the new demarcation points predicted in step S2 to the point set, reconstruct the triangulation network, and determine whether to continue iterating; through multiple rounds of progressive encryption, optimize spatial coverage and prediction accuracy, and gradually construct a complete and high-precision demarcation point set.

[0072] The specific judgment of whether to continue iteration includes: each round of interpolation results participates in a new round of triangulation network construction, and whether to terminate the iteration is determined based on the prediction error convergence criterion, spatial point density balance criterion and uncertainty threshold criterion.

[0073] S4. Calculate the volume of each earthwork and the ratio of earthwork to rockwork: Based on the final generated set of demarcation points, fit the earthwork boundary surface, integrate it with the digital terrain model (DTM) and the designed elevation surface, construct a closed stratum 3D model, and calculate the volume of each earthwork and the ratio of earthwork to rockwork based on the model.

[0074] S5. Generate confidence intervals and predicted distributions for soil-rock ratios: Integrating real-time sensor data changes, the interpolation model parameters are dynamically updated through online learning mechanisms, including kernel function hyperparameters, covariance structure, and interpolation weight factors. Dynamic Bayesian networks (DBNs) and evidence theory (DSTs) are introduced to model the uncertainty of terrain disturbances and lithology changes. Combined with Monte Carlo simulations, confidence intervals and predicted distributions for soil-rock ratios are generated, providing intelligent support for engineering risk decision-making. Specifically, this includes:

[0075] S51. For each new data point, assign a dynamic confidence weight ω:

[0076]

[0077] Among them, λ and μ are adjustable parameters, δ is the sampling delay, and σ is the noise index;

[0078] Through dynamic weights, the data set is fused: D*=D∪{(xi ,y i ,z i ,ω i )},x i ,y i is the plane coordinate of the i-th data point, z i is the real-time observation value of the point, ω i is the dynamic weight of the i-th data point; D is the existing data set, D * The dataset after fusion update;

[0079] S52, construct dynamic Bayesian network DBN to model the soil-rock ratio change trend, assuming S t is the soil-rock ratio state at time t, O t is the observation value at time t, then the Bayesian update formula is as follows:

[0080]

[0081] P(S t-1 |O 1:t-1 ) is the posterior distribution of the state at the previous moment, P(S t |S t-1 ) is the state prediction model, P(O t |S t ) is the likelihood model of the current observation, P(O t |O 1:t-1 ) is used for normalization and does not participate in the final prediction, dS t-1 is the integration of the state variables, combined with the current observation P(O t |S t ) is updated to the new posterior P(S t |O 1:t ), dynamically adjust the soil and rock prediction surface;

[0082] S53, introduce the evidence theory DST for joint inference, assuming that the soil-rock ratio state of a certain area is θ, different models or sensors give different confidence values Where A and B are possible state subsets proposed by different models, m1(A)·m2(B) is the confidence level of each subset, and K is the conflict degree. Finally, by rationally integrating data from different sources and combining it with Monte Carlo simulation, we generate confidence intervals and joint prediction distributions for the soil-rock ratio. This ultimately forms a unified uncertainty description for subsequent soil-rock ratio calculations and engineering risk-assisted decision-making.

[0083] Example 2: A certain "civil airport project" uses an intelligent assessment method for soil-rock ratio of mountain airports based on progressive spatial interpolation

[0084] To scientifically assess the soil-rock ratio at a "civil airport project" site in a mountainous area, a surveying company employed the intelligent soil-rock ratio assessment method based on progressive spatial interpolation proposed in this paper. This method addresses the problems of traditional interpolation in complex mountainous terrain, including insufficient prediction accuracy, fuzzy interface representation, and inability to quantitatively characterize uncertainty. The implementation steps are as follows:

[0085] Step 1: A survey unit undertook a "civil airport project." The excavation and filling work exposed numerous strata. To calculate the soil-rock ratio of the site, the proposed intelligent soil-rock ratio assessment method for mountain airports based on progressive spatial interpolation was used to determine the soil-rock interface. In accordance with relevant regulations, the rock and soil strata within the survey area were classified into soil and rock categories based on the difficulty of excavation, as shown in Table 1:

[0086] Table 1 Soil and rock classification table

[0087]

[0088] Step 2: After preprocessing the borehole data, the soil-rock boundary points are extracted. Their spatial distribution is shown in Figure 2(a), and a Delaunay triangulation is constructed. Its vertices are the spatial coordinates of the soil-rock boundary points obtained by drilling, as shown in Figure 2(b). This project uses the Gaussian process regression method to determine the data points as Gaussian process sampling points:

[0089] y(x)~Ν(μ(x),k(x,x′)) (1)

[0090] Where μ(x) is the mean function. It is recommended to assume that the a priori mean function is 0. k(x, x′) is the kernel function. The Gaussian kernel function is selected for calculation in this project:

[0091]

[0092] in l, They are all hyperparameters, namely signal variance, bandwidth, and noise variance, which are solved by maximum likelihood estimation:

[0093]

[0094] Finally, the prediction point expression is determined based on the posterior probability:

[0095]

[0096] Among them, the predicted mean is K * K -1 y, K * is the kernel function between the predicted point and the known point, K is the kernel function between the known points, y is the known elevation point data, and the elevation value at the center of gravity of each triangulation is predicted; using the prediction variance where K** is the kernel function formed between the prediction points, and the covariance structure is obtained.

[0097] In step 3, the predicted triangulated centroid points are added to the dataset as new data points, the triangulated network is reconstructed, and the prediction process is repeated, achieving a gradual evolution of the interpolation model through a "prediction-encryption-reconstruction" process. This process involves dense encryption in areas with steep terrain changes and moderate interpolation in areas with gentle terrain, forming a spatially adaptive optimization strategy. Through two rounds of interpolation iterations, this project constructed a denser and more coherent soil-rock boundary point network. Figure 3(a) shows the result of the first encryption, and Figure 3(b) shows the result of the second encryption.

[0098] Step 4: Based on the interface formed by the final prediction and the original point, the three-dimensional surface of the soil-rock interface is fitted, and the three-dimensional soil-rock boundary entity model with upper and lower envelopes is constructed by combining the digital terrain model (DTM) and the design elevation surface. The total earthwork volume and soil-rock ratio results in the site are calculated by volume difference. At the same time, the predicted covariance output by GPR is used to perform perturbation sampling on the interface morphology by Monte Carlo simulation to obtain the confidence interval expression of the soil-rock ratio. Figure 4 (a) shows the three-dimensional entity modeling of the soil-rock boundary and the design elevation surface, with a volume of 349456294.41m 3 ,Figure 4(b) shows the three-dimensional solid modeling of the terrain surface and the design elevation surface, with a volume of 413543148.98m 3 The earthwork volume and earthwork ratio are 1.5:8.5, and the uncertainty of the earthwork ratio is evaluated based on the covariance structure of the cutoff point prediction. Figure 5 The mean is 1.5:8.5, the standard deviation is 0.0415, and the 95% confidence interval is (0.099, 0.261), that is, (0.9:9.1, 2.1:7.9).

[0099] Step 5: Deploy intelligent survey sensor equipment in key areas, and combine with the Internet of Things system to collect the latest terrain and geological change data in real time. Through the dynamic Bayesian network (DBN) model, historical status and new observations are integrated to dynamically adjust the interpolation parameters and local triangulation structure to achieve efficient real-time updates. Based on the Dependency of Evidence Theory (DST), the system integrates confidence information from different sensors and model sources to enhance the robustness of the prediction results. After each data update, the local area quickly rebuilds the triangulation network and re-predicts to avoid global recalculation, greatly improving computing efficiency and response speed, and realizing an intelligent evaluation process of "construction, prediction, monitoring, and correction". The system can output a trend chart of the latest soil-rock ratio confidence interval over time, such as Figure 6 As shown, the present invention is used to dynamically monitor areas with large terrain variability, support construction management and early warning decisions, and greatly improve the engineering intelligence level and risk response capabilities.

[0100] Based on the same inventive concept as the above method embodiment, the present application embodiment also provides a mountain airport earth-rock ratio evaluation system based on progressive spatial interpolation, which can implement the functions provided by the above method embodiment, such as Figure 7 As shown, the system includes the following modules:

[0101] Data acquisition module 110;

[0102] Boundary elevation prediction module 120: constructs an initial Delaunay triangulation based on the collected data, and uses a regionally adapted spatial interpolation algorithm at the centroid of each triangle to predict the boundary elevation;

[0103] A complete and high-precision demarcation point set construction module 130 includes the new demarcation points predicted by the demarcation elevation prediction module into the point set, reconstructs the triangulation network, and determines whether to continue iteration; through multiple rounds of progressive encryption, the spatial coverage and prediction accuracy are optimized, and a complete and high-precision demarcation point set is gradually constructed;

[0104] The earthwork volume and earthwork ratio calculation module 140 is used to fit the earthwork boundary surface based on the final generated boundary point set, integrate it with the digital terrain model DTM and the design elevation surface, construct a closed stratum three-dimensional model, and calculate the earthwork volume and earthwork ratio based on the model;

[0105] Soil-rock ratio confidence interval and predicted distribution generation module 150: Combined with real-time sensor data changes, the interpolation model parameters are dynamically updated through an online learning mechanism. Dynamic Bayesian network DBN and evidence theory DST are introduced to model the uncertainty of terrain disturbance and rock property changes, and combined with Monte Carlo simulation, the soil-rock ratio confidence interval and predicted distribution are generated.

[0106] Based on the same inventive concept as the above method embodiment, the embodiment of the present application further provides an electronic device, such as Figure 8 As shown, the device includes: a processor 210; and a memory 220 for storing one or more programs;

[0107] When the one or more programs are executed by the processor 210 , the processor is enabled to execute the method for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation.

[0108] The soil-rock ratio evaluation method for mountain airports based on progressive spatial interpolation includes the following steps:

[0109] Data collection;

[0110] Boundary elevation prediction: Based on the collected data, the initial Delaunay triangulation is constructed, and the boundary elevation is predicted using a regionally adapted spatial interpolation algorithm at the center of each triangle;

[0111] Construct a complete and high-precision demarcation point set: Incorporate the predicted new demarcation points into the point set, reconstruct the triangulation network, and determine whether to continue iterating. Through multiple rounds of progressive encryption, optimize spatial coverage and prediction accuracy, and gradually construct a complete and high-precision demarcation point set.

[0112] Calculate the volume and soil-rock ratio of each earthwork: Based on the final generated boundary point set, fit the earthwork boundary surface, merge it with the digital terrain model (DTM) and the designed elevation surface, build a closed stratum 3D model, and calculate the volume and soil-rock ratio of each earthwork based on the model;

[0113] Generate confidence intervals and predicted distributions of soil-rock ratios: Combined with real-time sensor data changes, the interpolation model parameters are dynamically updated through an online learning mechanism. Dynamic Bayesian networks (DBNs) and evidence theory (DSTs) are introduced to model the uncertainty of terrain disturbances and lithology changes. Monte Carlo simulations are then used to generate confidence intervals and predicted distributions of soil-rock ratios.

[0114] Based on the same inventive concept as the above-mentioned method embodiment, the embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by the processor 210, the method for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation is implemented.

[0115] The soil-rock ratio evaluation method for mountain airports based on progressive spatial interpolation includes the following steps:

[0116] Data collection;

[0117] Boundary elevation prediction: Based on the collected data, the initial Delaunay triangulation is constructed, and the boundary elevation is predicted using a regionally adapted spatial interpolation algorithm at the center of each triangle;

[0118] Construct a complete and high-precision demarcation point set: Incorporate the predicted new demarcation points into the point set, reconstruct the triangulation network, and determine whether to continue iterating. Through multiple rounds of progressive encryption, optimize spatial coverage and prediction accuracy, and gradually construct a complete and high-precision demarcation point set.

[0119] Calculate the volume and soil-rock ratio of each earthwork: Based on the final generated boundary point set, fit the earthwork boundary surface, merge it with the digital terrain model (DTM) and the designed elevation surface, build a closed stratum 3D model, and calculate the volume and soil-rock ratio of each earthwork based on the model;

[0120] Generate confidence intervals and predicted distributions of soil-rock ratios: Combined with real-time sensor data changes, the interpolation model parameters are dynamically updated through an online learning mechanism. Dynamic Bayesian networks (DBNs) and evidence theory (DSTs) are introduced to model the uncertainty of terrain disturbances and lithology changes. Monte Carlo simulations are then used to generate confidence intervals and predicted distributions of soil-rock ratios.

[0121] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0122] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0123] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk. It should be noted that, in this article, the terms "include", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0124] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0125] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0126] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0127] The references to "first" and "second" in the embodiments merely distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the specific order or precedence of "first" and "second" can be interchanged where appropriate. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0128] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating the earth-rock ratio of mountain airports based on progressive spatial interpolation, characterized in that: The steps include: S1, data collection; S2. Boundary elevation prediction: Based on the collected data, the initial Delaunay triangulation is constructed, and the boundary elevation is predicted using a regionally adapted spatial interpolation algorithm at the center of each triangle; S3. Construct a complete and high-precision demarcation point set: Add the new demarcation points predicted in step S2 to the point set, reconstruct the triangulation network, and determine whether to continue iterating; through multiple rounds of progressive encryption, optimize spatial coverage and prediction accuracy, and gradually construct a complete and high-precision demarcation point set; S4. Calculate the volume of each earthwork and the ratio of earthwork to rockwork: Based on the final generated boundary point set, fit the earthwork boundary surface, merge it with the digital terrain model (DTM) and the design elevation surface, and construct a closed stratum 3D model. Calculate the volume of each earthwork and the ratio of earthwork to rockwork based on the model. S5. Generate confidence intervals and predicted distributions for soil-rock ratios: Integrate real-time sensor data changes, dynamically update interpolation model parameters through an online learning mechanism, introduce dynamic Bayesian networks (DBNs) and evidence theory (DSTs) to model the uncertainty of terrain disturbances and lithologic changes, and combine Monte Carlo simulations to generate confidence intervals and predicted distributions for soil-rock ratios. Specifically, this includes the following: S51. For each new data point, assign a dynamic confidence weight ω: Among them, λ and μ are adjustable parameters, δ is the sampling delay, and σ is the noise index; Through dynamic weights, the data set is fused: D*=D∪{(x i ,y i ,z i ,ω i )},x i ,y i is the plane coordinate of the i-th data point, z i is the real-time observation value of the point, ω i is the dynamic weight of the i-th data point; D is the existing data set, D * The dataset after fusion update; S52, construct dynamic Bayesian network DBN to model the soil-rock ratio change trend, assuming S t is the soil-rock ratio state at time t, indicating the soil-rock ratio information of the current area, O t is the observation value at time t, collected by the sensor, then the Bayesian update formula is as follows: P(S t-1 |O 1:t-1 ) is the posterior distribution of the state at the previous moment, P(S t |S t-1 ) is the state prediction model, P(O t |S t ) is the likelihood model of the current observation, P(O t |O 1:t-1 ) is used for normalization and does not participate in the final prediction, dS t-1 is the integration of the state variables, combined with the current observation P(O t |S t ) is updated to the new posterior P(S t |O 1:t ), dynamically adjust the soil and rock prediction surface; S53, introduce evidence theory DST for joint inference, set the soil-rock ratio state of a certain area as θ, judge the rock property, and different models or sensors give different confidence values Among them, the conflict Among them, A and B are the possible state subsets proposed by different models, and m1(A)·m2(B) is the confidence level of each subset. Finally, by reasonably integrating data from different sources and combining Monte Carlo simulation, the soil-rock ratio confidence interval and joint prediction distribution are generated.

2. The method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation according to claim 1 is characterized by: In step S1, soil and rock classification standards are determined based on the project overview and relevant specifications, drilling data is processed, and the three-dimensional coordinates of typical soil and rock boundary points are extracted. Then, geological and topographic data are collected in real time using multi-source equipment to establish an initial spatial interpolation dataset, and each point is assigned a dynamically updated timestamp and confidence weight.

3. The method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation according to claim 2 is characterized in that: The data collection method includes drilling data extraction and real-time survey data fusion; the multi-source equipment includes geological sensors, elevation sensors and GNSS positioning equipment.

4. The method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation according to claim 1 is characterized by: In step S2, the specific steps include: S21. Use the drilling demarcation points to construct a Delaunay triangulation network, and increase the density of points or grids in areas with severe terrain fluctuations to improve the accuracy of interpolation prediction; S22, automatically generate the centroid of the triangulated network and select the spatial interpolation method based on regional characteristics; S23. Calculate the covariance or joint variance of the prediction results in combination with the selected interpolation model as an indicator for evaluating the interpolation accuracy and uncertainty.

5. The method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation according to claim 4 is characterized in that: The spatial interpolation method selected according to regional characteristics specifically includes: For areas with drastic terrain changes, kernel regression (KR) or inverse distance weighted interpolation (IDW) methods are used. For areas with flat terrain, choose Gaussian process regression (GPR) or Kriging interpolation method. Multi-model ensemble learning is introduced in abnormal areas, including local regression combined with random forest to supplement the prediction method.

6. The method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation according to claim 1 is characterized by: In step S3, determining whether to continue iteration specifically includes: each round of interpolation results participates in a new round of triangulation network construction, and determining whether to terminate the iteration based on the prediction error convergence criterion, the spatial point density balance criterion and the uncertainty threshold criterion.

7. A system according to the method for evaluating the soil-rock ratio of a mountain airport based on progressive spatial interpolation according to any one of claims 1 to 6, characterized in that: The system includes the following modules: Data acquisition module (110); Boundary elevation prediction module (120): constructing an initial Delaunay triangulation based on the collected data, and using a regionally adapted spatial interpolation algorithm at the center of gravity of each triangle to predict the boundary elevation; A complete and high-precision demarcation point set construction module (130): incorporates the new demarcation points predicted by the demarcation elevation prediction module into the point set, reconstructs the triangulation network, and determines whether to continue iteration; through multiple rounds of progressive encryption, optimizes spatial coverage and prediction accuracy, and gradually constructs a complete and high-precision demarcation point set; Module (140) for calculating the volume of each earthwork and the ratio of earthwork to rockwork: Based on the final generated boundary point set, the earthwork boundary surface is fitted, and the surface is integrated with the digital terrain model DTM and the design elevation surface to construct a closed stratum three-dimensional model, and the volume of each earthwork and the ratio of earthwork to rockwork is calculated based on the model; Soil-rock ratio confidence interval and prediction distribution generation module (150): Combined with real-time sensor data changes, the interpolation model parameters are dynamically updated through an online learning mechanism, and the dynamic Bayesian network DBN and evidence theory DST are introduced to model the uncertainty of terrain disturbance and rock property changes, and combined with Monte Carlo simulation to generate soil-rock ratio confidence interval and prediction distribution.

8. An electronic device, characterized in that: The electronic device includes: a processor (210); and a memory (220) for storing one or more programs; When the one or more programs are executed by the processor (210), the processor is enabled to execute the method for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor (210), the method for evaluating the earth-rock ratio of a mountain airport based on progressive spatial interpolation according to any one of claims 1 to 6 is implemented.

Images