Intelligent surveying and mapping method and device for pile foundation embedded area based on fuzzy coordinate compensation

Abstract

The invention provides a pile foundation embedded area intelligent surveying and mapping method and device based on fuzzy coordinate compensation, and relates to the technical field of pile foundation surveying and mapping. Generating dense measuring points corresponding to the areas in the pile foundation key node areas and the terrain sudden change areas; outputting error probability density representing topographic errors of the surveying and mapping area; surveying and mapping equipment is deployed in a surveying and mapping area, and collected data are preprocessed and converted into membership degree values through fuzzification processing; and inputting the corrected acquired data into the model, and re-estimating model parameters through an EM algorithm to realize high-precision construction optimization. According to the method, the strength values of the terrain sudden change area and the pile foundation key nodes are quantified, the grid size and the measuring point density are dynamically adjusted, the plane terrain and the elevation error are controlled to be smaller than or equal to 2 cm and smaller than or equal to 1 cm respectively, the data redundancy rate is reduced by 30%-50%, the coverage rate of the key area is increased to 95% or above, and the terrain features are accurately reflected.

Description

Technical Field

[0001] The present invention relates to the technical field of pile foundation surveying and mapping, and in particular to a method and device for intelligent surveying and mapping of a pile foundation pre-embedded area based on fuzzy coordinate compensation. Background Art

[0002] Pile foundation pre-embedded area surveying is a key technical link in modern civil engineering and infrastructure construction, and is widely used in the pre-construction planning and implementation stages of bridges, high-rise buildings, port facilities, and large-scale infrastructure. With the acceleration of urbanization and the advancement of large-scale infrastructure construction, the demand for surveying and mapping of pile foundation pre-embedded areas is growing. At the same time, with the rapid development of drone photogrammetry, point cloud data processing, and artificial intelligence technology, intelligent surveying and mapping technology has gradually become an important means to solve complex terrain surveying and mapping and high-precision construction needs.

[0003] Although existing surveying and mapping technologies can provide a certain degree of accuracy, they often face problems such as low efficiency, data redundancy, error accumulation, and insufficient adaptability to sudden changes in terrain and pile foundation layout in complex terrain construction environments, especially in mountainous areas, wetlands, densely populated urban areas, and scenes requiring high-precision construction. For example, in mountain surveying and mapping, the surveying and mapping technology causes uneven coverage of measurement points due to terrain undulations and occlusions, resulting in insufficient data accuracy in key areas and redundant data in non-key areas. Although drone photogrammetry can quickly cover large areas, its point cloud data is not accurate enough in areas with vegetation occlusion and large terrain undulations, making it difficult to adapt to sudden changes in terrain and dynamic changes in pile foundation layout.

[0004] In addition, the measurement point planning method in traditional surveying and mapping relies on fixed grid division (or uniform grid division), and cannot dynamically adjust the measurement point density according to the complexity of the terrain and engineering requirements. For example, in mountainous terrain, the errors in flat areas are relatively concentrated, while the errors in terrain mutation areas (such as steep slopes and valleys) are more dispersed. The traditional method will arrange too many measurement points in flat areas, resulting in data redundancy, while in areas with terrain mutations, there are insufficient measurement points, and it is impossible to capture key terrain features and error distribution. This unreasonable measurement point distribution not only increases the complexity of data processing, but also leads to insufficient measurement accuracy in key areas, affecting the subsequent construction accuracy and engineering quality, resulting in the measurement data being unable to accurately reflect the terrain characteristics, which in turn affects the design and construction accuracy of the pier foundation. Summary of the invention

[0005] In view of the deficiencies in the prior art, the object of the present invention is to provide a method and device for intelligent mapping of pile foundation pre-embedded areas based on fuzzy coordinate compensation, so as to solve the problems raised in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention is implemented by the following technical solution: an intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation, comprising the steps of: Determine the constraints and initialize the M×N matrix that matches the dimensions of the grid cells (i, j) in the survey area; use the Sigmoid function to calculate the terrain constraint strength value T (i,j) , and combined with Gaussian kernel density to calculate the pile foundation constraint strength distribution value P (i,j) , the dynamic constraint association matrix is ​​generated by linear superposition and nonlinear correction, , where α and β are weight coefficients used to measure the interaction between terrain and pile foundation constraints, and η is the interaction enhancement coefficient; According to the normalized dynamic constraint association matrix, the density of measuring points in each grid unit in the surveying and mapping area is determined, wherein the higher the constraint strength is set, the higher the density of measuring points is proportionally increased. Secondly, the slope and curvature data of all grid units in the surveying and mapping area are integrated, combined with the preset weight coefficient, the terrain complexity estimation of the current surveying and mapping area is calculated, the grid size required for surveying and mapping is dynamically adjusted, and the logic of measuring point layout that meets the constraint conditions is generated; Deploy equipment, generate dense coordinates based on the measurement point layout logic and collect elevation and point cloud data. After preprocessing, construct a structured data set, fuzzify it into low, medium and high fuzzy sets through fuzzy processing, and use fuzzy clustering to extract the collected data features; Gaussian components are distributed to different terrains in the surveying and mapping area, and the EM algorithm is used for iterative optimization until the model converges. The characteristics of the collected data as the model input vector are corrected according to the fuzzy rule library and then input into the model to output the error probability density that represents the terrain error in the surveying and mapping area, thereby achieving high-precision construction optimization.

[0007] As a second aspect of the present invention, an intelligent surveying and mapping device for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation is proposed, comprising a memory and a processor, wherein the memory comprises an intelligent surveying and mapping program for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation, and when the intelligent surveying and mapping program for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation is executed by the processor, the intelligent surveying and mapping method for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation proposed above is implemented.

[0008] Compared with the prior art, the present invention has the following beneficial effects: 1. In order to solve the problem that static uniform distribution is adopted in the planning of measuring points in the prior art, resulting in insufficient data in the terrain mutation area, omission of key nodes of pile foundation, and high data redundancy, the present invention constructs a constraint association matrix, quantifies the strength values ​​of the terrain mutation area and the key nodes of the pile foundation, dynamically adjusts the grid size and measuring point density, and encrypts the measuring points in the high-complexity area, so that the plane terrain and elevation errors are controlled within ≤2cm and ≤1cm respectively, the data redundancy rate is reduced by 30% to 50%, the coverage rate of key areas is increased to more than 95%, and the terrain characteristics are accurately reflected; 2. In order to solve the problem of insufficient accuracy of terrain error collection under complex terrain conditions, the present invention realizes data optimization through fuzzy reasoning correction. First, the key terrain features (standardized elevation value, point cloud density, elevation deviation) are fuzzified into membership values ​​to generate fuzzy vectors. Then, fuzzy clustering is used to identify the key features of terrain data, evaluate the importance of feature clusters and extract key features. Then, the correction weights are calculated through fuzzy reasoning, and the elevation and point cloud density data are dynamically adjusted. Finally, the corrected data is input into the Gaussian mixture model and the model parameters are updated, thereby improving the adaptability and prediction accuracy of the terrain error probability model and ensuring high-precision mapping and construction optimization under different terrain conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The disclosure of the present invention is described with reference to the accompanying drawings. It should be understood that the drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In the drawings, the same reference numerals are used to refer to the same components. Among them: Figure 1 A schematic diagram of a process for constructing an offline data collection strategy to ensure data collection accuracy, as proposed in one embodiment of the present invention; Figure 2 A schematic diagram of a process for constructing a terrain error probability model to control the construction error within a millimeter range, as proposed in one embodiment of the present invention; Figure 3 A schematic diagram of a process for optimizing input elevation and point cloud data using fuzzy clustering, and finally updating a terrain error probability model to improve surveying and mapping accuracy, as proposed in one embodiment of the present invention; Figure 4 A schematic diagram of a process for realizing high-precision construction optimization proposed in one embodiment of the present invention; Figure 5 This is a schematic diagram of the overall structure of a total station surveying and mapping instrument proposed in one embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a surveying and mapping tripod support frame and a rectangular displacement assembly proposed in one embodiment of the present invention; Figure 7 This is a schematic diagram of the split structure of the rectangular displacement component proposed in one embodiment of the present invention.

[0010] Reference numerals: 1. Surveying and mapping tripod support frame; 11. Center round rod frame; 111. Lower collar; 112. Upper collar; 12. Support angle adjustment assembly; 121. Thick sleeve connecting rod; 122. Angle clamping block; 123. Angle support rod; 13. Height adjustment assembly; 131. Thin sleeve connecting rod; 1311. Support ball; 1312. Pin; 132. Limit clamping block; 2. Rectangular displacement assembly; 21. Displacement rectangular frame; 211. Lower linear slot; 212. Upper linear slot; 213. Rectangular rod; 2131. Limit opening; 22. Limit cover; 221. Center mark; 222. Cross slot; 223. Side snap-in; 3. Level; 4. Surveying instrument components. DETAILED DESCRIPTION

[0011] It is easy to understand that according to the technical solution of the present invention, without changing the essential spirit of the present invention, a person skilled in the art can propose a variety of interchangeable structural modes and implementation modes. Therefore, the following specific implementation modes and drawings are only exemplary descriptions of the technical solution of the present invention, and should not be regarded as the whole of the present invention or as a limitation or restriction to the technical solution of the present invention.

[0012] The present invention is further described in detail below with reference to the accompanying drawings, but is not intended to limit the present invention.

[0013] As an understanding of the technical concept of the present invention, the traditional measurement point planning adopts static uniform distribution, which is difficult to adapt to complex terrain (such as slope mutation, pile foundation dense area), resulting in data redundancy (flat area is too dense) or omission of key areas (insufficient mutation area). Therefore, the present invention proposes to generate a dynamic grid by quantifying the terrain mutation area (slope-Sigmoid mapping as intensity value) and the constraints of the pile foundation nodes (Gaussian kernel density estimation). For example, in mountain surveying, the measurement point density in the area with a slope > 15° is increased to 2 times to ensure the capture of terrain undulations, and the grid in the 2d radius area around the pile foundation is compressed to Δ final / 2, accurately covering the pile foundation coupling effect. Next, in order to capture the key terrain features and error distribution, the present invention allocates Gaussian components according to terrain types (flat areas, mutation areas, pile positions) to capture the error distribution of different areas, and dynamically adjusts weights, means, and covariances through expected maximization iterations to effectively deal with the skewed error distribution caused by construction disturbances in the pile position area, so as to achieve the effect of accurately quantifying the scope of construction influence. Finally, in order to make the measurement data accurately reflect the terrain features, the present invention converts continuous variables (elevation, point cloud density) into fuzzy sets (such as "high deviation" and "low density"), eliminates dimensional differences, and dynamically adjusts error model parameters based on expert knowledge or data-driven rules (such as "IF high deviation AND low density THEN increase compensation weight") to improve the accuracy and reliability of complex terrain mapping.

[0014] As an embodiment of the present invention, a method for intelligent mapping of a pile foundation pre-embedded area based on fuzzy coordinate compensation is first proposed, comprising the following steps: like Figure 1 As shown in S1, an offline data acquisition strategy is constructed to complete the grid division and measurement point coordinate location planning of the terrain and pile foundation coupling in the surveying area (pile foundation pre-buried area) under different terrain conditions, so as to ensure that the terrain mutation area and the key nodes of the pile foundation layout are accurately covered during the subsequent surveying and mapping, and data redundancy is avoided. The implementation steps include: S1-1. According to the design requirements of the infrastructure project, determine the terrain mutation area with a slope value greater than 15° and the pile foundation coordinates (x k ,y k ) The constraint conditions include the key node area of ​​the pile foundation group with a surrounding radius of n=2 times the average spacing d of the pile foundation. It can be understood that the purpose of determining the constraint conditions is to guide the reasonable layout of the measuring points and ensure that more measuring points can be allocated in areas with high terrain complexity (such as areas with large slopes or drastic changes in curvature), thereby improving the measurement accuracy. Through the constraint conditions, the grid size and measuring point density can be dynamically adjusted to generate a dense set of measuring point coordinates in key areas (such as key nodes of pile foundations and terrain mutation zones), ensuring that the acquisition accuracy and elevation error of the surveying and mapping data are controlled within the range of engineering design requirements, while optimizing resource allocation, avoiding excessive layout of measuring points in flat or simple terrain areas, and improving surveying and mapping efficiency.

[0015] Initialize an M×N matrix and make its dimension match the grid unit (i, j) division of the survey area; where the terrain mutation area calculates the slope value S of each grid unit through the DEM data model (i,j) Determined, if the slope value S (i,j) Greater than the slope threshold S th =15°, it is regarded as a sudden terrain change area. Assuming that the surveying and mapping area is divided into M×N grid units, the size of the constraint association matrix is ​​also M×N; the radius around the pile foundation coordinates is 2d, which refers to the circular area defined by the coordinates of each pile foundation position as the center and n=2 times the average spacing d of the pile foundation as the radius during the pile foundation construction. This area is used to define the key nodes of the pile foundation group to ensure that the pile position and its surrounding terrain can be measured and analyzed in detail during the surveying and construction process, thereby ensuring the accuracy and stability of the pile foundation construction.

[0016] The Sigmoid function is used to map the terrain mutation area (slope>15°) into a continuous intensity value T (i,j) (0-1), and quantify discrete terrain features into continuous data. Through this mapping, the influence of slope on construction difficulty or measurement accuracy can be more intuitively expressed. , where S (i,j) is the actual slope measurement value at the grid cell (i, j) in the survey area, S th=15°, is the slope threshold, r=0.5, is the slope sensitivity parameter, used to control the steepness of the Sigmoid function, T (i,j) It is used to reflect the impact of slope on construction difficulty. The larger the value, the more complex the terrain. Based on the obtained pile foundation coordinates (x k ,y k ) and the average spacing d of pile foundations, the influence of the density of key nodes of pile groups on the grid unit (i, j) is quantified by Gaussian kernel density, and the normalized distribution value P of pile foundation constraint strength is generated. (i,j)： ， In the formula, (x k ,y k ) is the coordinate position of the kth pile foundation, k=1,2,…,K, K is the total number of pile foundations. It can be understood that the density relationship between each grid unit and the pile position is calculated by the Gaussian kernel function, the purpose of which is to reflect the distribution of pile foundations in the surveying area. In order to make the results more comparable, the calculated values ​​need to be normalized so that their values ​​are between 0 and 1: , where max (p,q) is the maximum value in the entire pile foundation constraint strength distribution, which is used for normalization to ensure that all values ​​are scaled to the range of 0 to 1. (p,q) is the original value at a grid unit (i, j), p and q are index variables. Through this quantification process, the constraint conditions of the key nodes of the pile group can be converted into continuous strength values, providing data support for subsequent measurement point planning.

[0017] The continuous intensity value T (i,j) and the pile foundation constraint strength distribution value P (i,j) Linear superposition and the introduction of nonlinear correction factors are used to construct a dynamic and unnormalized constraint association matrix to realize the surveying and mapping logic that needs to be focused on in complex terrain and dense pile groups in infrastructure projects: , where α and β are weight coefficients used to measure the interaction between terrain and pile foundation constraints, usually α=β=1, and η is the interaction enhancement coefficient, usually 0.5. After the matrix construction is completed, the preliminary distribution of the measurement point density ρ(i,j) at each grid unit (i,j) is output to understand the distribution of the measurement point coordinates under different terrain conditions, to ensure that the measurement points can accurately cover the terrain mutation area and the key nodes of the pile foundation, and to avoid data redundancy in non-critical areas, so as to improve the efficiency and accuracy of subsequent surveying and mapping work, and provide reliable measurement point data for the subsequent construction of terrain error probability model and pile foundation pre-embedded construction. The calculation steps of the measurement point density ρ(i,j) are as follows: First, the constraint incidence matrix W raw Linear mapping to the range 0 to 1: , where max (raw)and min (raw) are the maximum and minimum values ​​in the constraint association matrix, respectively, W nor (i, j) is the value of grid cell (i, j) in the normalized constraint association matrix; Secondly, for high terrain strength (such as T (i,j) >0.8) and high pile strength (such as P (i,j) >0.7), increase its weight value to achieve priority adjustment of conflicting areas: W nor (i,j)=min(1.0,W nor (i,j)+0.2); Finally, the measurement point density of each grid cell (i, j) is calculated based on the normalized constraint association matrix: ρ(i, j) = ρ base ×(1+h×W nor (i,j)), where ρ base is the basic measurement point density, ρ base =1 / Δ 2 , represents the expected number of basic measuring points within the unit grid area, the coefficient h=3, is the amplification factor of the constraint strength on the measuring point density, which is used to enhance the impact of the constraint strength on the measuring point density, Δ is the basic grid size divided according to the terrain complexity estimate C and the average pile foundation spacing d, Δ=d / (k×C), k is the adjustment coefficient, which is determined according to the terrain complexity and the pile foundation density. In this embodiment, in areas with complex terrain or dense pile foundations, k=1.5 is taken to reduce the grid size and increase the measuring point density. In areas with simple terrain or sparse pile foundations, k=2.0 is taken to increase the grid size and improve the collection efficiency.

[0018] S1-2. Calculate the terrain complexity estimate C according to the terrain characteristics of the survey area to quantify the complexity of the terrain. Then, dynamically adjust the grid size Δ based on the terrain complexity estimate C. final It should be noted that the terrain complexity estimation C needs to comprehensively consider the two factors of slope S and curvature K for comprehensive calculation: , where is the slope value of the i-th measuring point, reflecting the inclination of the terrain in the surveying area. The larger the absolute value, the steeper the slope. is the curvature value of the i-th measuring point, reflecting the curvature of the terrain in the surveying area. The larger the absolute value, the more drastic the terrain change. The maximum slope value in the survey area is used to normalize the slope so that the slopes at different measuring points are comparable. is the maximum curvature value in the surveying area. a and b are the weight coefficients of slope and curvature respectively. According to experience, the slope weight is 40% and the curvature weight is 40%. The remaining 20% ​​is adjusted according to other factors in actual operation (such as elevation change rate).

[0019] Dynamically adjust the grid size Δ final The formula is: , where Δ is the basic grid size divided according to the terrain complexity estimate C and the average spacing d of pile foundations, ρ base is the basic measurement point density, ρ(i,j) is the measurement point density, η is an adjustment index used to control the influence of the measurement point density on the grid size, usually between 0.5 and 2, and the specific value is determined according to the actual terrain complexity and engineering requirements, ξ is an adjustment coefficient used to further fine-tune the grid size, which is set according to the actual measurement accuracy requirements and resource constraints, and usually between 0 and 1. So far, by dynamically adjusting the grid size Δ final , reduce the grid size in areas with complex terrain and high density, and increase the size conversely, and simultaneously optimize the distribution of measurement point density to ensure that the measurement point density in high-complexity areas is increased to 2 times, and the density in low-complexity areas is reduced to avoid data redundancy, and finally generate an adaptive grid division scheme to balance the subsequent surveying and mapping accuracy and efficiency.

[0020] S1-3, according to the adjusted grid size Δ final , divide the survey area into multiple grid units, generate the measurement point layout logic that meets the constraint conditions, where the size of each grid unit is set to Δ final ×Δ final , in each grid cell, the measuring points are evenly distributed according to the measuring point density ρ(i,j) in order to capture the terrain features around the pile foundation in detail. The specific logic of measuring point layout is as follows: In the pile foundation coordinates (x k ,y k ) In the key node area of ​​the pile group with a radius of 2 times the average pile spacing d, the grid density is increased to twice the original, and the grid size is Δ final / 2, generate dense measurement point coordinates according to the following formula: , where k is the index of the measuring point, from 0 to ρ(i,j)-1, that is, the dense measuring points are based on the starting point and are alternately offset according to the parity of index k, with a horizontal interval of Δ final / 2, the vertical direction increases by a fixed step size, x start is the starting coordinate of the pile foundation in the x-axis direction, y start It is the starting coordinate of the pile foundation coordinate in the y-axis direction, usually indicating the starting position or reference point of the pile foundation coordinate. It is the basis for generating dense measuring point coordinates and is used to determine the starting position of dense measuring points in the horizontal and vertical directions.

[0021] In the terrain mutation area with a slope value greater than 15°, the measurement point position is adjusted according to the local curvature K to increase the measurement point density. The greater the curvature, the greater the measurement point offset. The offset direction is determined by the horizontal and vertical components of the curvature, thereby ensuring that the measurement point density increases with the complexity of the terrain and avoiding data distortion caused by excessive offset. Generate dense measurement point coordinates according to the following formula: , where is the coordinate of the measured point after adjustment, , The fixed base offset is usually 0.5 meters to ensure that the adjustment range is within a reasonable range. , The components of the local curvature in the x and y directions are used to adjust the measurement point position according to the terrain curvature.

[0022] S1-4. Final output of dense measurement point coordinate set To ensure that the data collection accuracy of the surveying and mapping area reaches a plane error of ≤2cm and an elevation error of ≤1cm, meeting the engineering design requirements.

[0023] like Figure 2 As shown, as an embodiment of the present invention, the proposed intelligent surveying and mapping method further includes the following steps: S2. Construct terrain error probability model.

[0024] It should be noted that the terrain error probability model is constructed based on the Gaussian mixture model (GMM). The purpose is to accurately quantify the statistical characteristics and spatial correlation of terrain errors in terrain mapping and pile foundation construction. By fusing elevation data and point cloud data, the model can capture subtle changes and complex features of the terrain, especially in the pre-buried pile foundation area, which usually has a high point cloud density and significant elevation deviation. This model initializes the Gaussian component parameters, iterates optimization, and verifies the output, and finally generates the error probability density and risk identification matrix. The output data can directly support the real-time decision-making and automated compensation of the construction management system to ensure that the construction accuracy meets the engineering requirements. For example, in the pre-buried pile foundation area, the model can identify high-probability error areas, trigger construction alarms, and generate compensation strategies, thereby controlling the construction error within the millimeter range, significantly improving construction efficiency and safety.

[0025] It is understood that in the embodiments of the present invention, terrain error specifically refers to measurement errors caused by terrain features (such as slope, curvature, terrain mutation, etc.), which are mainly related to terrain changes and are the differences between the equipment measurement value and the actual terrain value caused by various factors. These errors come from equipment accuracy limitations, terrain complexity, environmental interference or data processing methods, etc. As shown in Table 1, there are several common types of terrain errors in infrastructure projects and their specific manifestations: Table 1

[0026] The specific implementation steps of S2 include: S2-1. Gaussian mixture model (GMM) initialization: In the model initialization stage, Gaussian components are first allocated to different terrains in the survey area. For the pile location area, M1=3 Gaussian components are allocated, and their mean is initialized to the center of the encrypted grid. The covariance matrix is ​​set to a diagonal matrix containing (Δ / 4) 2 、(Δ / 4) 2 and σ e 2 ; M2 = 2 components are assigned to the mutation area, and their means are weighted by curvature; M3 = 1 component is assigned to the flat area, and its covariance matrix is ​​set to the maximum value to simplify the model. It can be understood that in order to quantify the multimodal distribution and spatial correlation of terrain errors, it is necessary to assign Gaussian components according to terrain types (flat areas, mutation areas, and pile areas) to capture terrain data errors in different surveying and mapping areas. In practice, the high-density measurement point data in the pile area (step S1) enables GMM to assign 3 Gaussian components, which can capture the disturbance of pile foundation construction, soil bearing capacity differences, and surrounding micro-topography coupling effects respectively.

[0027] Secondly, the EM algorithm is iterated. It should be noted that in the iterative optimization process of the EM algorithm, the E step (expectation step) is first executed to calculate the posterior probability of each grid unit belonging to each Gaussian component. The posterior probability is realized by substituting the current weight, mean and covariance matrix into the Gaussian distribution density function. The Gaussian distribution density function is used to measure the matching degree between the input vector and each Gaussian component, and the posterior probability is used to reflect the possibility that each grid unit data point belongs to each Gaussian component. It can be understood that the covariance matrix output by GMM quantifies the spatial correlation of errors (such as the error similarity of adjacent grids), providing a physical basis for subsequent fuzzy correction rules. If GMM shows that the spatial correlation of errors in a certain area is high, the fuzzy rules will give priority to overall compensation for the area rather than local adjustment.

[0028] Again, execute M steps (maximization steps) to update the model parameters in sequence to maximize the log-likelihood function: first update the weights by summing and normalizing the posterior probabilities belonging to each Gaussian component to obtain a new weight value ωj; then update the mean by multiplying the input vector of each grid cell by the posterior probability and summing them, and then dividing them by the sum of the posterior probabilities of the Gaussian component; finally, update the covariance matrix by calculating the outer product of the difference between the input vector and the new mean, multiplying it by the posterior probability and summing them, and then normalizing them.

[0029] Finally, the model convergence condition is set: that is, the iteration is stopped when the change in the log-likelihood value of two consecutive iterations is less than the system threshold (10 to the negative 5th power) to ensure that the model parameters are stable and optimal, thereby optimizing the parameters of the Gaussian mixture model to better fit the data and accurately quantify the probability distribution of terrain errors.

[0030] S2-2, verify the model and generate error probability density: log likelihood evaluation, select the optimal number of Gaussian components; perform residual analysis to verify the rationality of the model; output structured error probability density data for quantifying terrain errors, including Gaussian component parameters, error probability density and risk identification matrix. It can be understood that the risk identification matrix (such as marking high-risk areas as 1) directly guides the construction path planning in step S4.

[0031] It should be noted that in the model verification and application stage, when the model is verified to ensure its effectiveness, the log-likelihood evaluation is to evaluate the model fitting effect by calculating the log-likelihood value of the test set, and then (such as through the BIC criterion) select the Gaussian component number M that maximizes the log-likelihood value as the optimal Gaussian component number; residual analysis is to verify whether the residual between the predicted elevation and the actual elevation obeys the normal distribution with a mean of 0 by calculating the residual. In specific implementation, such as verification by QQ graph or KS test, the commonly used software tool is preferably Python's scikit-learn library for the implementation of Gaussian mixture model and the calculation of BIC criterion, and Python's SciPy library is preferably used for QQ graph drawing and KS test. Error probability density is to calculate the error probability density of each grid unit through the model to form an error probability density map. In specific implementation, this step is preferably visualized using Python's Matplotlib or Seaborn library to intuitively display the error distribution. Based on Python's NumPy library, high-risk areas (error probability greater than 0.9) are marked as 1, and other areas are marked as 0 to quickly generate a risk identification matrix.

[0032] In one embodiment of the present invention, the error probability density calculation formula is: , where M is the number of Gaussian components in the Gaussian mixture model (GMM). The model consists of M Gaussian components, each with a weight of ωj and a mean of , the variance is It can be understood that the contribution of each Gaussian component is determined by its weight and the Gaussian distribution density function. The weight reflects the importance of the component in the overall model, while the Gaussian distribution density function describes the distribution of errors under the component. In this embodiment, ωj is the weight of the jth Gaussian component, indicating the importance of the component in the overall model. is the Gaussian distribution density function, which represents the probability density of the error e under the jth Gaussian component. is the mean of the jth Gaussian component, indicating the center position of the component, is the variance of the jth Gaussian component, indicating the distribution range of the component.

[0033] like Figure 3 As shown, as an embodiment of the present invention, the proposed intelligent surveying and mapping method further includes the following steps: S3. Update the terrain error probability model to improve surveying and mapping accuracy (plane error ≤ 2cm, elevation error ≤ 1cm). The implementation steps include: S3-1. Deploy surveying equipment in the surveying area (pre-buried pile foundation area) and obtain original terrain data that accurately covers the terrain mutation area and the key node area of ​​the pile foundation through the coordinates of the measuring points. The original terrain data includes: elevation data Z that characterizes the basic terrain attributes of the surveying area collected by the total station surveying instrument, GPS equipment and drone photogrammetry equipment i,j And point cloud data PC i,j In this embodiment, high-density measurement is performed in the area surrounding the pile foundation (such as radius r=2d) to obtain elevation data Z i,j , with an accuracy of ±2 mm, the GPS device used is set to provide global geographic positioning, ensuring that the coordinate system is WGS84, and the coverage error is controlled within ±5 cm. When the drone photogrammetry equipment is used for measurement: point cloud data is collected through a multispectral sensor PC i,j , with a resolution of 0.1 m, focusing on covering terrain mutation areas with slope S>15∘.

[0034] S3-2, outlier removal: remove outliers caused by noise from surveying equipment or environmental interference (such as vegetation occlusion), use the 3σ principle to filter outliers in elevation data, and clean invalid points in point cloud data through statistical filtering. In this embodiment, when removing outliers, first perform an analysis on the elevation data Z. i,j Filter and calculate the global elevation mean μ Z and standard deviation σ Z , and then remove those exceeding μ Z ±3σ Z The elevation values ​​within the range of three standard deviations around the mean are retained. In practice, elevation values ​​outside this range are considered outliers and are removed. , , where M and N are the number of rows and columns of the grid, respectively, which determines the total number of grids to be MN.

[0035] For point cloud data cleaning, radius filtering technology (such as Radius Outlier Removal) is used to calculate the distance dk from each point cloud data to the center of its grid. If the distance dk exceeds twice the final grid size 2Δfinal , the point cloud data point is considered to be an isolated point and is removed from the data set. In this embodiment, isolated points with less than 5 points in the neighborhood are removed. This ensures that the retained point cloud data is reasonable in spatial distribution and removes abnormal points caused by measurement errors or environmental interference. It can be understood that through the above steps, the outliers and invalid points in the original terrain data can be effectively cleaned up, thereby improving the accuracy and reliability of the terrain error probability model finally constructed.

[0036] S3-3, dynamically adjust the grid size to adapt to the terrain complexity and pile foundation layout, such as compressing the grid in the pile area to increase data density and construct a structured data set D. The specific implementation steps are: S3-31. Dynamically adjust the grid size according to the terrain complexity and pile foundation layout: For the pile location area, compress the grid size to Δ final / 2 to double the measurement point density; for terrain mutation areas (slope S>15°), keep the grid size Δ final = 1 meter; for flat areas (slope S < 15°), the grid size is expanded to Δ final =2m; S3-32, Next, coordinate mapping is performed to ensure that the measuring points are accurately mapped to the corresponding grid cells. Mapping to grid index (i,j): , , where and is the minimum coordinate of the surveying area.

[0037] S3-33, perform Z-score standardization on the elevation data and construct a structured dataset D, D = {( Z' i,j ,PC xc , yc .las)}, containing the standardized elevation data Z' i,j And the corresponding point cloud file PC xc , yc .las, where the point cloud file is named according to the coordinates of the grid center, such as PC105.535.5.las, in order to associate its location information.

[0038] S3-4. Extract the standardized elevation value Z' of each grid in the structured data set D. i,j , point cloud density N i,j (number of point clouds in the grid), elevation deviation e i,j (The absolute value of the difference between the measured value and the theoretical value). Construct the model input vector V i,j , V i,j = [Z' i,j , Ni,j , e i,j ] for subsequent Gaussian mixture model (GMM) training and optimization to quantify the spatial distribution of terrain errors. In specific implementation, for the point cloud density N i,j Based on the above coordinate mapping steps, after the point cloud data is mapped to the grid cells, the number of point clouds in each grid cell (i, j) is counted and recorded as the point cloud density N i,j ; For elevation deviation e i,j , calculated by quantizing the average deviation of the point cloud elevation within the grid cell (i, j) and the standardized elevation value: , where Zp is the elevation value of the pth point cloud point, which represents the elevation data actually measured.

[0039] S3-5, perform feature selection and fuzzy processing, and input the model representing the terrain features into the vector V i,j , V i,j =[Z' i,j , N i,j , e i,j ] into a fuzzy set, which is converted into a quantifiable membership value to generate a fuzzy vector F i , F i =[μ 低 (Z' i,j ),μ 中 (N i,j ),μ 高 (e i,j ),…], and then quantify the influence of each feature data on the terrain error. Among them, for the standardized elevation value Z' i,j , construct the triangle membership function, and fuzzify it into three fuzzy sets of "low elevation", "medium elevation" and "high elevation", which correspond to different elevation ranges, thus reflecting the influence of elevation data on terrain error. i,j The low elevation membership function in is defined as follows: when Z' i,j In [Z min ,Z mid1 ] interval, the membership degree changes with Z' i,j increases and decreases linearly until Z mid1 When the value is beyond this interval, the membership is always 0. i,j The mid-to-high-altitude membership function in is defined as follows: min ,Z mid1 ] interval, the membership degree changes with Z' i,j Increases linearly, in (Z mid1 ,Z mid2 ] interval, the membership degree changes with Z' i,jWhen the value increases, it decreases linearly. When it exceeds this range, the membership is 0. i,j The high altitude membership function in is defined as follows: when Z' i,j In [Z mid2 ,Z max ] interval, the membership degree changes with Z' i,j Increases linearly until Z max When it exceeds this interval, the membership degree remains at 1 (if Z' i,j More than Z max ) or always equal to 0 (if Z' i,j Below Z mid2 ).

[0040] For the point cloud density N i,j , through the trapezoidal membership function fuzzy into "low density", "medium density" and "high density", quantifying the impact of point cloud density data reliability on terrain error. In this embodiment, when the point cloud density N i,j Less than or equal to the low density threshold N low When N i,j In (N low ,N mid ] interval, the membership degree decreases linearly with the increase of density until N mid When it exceeds this interval, the membership degree is always 0. low ,N mid ] interval, the membership increases linearly with the density. mid ,N high ] interval, the membership decreases linearly with the increase of density. When it exceeds this range, the membership is 0. i,j In [N mid ,N high ] interval, the membership increases linearly with the density until N high reaches 1 when the density exceeds N high When the membership degree remains at 1, if the density is lower than N mid , the degree of membership is always 0.

[0041] For the elevation deviation e i,j , the triangle membership function is used to fuzzy it into "low deviation", "medium deviation" and "high deviation" to directly reflect the degree of measurement error. In this embodiment, for the elevation deviation e i,j The low deviation membership function of is defined as follows: when the elevation deviation e i,j In [0,e low ] interval, the membership degree decreases linearly with the increase of deviation until e low When it exceeds this interval, the membership is always 0. Medium deviation membership function: In [0,emid ] interval, the membership increases linearly with the increase of deviation. mid ,e high ] interval, the membership decreases linearly with the increase of deviation. When it exceeds this range, the membership is 0. High deviation membership function: When the deviation e i,j In [e high ,e max ] interval, the membership increases linearly with the increase of deviation until e max reaches 1, when the deviation exceeds e max When the membership degree remains at 1, if the deviation is lower than e high , the degree of membership is always 0.

[0042] Based on the above technical concept, it can be understood that by blurring the above features, the model can process complex terrain data more flexibly and achieve refined processing of terrain errors, thereby improving the adaptability and prediction accuracy of the model under complex terrain conditions.

[0043] S3-6. Construct a membership matrix to identify the key features of terrain data. It is understandable that the key features of terrain data include: Flat area: The terrain is relatively flat, with a small slope and low curvature. In actual infrastructure construction, these areas are characterized by gentle elevation changes and uniform data distribution, and usually do not require high-density measurement points; Terrain mutation area: The terrain changes dramatically, the slope is large (such as a slope greater than 15°), and the curvature is high. These areas require special attention in actual infrastructure construction because they have a significant impact on construction accuracy and stability. It is usually necessary to increase the density of measurement points to capture terrain details; Pile position area: The key area for pile foundation construction, usually centered on the pile foundation coordinates and with a radius of 2d around it. In actual infrastructure construction, these areas require high-density measurement points to ensure the accuracy of pile foundation construction. The specific implementation steps include: S3-61. Construct a clustering algorithm to minimize the objective function: , where N is the total number of grids, indicating the number of grids divided in the entire survey area, and C=3 is the number of clusters, representing the flat area, mutation area, and pile position area, respectively. It should be noted that the three terrain types have different correction requirements in the actual intelligent surveying of the pile foundation pre-embedded area. ic is the membership degree of grid i to cluster c, indicating the degree to which grid i belongs to cluster c, satisfying ∑ c=1 C u ic=1, the purpose is to identify the distribution of different terrain features in the pile foundation pre-buried area, m=2 is the fuzzy index, which is used to describe the fuzziness of features such as standardized elevation value, point cloud density, elevation deviation, etc., in order to control the fuzziness of the membership. It can be understood that a larger fuzzy index allows the grid to belong to multiple clusters at the same time, which is particularly important for processing the transition zone of terrain features in the pile foundation pre-buried area. vc is the center vector of cluster c, which characterizes the core features of the cluster and provides a basis for the subsequent feature cluster importance evaluation and fuzzy rule base construction. ||·|| is the Euclidean distance, which is used to measure the distance between the fuzzy vector Fi and the cluster center vc to ensure the accuracy and reliability of the clustering results.

[0044] S3-62, construct a membership update formula, update the cluster center, and realize the recognition of key features of the collected terrain data. In specific implementation, the membership update formula is: , where v d is the center vector of cluster d.

[0045] Cluster Center Update: ; In order to avoid infinite iterations, the following comprehensive termination conditions are set in the implementation to ensure the stability and efficiency of the clustering process: set a maximum number of iterations, such as when the number of iterations reaches Tmax = 100, the iteration is stopped regardless of whether the clustering is fully converged. Or it is stopped when any one of the conditions of membership matrix change, cluster center change or objective function change is met. Among them, the membership matrix change condition: the change of the membership matrix U in two consecutive iterations is less than the system set threshold; the cluster center change condition: the change of the cluster center vc in two consecutive iterations is less than the system set threshold; the objective function change condition: the change of the objective function J in two consecutive iterations is less than the system set threshold.

[0046] Get the membership matrix U, U=[u ic ] N×C， To represent the membership of each grid to each cluster; the cluster center vectors {v1, v2, v3} correspond to the core features of the flat area, mutation area, and pile area, respectively.

[0047] Based on the above technical concept, it can be understood that by minimizing the objective function J, the clustering process continuously optimizes the membership matrix U and the cluster center vc, and finally outputs the membership matrix U and the cluster center vc, the terrain error can be finely processed in the subsequent intelligent mapping of the pile foundation pre-buried area.

[0048] S3-7. It should be noted that in topographic surveying, due to the complexity and diversity of topographic features, such as flat areas, terrain mutation areas, and pile position areas, traditional measurement methods and models are often difficult to accurately capture terrain changes, resulting in errors in measurement data. These errors will affect construction accuracy and project costs. Therefore, in this embodiment, it is continued to propose the use of feature cluster importance evaluation to quantify the impact of each feature on terrain errors, ensure that the measuring points can accurately cover terrain mutation areas and key nodes of pile foundations, and avoid data redundancy in non-critical areas. The specific implementation steps are: First, the compactness of the feature cluster is evaluated by calculating the intra-cluster variance. The smaller the variance, the higher the consistency of the intra-cluster data and the higher the importance score of the feature cluster. Secondly, the discrimination between clusters is evaluated by calculating the distance between cluster centers. The larger the distance, the higher the discrimination between clusters and the higher the importance score of the feature cluster. Thirdly, the correlation between each feature and the cluster center is calculated. Features with a correlation coefficient greater than 0.7 are selected as key features. It is understandable that these key features usually include standardized elevation values, point cloud density and elevation deviation, which have the greatest impact on terrain errors. Finally, this key feature is input into the fuzzy rule base built based on expert experience to provide a basis for subsequent terrain error correction, thereby ensuring that the model can dynamically adjust the correction weight according to changes in the actual measurement environment and improve the adaptability and prediction accuracy of the model.

[0049] In this embodiment, the specific steps for implementing the correction of the collected data features are: Firstly, the relationship between feature combination and correction weight is defined through the fuzzy rule base built based on expert experience, such as the rule "IF high deviation AND low density THEN high weight", in which the trigger strength of the rule is determined by the membership of the relevant features, such as the high membership of elevation deviation and the low membership of point cloud density; secondly, the output fuzzy set is constructed by Mamdani fuzzy controller reasoning, and the specific correction weight is obtained by defuzzification through the centroid method; finally, the elevation and point cloud density are adjusted using the correction weight to ensure that the output of the terrain error probability model is more accurate and adaptable to different terrain conditions.

[0050] S3-8, update the terrain error probability model. The specific implementation steps are: The corrected elevation values ​​and point cloud density are input into the Gaussian mixture model (GMM), and the model parameters, including weights, mean and covariance matrix, are re-estimated using the EM algorithm. The weights reflect the mixing ratio of the corrected error distribution, while the mean and covariance describe the center and distribution range of each Gaussian component. With the updated parameters, the model can more accurately describe the probability distribution of terrain errors, thereby improving the prediction accuracy.

[0051] like Figure 4As shown, as an embodiment of the present invention, the proposed intelligent surveying and mapping method further includes the following steps: S4. Based on the updated terrain error probability model, high-precision construction optimization is achieved. The specific implementation steps are: Use AutoCAD Civil 3D to generate sub-meter terrain surfaces, combine with OpenCV library to extract pile foundation boundaries, and build high-precision BIM models; Through the NSGA-II algorithm and ROS mechanical path planning, with the goal of minimizing construction errors (depending on the terrain error probability model) and maximizing efficiency, high-risk areas are dynamically avoided and the optimal pre-embedded points are recommended; Using the Unity digital twin platform to visualize construction data in real time, continuously update the error model and adjust the embedded points; During the acceptance stage of infrastructure projects, the design model is compared with the corrected terrain to generate a deviation report to ensure that the plane error is ≤2cm and the elevation error is ≤1cm, so as to achieve accurate positioning of the pre-buried area of ​​the pile foundation.

[0052] As a second aspect of the present invention, an intelligent surveying and mapping device for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation is proposed, comprising a memory and a processor, wherein the memory comprises an intelligent surveying and mapping program for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation, and when the intelligent surveying and mapping program for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation is executed by the processor, the intelligent surveying and mapping method for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation proposed above is implemented.

[0053] like Figure 5-Figure 7 As shown, as an embodiment of the present invention, the proposed total station surveying instrument includes: A surveying and mapping tripod support frame 1, the upper end of which is fixedly provided with a rectangular displacement component 2 for providing a movable guide rail, a level 3 for adjusting the horizontal state is placed through the upper end of the rectangular displacement component 2, and a surveying and mapping instrument component 4 for planning and surveying is rotatably sleeved on the upper end of the level 3.

[0054] In one embodiment of the present invention, the surveying and mapping tripod support frame 1 includes a central round rod frame 11, a support angle adjustment component 12, and a height adjustment component. It can be understood that the central round rod frame 11 is the core component of the surveying and mapping tripod support frame 1, and plays a supporting and connecting role in the overall structure. The upper end thereof is sleeved with an upper collar 112, and the lower end thereof is sleeved with a lower collar 111. The distance between the upper collar and the lower collar can be adjusted by adjusting the height of the upper collar to meet different measurement requirements. The design purpose of the central round rod frame 11 is to ensure the stability and flexibility of the support angle adjustment component 12 and the height adjustment component 13.

[0055] The support angle adjustment assembly 12 is a key part of the surveying tripod support frame, which is used to adjust the support angle to adapt to uneven ground conditions. The support angle adjustment assembly 12 is provided with multiple groups, and each group of the support angle adjustment assembly 12 includes a coarse sleeve rod 121, an angle clamping block 122 and an angle support rod 123. Among them, the coarse sleeve rod 121 is connected to the upper sleeve ring 112, and the angle support rod 123 is connected to the lower sleeve ring 111. The angle clamping block 122 is installed between the coarse sleeve rod 121 and the angle support rod 123 to fix and adjust the angle between the two. By adjusting the angle clamping block 122, the angle between the coarse sleeve rod 121 and the angle support rod 123 can be changed, thereby adjusting the support height. This design enables the surveying instrument to remain stable on an inclined ground, ensuring the accuracy of the measurement data from the perspective of physical parameters.

[0056] The height adjustment assembly 13 is used to fine-tune the overall height of the surveying instrument to adapt to different measurement environments. The height adjustment assembly 13 is provided with multiple groups, each of which includes a thin sleeve rod 131, a limit clamping block 132, a support ball 1311 and a pin 1312. Among them, the thin sleeve rod 131 is movably sleeved in the thick sleeve rod 121, and the height can be adjusted by telescopic movement, and is fixed by the limit clamping block 132. The support ball 1311 provides a stable support point, and the pin 1312 is inserted into the ground to ensure the stability of the structure, so that the surveying instrument can quickly adapt to different terrain conditions.

[0057] In one embodiment of the present invention, the rectangular displacement assembly 2 includes a displacement rectangular frame 21 and a limit cover 22. It can be understood that the displacement rectangular frame 21 is the core part of the rectangular displacement assembly, which is used to provide the movement of the level. The displacement rectangular frame 21 is provided with a lower linear groove 211 and an upper linear groove 212 which are perpendicular to each other. The lower linear groove and the upper linear groove have different depths, which ensure that the level can move slightly within the horizontal range. Rectangular rods 213 are provided on both sides, and a limit opening 2131 is provided in the middle position, which is used to limit the level, ensure that the level remains in a horizontal state during movement, and reduce measurement errors.

[0058] The limit cover 22 is fixedly arranged on the upper end of the displacement rectangular frame 21, and is used for limiting the moving range of the level, wherein a center mark 221 is drawn or coated on the upper end of the limit cover 22 to mark the center position of the disc, a cross groove 222 is opened in the center of the disc, and side clips 223 are opened on both sides for limiting the level, thereby ensuring accurate calibration and stable movement of the level.

[0059] In one embodiment of the present invention, in order to ensure the precise movement and limitation of the level and prevent deviation during movement, an in-slot slider that adapts to the displacement rectangular frame 21 and the cross-shaped slot 222 can be installed at the bottom thereof, and side clamping blocks are arranged around it so that the in-slot slider can be movably engaged in the cross-shaped slot of the limiting cover and slidably engaged in the side clamping port 223 through the side clamping blocks.

[0060] The technical scope of the present invention is not limited to the contents in the above description. Those skilled in the art can make various deformations and modifications to the above embodiments without departing from the technical idea of ​​the present invention, and these deformations and modifications should all fall within the protection scope of the present invention.

Claims

1. An intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation, characterized in that: Includes steps: Determine the constraints and initialize the M×N matrix that matches the dimensions of the grid cells (i, j) in the survey area; use the Sigmoid function to calculate the terrain constraint strength value T (i,j) , and combined with Gaussian kernel density to calculate the pile foundation constraint strength distribution value P (i,j) , the dynamic constraint association matrix is ​​generated by linear superposition and nonlinear correction, , where α and β are weight coefficients used to measure the interaction between terrain and pile foundation constraints, and η is the interaction enhancement coefficient; According to the normalized dynamic constraint association matrix, the density of measuring points in each grid unit in the surveying and mapping area is determined, wherein the higher the constraint strength is set, the higher the density of measuring points is proportionally increased. Secondly, the slope and curvature data of all grid units in the surveying and mapping area are integrated, combined with the preset weight coefficient, the terrain complexity estimation of the current surveying and mapping area is calculated, the grid size required for surveying and mapping is dynamically adjusted, and the logic of measuring point layout that meets the constraint conditions is generated; Deploy equipment, generate dense coordinates based on the measurement point layout logic and collect elevation and point cloud data. After preprocessing, construct a structured data set, fuzzify it into low, medium and high fuzzy sets through fuzzy processing, and use fuzzy clustering to extract the collected data features; Gaussian components are distributed to different terrains in the surveying and mapping area, and the EM algorithm is used for iterative optimization until the model converges. The characteristics of the collected data as the model input vector are corrected according to the fuzzy rule library and then input into the model to output the error probability density that represents the terrain error in the surveying and mapping area, thereby achieving high-precision construction optimization.

2. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 1 is characterized in that: The constraint conditions are the terrain mutation area with a slope value greater than the slope threshold and the pile foundation coordinates (x k ,y k ) The key node area of ​​the pile foundation group with a radius of n times the average spacing d of the pile foundations; the measurement point layout logic that meets the above constraints is as follows: For the key node area of ​​the pile foundation group: at the pile foundation coordinates (x k ,y k ) In the survey area with a radius of nd around, the grid density is increased to n times the original, and the grid size is reduced to Δ final / n, where the output dense measurement point coordinates Based on the starting point, the index k is shifted alternately according to its parity, with a horizontal interval of Δ final / n, vertical direction increases by fixed step length; for terrain mutation area: output dense measurement point coordinates Dynamically adjusts based on the local curvature of the terrain.

3. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 1 is characterized in that: Dynamically adjust the grid size Δ final The specific steps are: First, calculate the measurement point density, ρ(i,j)=ρ base ×(1+h×W nor (i,j)), where W nor (i, j) is the value of grid cell (i, j) in the normalized constraint association matrix; Secondly, through the formula , calculate the terrain complexity estimate C, where ρ base is the basic measurement point density, ρ base =1 / Δ 2 , represents the expected number of basic measuring points within the unit grid area, the coefficient h is the magnification factor of the constraint strength to the measuring point density, Δ is the basic grid size, Δ=d / (k×C), k is the adjustment coefficient, is the slope value of the i-th measuring point, is the curvature value of the i-th measuring point, is the maximum slope value in the survey area, is the maximum curvature value in the survey area, a and b are the weight coefficients of slope and curvature respectively; Finally, through the formula , dynamically adjust the grid size Δ final , where η is an adjustment index and ξ is an adjustment coefficient.

4. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 1 is characterized in that: The specific steps to build a structured data set are: First, the grid size is dynamically adjusted according to the terrain complexity and pile foundation layout; Secondly, coordinate mapping is performed to convert the coordinates of the measuring points Mapping to grid index (i,j): , , where and is the minimum coordinate of the survey area; Finally, the elevation data is normalized by Z-score, and the standardized elevation data Z' is constructed. i,j And the corresponding point cloud file PC xc , yc .las, dataset D.

5. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 1 or 4, characterized in that: The specific steps of using fuzzy clustering to extract the characteristics of collected data are as follows: First, in the structured data set D, the standardized elevation value Z' of each grid is extracted i,j , point cloud density N i,j , elevation deviation e i,j， And transform it into a fuzzy set to generate a fuzzy vector F i ; Second, construct a clustering algorithm to minimize the objective function: , where N is the total number of grids, C is the number of clusters, and u ic is the membership degree of grid i to cluster c, indicating the degree to which grid i belongs to cluster c, satisfying ∑ c=1 C u ic =1, m=2 is the fuzzy index, vc is the center vector of cluster c, ||·|| is the Euclidean distance; Next, construct the membership update formula, update the cluster center, and realize the recognition of the characteristics of the collected data. The membership update formula is: , where v d is the center vector of cluster d; Finally, we get the membership matrix U: U=[u ic ] N×C , to indicate the membership of each grid to each cluster.

6. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 5 is characterized in that: In the process of cluster center update, when the number of iterations reaches Tmax = 100, the iteration is stopped regardless of whether the clustering is fully converged or not, or when any one of the conditions of membership matrix change, cluster center change or objective function change is met: Membership matrix change condition: the change of membership matrix U in two consecutive iterations is less than the system set threshold; Cluster center change condition: the change of cluster center vc in two consecutive iterations is less than the system set threshold; Objective function change condition: The change of the objective function J in two consecutive iterations is less than the system set threshold.

7. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 5 is characterized in that: In the process of realizing feature recognition of collected data, it is also necessary to use the method of feature cluster importance evaluation to quantify the impact of key features of each collected data on terrain error, ensure that the measuring points can accurately cover the terrain mutation area and key nodes of the pile foundation, and avoid data redundancy in non-critical areas.

8. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 1 or 7, characterized in that: The specific steps to achieve the correction of collected data features are: Firstly, the relationship between feature combination and correction weight is defined based on the fuzzy rule base, and the rule triggering strength is determined by the membership degree of relevant features; secondly, the output fuzzy set is constructed by Mamdani fuzzy controller reasoning, and the specific correction weight is obtained by defuzzification through the centroid method; finally, the elevation and point cloud density are adjusted using the correction weight to ensure that the model output is more accurate and adaptable to different terrain conditions.

9. The intelligent mapping method for pile foundation pre-embedded area based on fuzzy coordinate compensation according to claim 1 is characterized in that: The calculation formula for the error probability density that outputs the terrain error in the surveyed area is: , where M is the number of Gaussian components in the model. The model consists of M Gaussian components, each with a weight of ωj and a mean of , the variance is , is the Gaussian distribution density function, which represents the probability density of the error e under the jth Gaussian component. is the mean of the jth Gaussian component, indicating the center position of the component, is the variance of the jth Gaussian component, indicating the distribution range of the component.

10. An intelligent mapping device for pile foundation pre-embedded area based on fuzzy coordinate compensation, characterized in that: include: A memory and a processor, wherein the memory includes an intelligent mapping program for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation, and when the intelligent mapping program for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation is executed by the processor, the intelligent mapping method for a pre-buried area of ​​a pile foundation based on fuzzy coordinate compensation according to any one of claims 1 to 9 is implemented.

Images