Intelligent positioning and precise construction method for pile foundation in karst area

Abstract

The invention provides a karst area pile foundation intelligent positioning and precise construction method which comprises the steps that a karst development characteristic data set of a target engineering area is obtained, and the karst development characteristic data set comprises a three-dimensional geological exploration data set and a karst attribute data set; and preprocessing the data set to obtain a karst preprocessed data set. And based on a feature extraction model, performing feature extraction on the preprocessed three-dimensional geological exploration data set to generate a three-dimensional geological feature map. And identifying the map through a karst cavity identification model to generate a karst cavity distribution thermodynamic diagram. And karst cave feature conversion processing is conducted on the karst preprocessing data set, and a pile foundation construction feature data set is obtained. And according to the karst cavity distribution thermodynamic diagram, constraint processing is conducted on the pile foundation construction characteristic data set, and a pile foundation constraint boundary diagram is generated. And outputting a pile foundation end hole positioning coordinate set according to a pile foundation positioning optimization algorithm and the pile foundation constraint boundary diagram. The construction safety and accuracy of the pile foundation in the karst area can be improved, and the construction risk and cost are reduced.

Description

Technical Field

[0001] The present invention relates to the field of karst geological engineering and intelligent construction technology, and more specifically, to a method for intelligent positioning and precise construction of pile foundations in karst areas. Background Art

[0002] When constructing pile foundations in karst areas, traditional methods face two major technical bottlenecks: First, due to the insufficient spatial positioning accuracy of caves, traditional geological exploration methods such as advance drilling can only obtain discrete point data, making it difficult to construct a complete three-dimensional cave model. This limitation leads to significant deviations between the design coordinates of the pile foundation and the actual bearing layer position, which in turn causes construction quality problems such as insufficient pile length and hanging pile ends. Especially when the thickness of the cave roof is less than 3 meters or the filling material is plastic, the error rate of manual judgment remains high when the pile foundation needs to penetrate the cave or undergo reinforcement treatment. Secondly, during the dynamic construction process, changes in geological conditions such as karst fissures and groundwater infiltration can lead to sudden engineering disasters, such as rapid loss of mud, negative pressure collapse of the overburden, and abnormal slippage of the drill bit.

[0003] Existing technologies rely too heavily on manual judgment and experience, making it difficult to respond promptly to these dynamic changes. This delays emergency response and significantly increases the incidence of construction accidents. For example, when installing steel casing in multi-layered karst caves, it is necessary to penetrate the cave roof layer by layer. However, when faced with sudden slurry leakage, the casing's lowering often lags behind the speed of the disaster, easily leading to serious drilling accidents. These technical shortcomings severely restrict the safety and reliability of pile foundation construction in karst areas. Summary of the Invention

[0004] The present invention provides a method for intelligent positioning and precise construction of pile foundations in karst areas, comprising:

[0005] Acquire a karst development characteristic data set of a target engineering area, wherein the karst development characteristic data set includes a three-dimensional geological exploration data set and a karst attribute data set;

[0006] Preprocessing the karst development characteristic data set to obtain a karst preprocessed data set, wherein the karst preprocessed data set includes a three-dimensional geological exploration preprocessed data set and a karst attribute preprocessed data set;

[0007] Based on the feature extraction model, feature extraction is performed on the three-dimensional geological exploration preprocessing data group to obtain a three-dimensional geological feature map;

[0008] The three-dimensional geological feature map is identified by using a karst cavity identification model to generate a karst cavity distribution thermal map;

[0009] Performing cave feature conversion processing on the karst preprocessing dataset to obtain a pile foundation construction feature dataset, wherein the pile foundation construction feature dataset includes a pile foundation coordinate dataset and a bearing layer feature dataset;

[0010] Based on the karst cavity distribution thermodynamic map, the pile foundation construction feature data set is subjected to constraint processing to generate a pile foundation constraint boundary map;

[0011] According to the pile foundation positioning optimization algorithm and the pile foundation constraint boundary map, a pile foundation final hole positioning coordinate set is output.

[0012] Furthermore, the step of obtaining a karst development characteristic dataset of the target engineering area includes:

[0013] Acquiring an original geological exploration data set as an initial exploration data set, wherein the original geological exploration data set includes a three-dimensional seismic wave data set and a geological radar data set;

[0014] According to a pre-set pile foundation construction area, spatially screening the three-dimensional seismic wave data group in the initial exploration set to obtain a target area exploration set;

[0015] According to the karst development intensity threshold, feature screening is performed on the geological radar data set of the target area exploration concentration to obtain a karst feature data set;

[0016] Performing position screening on the karst feature data set according to the pile foundation construction coordinate range to obtain a target position feature set;

[0017] The karst attribute data group is concentrated based on the target position feature, and divided into a three-dimensional geological exploration data group and a karst attribute data group.

[0018] Furthermore, the preprocessing of the karst development characteristic dataset to obtain a karst preprocessed dataset includes:

[0019] For each three-dimensional geological exploration data in the karst development characteristic data set, the following steps are performed:

[0020] Acquiring attribute fields of the three-dimensional geological exploration data;

[0021] Constructing a karst anomaly area identifier based on the attribute fields of the three-dimensional geological exploration data;

[0022] generating pre-processed geological exploration data based on the karst anomaly area identification;

[0023] Converting the pre-processed geological exploration data into a preset data format to obtain three-dimensional geological exploration pre-processed data;

[0024] The various 3D geological exploration preprocessing data are integrated into a karst preprocessing data set.

[0025] Furthermore, the feature extraction model is used to extract features from the three-dimensional geological exploration preprocessing data set to obtain a three-dimensional geological feature map, including:

[0026] According to the karst identification characteristic dimension, feature reconstruction is performed on each 3D geological exploration preprocessed data in the 3D geological exploration preprocessed data group to obtain exploration data that meets the characteristic dimension;

[0027] The exploration data satisfying the characteristic dimensions are subjected to spatial interpolation processing to obtain a three-dimensional geological characteristic map.

[0028] Furthermore, the karst pre-processing dataset is subjected to cave feature conversion processing to obtain a pile foundation construction feature dataset, including:

[0029] According to the pile foundation construction parameter standard, parameter conversion is performed on the karst attribute preprocessing data group in the karst preprocessing data set to obtain attribute data that meet the construction parameter standard;

[0030] Coordinate encoding is performed on each pile foundation coordinate data meeting the construction parameter standard and each bearing layer characteristic data meeting the construction parameter standard to obtain a pile foundation coordinate data set and a bearing layer characteristic data set;

[0031] performing coordinate calibration on the pile foundation coordinate data set according to the pile foundation design specifications to obtain a pile foundation construction coordinate data set;

[0032] The pile foundation construction coordinate dataset and the bearing layer characteristic dataset are integrated into a pile foundation construction characteristic dataset.

[0033] Furthermore, the outputting of the pile foundation final hole positioning coordinate set according to the pile foundation positioning optimization algorithm and the pile foundation constraint boundary map includes:

[0034] According to the pile foundation diameter specification, the pile foundation constraint boundary map is subjected to buffer boundary processing to obtain a pile foundation obstacle avoidance buffer zone map;

[0035] Based on the pile foundation obstacle avoidance buffer zone map, position adjustment is performed on the pile foundation construction coordinate data set to generate an optimized pile foundation coordinate set;

[0036] Performing collision detection on the optimized pile foundation coordinate set through the pile foundation positioning verification model to obtain a verified pile foundation coordinate set;

[0037] The verified pile foundation coordinate set is converted into a final hole positioning coordinate output format to obtain a pile foundation final hole positioning coordinate set.

[0038] Furthermore, the karst cavity identification model is used to identify the three-dimensional geological feature map to generate a karst cavity distribution thermal map, including:

[0039] According to the karst development classification standard, color mapping relationships of different karst rates are set; the three-dimensional geological characteristic map is continuously sliced ​​to obtain karst characteristic layers at various elevations;

[0040] Based on the parameters of the cavity identification model, the cavity probability of each karst characteristic layer is calculated to generate a karst probability matrix;

[0041] The karst probability matrix is ​​converted into a three-dimensional thermal distribution map through the color mapping relationship.

[0042] Furthermore, based on the karst cavity distribution thermodynamic map, the pile foundation construction feature data set is subjected to constraint processing to generate a pile foundation constraint boundary map, including:

[0043] Extracting a vertex coordinate set of a high-risk karst area in the karst cavity distribution thermodynamic map;

[0044] According to the preset safety distance threshold, a constrained polygon corresponding to each vertex coordinate set is constructed;

[0045] Performing a spatial Boolean operation on the constraint polygon and the pile foundation design coordinates to obtain a constructible area of ​​the pile foundation;

[0046] Boundary topological data of the pile foundation construction area is generated to form a pile foundation constraint boundary map.

[0047] Furthermore, the performing of collision detection on the optimized pile foundation coordinate set by using the pile foundation positioning verification model includes:

[0048] Establishing a cylindrical space model for pile foundation construction, wherein the diameter of the cylindrical space model is equal to 1.2 times the designed diameter of the pile foundation;

[0049] Calculate the minimum clear distance between adjacent pile foundation space models;

[0050] When the minimum clearance value is less than the preset safety clearance threshold, it is marked as a collision pile foundation;

[0051] The spatial coordinates of the collision pile foundation are adjusted until all minimum clearance values ​​are greater than a preset safety clearance threshold.

[0052] Furthermore, it also includes:

[0053] Control the drilling rig positioning system according to the final hole positioning coordinate set of the pile foundation to implement precise drilling construction;

[0054] Collect drilling offset data in real time and generate construction error distribution map;

[0055] When the offset value in the construction error distribution map is greater than a preset threshold, an automatic correction instruction is triggered;

[0056] Verify the matching degree between the corrected drilling coordinates and the final positioning coordinates of the pile foundation, and output the pile foundation hole quality report.

[0057] The above embodiments of the present invention have at least the following beneficial effects:

[0058] 1. By acquiring and preprocessing a dataset of karst development characteristics and combining it with a feature extraction model and a karst cavity identification model, we can accurately generate a karst cavity distribution heat map, thereby providing a detailed geological risk reference for pile foundation construction, effectively avoiding engineering accidents caused by karst cavities during pile foundation construction, and ensuring construction safety.

[0059] 2. Constraint processing of the pile foundation construction feature dataset is performed based on the karst cavity distribution thermodynamic map to generate a pile foundation constraint boundary map. Combined with the pile foundation positioning optimization algorithm, the final pile hole positioning coordinate set is output. This achieves intelligent and precise pile foundation positioning, reduces pile foundation positioning deviations caused by human factors or inaccurate traditional methods, improves pile foundation construction quality, and ensures that the pile foundation bearing capacity meets engineering requirements.

[0060] 3. This method covers the entire process from data acquisition and processing to construction positioning, forming a complete set of pile foundation construction solutions in karst areas. Compared with traditional construction methods, it can more systematically cope with the complex geological conditions in karst areas, reduce construction difficulty, shorten construction period, and improve construction efficiency, which is of great significance to promoting engineering construction in karst areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0062] Figure 1 A schematic flow chart of a method for intelligent positioning and precise construction of pile foundations in karst areas provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0063] The technical solutions of this application will be described clearly and completely below, in conjunction with the accompanying drawings. It should be understood that the described embodiments represent only a portion of the embodiments of this application, and not all of them. The components of this application, generally described and illustrated in the drawings herein, may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but rather merely represents selected embodiments of this application. All other embodiments derived by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application. It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. Furthermore, in the description of this application, the terms "first," "second," etc., are used solely to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0064] like Figure 1 As shown, this application proposes a method for intelligent positioning and precise construction of pile foundations in karst areas, including:

[0065] S1. Acquire a karst development characteristic dataset of a target engineering area, wherein the karst development characteristic dataset includes a three-dimensional geological exploration data set and a karst attribute data set;

[0066] S2. Preprocessing the karst development characteristic data set to obtain a karst preprocessed data set, wherein the karst preprocessed data set includes a three-dimensional geological exploration preprocessed data set and a karst attribute preprocessed data set;

[0067] S3. Based on the feature extraction model, extract features from the 3D geological exploration preprocessing data set to obtain a 3D geological feature map;

[0068] S4. Using the karst cavity identification model, identify the three-dimensional geological feature map and generate a karst cavity distribution thermal map;

[0069] S5. Perform cave feature conversion processing on the karst preprocessing dataset to obtain a pile foundation construction feature dataset, wherein the pile foundation construction feature dataset includes a pile foundation coordinate dataset and a bearing layer feature dataset;

[0070] S6. Based on the karst cavity distribution thermal map, the pile foundation construction feature data set is constrained and processed to generate a pile foundation constraint boundary map;

[0071] S7. Output the pile foundation final hole positioning coordinate set according to the pile foundation positioning optimization algorithm and the pile foundation constraint boundary map.

[0072] It should be noted that the karst development characteristic dataset refers to a multi-source data set integrating 3D geological exploration and karst attribute parameters. Specifically, it can be acquired through a combination of 3D seismic wave detection and geological radar scanning. It is used to construct a full-space geological model covering the construction area. This dataset provides high-resolution input for subsequent intelligent analysis, resolving the incomplete 3D modeling issues caused by traditional discrete data.

[0073] Preprocessing involves filtering out noise and standardizing the format of raw exploration data. This can be achieved using an outlier removal algorithm and a unified coordinate conversion protocol to ensure that data collected by different exploration devices maintains consistency in spatial coordinate systems and accuracy levels. Preprocessing eliminates the interference of data heterogeneity on model training and improves the reliability of subsequent feature extraction.

[0074] Specifically, the feature extraction model uses a 3D convolutional neural network to process a 3D geological exploration preprocessed data set, with input being standardized grid data (resolution 0.2m × 0.2m × 0.5m). The model extracts geological features through progressive convolutional layers:

[0075] The first two layers use a 3×3×3 convolution kernel (stride 1) combined with a ReLU activation function to capture the rock boundary and crack distribution;

[0076] The third layer uses a 5×5×5 convolution kernel (step size 2) to analyze macroscopic structures such as cave connectivity; the fourth layer performs global average pooling to compress the data dimension;

[0077] The fifth fully connected layer outputs a 256-dimensional feature vector to form a three-dimensional geological feature map.

[0078] The model is trained on 10,000 sets of labeled data, and its robustness is enhanced by random rotation (±15°) and Gaussian noise (standard deviation 0.05). It is pre-trained using the public dataset OpenKIM and then fine-tuned for 50 rounds using the target area data.

[0079] The optimizer uses Adam (learning rate 0.001, decay rate ), the loss function is the mean square error (MSE). In practical applications, after the preprocessed data is input into the model, the geological feature map is automatically output for the karst cavity recognition model to call.

[0080] The karst cavity identification model is a cave distribution prediction algorithm based on probability density estimation. Specifically, it employs a Gaussian mixture model to probabilistically cluster 3D geological features, generating a thermal distribution map that quantifies the intensity of cave development. This model transforms complex geological conditions into visual risk levels, providing a dynamic basis for decision-making regarding pile foundation obstacle avoidance.

[0081] The karst cavity recognition model is based on a 3D U-Net architecture. Its input is a 3D geological feature map generated by a feature extraction model. The encoder extracts deep features through four levels of downsampling (each consisting of two 3×3×3 convolutional layers and a 2×2×2 max pooling layer). The decoder symmetrically performs four levels of upsampling (transposed convolution and encoder feature concatenation to incorporate boundary information). The output layer undergoes a 1×1×1 convolution followed by a sigmoid function to generate a karst probability matrix (range [0, 1]).

[0082] During implementation, the probability matrix is ​​converted into a three-dimensional thermal map according to the preset karst development classification standard:

[0083] Probability values ​​≤ 0.3 are mapped to blue (low risk),

[0084] 0.3–0.7 is yellow to orange (medium risk),

[0085] ≥0.7 is red (high risk).

[0086] Cave feature conversion is the mathematical process of mapping geological parameters into engineering parameters. Specifically, finite element analysis is used to calculate the relationship between the cave roof bearing capacity and pile foundation settlement. This allows for the standardized output of geological data into construction parameters such as pile diameter and length. This process ensures that pile foundation design parameters precisely match the underground karst conditions.

[0087] The pile foundation constraint boundary map is a spatial restricted area topology generated based on a safety distance threshold. Specifically, a Voronoi diagram algorithm is used to delineate the geometric boundaries between high-risk cave areas and construction-permitted areas, forming hard constraints for pile placement. This boundary map quantifies geological risks as restricted areas for construction, preventing pile ends from falling into unreinforced cave areas.

[0088] The pile foundation positioning optimization algorithm is an iterative coordinate adjustment mechanism that considers multiple constraints. Specifically, a genetic algorithm is used to globally optimize pile position coordinates, maximizing pile density while meeting clearance requirements and bearing capacity standards. This algorithm dynamically balances geological risk with engineering economics, resolving the suboptimal nature of traditional manual pile placement.

[0089] The pile foundation positioning optimization algorithm is based on the genetic algorithm framework and uses the pile foundation constraint boundary map as the spatial constraint to optimize the pile foundation construction coordinate data set. The algorithm initializes 100-200 sets of pile position coordinate solutions as the population, and the fitness function is defined as:

[0090]

[0091] in is the minimum distance between the pile foundation center and the boundary of the high-risk cave, is the effective bearing area of ​​the bearing layer covered by the pile group, is the sum of the Euclidean distances of the pile positions from the original design. The iterative process performs three steps:

[0092] Selection: retain the top 20% elite solutions in terms of fitness;

[0093] Crossover: Exchange 50% of the random pile coordinates with a probability of 0.7;

[0094] Mutation: A single pile coordinate is randomly offset by ±0.5 meters with a probability of 0.02. After each iteration, a cylindrical spatial model of the pile foundation (diameter = designed pile diameter × 1.2) is established, and the minimum clearance between adjacent piles is detected. If the clearance is less than 0.8 meters, the collision pile is moved 0.3-0.5 meters away using the gradient descent method. The optimization loop terminates when the fitness improvement rate is less than 1% for 10 consecutive generations or when 100 iterations are reached, and the final hole positioning coordinate set is output. In practice, the algorithm automatically reads the pile foundation constraint boundary map and construction coordinate data, and after optimization, generates executable instructions for the drilling rig, such as a CSV coordinate file.

[0095] Specifically, we first acquire the karst development characteristic datasets of the target project area, including 3D geological exploration datasets and karst attribute datasets. These datasets cover the geological structure and characteristic information of the karst area.

[0096] Next, the karst development characteristic dataset is preprocessed to obtain a karst preprocessed dataset. The preprocessing process may include operations such as data cleaning and standardization to improve the accuracy of subsequent analysis.

[0097] Then, based on the feature extraction model, the 3D geological exploration preprocessed data set is subjected to feature extraction to generate a 3D geological feature map. This step aims to extract key geological features from the preprocessed data and form a visual 3D map.

[0098] The karst cavity identification model identifies the three-dimensional geological feature map and generates a karst cavity distribution heat map, which visually displays the distribution and risk level of karst cavities.

[0099] The karst preprocessing dataset is converted into cave characteristics to obtain a pile foundation construction characteristic dataset. This step converts geological characteristics into engineering parameters, including a pile foundation coordinate dataset and a bearing layer characteristic dataset.

[0100] Based on the karst cavity distribution thermodynamic map, the pile foundation construction feature dataset was constrained to generate a pile foundation constraint boundary map. This step determined the safety boundary of the pile foundation construction.

[0101] Finally, based on the pile foundation positioning optimization algorithm and the pile foundation constraint boundary map, the final pile hole positioning coordinate set is output. This step comprehensively considers the geological conditions and engineering requirements to obtain the optimal pile foundation positioning solution.

[0102] The entire process achieves precise and automated positioning of pile foundations in karst areas through data-driven and intelligent algorithms, effectively solving the problems of insufficient spatial positioning accuracy of caves and delayed disaster response during construction in traditional methods.

[0103] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0104] To obtain a dataset of karst development characteristics in the target project area, a combination of 3D seismic exploration and geological radar scanning can be used. 3D seismic exploration provides large-scale underground structural information, while geological radar scanning provides higher-resolution near-surface karst details.

[0105] When preprocessing karst development characteristic datasets, filtering algorithms can be used to remove noise and interpolation methods can be used to fill data gaps. The preprocessed datasets should have a uniform format and resolution.

[0106] The feature extraction model can use a convolutional neural network, which has been trained with karst geological data and can effectively identify karst features. The extracted features include cave shape, size, connectivity, etc.

[0107] Karst cavity identification models can be based on machine learning algorithms, such as support vector machines or random forests, to identify new karst cavities by learning the characteristics of known karst cavities. Identification results are presented as heat maps, with color depth indicating the probability of cavity presence.

[0108] The conversion of karst characteristics can be achieved by establishing a mathematical model to convert karst properties such as cavity size, depth, and filling properties into pile foundation design parameters such as pile length, diameter, and bearing capacity.

[0109] During the constraint processing, a safety threshold can be set. For example, when the heat map shows that the karst development level in a certain area exceeds the preset threshold, the area will be marked as a prohibited construction area.

[0110] Pile positioning optimization algorithms can use genetic algorithms or particle swarm optimization algorithms to find the optimal pile layout solution while satisfying constraints. The algorithm's objective function can include factors such as minimizing the total length of the pile foundation and balancing the pile foundation forces.

[0111] The present application further proposes obtaining an original geological exploration data set as an initial exploration set, the original geological exploration data set including a three-dimensional seismic wave data set and a geological radar data set; performing spatial screening on the three-dimensional seismic wave data set in the initial exploration set according to a pre-set pile foundation construction area to obtain a target area exploration set; performing feature screening on the geological radar data set in the target area exploration set according to a karst development intensity threshold to obtain a karst feature data set; performing position screening on the karst feature data set according to a pile foundation construction coordinate range to obtain a target position feature set; and dividing the three-dimensional geological exploration data set and the karst attribute data set into the target position feature set based on the karst attribute data set in the target position feature set.

[0112] The pile foundation construction area is defined as a polygonal coordinate range, such as the boundary coordinate point set extracted from the pile foundation layout diagram in the construction drawings. When spatially filtering the 3D seismic wave data set, only seismic wave data within a 5-10 meter radius of the pile foundation construction area boundary is retained; data outside this range is discarded. The karst development intensity threshold is quantified as a numerical range of 0.5-0.8. Signals in the geological radar data set with reflected wave amplitudes below this threshold are marked as invalid data. The pile foundation construction coordinate range is determined by the coordinate extremes of the pile foundation design plan. Data in the karst characteristic data set with cave vertex coordinates outside this range is excluded. The division between the 3D geological exploration data set and the karst attribute data set is achieved through data field classification. For example, formation density and wave velocity parameters are classified into the 3D geological exploration data set, while cave size and filling type are classified into the karst attribute data set.

[0113] Specifically, after the original geological exploration dataset is acquired, the 3D seismic wave data set is first spatially filtered based on the pile foundation construction area. For example, the pile foundation construction area is set as a square area with a side length of 200 meters. Only data within an 8-meter radius extending from the square boundary is retained in the 3D seismic wave data set, and the remaining data is filtered. Subsequently, the reflected wave amplitude in the geological radar data set is calculated and compared with the karst development intensity threshold. For example, data with a reflected wave amplitude below 0.6 is judged to have low karst development intensity and is removed from the target area exploration set. After feature screening, the karst feature data set is further matched with the pile foundation construction coordinate range. For example, the pile foundation construction coordinate range is 1000-1200 meters on the X axis and 500-700 meters on the Y axis. Only data with cave vertex coordinates within this range is retained. The final divided 3D geological exploration data set contains the filtered seismic wave velocity field data, and the karst attribute data set contains structural parameters such as cave height and filling density.

[0114] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0115] Obtain an original geological exploration dataset as the initial exploration dataset. The original geological exploration dataset includes a 3D seismic wave data set and a geological radar data set. The 3D seismic wave data set may include parameters such as P-wave velocity, S-wave velocity, and wave impedance. The geological radar data set may include parameters such as electromagnetic wave reflection time and amplitude.

[0116] Based on the pre-defined pile foundation construction area, the 3D seismic wave data set in the initial exploration set is spatially filtered to obtain the target area exploration set. For example, the pile foundation construction area can be set as a 100m×100m rectangular area, and only the 3D seismic wave data within this area is retained.

[0117] Based on the karst development intensity threshold, the geological radar data set from the target area exploration is screened for features to obtain a karst feature data set. The karst development intensity threshold can be set to 0.5, screening out karst feature data with a development intensity greater than 0.5.

[0118] Based on the pile foundation construction coordinate range, the karst feature data set is positionally screened to obtain the target location feature set. The pile foundation construction coordinate range can be set as a circular area with a radius of 5m centered on the designed pile position, and only the karst feature data within this range is retained.

[0119] Based on the target location characteristics, the karst attribute data set is divided into a 3D geological exploration data set and a karst attribute data set. The 3D geological exploration data set can include information such as stratigraphic structure and lithology distribution. The karst attribute data set can include information such as cave size and filling properties.

[0120] The present application further proposes to perform the following steps for each three-dimensional geological exploration data in the karst development characteristic data set: obtaining the attribute fields of the three-dimensional geological exploration data; constructing a karst anomaly area identifier based on the attribute fields of the three-dimensional geological exploration data; generating preprocessed geological exploration data based on the karst anomaly area identifier; converting the preprocessed geological exploration data into a preset data format to obtain three-dimensional geological exploration preprocessed data; and integrating each three-dimensional geological exploration preprocessed data into a karst preprocessed data set.

[0121] Attribute fields acquired can include key geological parameters such as rock density, cave distribution, or groundwater permeability. The data parsing module extracts structured features from multidimensional data. Karst anomaly area identifiers can be constructed using logical rules or thresholds. For example, when the cave density exceeds 0.5 per cubic meter or the rock density falls below 2.5 g / cm³, the identifier is triggered. The boundary coordinates of the anomaly area are extended and marked using a spatial interpolation algorithm. During the generation of preprocessed geological exploration data, the anomaly area identifiers are encoded as independent data layers and mapped to the original exploration data. Missing attribute values ​​are supplemented by weighted averaging of neighboring data. Conversion to the pre-set data format involves unifying heterogeneous data into standardized grid data with a grid resolution adjustable from 0.1 to 0.5 meters. Coordinate system conversion utilizes Gauss-Krüger projection parameters to align multi-source data. During the data integration phase, spatial indexing is used to establish data associations. An octree data structure is employed to optimize storage efficiency. Data integrity is verified through hash value comparison.

[0122] Specifically, when obtaining attribute fields, the data parsing module separates lithologic parameters, geophysical response values, and geometric coordinate information from the original exploration data, where the geophysical response values ​​may include seismic wave reflection intensity or electromagnetic wave attenuation coefficient. In the process of constructing the karst anomaly area identification, the reflection intensity mutation area is marked based on the cave boundary detection algorithm, and the fracture zone area is identified by spatial clustering of continuous low-density value areas. When generating preprocessed data, the anomaly area identification is converted into a binary mask layer, the noise data is eliminated by the median filtering algorithm, and the redundant data outside the anomaly area is cropped to reduce the computational load. During the data format conversion stage, the discrete point cloud data collected by different devices are resampled into a voxel grid of uniform resolution, the coordinate system deviation is corrected by the feature point matching algorithm, and the data conversion error is controlled within the millimeter range.

[0123] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0124] The following steps are performed for each 3D geological exploration data point in the karst development characteristic dataset: First, the attribute fields of the 3D geological exploration data are obtained, including key geological parameters such as lithology, density, and porosity. Then, karst anomaly area identifiers are constructed based on these attribute fields. For example, potential karst cave areas are identified by setting density thresholds or porosity ranges. Next, preprocessed geological exploration data is generated based on the karst anomaly area identifiers, removing noise data and supplementing missing values. The preprocessed geological exploration data is converted into a preset data format, such as a unified grid data format or coordinate system. Finally, the individual 3D geological exploration preprocessed data points are integrated into a karst preprocessed dataset.

[0125] The present application further proposes to perform feature extraction on a three-dimensional geological exploration preprocessing data group based on a feature extraction model to obtain a three-dimensional geological feature map, including feature reconstruction of each data in the three-dimensional geological exploration preprocessing data group according to the karst identification feature dimension to obtain exploration data that meets the feature dimension, and spatial interpolation processing of these exploration data to obtain a three-dimensional geological feature map.

[0126] Feature reconstruction involves converting heterogeneous parameters such as seismic wave reflection intensity and the dielectric constant of geological radar into standardized feature vectors. For example, seismic wave amplitude values ​​are normalized to the range of 0-1, while the dielectric constant of geological radar is converted into the difference in relative permittivity. Spatial interpolation utilizes the Kriging algorithm, with the variation function set to a spherical model, the nugget value controlled between 0.05 and 0.1, and the maximum lag distance set to three times the distance between exploration points, thereby integrating regional geological trends with local variation characteristics. The reconstructed data must meet preset dimensional alignment requirements. For example, the 128-dimensional features of 3D seismic wave data and the 64-dimensional features of geological radar data are mapped to a unified 256-dimensional feature space through a fully connected layer. During the spatial interpolation process, the weights of adjacent exploration points are assigned using the inverse distance squared weighting method, and weight calculation is automatically terminated when the distance between two points exceeds a critical value of 50 meters.

[0127] Specifically, the feature reconstruction stage converts the physical quantities output by different exploration equipment into dimensionless characteristic values ​​by establishing a feature mapping table. For example, the seismic wave reflection time difference Δt and the rock wave velocity v are converted into velocity disturbance values ​​through the formula Δv=Δt / (2d), where d is the exploration depth reference value. The spatial interpolation stage adopts adaptive grid division. When there is a known fault in the interpolation area, the grid density is automatically increased to twice the conventional density, and independent interpolation domains are set on both sides of the fault. In the three-dimensional geological feature map formed by double processing, the gradient change rate of the cave boundary is enhanced to the order of 0.3-0.5 / meter, so that the subsequent thermal map generation can accurately capture the outline of caves with a diameter greater than 1.5 meters.

[0128] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0129] Based on the feature extraction model, feature extraction is performed on the 3D geological exploration preprocessing data set to obtain a 3D geological feature map. Specifically, first, based on the karst identification characteristic dimension, the features of each 3D geological exploration preprocessing data in the 3D geological exploration preprocessing data set are reconstructed to obtain exploration data that meet the characteristic dimension. For example, heterogeneous parameters such as seismic wave reflection intensity and geological radar dielectric constant can be converted into standardized feature vectors. Furthermore, spatial interpolation processing is performed on each exploration data that meets the characteristic dimension to obtain a 3D geological feature map. Among them, the spatial interpolation processing can use the Kriging interpolation method to integrate regional geological trends and local variation characteristics, so that the cave boundaries show clear gradient changes in the 3D map.

[0130] The present application further proposes to perform cave feature conversion processing on the karst preprocessing data set to obtain a pile foundation construction feature data set, including: performing parameter conversion on the karst attribute preprocessing data group in the karst preprocessing data set according to the pile foundation construction parameter standard to obtain each attribute data that meets the construction parameter standard; performing coordinate encoding on each pile foundation coordinate data that meets the construction parameter standard and each bearing layer characteristic data that meets the construction parameter standard to obtain a pile foundation coordinate data set and a bearing layer characteristic data set; performing coordinate calibration on the pile foundation coordinate data set according to the pile foundation design specifications to obtain a pile foundation construction coordinate data set; and integrating the pile foundation construction coordinate data set and the bearing layer characteristic data set into a pile foundation construction feature data set.

[0131] Parameter conversion involves converting the cave diameter and fill elastic modulus in the karst attribute data into the pressure units required for pile foundation bearing capacity calculations. For example, this involves converting the cave diameter from meters to a multiple of the pile diameter, and converting the fill flow rate from centimeters per second to a matching value for the mud pump displacement. Coordinate encoding utilizes a dual mapping between the geographic coordinate system and the local coordinate system of the pile foundation. For example, the WGS84 coordinates of the cave vertex are converted to rectangular coordinates in the construction area plane while retaining the millimeter-level accuracy of the elevation data. Coordinate calibration eliminates deviations between the construction coordinate system and the design coordinate system through a coordinate translation matrix. For example, when the pile foundation design specifications require a pile spacing error of less than 5 cm, the coordinate dataset is calibrated at the sub-pixel level through interpolation. During the integration process, the bearing layer feature dataset and the pile foundation construction coordinate dataset are linked through spatial indexing, such as using an R-tree index for fast query matching.

[0132] Specifically, the cave geometry parameters in the karst property preprocessing data set are first converted to equivalent diameters based on the pile foundation bearing capacity calculation standard. For example, the cave diameter is divided by a safety factor of 1.2 to obtain the pile foundation design diameter. The rock stratum compressive strength in the bearing stratum characteristic data is dimensionally normalized to megapascals and mapped to the pile foundation concrete strength grade. During the coordinate encoding process, the cave roof elevation data is converted to the pile foundation bearing stratum elevation. For example, when the cave roof depth is 15 meters and the designed pile length is 20 meters, the bearing stratum elevation is set to -35 meters. During coordinate calibration, the planar position of the pile foundation coordinate dataset is fitted to the construction control network using the least squares method. For example, pile positions with coordinate deviations greater than 3 centimeters are corrected for translation. The integrated pile foundation construction characteristic dataset is stored in a key-value pair structure, with the pile foundation construction coordinates serving as the primary key to link the bearing stratum characteristic data, enabling real-time retrieval and verification during construction. Therefore, through multi-level data conversion and spatial calibration, the karst geological characteristics and pile foundation construction parameters are accurately mapped, which solves the problem of pile position offset exceeding the allowable error due to incompatibility of parameter systems in traditional methods, improves the pile foundation coordinate positioning accuracy to the centimeter level, and increases the bearing layer feature matching accuracy to more than 95%.

[0133] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0134] The karst preprocessing dataset is converted to cave characteristics to obtain a pile foundation construction characteristic dataset. First, according to the pile foundation construction parameter standard, the karst attribute preprocessing data group in the karst preprocessing dataset is parameterized. For example, the karst cavity volume data is converted into the bearing capacity parameters required for pile foundation design, and the karst development degree is converted into the foundation treatment coefficient. Secondly, the converted pile foundation coordinate data and bearing layer characteristic data are coordinate-encoded. Specifically, the UTM projection coordinate system can be used to convert geographic coordinates into plane rectangular coordinates, and each pile position is assigned a unique code. Furthermore, the pile foundation coordinate dataset is coordinate-calibrated according to the pile foundation design specifications. For example, the pile foundation coordinates are aligned with the construction machinery operating system through coordinate translation and rotation. Finally, the calibrated pile foundation construction coordinate dataset and bearing layer characteristic dataset are integrated into the pile foundation construction characteristic dataset.

[0135] The present application further proposes performing buffer boundary processing on the pile foundation constraint boundary map according to the pile foundation diameter specification to obtain a pile foundation obstacle avoidance buffer zone map; performing position adjustment on the pile foundation construction coordinate data set based on the pile foundation obstacle avoidance buffer zone map to generate an optimized pile foundation coordinate set; performing collision detection on the optimized pile foundation coordinate set through the pile foundation positioning verification model to obtain a verified pile foundation coordinate set; and converting the verified pile foundation coordinate set into a final hole positioning coordinate output format to obtain a pile foundation final hole positioning coordinate set.

[0136] Buffer boundary processing forms a safe operating space by expanding the pile foundation constraint boundary outward. The expansion amount is dynamically adjusted according to the pile foundation diameter specifications. For example, when the pile diameter is 1.2 meters, the buffer zone expansion amount is set to 0.6 meters. Position optimization uses a gradient descent algorithm to iteratively adjust the pile foundation coordinates within the obstacle avoidance buffer map to ensure that the distance between the pile foundation center point and the boundary of the high-risk area of ​​the cave is always greater than the safety threshold. Collision detection calculates the minimum clearance between adjacent pile foundations by establishing a cylindrical space model with an enlarged diameter. When the pile foundation diameter is 1.5 meters, the diameter of the cylindrical model is expanded to 1.8 meters, and the safety clearance threshold is set to 0.8 meters. Format conversion uses the mapping rules of the WGS84 coordinate system and the local coordinate system of the construction drilling rig to achieve lossless transmission of coordinate data.

[0137] Specifically, based on the pile foundation constraint boundary map, the buffer extension amount is first determined based on the pile foundation diameter specifications, for example, 0.5 times the pile diameter is used as the buffer radius. The original boundary is then expanded outward to form an obstacle avoidance buffer map. Subsequently, the initial coordinate points in the pile foundation construction coordinate dataset are imported into the obstacle avoidance buffer map. A coordinate tuning algorithm is used to optimize the pile position layout while avoiding high-risk areas of karst caves, so that the spacing between adjacent pile foundations meets the operational requirements of the drilling rig. The tuned coordinate set is input into the pile foundation positioning verification model. This model simulates actual construction occupancy by constructing a cylindrical spatial model with an enlarged diameter, calculates the minimum clearance between the outer walls of adjacent models, and automatically triggers a secondary coordinate adjustment when insufficient clearance is detected. Finally, the coordinate conversion module converts the verified coordinate data into a binary encoding format recognizable by the drilling rig control system, for example, using the IEEE 754 floating-point standard for coordinate value storage, enabling direct connection between the final hole positioning data and the construction equipment.

[0138] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0139] Based on the pile foundation diameter specifications, the pile foundation constraint boundary map is buffered to create a pile foundation obstacle avoidance buffer zone map. Specifically, the buffer zone analysis method used in GIS spatial analysis can be used to create a buffer zone by extending the boundary line in the pile foundation constraint boundary map outward a certain distance. The buffer zone distance can be set to 1.5 times the pile foundation diameter to ensure sufficient construction space.

[0140] Based on the pile foundation obstacle avoidance buffer map, the pile foundation construction coordinate dataset is positionally optimized to generate an optimized pile foundation coordinate set. Furthermore, a genetic algorithm can be used to optimize the pile foundation coordinates. First, the initial pile foundation coordinates are used as a population, and the fitness function is defined as the minimum distance between the pile foundation and the buffer zone boundary. New coordinate solutions are generated through operations such as crossover and mutation, and the optimization is iteratively optimized until the preset conditions are met.

[0141] Using the pile foundation positioning verification model, collision detection is performed on the optimized pile foundation coordinate set, resulting in a verified pile foundation coordinate set. This allows the construction of a cylindrical spatial model for the pile foundation, with the cylinder diameter set to 1.2 times the designed pile foundation diameter. The minimum clearance between adjacent pile foundation spatial models is calculated. When the minimum clearance falls below the preset safety clearance threshold, the pile foundation is marked as colliding and adjustments are made.

[0142] The verified pile foundation coordinate set is converted into a final hole positioning coordinate output format to obtain the final hole positioning coordinate set of the pile foundation. For example, the coordinate data can be converted into a CSV format that can be recognized by construction equipment, including information such as the pile number, X coordinate, Y coordinate, and Z coordinate.

[0143] The present application further proposes setting a color mapping relationship for different karst rates according to the karst development classification standard, performing continuous slicing processing on the three-dimensional geological characteristic map to obtain karst characteristic layers at each elevation, performing void probability calculation on the karst characteristic layers at each elevation based on the void recognition model parameters to generate a karst probability matrix, and converting the karst probability matrix into a three-dimensional thermal distribution map through the color mapping relationship.

[0144] The color mapping relationship is divided into color gradients based on the karst rate threshold. For example, every 10% increase in the karst rate corresponds to a corresponding color change, forming a transition from cold to warm colors. Continuous slicing processing layers the three-dimensional geological feature map at preset elevation intervals. The cutting interval can be 0.5 meters or 1 meter, so that each karst feature layer corresponds to an independent elevation interval. The cavity probability calculation uses convolutional neural network model parameters to identify features for each slice and output a probability value. When the probability threshold is set to 0.7, it is determined to be a high-risk area. The three-dimensional thermal distribution map uses voxel rendering technology to fuse the probability matrix with the color gradient, where the color depth of each voxel is positively correlated with the karst probability.

[0145] Specifically, after the three-dimensional geological feature map is cut into multiple horizontal karst feature layers, the karst development characteristics in each layer are analyzed independently. The parameters of the cavity recognition model are optimized through training data. For example, the convolution kernel weights are trained using karst sample data, which increases the model's accuracy in identifying cave boundaries to over 92%. Each element value in the karst probability matrix represents the probability of the existence of a cave at the corresponding coordinate point. When the probability value is higher than 0.7, it is marked as a high-risk area with a red color scale. The three-dimensional thermal distribution map forms a spatially continuous risk distribution visualization model by superimposing the color mapping results of each elevation layer. Therefore, construction personnel can quickly identify high-risk cave areas at different depths through the distribution of color blocks. For example, the red area corresponds to the cave-dense area where pile foundations need to avoid, and the blue area represents the safe construction area.

[0146] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0147] According to the karst development classification standard, set the color mapping relationship of different karst rates. For example, the karst rate of 0-20% can be mapped to green, 20%-40% to yellow, 40%-60% to orange, 60%-80% to red, and 80%-100% to dark red.

[0148] The 3D geological feature map is sliced ​​continuously to obtain the karst feature layers at each elevation. Specifically, a slice can be made every 0.5 meters along the vertical direction to generate a series of 2D plane images.

[0149] Based on the parameters of the cavity identification model, cavity probabilities are calculated for each elevational karst feature layer to generate a karst probability matrix. The cavity identification model can employ a convolutional neural network, optimizing model parameters using a training dataset. A convolution operation is performed on the image of each elevation layer to extract features and calculate the cavity probability value for each pixel to form a probability matrix.

[0150] Through color mapping, the karst probability matrix is ​​converted into a three-dimensional thermal distribution map. Furthermore, using 3D visualization software, the probability matrices of each elevation layer can be overlaid and color mapped to generate a three-dimensional thermal distribution map. This allows engineers to visually observe the degree of karst development at different depths and locations.

[0151] The present application further proposes extracting vertex coordinate sets of high-risk karst areas in the karst cavity distribution thermodynamic map; constructing constraint polygons corresponding to each vertex coordinate set according to a preset safety distance threshold; performing spatial Boolean operations on the constraint polygons and the pile foundation design coordinates to obtain the pile foundation construction area; and generating boundary topological data of the pile foundation construction area to form a pile foundation constraint boundary map.

[0152] The extraction of vertex coordinate sets can be achieved using the Delaunay triangulation algorithm or the α-shape algorithm, and the contour capture accuracy can be controlled by setting a vertex density threshold. For example, when the curvature radius of the cave edge is less than 0.5 meters, sampling points are automatically added. The construction of the constrained polygon is achieved through a spatial buffer algorithm. The safety distance threshold can be set to 1.5 to 2 times the diameter of the pile foundation, and the buffer direction is dynamically adjusted according to the inclination of the cave roof. Spatial Boolean operations use a BSP tree structure for three-dimensional space cutting, and the operation accuracy is controlled at the ±5 cm level. The generation of boundary topology data uses NURBS surface fitting technology, and the output is a three-dimensional vector data format containing closed loops and hole marks.

[0153] Specifically, in the karst cavity distribution heat map, the outlines of high-risk areas are identified using an edge detection algorithm, and the marching cubes algorithm is used to extract discrete vertex sets. After the vertex coordinates are projected onto a plane, the convex hull algorithm is used to generate the initial polygon, and the polygon vertex density is then adjusted based on the thickness distribution data of the cave roof. The constrained polygon is expanded outward using a three-dimensional buffering algorithm to form a safety barrier layer, where the vertical buffer distance is set to 0.8 times the thickness of the cave roof, and the horizontal buffer distance is dynamically calculated based on the pile foundation diameter. During the spatial Boolean operation, the pile foundation design coordinates are converted into a cylindrical space model. After performing a subtraction operation with the constrained polygon, the coordinates of the pile positions completely outside the safe area are retained. The resulting boundary topology data contains multiple levels of detail (LOD) and can be adapted to drilling rig positioning systems of varying precision.

[0154] As a preferred embodiment, the solution of the present application is specifically implemented as follows: identifying the boundary vertices of the high-risk area from the karst cavity distribution thermal map, and obtaining the vertex coordinate set through the spatial coordinate extraction algorithm; setting the safety distance threshold based on the engineering safety specifications, and expanding along the normal vector direction of each vertex in the three-dimensional coordinate system to generate a constrained polygon; inputting the pile foundation design coordinates into the spatial calculation engine, performing the Boolean difference operation between the constrained polygon and the pile foundation coordinates, and automatically eliminating the pile positions that spatially overlap with the high-risk area of ​​the karst cave; extracting the closed polygon boundary of the constructible area through the boundary topology generation algorithm, and outputting vector graphics data containing the vertex sequence and topological relationship.

[0155] The present application further proposes to perform collision detection on the optimized pile foundation coordinate set through a pile foundation positioning verification model, including establishing a cylindrical space model for pile foundation construction, wherein the diameter of the cylindrical space model is equal to 1.2 times the design diameter of the pile foundation; calculating the minimum clearance value between adjacent pile foundation space models; when the minimum clearance value is less than a preset safety clearance threshold, marking it as a collision pile foundation; and adjusting the spatial coordinates of the collision pile foundation until all minimum clearance values ​​are greater than the preset safety clearance threshold.

[0156] Among them, the diameter expansion ratio of the cylindrical space model can be dynamically adjusted based on the accuracy of the construction equipment or geological conditions. For example, a 1.25-fold expansion coefficient is used in areas with developed karst fissures, and a 1.15-fold expansion coefficient is used in stable strata. The minimum clearance value of adjacent models is obtained through three-dimensional space vector calculation, specifically the shortest distance between the axes of the two cylinders minus the sum of their respective radii. The safety clearance threshold is set according to the pile foundation construction specifications. For example, a pile foundation with a diameter of 1.5m corresponds to a safety clearance of 0.8m. The coordinate adjustment process uses a gradient descent algorithm, and through iterative calculation, the colliding pile foundation is moved along the optimal path to avoid causing new collisions.

[0157] Specifically, the cylindrical spatial model for pile foundation construction is constructed by expanding the design diameter by 20% to cover the maximum deviation range caused by drill bit swing. For example, for a pile foundation with a design diameter of 1.0m, the spatial model diameter is set to 1.2m, which can accommodate drill rig guidance errors of ±0.1m and karst stratum compression deformation of 0.05m. When calculating the minimum clearance value, a spatial geometry algorithm is used to solve the shortest distance between the two cylindrical axes, and the expanded radius value is deducted. For example, if the distance between the two axes is 3.0m, the actual clearance is 3.0m-(0.6m+0.6m)=1.8m. When the clearance is detected below the safety threshold, the colliding pile foundation is moved to a low-density area using a coordinate translation algorithm, with a movement step size set to 10%-15% of the pile foundation diameter, for example, 0.12m-0.18m per adjustment. During this adjustment process, the spatial model topology is updated in real time until the clearance between all adjacent pile foundations meets the safety standard, eliminating the risk of equipment interference.

[0158] As a preferred embodiment, the solution of the present application is specifically implemented as follows: During the pile foundation positioning verification process, a cylindrical space model is first constructed based on the pile foundation design diameter. The diameter of the model is set to 1.2 times the pile foundation design diameter to simulate the dynamic offset range that may occur in actual construction. Subsequently, the minimum clearance value between the cylindrical space models corresponding to adjacent pile foundations is obtained through three-dimensional space geometric calculations, and the bounding box collision detection algorithm is used for fast distance estimation during the calculation. When the minimum clearance value is detected to be lower than the preset safety clearance threshold, the corresponding pile foundation coordinates are automatically marked as a collision pile foundation. The coordinate adjustment of the collision pile foundation is achieved through an iterative optimization algorithm, specifically using the gradient descent method to fine-tune the pile foundation coordinates. After each adjustment, the minimum clearance value of adjacent pile foundations is recalculated until the spacing between all pile foundations meets the safety requirements. During the adjustment process, priority is given to maintaining the overall layout stability of the pile foundation group, and coordinate offset correction is only performed on local conflict areas.

[0159] This application further proposes a technical solution for controlling the drilling rig positioning system according to the pile foundation final hole positioning coordinate set to implement precise drilling construction, collecting drilling offset data in real time to generate a construction error distribution map, triggering an automatic correction instruction when the offset value is greater than a preset threshold, and verifying the matching degree of the drilling coordinates after correction with the final hole positioning coordinates to output a pile foundation hole quality report.

[0160] The drilling rig positioning system generates control commands based on a coordinate transformation algorithm, converting the final hole positioning coordinates into mechanical drive parameters. For example, the coordinate translation matrix is ​​used to calculate the drill rod travel angle and depth. The construction error distribution map is generated by real-time data collection from inclination and displacement sensors installed on the drill rod. Specifically, the inclination sensor monitors the drill bit deflection angle with 0.1° accuracy, and the displacement sensor records the drill rod downward pressure with millimeter resolution. This data is processed using a Kalman filter to generate a three-dimensional error vector field. Preset thresholds can be dynamically adjusted based on the characteristics of the karst formation. For example, in areas with dense caves, the horizontal offset threshold is set to 5cm and the vertical offset threshold to 3cm, while in stable bedrock areas, the thresholds are relaxed to 8cm and 5cm. Automatic deviation correction commands are triggered using a PID control algorithm to generate a reverse compensation. This is achieved by adjusting the pressure distribution ratio of the hydraulic propulsion system. For example, when the horizontal offset reaches a threshold, the oil supply pressure to the hydraulic cylinder on the opposite side of the offset direction is increased to 65%-70%. The matching degree verification uses the least squares method to calculate the residual sum of squares between the corrected coordinates and the design coordinates. When the residual is less than 0.5cm, it is judged to be qualified, and a quality report containing a coordinate deviation heat map and compliance rating is automatically generated.

[0161] Specifically, during the drilling rig startup phase, the final hole positioning coordinate set is transmitted to the drilling rig control system via the industrial bus, driving the servo motor to adjust the initial angle of the drill pipe to the designed axis. During the drilling process, the multi-axis inertial measurement unit captures the drill bit's motion trajectory at a 50Hz sampling rate. After preprocessing, the data generates a real-time error distribution map, which displays the accumulated offset at different depths as contour lines. If the horizontal offset of a particular section of the drill hole exceeds the 5cm threshold, the control system immediately interrupts drilling and initiates a correction program. This program generates a reverse force by adjusting the hydraulic extension and retraction of the drill pipe guide. For example, if the offset is 6cm in the positive X-axis direction, the guide is controlled to apply a correction pressure of 2MPa in the negative X-axis direction for 30 seconds. After the correction is completed, the laser ranging module built into the drill pipe re-collects the coordinate data and compares it point by point with the final hole positioning coordinates. An evaluation report is generated that includes the maximum deviation value, average deviation value, and pass rate indicators.

[0162] Through the above technical solution, this application effectively solves the problem of drilling position deviation caused by dynamic changes in karst strata. Through a closed-loop control mechanism of real-time monitoring and automatic deviation correction, the drilling trajectory is dynamically corrected to within the design allowable deviation range, avoiding the error accumulation caused by delayed manual intervention. At the same time, a coordinate matching verification method is used instead of traditional sampling inspection to ensure that the location of each pile foundation drilling meets the bearing layer contact area requirements, which essentially improves the bearing stability and geological disaster resistance of the pile foundation structure.

[0163] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for intelligent positioning and precise construction of pile foundations in karst areas, characterized in that: include: Acquire a karst development characteristic data set of a target engineering area, wherein the karst development characteristic data set includes a three-dimensional geological exploration data set and a karst attribute data set; Preprocessing the karst development characteristic data set to obtain a karst preprocessed data set, wherein the karst preprocessed data set includes a three-dimensional geological exploration preprocessed data set and a karst attribute preprocessed data set; Based on the feature extraction model, feature extraction is performed on the three-dimensional geological exploration preprocessing data group to obtain a three-dimensional geological feature map; The three-dimensional geological feature map is identified by using a karst cavity identification model to generate a karst cavity distribution thermal map; Performing cave feature conversion processing on the karst preprocessing dataset to obtain a pile foundation construction feature dataset, wherein the pile foundation construction feature dataset includes a pile foundation coordinate dataset and a bearing layer feature dataset; Based on the karst cavity distribution thermodynamic map, the pile foundation construction feature data set is subjected to constraint processing to generate a pile foundation constraint boundary map; According to the pile foundation positioning optimization algorithm and the pile foundation constraint boundary map, a pile foundation final hole positioning coordinate set is output.

2. The method according to claim 1, characterized in that The step of obtaining a karst development characteristic dataset of the target engineering area includes: Acquiring an original geological exploration data set as an initial exploration data set, wherein the original geological exploration data set includes a three-dimensional seismic wave data set and a geological radar data set; According to a pre-set pile foundation construction area, spatially screening the three-dimensional seismic wave data group in the initial exploration set to obtain a target area exploration set; According to the karst development intensity threshold, feature screening is performed on the geological radar data set of the target area exploration concentration to obtain a karst feature data set; Performing position screening on the karst feature data set according to the pile foundation construction coordinate range to obtain a target position feature set; The karst attribute data group is concentrated based on the target position feature, and divided into a three-dimensional geological exploration data group and a karst attribute data group.

3. The method according to claim 1, characterized in that The preprocessing of the karst development characteristic dataset to obtain a karst preprocessed dataset includes: For each three-dimensional geological exploration data in the karst development characteristic data set, the following steps are performed: Acquiring attribute fields of the three-dimensional geological exploration data; Constructing a karst anomaly area identifier based on the attribute fields of the three-dimensional geological exploration data; generating pre-processed geological exploration data based on the karst anomaly area identification; Converting the pre-processed geological exploration data into a preset data format to obtain three-dimensional geological exploration pre-processed data; The various 3D geological exploration preprocessing data are integrated into a karst preprocessing data set.

4. The method according to claim 1, wherein The method of performing feature extraction on the three-dimensional geological exploration preprocessing data set based on the feature extraction model to obtain a three-dimensional geological feature map includes: According to the karst identification characteristic dimension, feature reconstruction is performed on each 3D geological exploration preprocessed data in the 3D geological exploration preprocessed data group to obtain exploration data that meets the characteristic dimension; The exploration data satisfying the characteristic dimensions are subjected to spatial interpolation processing to obtain a three-dimensional geological characteristic map.

5. The method according to claim 1, characterized in that The step of performing cave feature conversion processing on the karst preprocessing dataset to obtain a pile foundation construction feature dataset includes: According to the pile foundation construction parameter standard, parameter conversion is performed on the karst attribute preprocessing data group in the karst preprocessing data set to obtain attribute data that meet the construction parameter standard; Coordinate encoding is performed on each pile foundation coordinate data meeting the construction parameter standard and each bearing layer characteristic data meeting the construction parameter standard to obtain a pile foundation coordinate data set and a bearing layer characteristic data set; performing coordinate calibration on the pile foundation coordinate data set according to the pile foundation design specifications to obtain a pile foundation construction coordinate data set; The pile foundation construction coordinate dataset and the bearing layer characteristic dataset are integrated into a pile foundation construction characteristic dataset.

6. The method according to claim 1, characterized in that Outputting a pile foundation final hole positioning coordinate set according to the pile foundation positioning optimization algorithm and the pile foundation constraint boundary map includes: According to the pile foundation diameter specification, the pile foundation constraint boundary map is subjected to buffer boundary processing to obtain a pile foundation obstacle avoidance buffer zone map; Based on the pile foundation obstacle avoidance buffer zone map, position adjustment is performed on the pile foundation construction coordinate data set to generate an optimized pile foundation coordinate set; Performing collision detection on the optimized pile foundation coordinate set through the pile foundation positioning verification model to obtain a verified pile foundation coordinate set; The verified pile foundation coordinate set is converted into a final hole positioning coordinate output format to obtain a pile foundation final hole positioning coordinate set.

7. The method according to claim 1, characterized in that The karst cavity identification model is used to identify the three-dimensional geological feature map to generate a karst cavity distribution thermal map, including: According to the karst development classification standard, color mapping relationships of different karst rates are set; the three-dimensional geological characteristic map is continuously sliced ​​to obtain karst characteristic layers at various elevations; Based on the parameters of the cavity identification model, the cavity probability of each karst characteristic layer is calculated to generate a karst probability matrix; The karst probability matrix is ​​converted into a three-dimensional thermal distribution map through the color mapping relationship.

8. The method according to claim 1, characterized in that The method of performing constraint processing on the pile foundation construction feature data set based on the karst cavity distribution thermodynamic map to generate a pile foundation constraint boundary map includes: Extracting a vertex coordinate set of a high-risk karst area in the karst cavity distribution thermodynamic map; According to the preset safety distance threshold, a constrained polygon corresponding to each vertex coordinate set is constructed; Performing a spatial Boolean operation on the constraint polygon and the pile foundation design coordinates to obtain a constructible area of ​​the pile foundation; Boundary topological data of the pile foundation construction area is generated to form a pile foundation constraint boundary map.

9. The method according to claim 6, characterized in that The method of performing collision detection on the optimized pile foundation coordinate set by using the pile foundation positioning verification model includes: Establishing a cylindrical space model for pile foundation construction, wherein the diameter of the cylindrical space model is equal to 1.2 times the design diameter of the pile foundation; Calculate the minimum clear distance between adjacent pile foundation space models; When the minimum clearance value is less than the preset safety clearance threshold, it is marked as a collision pile foundation; The spatial coordinates of the collision pile foundation are adjusted until all minimum clearance values ​​are greater than a preset safety clearance threshold.

10. The method according to claim 1, characterized in that Also includes: Control the drilling rig positioning system according to the final hole positioning coordinate set of the pile foundation to implement precise drilling construction; Collect drilling offset data in real time and generate construction error distribution map; When the offset value in the construction error distribution map is greater than a preset threshold, an automatic correction instruction is triggered; Verify the matching degree between the corrected drilling coordinates and the final positioning coordinates of the pile foundation, and output the pile foundation hole quality report.

Images