A method for directional blasting simulation based on intelligent analysis

Abstract

This invention discloses a directional blasting simulation method based on intelligent analysis, comprising: acquiring a three-dimensional geological feature dataset and constructing a basic blasting simulation model; pre-setting blasting contour parameters and blasting parameters, inputting them into the basic blasting simulation model for numerical simulation, and obtaining virtual blasting results; calculating the deviation vector between the virtual blasting results and the pre-set blasting contour parameters, and optimizing the blasting parameters based on the deviation vector using a genetic algorithm to obtain optimized blasting parameters; performing numerical simulation based on the optimized blasting parameters to obtain optimized virtual blasting results; and comparing the optimized virtual blasting results with the pre-set blasting contour parameters to obtain the final blasting parameters. The directional blasting simulation method proposed in this invention improves blasting accuracy and efficiency, reduces safety risks, and provides an effective solution for precise blasting construction under complex geological conditions.

Description

Technical Field

[0001] This invention relates to the field of tunnel blasting simulation technology, and in particular to a directional blasting simulation method based on intelligent analysis. Background Technology

[0002] Tunnel blasting, a key technology in geotechnical engineering and mining, plays a vital role in infrastructure construction and resource development. Precise blasting plans can significantly improve construction efficiency, reduce safety risks, and minimize environmental impact. However, existing blasting design methods largely rely on empirical formulas and simplified models, failing to fully consider the interaction between complex geological conditions and dynamic blasting effects. This leads to significant deviations between blasting results and expected profiles, often requiring repeated on-site adjustments, increasing time and costs. Furthermore, the core challenges currently facing blasting plan design are mainly concentrated in the following aspects: First, the acquisition and processing of actual scene data cannot fully reflect the complexity of mountain geological structures, such as rock fissures and stress distribution, resulting in insufficient model accuracy. Second, the construction of blasting plans lacks a precise mapping of dynamic feedback between virtual simulation and actual blasting, hindering iterative optimization. Finally, the evaluation of deviations between the preset tunnel blasting profile and simulation results lacks a systematic analytical method, affecting the generation of the optimal plan. These unresolved technical factors directly result in insufficient adaptability of blasting plans in complex geological environments, making it difficult to meet the requirements of high precision and high efficiency. Therefore, how to use intelligent analysis technology to construct a high-precision digital twin model, combine actual scene data with preset blasting contours, realize virtual simulation and iterative optimization, and finally generate the optimal blasting scheme that is highly consistent with the expected contour has become a key problem that urgently needs to be solved in the field of tunnel blasting. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention proposes a directional blasting simulation method based on intelligent analysis. This method achieves data-driven optimization of blasting parameters through numerical simulation and intelligent analysis, ensuring the stability of the blasting effect.

[0004] To achieve the above objectives, this invention provides a directional blasting simulation method based on intelligent analysis, comprising:

[0005] Acquire a three-dimensional geological feature dataset and construct a basic model for blasting simulation;

[0006] Preset blasting profile parameters and blasting parameters, input the blasting simulation basic model to perform numerical simulation, and obtain virtual blasting results;

[0007] The deviation vector between the virtual blasting result and the preset blasting contour parameters is calculated, and the blasting parameters are optimized using a genetic algorithm based on the deviation vector to obtain the optimized blasting parameters.

[0008] Numerical simulations were performed based on the optimized blasting parameters to obtain optimized virtual blasting results.

[0009] The optimized virtual blasting results are compared and calculated with the preset blasting contour parameters to obtain the final blasting parameters.

[0010] Preferably, obtaining a three-dimensional geological feature dataset includes,

[0011] Obtain raw geological data, denoise the raw geological data, and obtain a geological dataset; the raw geological data includes rock mass fractures, stress distribution, and lithological parameters;

[0012] The geological datasets are fused to obtain a three-dimensional geological feature dataset.

[0013] Preferably, the construction of the basic model for blasting simulation includes,

[0014] Based on a three-dimensional geological feature dataset, a feature extraction method is used to separate the preset key features;

[0015] Based on the preset key features, an initial twin model is constructed using the finite element analysis method.

[0016] For the initial twin model, a dynamic adjustment method is used to optimize the model's mesh generation and construct the basic model for blasting simulation.

[0017] Preferably, preset blasting contour parameters and blasting parameters are input into the blasting simulation basic model for numerical simulation to obtain virtual blasting results, including:

[0018] Key geometric feature data are extracted from the blasting profile parameters, and profile boundary information is separated using data preprocessing methods; the blasting profile parameters include blasting profile point cloud data; the blasting parameters include charge parameters and borehole parameters;

[0019] Based on the outline boundary information and the preset blasting parameters, the deformation analysis method is used to calculate the local deformation distribution of the rock mass and generate a rock mass deformation model.

[0020] Boundary deformation data are extracted from the rock mass deformation model, and the boundary parameters of the model are adjusted using the boundary correction method to obtain the boundary optimized deformation model.

[0021] Based on the boundary optimization deformation model, a three-dimensional dynamic distribution view of the blasting effect is generated using a visualization method to obtain the virtual blasting results.

[0022] Preferably, calculating the deviation vector between the virtual blasting result and the preset blasting profile parameters includes:

[0023] The point cloud data of the blasting contour is obtained from the virtual blasting results, and a standardized point cloud model is generated by the point cloud segmentation method.

[0024] Based on a standardized point cloud model and preset blasting contour parameters, the deviation vectors of different spatial distributions are obtained by weighted least squares method.

[0025] Preferably, based on a standardized point cloud model and preset blasting contour parameters, the deviation vectors for different spatial distributions are obtained through weighted least squares calculation and analysis, including:

[0026] Spatial feature points are extracted from a standardized point cloud model and compared in three-dimensional space with feature points from a preset contour point cloud data to obtain spatial deviation distribution data.

[0027] Based on spatial deviation distribution data, the weighted least squares method is used to calculate the deviation vector for different spatial distributions.

[0028] Preferably, the blasting parameters are optimized using a genetic algorithm based on the deviation vector to obtain the optimized blasting parameters, including:

[0029] Based on the deviation vector, a genetic algorithm is constructed to optimize the blasting parameters and obtain a preliminary blasting parameter set.

[0030] Based on the initial blasting parameter set, the charge quantity parameters are adjusted using a linear interpolation method to obtain the adjusted charge quantity parameters;

[0031] Based on the preliminary blasting parameter set, the coordinates of the initiation point are adjusted using spatial geometric analysis algorithms and translation transformation methods to obtain the adjusted initiation point coordinates.

[0032] Based on the adjusted charge parameters and the adjusted detonation point coordinates, a genetic algorithm is used to optimize the blasting parameters and obtain the optimized blasting parameters.

[0033] Preferably, numerical simulation is performed based on the optimized blasting parameters to obtain optimized virtual blasting results, including:

[0034] The optimized blasting parameters are input into the blasting simulation basic model, and the blasting simulation is performed using numerical simulation methods to obtain the optimized virtual blasting results.

[0035] Preferably, the method includes comparing and calculating the optimized virtual blasting results with preset blasting contour parameters to obtain the final blasting parameters, including:

[0036] Extract blasting contour point cloud data from the optimized virtual blasting results, and perform initial alignment with the preset blasting contour parameters using the point cloud registration method to obtain the aligned point cloud data;

[0037] Based on the aligned point cloud data and the blasting contour point cloud data, the deviation value is calculated using a feature matching method. If the deviation value is lower than a preset threshold, the current blasting scheme is confirmed as the optimal scheme, and the current blasting parameters are obtained.

[0038] If the deviation value is higher than the preset threshold, key error points are extracted from the deviation value, and a genetic algorithm is used to generate optimized blasting parameters to obtain updated blasting parameters.

[0039] Compared with the prior art, the present invention has the following advantages and technical effects:

[0040] This invention proposes a directional blasting simulation method based on intelligent analysis, comprising: constructing a basic blasting simulation model; pre-setting blasting contour parameters and blasting parameters, inputting them into the basic blasting simulation model for numerical simulation, and obtaining virtual blasting results; calculating the deviation vector between the virtual blasting results and the pre-set blasting contour parameters, and optimizing the blasting parameters based on the deviation vector using a genetic algorithm to obtain optimized blasting parameters; performing numerical simulation based on the optimized blasting parameters to obtain optimized virtual blasting results; and comparing the optimized virtual blasting results with the pre-set blasting contour parameters to obtain the final blasting parameters. This invention achieves accurate simulation and optimization of the blasting process. The optimization of blasting parameters based on the deviation vector using a genetic algorithm, followed by numerical simulation of the optimized blasting parameters, improves blasting accuracy and efficiency, reduces safety risks, and provides an effective solution for precise blasting construction under complex geological conditions. Attached Figure Description

[0041] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0042] Figure 1 This is a schematic diagram of a directional blasting simulation method based on intelligent analysis according to an embodiment of the present invention. Detailed Implementation

[0043] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0044] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0045] like Figure 1 As shown, this invention proposes a directional blasting simulation method based on intelligent analysis, comprising:

[0046] Acquire a three-dimensional geological feature dataset and construct a basic model for blasting simulation;

[0047] Preset blasting profile parameters and blasting parameters, input the basic blasting simulation model to perform numerical simulation, and obtain virtual blasting results;

[0048] The deviation vector between the virtual blasting result and the preset blasting contour parameters is calculated. Based on the deviation vector, a genetic algorithm is used to optimize the blasting parameters and obtain the optimized blasting parameters.

[0049] Numerical simulations were performed based on the optimized blasting parameters to obtain optimized virtual blasting results.

[0050] The optimized virtual blasting results are compared and calculated with the preset blasting contour parameters to obtain the final blasting parameters.

[0051] Furthermore, obtaining a three-dimensional geological feature dataset includes,

[0052] The process involves acquiring raw geological data, denoising the raw geological data to obtain a geological dataset; the raw geological data includes rock mass fractures, stress distribution, and lithological parameters; and then using data fusion methods to fuse the geological dataset to obtain a three-dimensional geological feature dataset.

[0053] Specifically, in this embodiment, rock mass fractures, stress distribution, and lithological parameters can be collected by seismic wave sensors, stress gauges, and core analyzers, respectively. The original geological data is preprocessed, including denoising and standardization. Denoising can be achieved by wavelet transform to filter out sensor noise, such as removing interference signals with frequencies higher than 100Hz in the seismic wave data. Standardization normalizes data of different dimensions, such as converting fracture width and stress value into the 0-1 range for unified analysis.

[0054] Specifically, in this embodiment, fracture data, stress data, and lithological parameter data are fused to obtain more comprehensive rock mass information. Common data fusion methods selected include weighted average, Bayesian fusion, and Kalman filtering. Appropriate algorithms can be chosen based on the characteristics and requirements of the data.

[0055] Furthermore, based on the three-dimensional geological feature dataset, a feature extraction method is used to separate the preset key features;

[0056] Specifically, in this embodiment, the three-dimensional geological feature dataset contains 1,000 data points. After dimensionality reduction, preset key features can be extracted, including indicators such as fracture density, stress gradient change and lithological heterogeneity, while retaining 90% of the geological complexity information.

[0057] Furthermore, based on the preset key features, an initial twin model is constructed using the finite element analysis method;

[0058] For the initial twin model, a dynamic adjustment method is used to optimize the model's mesh generation and construct the basic model for blasting simulation.

[0059] Specifically, in this embodiment, a geometric model is created using computer-aided design (CAD) software based on the three-dimensional geological feature dataset of the actual engineering object. This model includes all relevant geometric features, such as shape, size, boundary conditions, etc.

[0060] Meshing: Discretizing the geometric model into a finite number of elements. Each element is a simple geometric shape (such as a tetrahedron, hexahedron, etc.), and these elements are combined to approximate the entire structure. The quality of the mesh directly affects the accuracy and computational efficiency of the finite element analysis. For example, if the volume of the geological body is 1 km²... 3 The average side length of the grid is approximately 10m, ensuring that spatial variations of complexity parameters are captured.

[0061] Furthermore, key geometric feature data are extracted from the blasting profile parameters, and the profile boundary information is separated using data preprocessing methods; the preset blasting profile parameters include blasting profile point cloud data; the preset blasting parameters include charge parameters and borehole parameters.

[0062] Specifically, in this embodiment, the preset blasting profile parameters include blasting profile point cloud data; the preset blasting parameters include charge parameters, borehole parameters, detonation parameters, delay time, detonation method, etc.

[0063] Furthermore, based on the contour boundary information and preset blasting parameters, the deformation analysis method is used to calculate the local deformation distribution of the rock mass and generate a rock mass deformation model;

[0064] Specifically, in this embodiment, deformation analysis methods are used to calculate the local deformation distribution of rock mass under blasting. Common methods include: Finite Element Method (FEM): The rock mass is discretized into a finite number of elements, each assuming homogeneous material properties, and the deformation of the entire rock mass is calculated by solving the equilibrium equations of each element. Finite Difference Method (FDM): Partial differential equations are solved using difference approximations, suitable for numerical calculations with regular meshes. Discrete Element Method (DEM): The rock mass is considered to be composed of a large number of discrete blocks, and the deformation and failure of the rock mass are simulated by calculating the interactions between the blocks.

[0065] Specifically, in this embodiment, the model is established by establishing a numerical model of the rock mass based on the contour boundary information and preset blasting parameters; a load is applied by applying a blasting load, such as a pressure wave generated by an explosive explosion, to the model; and the equations are solved by solving the equilibrium equations of the rock mass using numerical methods to obtain the local deformation distribution of the rock mass.

[0066] A rock mass deformation model is generated by extracting deformation information, such as displacement and strain, from numerical calculation results. Model generation: The extracted deformation information is combined with the geometric model of the rock mass to generate a rock mass deformation model.

[0067] Furthermore, boundary deformation data are extracted from the rock mass deformation model, and the boundary parameters of the model are adjusted using a boundary correction method to obtain a boundary-optimized deformation model. Based on the boundary-optimized deformation model, a three-dimensional dynamic distribution view of the blasting effect is generated using a visualization method to obtain the virtual blasting results.

[0068] Furthermore, point cloud data of the blasting contour is obtained from the virtual blasting results, and a standardized point cloud model is generated using a point cloud segmentation method;

[0069] Specifically, in this embodiment, the blasting contour point cloud data is obtained from the virtual blasting results. Virtual blasting: The blasting process is simulated using numerical simulation methods (such as finite element analysis, discrete element method, etc.) to obtain the rock mass contour after blasting.

[0070] Point cloud data: Point cloud data from simulation results to extract the blasting profile. Point cloud data is a set of three-dimensional coordinate points representing the geometry of the rock mass surface after blasting.

[0071] Point cloud segmentation: The extracted point cloud data is segmented to remove noise and irrelevant parts while retaining key information of the explosion contour.

[0072] Standardization: The segmented point cloud data is standardized, such as by aligning coordinate systems and unifying scales, to facilitate subsequent analysis.

[0073] Furthermore, based on the standardized point cloud model and the preset blasting contour parameters, the deviation vectors of different spatial distributions are obtained by weighted least squares calculation and analysis.

[0074] Furthermore, spatial feature points are extracted from the standardized point cloud model and compared in three-dimensional space with feature points of the preset contour point cloud data to obtain spatial deviation distribution data.

[0075] Based on spatial deviation distribution data, the weighted least squares method is used to calculate the deviation vector for different spatial distributions.

[0076] Specifically, in this embodiment, the weighted least squares method is a mathematical optimization method used in point cloud analysis to calculate the deviation between point cloud data and a preset contour; the deviation vector is the calculated deviation vector that represents the difference between the spatial distribution of point cloud data and the preset contour; the deviation vector can be a three-dimensional vector that represents the deviation of each point in the x, y, and z directions.

[0077] Furthermore, based on the deviation vector, a genetic algorithm is constructed to optimize the blasting parameters and obtain a preliminary set of blasting parameters;

[0078] Specifically, in this embodiment, the objective function is a function that measures the quality of the solution. In the optimization of blasting parameters, the objective function can be defined as the sum of the magnitudes of the deviation vectors, the maximum deviation, etc.

[0079] Specifically, in this embodiment, blasting parameters (such as charge amount, borehole spacing, detonation sequence, etc.) are encoded as chromosomes in the genetic algorithm. Initial Population: A set of random initial blasting parameters is generated as the initial population for the genetic algorithm. Selection Operation: Optimal solutions are selected based on the objective function value, i.e., parameter combinations with smaller deviation vector metrics are chosen. Crossover Operation: The selected optimal solutions are cross-combined to generate new parameter combinations. Mutation Operation: The new parameter combinations are randomly mutated to increase the diversity of solutions. Iterative Process: The selection, crossover, and mutation operations are repeated until convergence conditions are met (e.g., the number of iterations reaches the upper limit, the objective function value reaches the expected value, etc.). After multiple iterations, the genetic algorithm finds the blasting parameter combination that minimizes the objective function value, i.e., the optimal solution. Preliminary Blasting Parameter Set: The optimal solution is used as the preliminary blasting parameter set for subsequent verification and adjustment.

[0080] Furthermore, based on the preliminary blasting parameter set, the charge quantity parameters are adjusted using a linear interpolation method to obtain the adjusted charge quantity parameters;

[0081] Specifically, in this embodiment, linear interpolation is a numerical analysis method used to estimate the value of an unknown point between two known points. In adjusting the charge quantity parameters, linear interpolation can be used to estimate new charge quantity parameters based on the known relationship between blasting parameters and charge quantity.

[0082] Known points: Suppose there are two sets of known blasting parameters, each corresponding to a different charge quantity. For example, parameter set A corresponds to charge quantity Q1, and parameter set B corresponds to charge quantity Q2.

[0083] Unknown point: The charge quantity parameters need to be adjusted based on the initial blasting parameter set to obtain a new charge quantity parameter Q.

[0084] Linear interpolation: Calculate the new charge parameter Q using a linear interpolation formula.

[0085]

[0086] Where P is a parameter in the initial blasting parameter set, and P1 and P2 are the corresponding parameters in known points A and B, respectively.

[0087] The adjusted charge quantity parameter Q can be obtained through linear interpolation; this parameter can be used for subsequent blasting design and construction.

[0088] Furthermore, based on the preliminary blasting parameter set, the coordinates of the detonation point are adjusted using a spatial geometric analysis algorithm and a translation transformation method to obtain the adjusted detonation point coordinates;

[0089] Specifically, in this embodiment, based on the preliminary blasting parameter set, a spatial geometric analysis algorithm is used to calculate the relative distance between the detonation points, and the coordinates of the detonation points are adjusted by translation transformation to obtain the updated detonation point coordinates;

[0090] Furthermore, based on the adjusted charge parameters and the adjusted detonation point coordinates, a genetic algorithm is used to optimize the blasting parameters and obtain the optimized blasting parameters.

[0091] Specifically, in this embodiment, the Genetic Algorithm (GA) is an intelligent optimization algorithm that simulates the principles of natural selection and genetics. It searches for the optimal solution through selection, crossover, and mutation operations in an iterative process.

[0092] First, construct the objective function, which measures the quality of the solution. In blasting parameter optimization, the objective function can be defined as a measure of the difference between the blasting effect and the design, such as the sum of the magnitudes of the deviation vectors, the maximum deviation, etc. Second, optimize the objective: typically, we want to minimize the value of the objective function to make the blasting effect as close to the design as possible. Finally, optimize the blasting parameters: Parameter encoding: Encode the blasting parameters (such as charge amount, borehole spacing, detonation sequence, etc.) as chromosomes in the genetic algorithm; Initial population: Generate a set of random initial blasting parameters as the initial population of the genetic algorithm; Selection operation: Select the optimal solution based on the value of the objective function, i.e., select the parameter combination with the smaller deviation vector metric; Crossover operation: Cross the selected optimal solutions to generate new parameter combinations; Mutation operation: Randomly mutate the new parameter combinations to increase the diversity of solutions; Iterative process: Repeat the selection, crossover, and mutation operations until the convergence condition is met (such as reaching the upper limit of the number of iterations, the objective function value reaching the expected value, etc.); Finally, obtain the optimized blasting parameters.

[0093] Furthermore, the optimized blasting parameters are input into the basic blasting simulation model, and the blasting simulation is performed using numerical simulation methods to obtain the optimized virtual blasting results.

[0094] Furthermore, the point cloud data of the blasting contour is extracted from the optimized virtual blasting results, and the point cloud registration method is used to perform initial alignment with the preset blasting contour parameters to obtain the aligned point cloud data.

[0095] Based on the aligned point cloud data and the blasting contour point cloud data, the deviation value is calculated using the feature matching method. If the deviation value is lower than the preset threshold, the current blasting scheme is confirmed as the optimal scheme, and the current blasting parameters are obtained.

[0096] If the deviation value is higher than the preset threshold, key error points are extracted from the deviation value, and a genetic algorithm is used to generate optimized blasting parameters to obtain updated blasting parameters.

[0097] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A directional blasting simulation method based on intelligent analysis, characterized in that, include: Acquire a three-dimensional geological feature dataset and construct a basic model for blasting simulation; The construction of the basic model for blasting simulation include, Based on a three-dimensional geological feature dataset, a feature extraction method is used to separate the preset key features; Based on the preset key features, an initial twin model is constructed using the finite element analysis method. For the initial twin model, a dynamic adjustment method is used to optimize the model's mesh generation and construct the basic model for blasting simulation; Preset blasting profile parameters and blasting parameters, input the blasting simulation basic model to perform numerical simulation, and obtain virtual blasting results; Preset blasting contour parameters and blasting parameters, input the blasting simulation basic model for numerical simulation, and obtain virtual blasting results, including: Key geometric feature data are extracted from the blasting profile parameters, and profile boundary information is separated using data preprocessing methods. The blasting profile parameters include blasting profile point cloud data; the blasting parameters include charge parameters and borehole parameters. Based on the outline boundary information and the preset blasting parameters, the deformation analysis method is used to calculate the local deformation distribution of the rock mass and generate a rock mass deformation model. Boundary deformation data are extracted from the rock mass deformation model, and the boundary parameters of the model are adjusted using the boundary correction method to obtain the boundary optimized deformation model. Based on the boundary optimization deformation model, a three-dimensional dynamic distribution view of the blasting effect is generated using a visualization method to obtain the virtual blasting results; The deviation vector between the virtual blasting result and the preset blasting contour parameters is calculated, and the blasting parameters are optimized using a genetic algorithm based on the deviation vector to obtain the optimized blasting parameters. The calculation of the deviation vector between the virtual blasting result and the preset blasting profile parameters includes: The point cloud data of the blasting contour is obtained from the virtual blasting results, and a standardized point cloud model is generated by the point cloud segmentation method. Based on a standardized point cloud model and preset blasting contour parameters, the deviation vectors of different spatial distributions are obtained by weighted least squares method. Based on a standardized point cloud model and preset blasting contour parameters, the deviation vectors for different spatial distributions are obtained through weighted least squares calculation and analysis, including... Spatial feature points are extracted from a standardized point cloud model and compared in three-dimensional space with feature points from a preset contour point cloud data to obtain spatial deviation distribution data. Based on spatial deviation distribution data, the weighted least squares method is used to calculate the deviation vector for different spatial distributions; Numerical simulations were performed based on the optimized blasting parameters to obtain optimized virtual blasting results. The optimized virtual blasting results are compared and calculated with the preset blasting contour parameters to obtain the final blasting parameters.

2. The directional blasting simulation method based on intelligent analysis according to claim 1, characterized in that, Obtaining a 3D geological feature dataset includes, Obtain raw geological data, denoise the raw geological data, and obtain a geological dataset; the raw geological data includes rock mass fractures, stress distribution, and lithological parameters; The geological datasets are fused to obtain a three-dimensional geological feature dataset.

3. The directional blasting simulation method based on intelligent analysis according to claim 1, characterized in that, The blasting parameters are optimized using a genetic algorithm based on the deviation vector to obtain the optimized blasting parameters, including: Based on the deviation vector, a genetic algorithm is constructed to optimize the blasting parameters and obtain a preliminary blasting parameter set. Based on the initial blasting parameter set, the charge quantity parameters are adjusted using a linear interpolation method to obtain the adjusted charge quantity parameters; Based on the preliminary blasting parameter set, the coordinates of the initiation point are adjusted using spatial geometric analysis algorithms and translation transformation methods to obtain the adjusted initiation point coordinates. Based on the adjusted charge parameters and the adjusted detonation point coordinates, a genetic algorithm is used to optimize the blasting parameters and obtain the optimized blasting parameters.

4. The directional blasting simulation method based on intelligent analysis according to claim 1, characterized in that, Numerical simulations were performed based on the optimized blasting parameters to obtain optimized virtual blasting results, including: The optimized blasting parameters are input into the blasting simulation basic model, and the blasting simulation is performed using numerical simulation methods to obtain the optimized virtual blasting results.

5. The directional blasting simulation method based on intelligent analysis according to claim 1, characterized in that, This includes comparing and calculating the optimized virtual blasting results with preset blasting contour parameters to obtain the final blasting parameters, including: Extract blasting contour point cloud data from the optimized virtual blasting results, and perform initial alignment with the preset blasting contour parameters using the point cloud registration method to obtain the aligned point cloud data; Based on the aligned point cloud data and the blasting contour point cloud data, the deviation value is calculated using a feature matching method. If the deviation value is lower than a preset threshold, the current blasting scheme is confirmed as the optimal scheme, and the current blasting parameters are obtained. If the deviation value is higher than the preset threshold, key error points are extracted from the deviation value, and a genetic algorithm is used to generate optimized blasting parameters to obtain updated blasting parameters.

Images