AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method

Abstract

The invention provides an AI-driven complex geologic structure 3D printing parameter self-distribution intelligent modeling method which comprises the following steps: acquiring multi-source feature data of a complex geologic body, and preprocessing the multi-source feature data; geological geometric parameters are extracted and mapped into the 3D printing voxel model, and the geological geometric parameters are converted into geometric parameters capable of being used for 3D printing; learning a nonlinear mapping relation between historical complex geologic body physical parameters and material parameters by using an intelligent algorithm, constructing and training an AI model, and predicting material distribution parameters; the geometric parameters and the material distribution parameters are converted into a complex geological structure three-dimensional model and verified; exporting parameterized full-model slice data; and verifying the performance of the 3D printing complex geological structure model. Compared with the prior art, the method has the advantages that intelligent conversion from data to the model is realized, the heterogeneity of the complex space in the geological disaster model can be accurately described, the adaptability and accuracy of the model are improved, and a basis is provided for subsequent development of complex geological disaster prediction and prevention and control.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster prevention and control, and in particular to an AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method. Background Art

[0002] Geological disasters such as landslides and mudslides pose a serious threat to the safety of people's lives and property. Traditional geological disaster modeling methods rely on manual experience and limited geological exploration data, which makes it difficult to fully and accurately reflect the complexity and spatial heterogeneity of geological structures. With the development of geological exploration technology and the diversification of data collection methods, how to efficiently integrate multi-source geological data and intelligently extract key characteristic parameters has become an urgent problem to be solved in the field of geological disaster modeling. Existing methods usually adopt homogenization assumptions when modeling, which makes it difficult to accurately describe the complex spatial heterogeneity in geological disaster models and lack the intelligent conversion of material distribution parameters to three-dimensional structures. Therefore, there is an urgent need for an AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method to realize the intelligent conversion from data to model, accurately describe the complex spatial heterogeneity in geological disaster models, and improve the adaptability and accuracy of complex geological structure models. Provide a basis for subsequent scientific research, engineering design, disaster prediction and prevention of complex geological bodies. Summary of the invention

[0003] The purpose of the present invention is to provide a method that can efficiently integrate multi-source geological data and intelligently extract key characteristic parameters to construct a complex geological model, realize intelligent conversion from data to model, and thus accurately describe the complex spatial heterogeneity in the geological hazard model.

[0004] To achieve the above object, the present invention proposes an AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method, comprising the following steps: S1: Obtain multi-source characteristic data of actual complex geological bodies and perform preprocessing; S2: Extracting the geometric and physical parameters of the geological body based on the characteristic data of the geological body; S3: Mapping the extracted geometric parameters of the existing geological body to the 3D printing voxel model and converting them into geometric parameters that can be used for 3D printing; S4: Use intelligent algorithms to autonomously learn the nonlinear mapping relationship between the physical parameters of historical complex geological bodies and the parameters of 3D printing materials, and build and train AI models; S5: Input the existing physical parameters of complex geological bodies and use the trained AI model to predict the distribution parameters of 3D printing materials; S6: Form a printable three-dimensional voxel model from the determined geometric parameters and material distribution parameters of the existing complex geological body, realize the conversion of the multi-source parameter distribution of the geological body to the complex geological model, and verify the converted three-dimensional voxel model; S7: Import the slices exported from the verified 3D voxel model into the 3D printing device to complete the 3D printing of the complex geological structure model; S8: Verify the performance of the 3D printed complex geological structure model to ensure that the printed complex geological structure model can accurately reflect the complex spatial heterogeneity of the actual geological structure.

[0005] Furthermore, in step S1, the data acquisition method includes physical model testing, field survey and measurement, core drilling and analysis, and remote sensing technology; the multi-source characteristic data includes ice layer-rock layer alternating structure, ice layer thickness, geological body structural surface distribution, fracture network, porosity, and interlayer interface inclination.

[0006] Furthermore, in step S1, the preprocessing includes data cleaning, format conversion and standardization to ensure the consistency and accuracy of the data.

[0007] Furthermore, in step S2, the geometric and physical parameters of the geological body include geometric parameters and physical parameters, the geometric parameters include size, geometric shape and positional relationship; the physical parameters include porosity, fracture rate and inclination of the geological body.

[0008] Furthermore, step S3 specifically includes: determining the distribution of geometric dimensions of complex geological bodies in the 3D printed voxel model based on the extracted existing complex geological body geometric dimension data; determining the distribution of geometric shapes of complex geological bodies in the 3D printed voxel model based on the extracted geometric shape data; and determining the positional relationship of complex geological bodies in the 3D printed voxel model based on the extracted positional relationship data.

[0009] Furthermore, in step S4, machine learning or deep learning intelligent algorithms are used to train the AI ​​model using existing historical geological characteristic parameters and 3D printing material parameters. Specifically, machine learning or deep learning intelligent algorithms are used to train the AI ​​model using existing historical geological characteristic parameters and 3D printing material parameters, so that the AI ​​model can autonomously learn the nonlinear mapping relationship between geological characteristic parameters (such as porosity, fracture rate, geological body inclination, etc.) and final printing material parameters (such as material type, density, hardness, etc.) through a large amount of historical data.

[0010] Furthermore, in step S5, the preprocessed multi-source feature data is input into the trained AI model to predict the distribution parameters of the material, which include material type, density, material permeability, material strength, etc.

[0011] At the same time, the material needs to meet the following two characteristics: 1) Printability: compatible with mainstream 3D printing technologies (such as photocuring, fused deposition, etc.); 2) Performance adjustability: Continuous control of parameters such as hardness and density can be achieved through material ratio (such as resin doping ratio) and structural design (such as filling rate).

[0012] Furthermore, in step S6, based on the determined geometric parameters, a continuous three-dimensional voxel geometric model is generated using geological modeling software (such as Petrel, Gocad, Move), and the material distribution parameters are allocated to the three-dimensional voxel geometric model through an interpolation algorithm (such as Kriging method, etc.), and a three-dimensional voxel model that can reflect the geometric and physical parameter distribution of complex geological bodies is established. Then, by comparing the actual geological data with the three-dimensional voxel model, the accuracy of the three-dimensional voxel model is verified to ensure that the obtained three-dimensional voxel model can accurately reflect the spatial heterogeneity of the complex geological structure.

[0013] Furthermore, in step S7, the STL file exported from the three-dimensional voxel model is sliced ​​into a layered structure suitable for 3D printing, and seamlessly connected to the 3D printer, and the exported slice data is imported into the 3D printer to perform 3D printing of the geological structure model, thereby achieving high-precision printing of the geological disaster model.

[0014] Furthermore, in step S8, the performance of the 3D printed complex geological structure model is verified by comparing the features and parameters of the 3D printed complex geological structure model with the actual geological structure; the performance verification includes geometric accuracy verification, physical performance verification and mechanical performance verification. Among them, the geometric accuracy verification is specifically to verify whether the geometric size, shape and structure of the 3D printed model meet the design requirements; the physical performance verification is specifically to verify whether the physical properties such as density, strength, permeability of the 3D printed model are consistent with the actual geological structure. The mechanical performance verification is specifically to verify whether the mechanical properties of the 3D printed model can meet the needs of engineering simulation and experiments.

[0015] Compared with the prior art, the advantages of the present invention are: 1. The present invention uses an AI model to autonomously learn the complex nonlinear mapping relationship between geological parameters and 3D printing material parameters, thereby realizing the intelligent conversion from multi-source geological data to 3D printing models, avoiding the errors and inefficiencies caused by relying on manual experience in traditional methods.

[0016] 2. Traditional modeling methods usually adopt homogenization assumptions, which are difficult to accurately reflect the complex spatial heterogeneity of geological structures (such as fracture networks, pore distribution, etc.). The present invention can accurately reproduce the heterogeneous characteristics of actual geological bodies through three-dimensional voxel models and AI-driven parameter allocation, providing a more realistic model basis for disaster prediction and engineering simulation.

[0017] 3. The present invention realizes the intelligent construction and verification of geological disaster models by efficiently integrating, processing and analyzing geological structure characteristic data, and can be used for the evolution analysis of complex geological disaster bodies. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of an AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be further described below.

[0020] This embodiment proposes an AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method. Figure 1 As shown, the following steps are included: Step 1: Extraction of geological structure characteristic parameters, that is, obtaining multi-source characteristic data of actual geological bodies. The specific acquisition method is: based on physical model experiments, field surveys and measurements, core drilling and analysis, remote sensing technology and other means, to obtain multi-source characteristic data of actual complex geological bodies. Among them, the multi-source characteristic data include ice-rock alternating structure, ice layer thickness, geological body structural surface distribution, fracture network, porosity, and interlayer interface inclination.

[0021] Step 2: Multi-source data preprocessing, that is, preprocessing the acquired multi-source characteristic data of the actual geological body to ensure the consistency and accuracy of the data. The preprocessing method includes data cleaning, format conversion and standardization, as follows: Data cleaning: remove noisy data, fill in missing values, and correct erroneous data.

[0022] Format conversion: Convert data from different sources into a unified format for easy subsequent processing.

[0023] Standardization: Normalize the data to ensure that the data is compared and analyzed under the same dimension.

[0024] Step 3: Based on the characteristic data such as the structural surface distribution of the geological body and the spatial distribution of multi-source data, geometric parameters such as size, geometric shape, positional relationship and physical parameters such as porosity, fracture rate, and geological body inclination are extracted.

[0025] Step 4: Conversion of the geometric parameter distribution of the three-dimensional voxel model, i.e. mapping the extracted geological parameters to the spatial distribution of the 3D printing voxel model and converting them into parameters that can be used for 3D printing; specifically including: determining the distribution of the geometric dimensions of the complex geological body in the 3D printing voxel model based on the extracted geometric dimension data of the existing complex geological body; determining the distribution of the geometric shapes of the complex geological body in the 3D printing voxel model based on the extracted geometric shape data; determining the positional relationship of the complex geological body in the 3D printing voxel model based on the extracted positional relationship data.

[0026] Step 5: Use intelligent algorithms to autonomously learn the nonlinear mapping relationship between the physical parameters of historical complex geological bodies and the parameters of 3D printing materials, and build and train an AI model; specifically: use machine learning or deep learning intelligent algorithms to train the AI ​​model using historical geological characteristic parameters and 3D printing material parameters, so that the AI ​​model can autonomously learn the nonlinear mapping relationship between geological characteristic parameters (such as porosity, fracture rate, geological body inclination, etc.) and final printing material parameters (such as material type, density, hardness, etc.) through a large amount of historical data. For example, in this embodiment, the mapping relationship between geological parameters and material distribution parameters is shown in Table 1 below.

[0027] Table 1 Conventional geological parameters and material distribution parameters Geological parameters Mapping Logic Material selection Material distribution parameters Porosity Porosity reflects the void ratio of the geological body and directly affects the mechanical strength of the printed model. Resin High porosity: photosensitive resin + a certain proportion of internal grid cavities (simulating permeability); low porosity: a certain proportion of ceramic reinforced resin (simulating dense sandstone). Crack rate Areas with high crack rates need to simulate brittle failure behavior or preferential fluid pathways Materials with low fracture toughness (such as brittle resins) or embedded microcrack structures High crack rate: preset microcrack path during printing (simulating permeability); complex crack network area: brittle resin + different proportions of coarse and fine grids (simulating different types of microcracks). Dip angle of geological body Dip angle and bedding direction lead to anisotropy in geological mechanics, which needs to be reproduced by printing direction or material distribution Carbon fiber reinforced resin High-angle strata: Directed printing of high-strength fibers along the bedding direction (simulating compressive directionality); Horizontal bedding: Uniform material distribution (isotropic). Mineral components The hardness and chemical properties of different minerals vary greatly Ceramic resin; water-absorbent resin Quartz-rich area: high-hardness light-cured ceramic resin to simulate the strength of quartz; clay mineral area: water-absorbent resin to simulate the permeability change of clay after absorbing water. The material quality needs to meet the following requirements: 1) Printability: compatible with mainstream 3D printing technologies (such as photocuring, fused deposition, etc.); 2) Performance adjustability: Continuous control of parameters such as hardness and density can be achieved through material ratio (such as resin doping ratio) and structural design (such as filling rate).

[0028] Step 6: AI designs intelligent output of material parameter distribution in the three-dimensional voxel model, that is, predicts and outputs material distribution parameters through the trained AI model; the specific method includes inputting the pre-processed physical parameters of the existing complex geological body into the trained AI model, and then using the AI ​​model based on the rules learned during training (sample library) to directly output the matching optimal material distribution parameters for the newly input geological data, and predict the distribution parameters of the output material, which include material type, density, material permeability, material strength, etc.

[0029] Step 7: Automatic conversion and verification of the entire model of complex geological structures. The determined geometric parameters and material distribution parameters of the existing complex geological body are formed into a printable 3D voxel model, and the converted 3D voxel model is verified. In this step, based on the determined geometric parameters, a continuous 3D voxel geometric model is generated using geological modeling software (such as Petrel, Gocad, Move), and the material distribution parameters are assigned to the 3D voxel geometric model through an interpolation algorithm (such as Kriging, etc.). A 3D voxel model that can reflect the distribution of geometric and physical parameters of the complex geological body is established. The accuracy of the 3D voxel model is verified by comparing the actual geological data with the 3D voxel model to ensure that the obtained 3D voxel model can accurately reflect the spatial heterogeneity of the complex geological structure.

[0030] Step 8: Export the parameterized full model slice data, that is, import the slices exported from the verified three-dimensional voxel model into the 3D printing equipment to complete the 3D printing of the complex geological structure model; the specific operation method is: slice the STL and other files exported from the three-dimensional voxel model into a layered structure suitable for 3D printing, and seamlessly connect with the 3D printer, import the exported slice data into the 3D printer, and 3D print the geological structure model to ensure the smooth progress of the printing process and achieve high-precision printing of the geological disaster model.

[0031] Step 9: Verification of the performance of the 3D printed complex geological structure model, that is, verification of the performance of the 3D printed geological structure model to ensure that the printed geological structure model can accurately reflect the complex spatial heterogeneity of the actual geological structure. The specific verification method is: by comparing the characteristics and parameters of the 3D printed complex geological structure model with the actual geological structure, the performance of the 3D printed complex geological structure model is verified; the performance verification includes geometric accuracy verification, physical performance verification and mechanical performance verification. Among them, the geometric accuracy verification is specifically to verify whether the geometric size, shape and structure of the 3D printed model meet the design requirements; the physical performance verification is specifically to verify whether the physical properties of the 3D printed model such as density, strength, permeability, etc. are consistent with the actual geological structure. Mechanical performance verification is specifically to verify whether the mechanical properties of the 3D printed model can meet the needs of engineering simulation and experiments.

[0032] The 3D printed complex geological structure model obtained by the above-mentioned embodiment method can accurately describe the complex spatial heterogeneity in the geological disaster model.

[0033] The above is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any technician in the relevant technical field, without departing from the scope of the technical solution of the present invention, makes any form of equivalent replacement or modification to the technical solution and technical content disclosed in the present invention, which does not depart from the content of the technical solution of the present invention and still falls within the protection scope of the present invention.

Claims

1. An AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method, characterized in that: The steps include: S1: Obtain multi-source characteristic data of actual complex geological bodies and perform preprocessing; S2: Extracting the geometric and physical parameters of the geological body based on the characteristic data of the geological body; S3: Mapping the extracted geometric parameters of the existing geological body to the 3D printing voxel model and converting them into geometric parameters that can be used for 3D printing; S4: Use intelligent algorithms to autonomously learn the nonlinear mapping relationship between the physical parameters of historical complex geological bodies and the parameters of 3D printing materials, and build and train AI models; S5: Input the existing physical parameters of complex geological bodies and use the trained AI model to predict the distribution parameters of 3D printing materials; S6: Form a printable three-dimensional voxel model from the determined geometric parameters and material distribution parameters of the existing complex geological body, realize the conversion of the multi-source parameter distribution of the geological body to the complex geological model, and verify the converted three-dimensional voxel model; S7: Import the slices exported from the verified 3D voxel model into the 3D printing device to complete the 3D printing of the complex geological structure model; S8: Verify the performance of the 3D printed complex geological structure model to ensure that the printed complex geological structure model can accurately reflect the complex spatial heterogeneity of the actual geological structure.

2. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S1, the data acquisition method includes physical model testing, field survey and measurement, core drilling and analysis, and remote sensing technology; the multi-source characteristic data includes ice layer-rock layer alternating structure, ice layer thickness, geological body structural surface distribution, fracture network, porosity, and interlayer interface inclination.

3. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S1, the preprocessing includes data cleaning, format conversion and standardization.

4. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S2, the geometric and physical parameters of the geological body include geometric parameters and physical parameters. The geometric parameters include size, geometric shape and position relationship; the physical parameters include porosity, fracture rate and inclination of the geological body.

5. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: Step S3 specifically includes: determining the distribution of the geometric dimensions of the complex geological body in the 3D printed voxel model according to the extracted geometric dimension data of the existing complex geological body; determining the distribution of the geometric shape of the complex geological body in the 3D printed voxel model according to the extracted geometric shape data; and determining the positional relationship of the complex geological body in the 3D printed voxel model according to the extracted positional relationship data.

6. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S4, a machine learning or deep learning intelligent algorithm is used to train the AI ​​model using existing historical geological characteristic parameters and 3D printing material parameters to establish a nonlinear mapping relationship between the physical parameters of the geological body and the 3D printing material parameters.

7. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S5, the preprocessed physical parameters of the existing complex geological body are input into the trained AI model to predict the distribution parameters of the material, which include material type, density, material permeability and material strength.

8. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S6, based on the determined geometric parameters, a continuous three-dimensional voxel geometric model is generated using geological modeling software, and the material distribution parameters are allocated to the three-dimensional voxel geometric model through an interpolation algorithm. A three-dimensional voxel model that can reflect the geometric and physical parameter distribution of complex geological bodies is established. The accuracy of the three-dimensional voxel model is then verified by comparing the actual geological data with the three-dimensional voxel model to ensure that the obtained three-dimensional voxel model can accurately reflect the spatial heterogeneity of complex geological structures.

9. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S7, the STL file exported from the three-dimensional voxel model is sliced ​​into a layered structure suitable for 3D printing, and seamlessly connected to the 3D printer, and the exported slice data is imported into the 3D printer to complete the 3D printing of the complex geological structure model.

10. The AI-driven complex geological structure 3D printing parameter self-distribution intelligent modeling method according to claim 1 is characterized in that: In step S8, the performance of the 3D printed complex geological structure model is verified by comparing the characteristics and parameters of the 3D printed complex geological structure model with the actual geological structure; the performance verification includes geometric accuracy verification, physical performance verification and mechanical performance verification.

Images