Roadway geology visual modeling method and system under combined method

Abstract

The invention provides a roadway geology visual modeling method and system under a joint method, and the method comprises the steps: constructing a stratum curved surface model through employing a Kriging interpolation algorithm and an inverse distance weighting method, and employing a TIN-based surface model modeling method; acquiring intersecting lines of the fault and the stratum when each stratum is cut by the same fault so as to determine a control point set of the fault plane, and constructing a three-dimensional geologic model of the fault plane; taking a contour line of a local coordinate system established on each control point along the center line as a section, and carrying out tunneling roadway geometric modeling by using a section expansion modeling method; and performing dynamic prediction and model updating based on the static data of the modeling area and the dynamic data collected in the tunneling process to realize model visualization. According to the method, the form and internal attributes of the geologic body can be taken into consideration, hidden information and feature representation of data can be mined while sample data is learned by means of deep learning, and geological information can be learned and progressively predicted more accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of geological visualization modeling, and in particular relates to a tunnel geological visualization modeling method and system under a combined method. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Three-dimensional geological modeling technology is a technology used for geological analysis in a three-dimensional environment with the help of computers. This technology effectively integrates tools such as spatial information management, analysis and prediction, geological interpretation and statistics, entity content analysis, and graphic visualization. In the past few decades, researchers from different application fields have proposed many geological modeling methods based on actual needs.

[0004] The study of three-dimensional dynamic modeling in geological space has been a research hotspot in recent years, and at the same time, it is also one of the difficulties. According to the data source, it can be divided into four categories, namely modeling methods based on profiles, scattered points, boreholes and multi-source data. According to the technical level, it can be divided into five stages, namely visualization stage, measurement stage, analysis stage, update stage and temporal modeling stage, of which the first three are static stages and the last two stages are dynamic stages. The three-dimensional geological dynamic model based on multi-source data can be analyzed by fusion of dynamic and static based on the spatial data model.

[0005] Spatial data model is a general term for data constraints, data structure and data operations. It is constructed to facilitate data management, use, storage and exchange, and is the basis of the spatial relationship and morphology of geological bodies.

[0006] According to the geometric characteristics, it can be divided into three categories: surface-based data model, volume-based data model and hybrid data model. Different spatial data models are suitable for different corresponding spatial forms and have their own focus.

[0007] The surface-based data modeling method mainly uses the method of enclosing the spatial area by the surface of the model to express the geological conditions in three dimensions. The geometric characteristics of the geological body are generally embodied and described by some tiny face elements. Limited by its modeling principle, it is difficult to describe the internal attribute characteristics of the three-dimensional body, so it is impossible to view, edit and analyze the three-dimensional geological information. However, this modeling method has obvious advantages in expressing the spatial boundaries, visualization and geometric transformation of the geological body. And because its modeling theory is relatively mature and the program method is easy to implement, it is still the mainstream for realizing the construction of three-dimensional stratigraphic models.

[0008] The volume-based data modeling method is to abstract the three-dimensional geological body into a collection of many adjacent but non-intersecting three-dimensional unit entities, and use these tiny volume elements to express the space inside the geological body. This modeling method can better characterize the internal properties of the geological body, but it is difficult to describe the topological relationship between objects, and the calculation process will consume a lot of computer resources. Summary of the invention

[0009] In order to solve the above problems, the present invention proposes a tunnel geological visualization modeling method and system under a joint method. The present invention adopts multiple data models to comprehensively express different spatial geological bodies, which can take into account the morphology and internal properties of the geological bodies. At the same time, with the help of deep learning, it can mine the implicit information and feature representation of the data while learning the sample data, and can more accurately learn and progressively predict the geological information.

[0010] According to some embodiments, the present invention adopts the following technical solutions:

[0011] A tunnel geological visualization modeling method under a combined method includes the following steps:

[0012] The Kriging interpolation algorithm and the inverse distance weighted method are used together to construct the stratum surface model using the TIN-based surface modeling method.

[0013] Obtain the intersection lines of the fault and the strata when each stratum is cut by the same fault, so as to determine the control point set of the fault plane and construct a three-dimensional geological model of the fault plane;

[0014] The contour line of the local coordinate system established at each control point along the center line is used as the cross section, and the cross section extension modeling method is used to perform geometric modeling of the tunneling tunnel;

[0015] Dynamic prediction and model update are performed based on the static data of the modeling area and the dynamic data collected during the excavation process to achieve model visualization.

[0016] As an optional implementation, the process of combining the Kriging interpolation algorithm with the IDW method includes first using the IDW method for preliminary interpolation to obtain a rough model, and then applying the Kriging interpolation method to adjust and optimize the model.

[0017] As an optional implementation method, the process of constructing a stratum surface model using a TIN-based surface modeling method includes starting from an initial triangle or an edge, gradually expanding outward, and adding new points to the triangulated network in sequence until all points are included in the TIN; each time a new point is inserted, the new triangle maintains topological consistency with the existing triangular mesh, and uses the region boundary as the initial wavefront, advancing into the region according to preset rules, generating a mesh during the advancement process, and when all wavefronts converge and disappear within the region, the mesh generation is completed.

[0018] As an optional implementation method, the process of constructing a three-dimensional geological model of a fault plane includes:

[0019] (1) Establishment of the initial TIN model: Select initial data points, including fault strike, extension range, dip angle, etc., and establish the fault plane TIN model based on these data points;

[0020] (2) intersecting the TIN model in step (1) with the geological fault plane to obtain the fault intersection line;

[0021] (3) Based on the fault distance information, the drop between the original data corresponding point and the fault intersection line is calculated to determine the impact range;

[0022] (4) According to the properties of the normal and reverse faults, the stratum is divided into two regions, namely, the upper wall of the fault and the lower wall of the fault, and the fault intersection line in step (3) is inserted into the corresponding region to segment the TIN stratum grid in the region;

[0023] (5) Using the range obtained in step (3), construct a stratigraphic model after the displacement of the upper and lower plates of the fault in the stratigraphic TIN model. Repeat this step to obtain multiple stratigraphic TIN models, all of which contain the corresponding faults, and finally form a fault structure model.

[0024] As an optional implementation method, in the process of constructing the three-dimensional geological model of the fault plane, the ground plane is set as the top and bottom plates of the coal seam;

[0025] The fault plane is drawn based on the fault strike and dip information, and the fault coal intersection line is obtained by intersecting with the stratum;

[0026] Process the coal-breaking intersection line and obtain the coal-breaking intersection line after operation according to the breaking distance information;

[0027] Split the plane grid and generate a coal plane model based on fault attributes, including fault dislocation;

[0028] Repeat the above process to obtain the coal seam roof and floor surface model.

[0029] As an optional implementation method, the geometric modeling of the excavation tunnel is based on the theory of rotating bodies and stretching bodies. The section uses the contour line of the local coordinate system. The contour line is established at each control point along the center line of the tunnel. The method of geometric modeling of the excavation mine tunnel is used to model the section expansion.

[0030] As an optional implementation method, in the process of realizing model visualization, a long short-term memory network deep learning model is used for static data, and progressive prediction is performed based on historical data to achieve dynamic update operations.

[0031] A tunnel geological visualization modeling system based on a joint method includes:

[0032] The stratigraphic surface model building module is configured to comprehensively adopt the Kriging interpolation algorithm and the inverse distance weighted method to build the stratigraphic surface model using the TIN-based surface modeling method;

[0033] A fault plane model building module is configured to obtain intersection lines where the faults intersect the strata when each strata is cut by the same fault, so as to determine a control point set of the fault plane and build a three-dimensional geological model of the fault plane;

[0034] The tunnel geometry modeling module is configured to use the contour line of the local coordinate system established at each control point along the center line as a cross section, and use the cross section extension modeling method to perform geometric modeling of the tunneling tunnel;

[0035] The model visualization module is configured to perform dynamic prediction and model update based on static data of the modeling area and dynamic data collected during the excavation process to achieve model visualization.

[0036] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps in the above method are completed.

[0037] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention adopts Kriging interpolation algorithm and inverse distance weighting method as the mathematically defined spatial interpolation method used in the process of constructing the three-dimensional geological model. The inverse distance weighting method is first used for preliminary interpolation to obtain a rough model, and then the Kriging interpolation method is applied to adjust and optimize the model. By comparing and verifying the results of the two methods, the most suitable interpolation scheme is selected; the address surface model is constructed, the surface modeling method based on TIN is selected to construct the stratum surface model, the boundary advancement method is used to construct TIN and automatically generate the TIN model, an edge is selected from a given point set as the initial edge, and the point closest to the current boundary is continuously selected to form a new triangle, and the process is continuously repeated until all points are added to the triangulation network; the fault model is constructed, and the intersection line of the fault and the stratum when each stratum is cut by the same fault is obtained to determine the control point set of the fault surface, and then the boundary advancement algorithm is used to construct the three-dimensional geological model of the fault surface; based on the theoretical basis of the rotating body and the stretching body, the contour line of the local coordinate system established at each control point along the center line is used as the section, and the section extension modeling method is used to perform geometric modeling of the excavation tunnel.

[0040] The present invention also incorporates deep learning into the construction of dynamic models. When predicting the dynamic update of the lane model, the long short-term memory network (LSTM) and CNN deep learning models are introduced to make progressive predictions based on historical data, reducing the limitations of relying solely on static data updates and improving the prediction ability of this model. By introducing recurrent connections in the time dimension and adding new hidden layers between different time points, the entire neural network can model the relationship between sequences.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0043] Figure 1 A flowchart of a tunnel geological visualization modeling method based on a Kriging-IDW-LSTM joint method provided in an embodiment;

[0044] Figure 2 A basic process flow chart of the boundary pushing method provided for an embodiment;

[0045] Figure 3 A flow chart of fault modeling provided for an embodiment;

[0046] Figure 4 A flowchart of LSTM modeling is provided for an embodiment. DETAILED DESCRIPTION

[0047] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0049] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0050] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0051] Embodiment 1

[0052] The present invention provides a tunnel geological visualization modeling method, such as Figure 1 As shown, the following steps are included:

[0053] Step (1): Select a reasonable spatial interpolation method. One of the important theoretical bases for establishing geological models is spatial interpolation operation.

[0054] There are usually two key steps in simulating geological interfaces: one is to project the geological interface to be simulated on the reference plane and use triangulation at the projection location; the other is to use interpolation operations based on the original sampling data to obtain the three-dimensional coordinate values ​​of the grid nodes and generate a geological surface with three-dimensional spatial properties.

[0055] In the actual modeling process, the spatial coordinate values ​​of the sampling points are obtained by detailed analysis of the exploration geological data, and the three-dimensional geometric shape of the target interface is reflected, but the spatial coordinates of other places except the sampling points cannot be directly obtained.

[0056] Therefore, it is necessary to establish a certain type of geological surface through the acquired sampling point data, so that the actual sampling point can be passed through or as close as possible by the surface, and the spatial coordinate positions of other positions can also be inferred using the geological surface.

[0057] In general, the spatial distribution law of the geological surface is obtained by analyzing the original sampling data, which is the process of interpolation, and the spatial coordinates of the unknown area points are calculated from it. The interpolation algorithms used in the present invention mainly include Kriging method and inverse distance weighted method, which are mainly used in the creation of initial geological surfaces, local re-division of surfaces, and reconstruction of surfaces. Its basic principles and characteristics are as follows:

[0058] (1) Kriging interpolation algorithm

[0059] This method focuses on clarifying the weight coefficients to ensure that the interpolation function is in its best operating mode. Based on the theory of variogram and the analysis of the corresponding structural composition, the data variation in the area is valued within a limited data value domain, such as a certain stratigraphic domain, and an unbiased optimal valuation method is adopted for these data.

[0060] Based on the conclusion of function variation theory and its correlation analysis, it can be concluded that the data volume of the region has certain spatial correlations. In essence, the structural characteristics of the function transformation and the basic data of the regional data volume are used to take the best unbiased estimate of these acquired data. The advantage of the Kriging interpolation method is that it can greatly reduce the variance of possible errors. When establishing a geological model, the Kriging interpolation method can achieve a good fit between the initial sample data and the target geological interface, and the interpolation conclusion obtained is closer to the basic state and spatial appearance of the basic geological body. The Kriging interpolation algorithm has a good fitting result in scenes where the geological interface is smooth and continuous without large fluctuations, but the numerical point fitting effect is relatively poor for scenes with large fluctuations in the geological interface, such as the sides of large faults, mutations near folds, and irregular rock interfaces.

[0061] (2) Inverse Distance Weighting

[0062] The inverse distance weighting (IDW) method is based on the assumption that the known points closer to the target point have a greater impact on the predicted value of the target point. Specifically, the influence of each known point is weighted according to the inverse of its distance from the target point. The closer the distance, the greater the weight. Therefore, in geological modeling, especially when encountering local geological features such as faults, the data points at the feature are usually unevenly distributed, and the points near the fault are particularly important. Therefore, IDW can better capture the characteristics of such geological features, which makes up for the shortcomings of the Kriging interpolation method in geological features with large fluctuations. The predicted value is usually a weighted average. This method is simple and intuitive, but it is sensitive to data distribution and spatial heterogeneity.

[0063] The basic principle of the inverse distance weighted method (IDW) is to use the values ​​of known points to estimate the values ​​of unknown points, and weight them according to the distance between the known points and the unknown points. The closer the distance is, the greater the influence on the estimated value. The formula is as follows:

[0064]

[0065] in:

[0066] Z(x) is the estimated value at position x. Zi is the value at known point i. Wi is the weight of known point i for position x. n is the total number of known points used for interpolation. The weight Wi is usually calculated as follows:

[0067]

[0068] Where: di is the distance from the known point i to the unknown point x. p is a non-negative power exponent, usually 1 or 2, which determines the rate at which the weight decays with distance.

[0069] By taking advantage of the simplicity and intuition of IDW and the statistical model advantages of Kriging, more accurate prediction results can be obtained for geological data, making tunnel modeling more credible. Kriging interpolation can help deal with the problems that IDW may encounter when dealing with spatial heterogeneity and uneven distribution of data points. Improved stability: The spatial variation model of the Kriging method can improve the overall numerical stability and prediction reliability.

[0070] In the process of geological modeling, the present invention first adopts IDW to perform preliminary interpolation to obtain a rough geological model, and then uses Kriging interpolation method to adjust and optimize the model.

[0071] The main application of the present invention is to establish a coal and rock geological body model around the tunnel excavation and ensure high precision to accurately represent the spatial occurrence information, including coal and rock distribution, structure, stratum thickness and other elements, and only consider the attributes of the lithology classification of the stratum. Because the method of using the TIN model to represent a complex surface model can be achieved by changing the size and number of triangular meshes, thereby eliminating the generated redundant data and ensuring high fitting accuracy, the TIN-based surface modeling method is selected to construct the stratum surface model.

[0072] The TIN generation algorithm adopted by the present invention is the boundary advancement method. The basic idea is to start from an initial triangle (or an edge), gradually expand outward, and add new points to the triangulated network in sequence until all points are included in the TIN. The key to this process is to ensure that each time a new point is inserted, the new triangle maintains topological consistency with the existing triangular mesh, and to ensure that the entire mesh structure is non-overlapping, continuous and topologically reasonable. The regional boundary is used as the initial wavefront and is advanced into the interior of the region according to certain rules. During the advancement process, mesh generation is performed. When all wavefronts converge and disappear within the region, the mesh generation is completed. The specific generation method is as follows: Figure 2 shown.

[0073] In the fault modeling part, the idea of ​​establishing the fault in the modeling work of the present invention is to obtain the intersection line of the fault and the stratum when each stratum is cut by the same fault to determine the control point set of the fault plane, and then use the boundary advancement algorithm to construct a three-dimensional geological model of the fault plane. Specifically, there are the following processes:

[0074] (1) Establishment of the initial TIN model: Select initial data points, including fault strike, extension range, dip angle, etc., and establish the fault plane TIN model based on these data points;

[0075] (2) Intersect the TIN model in (1) with the geological fault plane to obtain the fault intersection line;

[0076] (3) Based on the fault distance information, the drop between the original data corresponding point and the fault intersection line is calculated to determine the impact range;

[0077] (4) According to the properties of normal and reverse faults, the stratum is divided into two regions, namely the fault hanging wall and the fault footwall. The fault intersection line in (3) is inserted into the corresponding region to split the TIN stratigraphic grid in the region.

[0078] (5) When constructing the stratigraphic TIN model, the stratigraphic model after the displacement of the upper and lower plates of the fault needs to be established using the drop range obtained in (3). Repeat this step to obtain multiple stratigraphic TIN models, all of which contain the corresponding faults, and finally form a fault structure model.

[0079] The above fault modeling process is described as follows: Figure 3 For example, assume that the stratigraphic plane is the roof and floor of the coal seam; draw the fault plane based on the fault strike, dip and other information, and obtain the coal-fault intersection line by intersecting with the stratigraphic plane; process the coal-fault intersection line, and obtain the coal-fault intersection line after operation based on the fault distance information; divide the plane grid, and generate a coal seam plane model based on the fault attributes (normal fault or reverse fault), and the model includes fault dislocation; the figure shows the coal seam roof and floor plane model obtained by repeating the above process; it is a complete fault structure model.

[0080] In the geometric modeling of the excavation tunnel, the present invention takes the rotating body and the stretching body as the theoretical basis, and the section adopts the contour line of the local coordinate system. The contour line is established at each control point along the center line of the tunnel. The method of geometric modeling of the excavation mine tunnel is used for section expansion modeling. The section of the corresponding tunnel is loaded on each control point of the center line, and then a judgment is made based on the Z value of the control point on the center line to determine whether it is on the top plate or the bottom plate. Then, the coordinates of the control point and the shape of the section are combined to form a tunnel section polygon, and then the generated tunnel section polygons are connected to generate a triangulated network, thereby generating a tunnel model.

[0081] The tunnel geological model visualization constructed above can be dynamically updated based on the static data of the modeling area and the dynamic data collected during the excavation process, and the long short-term memory network (LSTM) learning model is used for dynamic update operations. In the process of modeling the excavation tunnel, if only relying on the previous static data, the obtained model cannot fit the dynamic changes generated during the tunnel excavation process well. With the excavation of the tunnel, the surrounding stratum conditions, rock and soil properties and other factors may change, which may be a long-term change. The LSTM model can learn this long-term change and obtain its rules, so as to more accurately update the previous static geological model and make the model more accurate.

[0082] First, select suitable data for training and updating LSTM, such as geological data, including rock formation properties, soil conditions, and hydrological conditions; construction progress, including excavation speed, construction period, equipment used, etc.; environmental conditions, temperature, humidity, pressure, etc. Then train the preliminary model. The data selected in the present invention can be classified into time series data arranged in chronological order. According to the time step, the tunnel state is recorded at intervals, and the recorded data is used for training. Through these data, an LSTM model is established to predict the tunnel state in the future, thereby achieving dynamic updating of the geological model. The basic model supports predicting the key indicators of the next time point through historical time series data. At the same time, the LSTM is continuously updated dynamically. When new geological data, environmental conditions, construction progress and other information continue to flow into the LSTM, the LSTM continues to be trained so as to gradually adapt to the new data, thereby achieving a more accurate effect.

[0083] LSTM can overcome the problems of traditional RNN models, such as gradient disappearance and gradient explosion. Its principle is a special gated network structure. Compared with the traditional RNN model, LSTM not only outputs information to the hidden layer of the next moment at each moment, but also outputs internal information to the next moment. The internal state of LSTM is the part that processes internal information, denoted as Ct, and the historical information of the previous moments is recorded in the internal state at each moment. The expression of the internal state of LSTM at each moment is

[0084]

[0085] h t =O t tanh(C t )

[0086]

[0087] W c , b c are the weight matrix and bias of the internal memory unit at time t, f t It is a forget gate, which uses the importance to adjust the weight, selectively forgets non-critical information and repeated information, and controls the amount of information forgotten in the input layer and the internal state of the previous moment. The calculation formula is:

[0088] f t =σ(W f x t +U f h t-1 +b f )

[0089] The activation function σ is a Sigmoid function with a value range between 0 and 1. It acts as a gate and is defined as:

[0090]

[0091] i t is the input gate, which controls the information that needs to be saved at the current moment. The calculation formula is:

[0092] i t =σ(W o x t +U o h t-1 +b o )

[0093] W o , b o are the weight matrix and bias of the output gate at time t respectively.

[0094] The most obvious feature of the LSTM network structure is the gating mechanism. The parameters to be learned are E, U, and b. The elements in the three gating vectors are all between 0 and 1, and the transmission unit state can be operated in three gating modes. Since the content that needs to be remembered for a long time can be remembered by LSTM, but some unimportant content is ignored, it is called a long short-term memory network. The advantages of LTSM are particularly prominent in some environments that require longer memory. However, since the LSTM model has more parameters and more components, it is much more difficult to train the LSTM model than other models.

[0095] In the present invention, during the visualization of tunnel excavation, the LSTM model is used for static data, and progressive prediction is performed based on historical data to reduce the limitation of relying solely on static data updates. The steps for establishing the LSTM model are as follows: Figure 4 shown.

[0096] (1) Normalize the input geological data sample data;

[0097] (2) Divide the original data into training set and test set;

[0098] (3) Build an LSTM model and select appropriate model parameters;

[0099] (4) Input the data of the training set into the model to complete the model training;

[0100] (5) Input the test set data into the LSTM model, perform model testing, obtain the final results, and evaluate the results.

[0101] Embodiment 2

[0102] A tunnel geological visualization modeling system based on a joint method includes:

[0103] The stratigraphic surface model building module is configured to comprehensively adopt the Kriging interpolation algorithm and the inverse distance weighted method to build the stratigraphic surface model using the TIN-based surface modeling method;

[0104] A fault plane model building module is configured to obtain intersection lines where the faults intersect the strata when each strata is cut by the same fault, so as to determine a control point set of the fault plane and build a three-dimensional geological model of the fault plane;

[0105] The tunnel geometry modeling module is configured to use the contour line of the local coordinate system established at each control point along the center line as a cross section, and use the cross section extension modeling method to perform geometric modeling of the tunneling tunnel;

[0106] The model visualization module is configured to perform dynamic prediction and model update based on static data of the modeling area and dynamic data collected during the excavation process to achieve model visualization.

[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A tunnel geological visualization modeling method under a joint method, characterized by: The following steps are involved: The Kriging interpolation algorithm and the inverse distance weighted method are used together to construct the stratum surface model using the TIN-based surface modeling method. Obtain the intersection lines of the fault and the strata when each stratum is cut by the same fault, so as to determine the control point set of the fault plane and construct a three-dimensional geological model of the fault plane; The contour line of the local coordinate system established at each control point along the center line is used as the cross section, and the cross section extension modeling method is used to perform geometric modeling of the tunneling tunnel; Dynamic prediction and model update are performed based on the static data of the modeling area and the dynamic data collected during the excavation process to achieve model visualization.

2. The tunnel geological visualization modeling method under a combined method as claimed in claim 1 is characterized in that: The process of combining the Kriging interpolation algorithm with the IDW method includes first using the IDW method for preliminary interpolation to obtain a rough model, and then using the Kriging interpolation method to adjust and optimize the model.

3. The tunnel geological visualization modeling method under a combined method as claimed in claim 1 is characterized in that: The process of constructing a stratum surface model using the TIN-based surface modeling method includes starting from an initial triangle or an edge, gradually expanding outward, and adding new points to the triangulated network in sequence until all points are included in the TIN; each time a new point is inserted, the new triangle maintains topological consistency with the existing triangular mesh, and uses the regional boundary as the initial wavefront, advancing into the interior of the region according to preset rules, and generating meshes during the advancement process. When all wavefronts converge and disappear within the region, the mesh generation is completed.

4. The tunnel geological visualization modeling method under a combined method as claimed in claim 1 is characterized in that: The process of constructing a 3D geological model of a fault plane includes: (1) Establishment of the initial TIN model: Select initial data points, including fault strike, extension range, dip angle, etc., and establish the fault plane TIN model based on these data points; (2) intersecting the TIN model in step (1) with the geological fault plane to obtain the fault intersection line; (3) Based on the fault distance information, the drop between the original data corresponding point and the fault intersection line is calculated to determine the impact range; (4) According to the properties of the normal and reverse faults, the stratum is divided into two regions, namely, the upper wall of the fault and the lower wall of the fault, and the fault intersection line in step (3) is inserted into the corresponding region to segment the TIN stratum grid in the region; (5) Using the range obtained in step (3), construct a stratigraphic model after the displacement of the upper and lower plates of the fault in the stratigraphic TIN model. Repeat this step to obtain multiple stratigraphic TIN models, all of which contain the corresponding faults, and finally form a fault structure model.

5. The tunnel geological visualization modeling method under a combined method as claimed in claim 1, characterized in that: In the process of constructing the three-dimensional geological model of the fault plane, the ground plane is assumed to be the top and bottom plates of the coal seam; The fault plane is drawn based on the fault strike and dip information, and the fault coal intersection line is obtained by intersecting with the stratum; Process the coal-breaking intersection line and obtain the coal-breaking intersection line after operation according to the breaking distance information; Split the plane grid and generate a coal plane model based on fault attributes, including fault dislocation; Repeat the above process to obtain the coal seam roof and floor surface model.

6. The tunnel geological visualization modeling method under a combined method as claimed in claim 1, characterized in that: The geometric modeling of the excavation tunnel is based on the theory of rotational bodies and tensile bodies. The section adopts the contour line of the local coordinate system. The contour line is established at each control point along the center line of the tunnel. The method of geometric modeling of the excavation mine tunnel is used to model the section expansion.

7. The tunnel geological visualization modeling method under a combined method as claimed in claim 1 is characterized in that: In the process of realizing model visualization, the long short-term memory network deep learning model is used for static data, and progressive predictions are made based on historical data to achieve dynamic update operations.

8. A tunnel geological visualization modeling system based on a joint method, characterized by: include: The stratigraphic surface model building module is configured to comprehensively adopt the Kriging interpolation algorithm and the inverse distance weighted method to build the stratigraphic surface model using the TIN-based surface modeling method; A fault plane model building module is configured to obtain intersection lines where the faults intersect the strata when each strata is cut by the same fault, so as to determine a control point set of the fault plane and build a three-dimensional geological model of the fault plane; The tunnel geometry modeling module is configured to use the contour line of the local coordinate system established at each control point along the center line as a cross section, and use the cross section extension modeling method to perform geometric modeling of the tunneling tunnel; The model visualization module is configured to perform dynamic prediction and model update based on static data of the modeling area and dynamic data collected during the excavation process to achieve model visualization.

9. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, implement the steps of the method described in any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images