A dynamic optimization system and method for tunnel construction parameters based on point cloud data geological information

Abstract

This invention relates to the field of tunnel construction technology, and more particularly to a system and method for dynamically optimizing tunnel construction parameters based on geological information from point cloud data. At multiple monitoring time points, point cloud data is collected from the tunnel segment to be constructed, obtaining multiple point cloud datasets. The tunnel segment is divided into multiple construction areas, and multiple regional point cloud datasets are obtained from these datasets. Point cloud change analysis is performed on each regional dataset to obtain multiple point cloud change rates. Based on these regional point cloud datasets, reflection intensity analysis is conducted to obtain multiple reflection intensity coefficients. Combined with the multiple point cloud change rates, geological analysis is performed to obtain the distribution of concealed geological information. Based on this distribution, tunnel construction parameters are dynamically optimized to obtain optimized tunnel construction parameters for tunnel construction. This achieves the technical effect of improving the efficiency and safety of tunnel construction while reducing construction risks and costs.

Description

Technical Field

[0001] This invention relates to the field of tunnel construction technology, and in particular to a system and method for dynamic optimization of tunnel construction parameters based on point cloud data geological information. Background Technology

[0002] In the field of tunnel construction, traditional methods for determining tunnel construction parameters primarily rely on preliminary geological survey data. Preliminary geological surveys typically employ methods such as drilling and ground-penetrating radar to conduct initial exploration of the geological conditions in the tunnel construction area. However, the data obtained from these surveys is static and cannot reflect the dynamic changes in geological conditions during tunnel construction. During construction, geological conditions may change due to various factors, and traditional methods cannot capture these changes in a timely manner. This leads to delays in adjusting construction parameters, impacting construction progress and safety. This results in technical problems that affect the efficiency and safety of tunnel construction, and increase construction risks and costs. Summary of the Invention

[0003] This invention addresses the technical problems in the prior art that affect the efficiency and safety of tunnel construction, as well as the high construction risks and costs, by providing a dynamic optimization system and method for tunnel construction parameters based on point cloud data geological information.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0005] In a first aspect, the present invention provides a dynamic optimization system for tunnel construction parameters based on geological information from point cloud data, comprising: a point cloud data acquisition module, used to collect point cloud data of the tunnel segment to be constructed at multiple monitoring time points to obtain multiple point cloud data; a point cloud change analysis module, used to divide the tunnel segment into multiple construction areas, divide the multiple point cloud data into multiple regional point cloud datasets, perform point cloud change analysis on each region, and obtain multiple point cloud change rates; a concealed geological analysis module, used to perform reflection intensity analysis based on the multiple regional point cloud datasets to obtain multiple reflection intensity coefficients, and combine the multiple point cloud change rates to perform geological analysis to obtain the distribution of concealed geological information; and a construction parameter optimization module, used to dynamically optimize tunnel construction parameters based on the distribution of concealed geological information to obtain optimized tunnel construction parameters for tunnel construction.

[0006] Optionally, point cloud data is collected from the tunnel segment to be constructed at multiple monitoring time points to obtain multiple point cloud data, including: determining the tunnel segment to be constructed; and collecting point cloud data from the tunnel segment at multiple monitoring time points using the same point cloud collection parameters to obtain multiple point cloud data.

[0007] Optionally, the tunnel segment is divided into multiple construction areas, and the multiple point cloud data are divided into multiple regional point cloud datasets. Point cloud change analysis is performed on each of the multiple regional point cloud datasets to obtain multiple point cloud change rates. This includes: dividing the tunnel segment into multiple construction areas of equal area; dividing the multiple point cloud data into multiple regional point cloud datasets according to the multiple construction areas to obtain multiple regional point cloud datasets; and performing point cloud change analysis on each of the multiple regional point cloud datasets to obtain multiple point cloud change rates.

[0008] Specifically, point cloud change analysis is performed on the multiple regional point cloud datasets to obtain multiple point cloud change rates, including: within each regional point cloud dataset, the number of duplicate data points in the multiple regional point cloud data is statistically calculated, and the percentage of duplicate point clouds is calculated; based on the percentage of duplicate point clouds, multiple point cloud change rates are calculated.

[0009] Specifically, based on the multiple regional point cloud datasets, reflection intensity analysis is performed to obtain multiple reflection intensity coefficients. Combined with the multiple point cloud change rates, geological analysis is conducted to obtain the distribution of concealed geological information. This includes: obtaining the reflection intensity of each data point in the multiple regional point cloud datasets to obtain multiple regional reflection intensity sets; obtaining a standard reflection intensity; calculating the ratio of all reflection intensities in the multiple regional reflection intensity sets to the standard reflection intensity, and calculating the mean to obtain multiple reflection intensity coefficients; and conducting geological analysis based on the multiple point cloud change rates and multiple reflection intensity coefficients to obtain multiple concealed geological probabilities in multiple construction areas, thereby obtaining the distribution of concealed geological information.

[0010] The process involves geological analysis based on multiple point cloud change rates and multiple reflection intensity coefficients to obtain multiple hidden geological probabilities for multiple construction areas. Obtaining the distribution of hidden geological information includes: calling a hidden geological analyzer, which is built based on machine learning and trained using a set of sample point cloud change rates, a set of sample reflection intensity coefficients, and a set of sample hidden geological probabilities. The hidden geological probability includes the proportion of hidden geology present under different point cloud change rates and reflection intensity coefficients; combining the multiple point cloud change rates and multiple reflection intensity coefficients respectively, inputting them into the hidden geological analyzer, and outputting multiple hidden geological probabilities as the distribution of hidden geological information.

[0011] Optionally, based on the distribution of the concealed geological information, the tunnel construction parameters are dynamically optimized to obtain optimized tunnel construction parameters, and tunnel construction is carried out. This includes: randomly generating first tunnel construction parameters and obtaining a first construction rate for the first tunnel construction parameters; calculating a first construction fitness based on the first construction rate and the distribution of concealed geological information; iteratively optimizing the tunnel construction parameters, obtaining optimized tunnel construction parameters with the largest construction fitness after optimization convergence, and carrying out tunnel construction.

[0012] The calculation of the first construction fitness based on the first construction rate and the distribution of concealed geological information includes: obtaining the average construction rate; calculating the first rate ratio of the first construction rate to the average construction rate to obtain the first speed fitness; obtaining the first safety fitness based on the distribution of concealed geological information and the first rate ratio; and calculating the first construction fitness based on the first speed fitness and the first safety fitness.

[0013] Secondly, this invention provides a method for dynamically optimizing tunnel construction parameters based on geological information from point cloud data, including:

[0014] Point cloud data was collected from the tunnel section to be constructed at multiple monitoring time points to obtain multiple point cloud data.

[0015] The tunnel section is divided into multiple construction areas, and multiple point cloud datasets are obtained by dividing the multiple point cloud data into multiple areas. Point cloud change analysis is performed on each area to obtain multiple point cloud change rates.

[0016] Based on the multiple regional point cloud datasets, reflection intensity analysis is performed to obtain multiple reflection intensity coefficients. Combined with the multiple point cloud change rates, geological analysis is conducted to obtain the distribution of hidden geological information.

[0017] Based on the distribution of the hidden geological information, the tunnel construction parameters are dynamically optimized to obtain the optimized tunnel construction parameters, and then the tunnel construction is carried out.

[0018] By implementing this invention, point cloud data can be collected from the tunnel section to be constructed at multiple monitoring time points, resulting in multiple point cloud data sets. This ensures the consistency and comparability of the point cloud data, providing an accurate and reliable data foundation for subsequent analysis of geological changes in the tunnel section.

[0019] By implementing this invention, the tunnel section can be divided into multiple construction areas, and multiple regional point cloud datasets can be obtained by dividing the multiple point cloud data. Point cloud change analysis can be performed on each of these datasets to obtain multiple point cloud change rates. Through regional division and targeted analysis, the geological changes in different areas of the tunnel section can be accurately located, improving the accuracy and targeting of geological change analysis and providing a more detailed basis for subsequent hidden geological analysis.

[0020] By implementing this invention, it is possible to perform reflection intensity analysis based on the multiple regional point cloud datasets to obtain multiple reflection intensity coefficients, and combine the multiple point cloud change rates to perform geological analysis to obtain the distribution of hidden geological information. This allows for accurate detection of hidden geological information within tunnel sections, early discovery of potential geological risks, and provides a scientific geological basis for optimizing construction parameters, thereby improving the safety and reliability of construction.

[0021] By implementing this invention, tunnel construction parameters can be dynamically optimized based on the distribution of the hidden geological information, thereby obtaining optimized tunnel construction parameters and carrying out tunnel construction. This achieves dynamic optimization of tunnel construction parameters, enabling adjustments to the parameters according to actual geological conditions, improving construction efficiency and safety, avoiding construction delays or safety accidents caused by changes in geological conditions, and reducing construction costs.

[0022] In summary, by implementing this invention, the technical effects of improving the efficiency and safety of tunnel construction and reducing construction risks and costs can be achieved. Attached Figure Description

[0023] Figure 1 A schematic diagram of a dynamic optimization system for tunnel construction parameters based on point cloud data geological information provided by the present invention;

[0024] Figure 2 This is a flowchart illustrating a method for dynamically optimizing tunnel construction parameters based on geological information from point cloud data, as provided by the present invention.

[0025] In the attached diagram, the components represented by each number are as follows:

[0026] Point cloud data acquisition module 11, point cloud change analysis module 12, concealed geological analysis module 13, construction parameter optimization module 14. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0030] Example 1, as Figure 1 As shown, this embodiment of the invention provides a dynamic optimization system for tunnel construction parameters based on point cloud data geological information, including:

[0031] The point cloud data acquisition module 11 is used to collect point cloud data of the tunnel section to be constructed at multiple monitoring time points to obtain multiple point cloud data.

[0032] The point cloud change analysis module 12 is used to divide the tunnel section into multiple construction areas, divide the multiple point cloud data into multiple area point cloud datasets, perform point cloud change analysis on each area, and obtain multiple point cloud change rates.

[0033] The concealed geological analysis module 13 is used to perform reflection intensity analysis based on the multiple regional point cloud datasets, obtain multiple reflection intensity coefficients, and perform geological analysis in combination with the multiple point cloud change rates to obtain the distribution of concealed geological information.

[0034] The construction parameter optimization module 14 is used to dynamically optimize the tunnel construction parameters based on the distribution of the hidden geological information, obtain optimized tunnel construction parameters, and carry out tunnel construction.

[0035] In this embodiment of the application, the point cloud data acquisition module 11 is used to collect point cloud data of the tunnel section to be constructed at multiple monitoring time points, and obtain multiple point cloud data, including:

[0036] Identify the tunnel sections to be constructed;

[0037] At multiple monitoring time points, the same point cloud acquisition parameters were used to collect point cloud data from the tunnel section, resulting in multiple point cloud data sets.

[0038] In this embodiment of the application, to achieve dynamic optimization of tunnel construction parameters, it is first necessary to determine the tunnel segment to be constructed. During tunnel construction, the overall construction route and segmented construction plan of the tunnel can be clarified through geological survey reports, design drawings, and other materials, thus determining the specific tunnel segment that needs to be constructed, i.e., the tunnel segment to be constructed. For example, the segment to be constructed can be delineated based on the tunnel's mileage marker (such as the section from K1+200 to K1+300) or areas with significant differences in geological conditions.

[0039] After the construction personnel arrive at the tunnel construction site, they also need to use surveying equipment such as total stations and GPS to locate the tunnel section to be constructed as determined in the design drawings, mark the start and end positions of the tunnel section, and ensure that it is consistent with the design documents.

[0040] In this embodiment, the point cloud is a dataset composed of a large number of discrete points. These points describe the surface morphology and features of an object through three-dimensional coordinates (X, Y, Z) and related attributes (such as reflection intensity, color, etc.). In engineering fields such as tunnel construction, point cloud data is usually acquired through technologies such as three-dimensional laser scanning, which can accurately reflect the spatial location and geometry of structures such as tunnel walls.

[0041] In this embodiment of the application, to achieve dynamic optimization of tunnel construction parameters based on geological information from point cloud data, it is first necessary to collect point cloud data from the tunnel segment using the same point cloud acquisition parameters to obtain multiple point cloud data sets.

[0042] The monitoring time points can be determined based on the tunnel construction schedule, the complexity of geological conditions, and the sensitivity of point cloud data changes. For example, for tunnel sections with complex geological conditions and high construction risks, the monitoring interval can be shortened (e.g., once every shift, i.e., once every 8 hours); for areas with stable geological conditions, the interval can be appropriately extended (e.g., once a day).

[0043] Point cloud acquisition can be performed using point cloud acquisition equipment suitable for the tunnel environment, such as 3D laser scanners (e.g., FAROFocus series, Leica P series). These devices are characterized by high precision and high resolution, and can achieve rapid scanning in the confined space of a tunnel.

[0044] When collecting data at multiple monitoring time points, it is necessary to ensure that the point cloud acquisition parameters remain consistent to guarantee the comparability of point cloud data collected multiple times. These point cloud acquisition parameters mainly include scanning distance, scanning resolution, and scanning angle.

[0045] For example, the scanning distance is fixed at 30 meters to ensure that the point cloud data collected at different times has the same coverage and density; the scanning resolution is fixed at 0.01 degrees to ensure that the detail of the point cloud data is consistent, which is convenient for subsequent comparative analysis. The scanning azimuth and elevation angles of the equipment are kept the same in each scan, for example, the scanner is fixed on a bracket on the same side of the tunnel, at a uniform height of 1.5 meters, facing the tunnel axis.

[0046] By using the above method, point cloud data can be collected from the tunnel section to be constructed at multiple monitoring time points, thus obtaining multiple point cloud data.

[0047] In this embodiment of the application, the point cloud change analysis module 12 is used to divide the tunnel segment into multiple construction areas, obtain multiple regional point cloud datasets from the multiple point cloud data, perform point cloud change analysis on each region, and obtain multiple point cloud change rates, including:

[0048] The tunnel section was divided into multiple construction areas of equal size.

[0049] According to multiple construction areas, multiple point cloud data are divided into multiple regional point cloud data to obtain multiple regional point cloud datasets;

[0050] Point cloud change analysis was performed on the multiple regional point cloud datasets to obtain multiple point cloud change rates.

[0051] In this embodiment, the tunnel segment is divided into multiple construction areas of equal area. This can be achieved by using an equal-area division method based on the tunnel's cross-sectional shape (e.g., circular, horseshoe-shaped) to ensure that the projected area of ​​each construction area on the tunnel's cross-section is consistent. For example, for a circular tunnel, it can be divided into six sector-shaped areas (each with a central angle of 60°) according to its central angle. The purpose of this step is to ensure that the size of each construction area is uniform, facilitating subsequent comparison of point cloud data changes between different areas.

[0052] One specific method for dividing the tunnel is to import the overall point cloud data of the tunnel using point cloud processing software (such as CloudCompare), construct a three-dimensional spatial model based on the tunnel design axis, and determine the start and end mileage of the tunnel segment to be divided (such as K1+200~K1+300).

[0053] Then, multiple cross sections are selected within the tunnel section (e.g., one cross section every 10 meters), and areas are divided on each cross section according to the principle of equal area. These areas are then extended along the tunnel axis to form multiple three-dimensional construction areas (e.g., columnar or fan-shaped columns).

[0054] Finally, each construction area should be uniquely numbered (e.g., A1, A2, B1, B2). The number should include the area's location information (e.g., mileage segment, cross-sectional sequence, and area orientation) to facilitate subsequent data management.

[0055] Furthermore, it is necessary to divide the point cloud data according to the construction area to obtain a regional point cloud dataset.

[0056] An octree spatial index can be constructed for point cloud data collected at different times (such as point clouds at time points T1, T2, and T3) to quickly locate the spatial region to which the three-dimensional coordinates (x, y, z) of each point belong. Then, the construction area boundaries defined in the previous steps are transformed into spatial geometric constraints (such as the angle range and radial distance range of the sector region) as the basis for point cloud data classification.

[0057] Next, for each point cloud data point, it is determined whether its coordinates satisfy the geometric constraints of a certain construction area. For example, for a sector area with a central angle of 60°, it is determined whether the polar angle of the point is within the range of [θ, θ+60°] and whether the radial distance is within the tunnel radius. Optionally, the batch processing function of Python scripts or point cloud processing software can be used to distribute point cloud data from multiple periods (i.e., point cloud data collected at different time points, such as point clouds at time points T1, T2, and T3) to the corresponding construction areas (such as A1, A2, B1, and B2), forming regional point cloud datasets (such as A1_T1.las, A1_T2.las, etc.).

[0058] The octree spatial indexing method and point cloud classification using Python scripts or point cloud processing software are existing technologies and will not be elaborated here.

[0059] Using the above method, multiple point cloud data can be divided into multiple regional point cloud data, thus obtaining multiple regional point cloud datasets.

[0060] Specifically, point cloud change analysis is performed on the multiple regional point cloud datasets to obtain multiple point cloud change rates, including:

[0061] Within each regional point cloud dataset, the number of duplicate data points in multiple regional point cloud datasets is statistically calculated, and the percentage of multiple duplicate point clouds is obtained.

[0062] Based on the proportion of multiple repeating point clouds, the change rate of multiple point clouds is calculated.

[0063] First, point cloud data needs to be preprocessed for point cloud registration. This involves using the Iterative Closest Point (ICP) algorithm or feature-based registration methods to unify the regional point cloud datasets from different time points into the same coordinate system, eliminating errors caused by differences in scanning positions. For example, using the point cloud at time T1 as a reference, the point clouds at time T2 and T3 are registered to this reference.

[0064] Next, the percentage of duplicate point clouds needs to be calculated. Specifically, the registered multi-phase point clouds are projected onto the same plane (e.g., a tunnel cross-section), and uniform sampling (e.g., voxel sampling) is used to ensure consistent point cloud density, avoiding the impact of density differences on the calculation results. Then, for a certain area of ​​point clouds at two time points (e.g., T1 and T2), the nearest neighbor of each point in the other phase of the point cloud is searched, and a distance threshold (e.g., 5cm) is set to determine if it is a duplicate point. The number of duplicate points and the total number of points N_total are counted. The percentage of duplicate point clouds P = number of duplicate points / total number of points, yielding multiple percentages of duplicate point clouds for the construction area, such as P_T1, P_T2, and P_T3. For example, if T1 has 1000 points, and T2 finds that 800 of these points are within the distance threshold (e.g., 5cm) of the points in T1, then the percentage of duplicate points P = 800 / 1000 = 80%.

[0065] The point cloud change rate can be represented as R = (1 - P) × 100%, where P is the percentage of repeating point clouds. A larger R value indicates a more significant change in the point cloud within that region. For example, when P = 80%, R = (1 - 0.8) × 100% = 20%, meaning that 20% of the point cloud in that region has changed. Multiple point cloud change rates can be calculated based on the percentages of repeating point clouds.

[0066] In this embodiment of the application, the concealed geological analysis module 13 is used to perform reflection intensity analysis based on the multiple regional point cloud datasets to obtain multiple reflection intensity coefficients, and to perform geological analysis in conjunction with the multiple point cloud change rates to obtain the distribution of concealed geological information, including:

[0067] Obtain the reflection intensity of each data point within the multiple regional point cloud datasets to obtain multiple regional reflection intensity sets;

[0068] Obtain the standard reflection intensity;

[0069] Calculate the ratio of all reflected intensities within the multiple regions to the standard reflected intensity, and calculate the mean to obtain multiple reflected intensity coefficients;

[0070] Based on multiple point cloud change rates and multiple reflection intensity coefficients, geological analysis is conducted to obtain multiple hidden geological probabilities for multiple construction areas, thus obtaining the distribution of hidden geological information.

[0071] The reflection intensity mentioned above refers to the ability of an object's surface to reflect a laser beam. It is usually represented by a value of 0-255. In point cloud data, each point contains a reflection intensity attribute in addition to its three-dimensional coordinates (X,Y,Z). The larger the value, the stronger the ability of the object's surface to reflect the laser. That is, the reflection intensity value can be directly obtained by the aforementioned three-dimensional laser scanner when collecting point cloud data.

[0072] To obtain the reflection intensity of each data point in the multiple regional point cloud datasets, specifically, the reflection intensity value of each point is extracted from the point cloud dataset of each construction area. For example, a regional point cloud contains 1000 points, each point has a reflection intensity value I, forming the reflection intensity set of the region [I1,I2,...,I1000]. For example, the reflection intensity set of region A at time T1 can be [150,160,145,...,155] (a total of 1000 values).

[0073] Furthermore, it is necessary to obtain the standard reflection intensity.

[0074] Specifically, the standard reflection intensity can be obtained by selecting the average reflection intensity of typical intact rock strata (such as sandstone) based on the geological survey report of the tunnel area; or by field calibration: scanning an unexcavated stable rock strata area and calculating its average reflection intensity as the standard reflection intensity. For example, if the survey reveals that the average reflection intensity of intact sandstone in the tunnel section is 150, then the standard reflection intensity can be set to 150.

[0075] Furthermore, it is necessary to calculate the ratio of all reflection intensities within the multiple regional reflection intensity sets to the standard reflection intensity, and calculate the mean to obtain multiple reflection intensity coefficients.

[0076] The specific calculation method is as follows: for each region's reflection intensity set, calculate the ratio of each value to the standard reflection intensity, and then calculate the mean. For example, the reflection intensity coefficient of the reflection intensity set of region A above can be calculated by calculating the ratio of each value in the reflection intensity set [150, 160, 145, ..., 155] to 150 (standard reflection intensity). For example, 150 / 150=1, 160 / 150≈1.07, 145 / 150≈0.97, ..., 155 / 150≈1.03, and then calculate the mean, that is, (1+1.07+0.97+...+1.03) / 1000≈1.02. Then the reflection intensity coefficient of region A is 1.02.

[0077] Using the above method, multiple reflection intensity coefficients can be calculated.

[0078] Among them, geological analysis was conducted based on multiple point cloud change rates and multiple reflection intensity coefficients to obtain multiple hidden geological probabilities for multiple construction areas, and the distribution of hidden geological information included:

[0079] The hidden geological analyzer is invoked, wherein the hidden geological analyzer is built based on machine learning and is trained using a set of sample point cloud change rates, a set of sample reflection intensity coefficients and a set of sample hidden geological probabilities. The hidden geological probability includes the proportion of hidden geologicals under different point cloud change rates and reflection intensity coefficients.

[0080] The multiple point cloud change rates and multiple reflection intensity coefficients are combined and input into the concealed geological analyzer to output multiple concealed geological probabilities as the distribution of concealed geological information.

[0081] In this embodiment, the concealed geology analyzer is mainly used to establish a nonlinear mapping relationship between point cloud change rate, reflection intensity coefficient, and the probability of concealed geology. Its input features are a combination of the point cloud change rate and reflection intensity coefficient for each construction area, forming a feature vector. If the point cloud change rate of area A is 20% (0.2) and the reflection intensity coefficient is 1.02, then the feature vector is [0.2, 1.02]. The output feature is the probability (a value between 0 and 1) of the presence of concealed geology in that area.

[0082] The sample data used to train the concealed geology analyzer consists of historical tunnel construction data. Each sample includes a set of reflection intensity coefficients, a set of point cloud change rates, and actual concealed geological conditions (such as whether faults or karst caves exist, indicated by yes or no).

[0083] Optionally, algorithms such as random forest, logistic regression, or neural networks can be used to train the concealed geological analyzer to learn the mapping relationship between features (point cloud change rate, reflection intensity coefficient) and concealed geological probabilities. The method of building the concealed geological analyzer using such algorithm models is existing technology, widely known and easily implemented by those skilled in the art, and will not be elaborated upon here.

[0084] The multiple point cloud change rates and multiple reflection intensity coefficients are combined and input into the concealed geological analyzer, which outputs multiple concealed geological probabilities. For example, inputting the combination of features from region A [0.2, 1.02] into the concealed geological analyzer outputs a concealed geological probability of 30%, and inputting the combination of features from region B [0.4, 0.85] into the concealed geological analyzer outputs a concealed geological probability of 80%.

[0085] In this embodiment, the construction parameter optimization module 14 is used to dynamically optimize tunnel construction parameters based on the distribution of the concealed geological information, obtain optimized tunnel construction parameters, and carry out tunnel construction, including:

[0086] Randomly generate the first tunnel construction parameters and obtain the first construction rate of the first tunnel construction parameters;

[0087] The first construction adaptability is calculated based on the first construction rate and the distribution of hidden geological information;

[0088] The tunnel construction parameters are iteratively optimized. After optimization convergence, the optimal tunnel construction parameters with the greatest construction adaptability are obtained, and tunnel construction is carried out.

[0089] The first set of tunnel construction parameters are the relevant operational parameters that determine the tunnel construction speed during tunnel excavation. For example, a set of tunnel construction parameters can be: excavation speed v = 5cm / cycle, which means that the excavation advance per unit time is 5cm per construction cycle; support spacing d = 1.0m, which means the longitudinal spacing between adjacent support structures (such as steel arches and anchors); grouting pressure p = 2.5MPa, which means the pressure value during grouting, where "2.5MPa" means that the grout is injected into the stratum at a pressure of 2.5 MPa.

[0090] The first construction rate is obtained by using historical data or simulation calculations to obtain the construction rate when using the first tunnel construction parameter P1 (e.g., 3.0m per day), which can be denoted as R1.

[0091] The first construction adaptability is calculated based on the first construction rate and the distribution of hidden geological information, including:

[0092] Obtain the average construction rate, calculate the first rate ratio of the first construction rate to the average construction rate, and obtain the first speed adaptability.

[0093] Based on the distribution of the concealed geological information and the first rate ratio, a first safety fitness is obtained;

[0094] The first construction adaptability is calculated based on the first speed adaptability and the first safety adaptability.

[0095] In this embodiment of the application, the average construction rate is determined based on the tunnel geological conditions and the capacity of the construction equipment, with a benchmark construction rate (e.g., 4.0 m / day). The first rate ratio can be calculated as: first rate ratio = first construction rate / average construction rate. For example, in the above example, the first rate ratio = 3 / 4 = 0.75, and this first rate ratio is used as the first speed fitness.

[0096] Furthermore, a first safety fitness level needs to be obtained based on the distribution of the concealed geological information and the first rate ratio.

[0097] The first safety fitness can be calculated by multiplying the reciprocal of the mean of the hidden geological probability by the first rate ratio. That is, first safety fitness = 1 / mean of the hidden geological information distribution × first rate ratio. The mean of the hidden geological probability refers to the average of the hidden geological probabilities in each construction area (for example, if area A has a risk of 0.3 and area B has a risk of 0.8, then the mean is (0.3 + 0.8) / 2 = 0.55). Assuming the first rate ratio is 0.75, then first safety fitness = 1 / 0.55 × 0.75 ≈ 1.36. A higher first safety fitness indicates a smaller impact from the current geological risk.

[0098] Furthermore, the first construction adaptability needs to be calculated based on the first speed adaptability and the first safety adaptability.

[0099] The first construction adaptability is a comprehensive index combining speed adaptability and safety adaptability. It can be calculated using a weighted summation method. For example, the first construction adaptability = w × first speed adaptability + (1 − w) × first safety adaptability. Here, w is the weight of speed adaptability (0 ≤ w ≤ 1), and (1 − w) is the weight of safety adaptability. The weight values ​​are adjusted according to the construction scenario. For example, in normal geological conditions, w = 0.6 (speed priority) can be set, while in high-risk geological conditions, w = 0.3 (safety priority) can be set.

[0100] Assuming the first speed fitness is 0.8, the first safety fitness is 0.7, and w=0.6, then the first construction fitness = 0.6*0.8 + 0.4*0.7 = 0.76.

[0101] Finally, it is necessary to iteratively optimize the tunnel construction parameters. After optimization convergence, the optimal tunnel construction parameters with the greatest construction adaptability are obtained, and tunnel construction is carried out.

[0102] First, when iteratively optimizing construction parameters, it is necessary to set certain parameter range constraints based on equipment conditions and construction environment, such as limiting the excavation speed to 2-8 cm / cycle, the support spacing to 20.6-1.5 m, and the grouting pressure to 21.5-4.0 MPa.

[0103] Specifically, a genetic algorithm can be used for iterative optimization. The iterative method involves randomly generating N sets (e.g., N=50 sets) of construction parameters, calculating the first fitness of each set, selecting parent generations (e.g., the top 30%) based on fitness, and cross-pollinating and mutating the parent parameters (e.g., taking the average of the parent generations for excavation speed) and (e.g., randomly perturbing the support spacing by ±10%) to obtain new sets of construction parameters. This process is repeated until the change in the first fitness is less than a threshold (e.g., 0.01) or the maximum number of iterations (e.g., 100) is reached. The construction parameters corresponding to the highest first fitness observed during the iteration process are selected as the optimized tunnel construction parameters for tunnel construction. Example 2, as follows... Figure 2 As shown, based on the same inventive concept as the tunnel construction parameter dynamic optimization system based on point cloud data geological information provided in Embodiment 1, this embodiment of the invention also provides a tunnel construction parameter dynamic optimization method based on point cloud data geological information, including:

[0104] S100: At multiple monitoring time points, point cloud data is collected from the tunnel section to be constructed, and multiple point cloud data are obtained;

[0105] S200: Divide the tunnel section into multiple construction areas, divide the multiple point cloud data into multiple area point cloud datasets, perform point cloud change analysis on each area, and obtain multiple point cloud change rates.

[0106] S300: Based on the multiple regional point cloud datasets, perform reflection intensity analysis to obtain multiple reflection intensity coefficients. Combined with the multiple point cloud change rates, perform geological analysis to obtain the distribution of hidden geological information.

[0107] S400: Based on the distribution of the hidden geological information, dynamically optimize the tunnel construction parameters to obtain optimized tunnel construction parameters, and then carry out tunnel construction.

[0108] In step S100 of this application embodiment, point cloud data is collected from the tunnel segment to be constructed at multiple monitoring time points to obtain multiple point cloud data, including: determining the tunnel segment to be constructed; and collecting point cloud data from the tunnel segment at multiple monitoring time points using the same point cloud collection parameters to obtain multiple point cloud data.

[0109] In step S200 of this embodiment, the tunnel segment is divided into multiple construction areas, and multiple regional point cloud datasets are obtained by dividing the multiple point cloud data. Point cloud change analysis is performed on each of the multiple regional point cloud datasets to obtain multiple point cloud change rates. This includes: dividing the tunnel segment into multiple construction areas of equal area; dividing the multiple point cloud data into multiple regional point cloud datasets according to the multiple construction areas to obtain multiple regional point cloud datasets; and performing point cloud change analysis on each of the multiple regional point cloud datasets to obtain multiple point cloud change rates.

[0110] Specifically, point cloud change analysis is performed on the multiple regional point cloud datasets to obtain multiple point cloud change rates, including: within each regional point cloud dataset, the number of duplicate data points in the multiple regional point cloud data is statistically calculated, and the percentage of duplicate point clouds is calculated; based on the percentage of duplicate point clouds, multiple point cloud change rates are calculated.

[0111] In step S300 of this embodiment, reflection intensity analysis is performed based on the multiple regional point cloud datasets to obtain multiple reflection intensity coefficients. Combined with the multiple point cloud change rates, geological analysis is performed to obtain the distribution of concealed geological information. This includes: obtaining the reflection intensity of each data point within the multiple regional point cloud datasets to obtain multiple regional reflection intensity sets; obtaining a standard reflection intensity; calculating the ratio of all reflection intensities within the multiple regional reflection intensity sets to the standard reflection intensity, and calculating the mean to obtain multiple reflection intensity coefficients; performing geological analysis based on the multiple point cloud change rates and multiple reflection intensity coefficients to obtain multiple concealed geological probabilities for multiple construction areas, thus obtaining the distribution of concealed geological information.

[0112] In step S400 of this application embodiment, the tunnel construction parameters are dynamically optimized according to the distribution of the hidden geological information to obtain optimized tunnel construction parameters, and tunnel construction is carried out. This includes: randomly generating first tunnel construction parameters and obtaining a first construction rate of the first tunnel construction parameters; calculating a first construction fitness based on the first construction rate and the distribution of hidden geological information; iteratively optimizing the tunnel construction parameters, obtaining the optimized tunnel construction parameters with the largest construction fitness after optimization convergence, and carrying out tunnel construction.

[0113] The calculation of the first construction fitness based on the first construction rate and the distribution of concealed geological information includes: obtaining the average construction rate; calculating the first rate ratio of the first construction rate to the average construction rate to obtain the first speed fitness; obtaining the first safety fitness based on the distribution of concealed geological information and the first rate ratio; and calculating the first construction fitness based on the first speed fitness and the first safety fitness.

[0114] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0115] Those skilled in the art will understand that embodiments of the present invention can provide methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0116] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0119] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0120] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A tunnel construction parameter dynamic optimization system based on point cloud data geological information, characterized in that, The system includes: The point cloud data acquisition module is used to collect point cloud data of the tunnel section to be constructed at multiple monitoring time points, and obtain multiple point cloud data. The point cloud change analysis module is used to divide the tunnel section into multiple construction areas, obtain multiple regional point cloud datasets from the multiple point cloud data, perform point cloud change analysis on each, and obtain multiple point cloud change rates. Specifically, it obtains the reflection intensity of each data point in the multiple regional point cloud datasets to obtain multiple regional reflection intensity sets; obtains the standard reflection intensity; calculates the ratio of all reflection intensities in the multiple regional reflection intensity sets to the standard reflection intensity, and calculates the mean to obtain multiple reflection intensity coefficients; based on the multiple point cloud change rates and multiple reflection intensity coefficients, it performs geological analysis to obtain multiple hidden geological probabilities in the multiple construction areas, and obtains the distribution of hidden geological information. Specifically, it calls a hidden geological analyzer, which is built based on machine learning and trained using a sample point cloud change rate set, a sample reflection intensity coefficient set, and a sample hidden geological probability set. The hidden geological probability includes the proportion of hidden geology under different point cloud change rates and reflection intensity coefficients; it combines the multiple point cloud change rates and multiple reflection intensity coefficients, inputs them into the hidden geological analyzer, and outputs multiple hidden geological probabilities as the distribution of hidden geological information. The concealed geological analysis module is used to perform reflection intensity analysis based on the multiple regional point cloud datasets, obtain multiple reflection intensity coefficients, and perform geological analysis in conjunction with the multiple point cloud change rates to obtain the distribution of concealed geological information. The construction parameter optimization module is used to dynamically optimize tunnel construction parameters based on the distribution of the hidden geological information, obtain optimized tunnel construction parameters, and then carry out tunnel construction. Specifically, First tunnel construction parameters are randomly generated, and a first construction rate is obtained based on these parameters. A first construction fitness is calculated based on the first construction rate and the distribution of hidden geological information. Specifically, this involves obtaining the average construction rate, calculating the ratio of the first construction rate to the average construction rate, and obtaining a first speed fitness. A first safety fitness is obtained based on the distribution of hidden geological information and the first speed ratio. A first construction fitness is calculated based on the first speed fitness and the first safety fitness. The tunnel construction parameters are iteratively optimized, and after optimization convergence, the optimized tunnel construction parameters with the highest construction fitness are obtained, and tunnel construction is then carried out.

2. The tunnel construction parameter dynamic optimization system based on point cloud data geological information according to claim 1, characterized in that, Point cloud data was collected at multiple monitoring time points for the tunnel section to be constructed, resulting in multiple point cloud data sets, including: Identify the tunnel sections to be constructed; At multiple monitoring time points, the same point cloud acquisition parameters were used to collect point cloud data from the tunnel section, resulting in multiple point cloud data sets. 3.The tunnel construction parameter dynamic optimization system based on point cloud data geological information of claim 1, wherein, The tunnel section is divided into multiple construction zones, and multiple point cloud datasets are obtained by dividing the multiple point cloud data into multiple regional point cloud datasets. Point cloud change analysis is performed on each region to obtain multiple point cloud change rates, including: The tunnel section was divided into multiple construction areas of equal size. According to multiple construction areas, multiple point cloud data are divided into multiple regional point cloud data to obtain multiple regional point cloud datasets; Point cloud change analysis was performed on the multiple regional point cloud datasets to obtain multiple point cloud change rates.

4. The tunnel construction parameter dynamic optimization system based on point cloud data geological information according to claim 3, characterized in that, Point cloud change analysis was performed on the multiple regional point cloud datasets to obtain multiple point cloud change rates, including: Within each regional point cloud dataset, the number of duplicate data points in multiple regional point cloud datasets is statistically calculated, and the percentage of multiple duplicate point clouds is obtained. Based on the proportion of multiple repeating point clouds, the change rate of multiple point clouds is calculated.

5. The tunnel construction parameter dynamic optimization method based on point cloud data geological information, characterized in that, The method is applied to the system according to any one of claims 1-4, and the method comprises: Point cloud data was collected from the tunnel section to be constructed at multiple monitoring time points to obtain multiple point cloud data. The tunnel section is divided into multiple construction areas, and multiple point cloud datasets are obtained by dividing the multiple point cloud data into multiple areas. Point cloud change analysis is performed on each area to obtain multiple point cloud change rates. Based on the multiple regional point cloud datasets, reflection intensity analysis is performed to obtain multiple reflection intensity coefficients. Combined with the multiple point cloud change rates, geological analysis is conducted to obtain the distribution of hidden geological information. Based on the distribution of the hidden geological information, the tunnel construction parameters are dynamically optimized to obtain the optimized tunnel construction parameters, and then the tunnel construction is carried out.

Images