Tunnel construction safety advanced early warning method and system based on three-dimensional laser scanning

Abstract

The invention discloses a tunnel construction safety advanced early warning method and system based on three-dimensional laser scanning. The method comprises the following steps: acquiring multi-source data of a tunnel construction area; unifying the point cloud to a geodetic coordinate system; obtaining multi-dimensional features of each tunnel section; constructing a spatio-temporal data set; training a space-time diagram neural network model based on the space-time data set; and inputting data acquired in real time into the trained time-space diagram neural network model to output a prediction result of the deformation risk of each section of the tunnel in a specified time period in the future, and giving an alarm. Therefore, the future section settlement risk is predicted through the space-time diagram neural network model, and sufficient time is reserved for risk disposal; three-dimensional laser scanning is taken as a core, and environment data and construction data are fused, so that the accuracy of model prediction is improved; an integrated system of acquisition, processing, modeling, early warning and feedback is constructed, the management and control efficiency is improved, and the system can feed back the actual effect of each adjustment to the model for continuous learning and improvement.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel construction, and particularly relates to a tunnel construction safety advanced warning method and system based on three-dimensional laser scanning. BACKGROUND

[0002] In the process of tunnel construction, due to complex and changeable geological conditions and harsh construction environment, safety accidents such as surrounding rock deformation, collapse and water inrush are prone to occur. Therefore, how to effectively predict and warn the safety risks in the process of tunnel construction has become a key problem to ensure the safety of tunnel construction.

[0003] At present, tunnel construction safety monitoring and warning technologies mainly include traditional manual monitoring, automatic monitoring systems and warning methods based on data analysis. Among them, three-dimensional laser scanning technology has been widely used in tunnel construction monitoring due to its high precision, non-contact and full coverage characteristics. CN104680579B discloses a tunnel construction information monitoring system based on three-dimensional scanning point cloud. The system uses three-dimensional laser scanning point cloud measurement technology to collect coordinate information and intensity information of the full-section spatial structure of the tunnel, performs automatic filtering processing and point cloud data automatic splicing, generates a two-dimensional plane model and a three-dimensional space model of the tunnel, and realizes real-time processing, updating and three-level warning and forecasting of monitoring data and construction information.

[0004] With the development of deep learning technology, tunnel construction quality evaluation and prediction methods combining three-dimensional point cloud data with intelligent algorithms have also gradually emerged. CN118864415A discloses a tunnel mechanized construction blasting quality prediction method based on three-dimensional point cloud and neural network. The method obtains tunnel point cloud data through a three-dimensional laser scanner, constructs a three-dimensional polygonal surface model after preprocessing and point processing, and constructs an overbreak and underbreak prediction model based on drilling construction logs, blasting design schemes and the like, to realize prediction of tunnel blasting quality.

[0005] In the aspect of tunnel deformation monitoring, CN120141338B proposes a tunnel lining wide and thick zone three-dimensional laser point cloud detection method and system in water assignment area. The method obtains tunnel point cloud data through three-dimensional laser scanning, establishes a high-fidelity tunnel twin model, simulates tunnel deformation through finite element, and performs tunnel point cloud registration and deformation analysis through a neural network model, significantly improving the accuracy of tunnel deformation analysis and processing.

[0006] For the identification and warning of tunnel surrounding rock risk areas, CN120163430A proposes a tunnel surrounding rock risk area safety classification warning method. The method uses three-dimensional laser scanning technology to obtain high-precision tunnel point cloud data, analyzes the spatial deformation distribution of surrounding rock and its evolution law over time, develops a potential risk area identification algorithm, and constructs a hierarchical safety warning system.

[0007] In addition, CN120808580B discloses a tunnel composite disaster intelligent early warning method and system based on tendency digital twinning, which constructs a digital twinning model based on three-dimensional point cloud data and design parameters of the tunnel structure, models the spatiotemporal features of the real-time collected monitoring data using a spatiotemporal graph convolution network, and calculates the disaster occurrence probability by modeling the dependency relationship between different disaster factors through a Bayesian network.

[0008] However, the existing tunnel construction safety early warning technology still has the following deficiencies: The existing technology relies on manual fixed-point monitoring or post-mortem review, lacks real-time perception and advanced prediction ability of the geological conditions of the tunnel face, and is difficult to identify potential risks in advance. Although three-dimensional laser scanning technology has been applied to tunnel monitoring, a comprehensive real-time monitoring system for the tunnel face and surrounding geological conditions has not yet been formed.

[0009] The existing technology fails to fully integrate high-precision geological data of three-dimensional laser scanning with construction parameters, environmental monitoring data and other multi-source information, resulting in incomplete data coverage and inability to support comprehensive advanced early warning modeling needs.

[0010] The existing technology mostly uses traditional statistical methods or simple machine learning models, and fails to fully consider the spatiotemporal correlation of tunnel deformation and the dynamic influence of geological conditions, resulting in low advanced prediction accuracy and poor warning timeliness. In particular, there is a lack of comprehensive models that can simultaneously learn the propagation law of tunnel cross-section features in spatial structure and the evolution law in time series.

[0011] The data collection, processing, modeling, and early warning steps in the existing technology are often scattered and independent, and have not formed an integrated system solution, which lacks engineering practicability and is difficult to meet the actual needs of tunnel construction safety advanced early warning.

[0012] In summary, the existing tunnel construction safety early warning method has at least the above problems. SUMMARY

[0013] The purpose of the present application is to overcome the deficiencies of the prior art and provide a tunnel construction safety advanced early warning method and system based on three-dimensional laser scanning.

[0014] The purpose of the present application is achieved by the following technical solutions: In a first aspect, the application discloses a tunnel construction safety advanced warning method based on three-dimensional laser scanning, comprising: S1, acquiring multi-source data of a tunnel construction area, including three-dimensional scanning data, construction parameters and environmental monitoring data, the three-dimensional scanning data being stored as a point cloud; S2, preprocessing the multi-source data; S3, completing coarse registration of the point cloud based on the coordinates of the design control points preset in the tunnel, and then performing fine registration through a three-dimensional point cloud registration algorithm to unify the point cloud to a geodetic coordinate system; S4, extracting the geometric features of the point cloud through a semantic segmentation model to obtain multi-dimensional features of each tunnel section; S5, constructing a spatio-temporal data set, including: taking a tunnel section as a node, splicing and fusing the multi-dimensional features of each node and the construction parameters and environmental monitoring data to obtain a feature vector of the corresponding node; and based on spatial proximity and geological similarity, establishing a weighted graph structure representing the correlation between sections, combining the node features of the nodes at consecutive multiple time steps and the corresponding weighted graph structure in chronological order to construct a spatio-temporal data set; S6, training a spatio-temporal graph neural network model based on the spatio-temporal data set; S7, inputting real-time collected data into the trained spatio-temporal graph neural network model to output a prediction result of the deformation risk of each section of the tunnel in a future specified time period, and performing safety warning according to the prediction result.

[0015] Further, in S5, the construction of the spatio-temporal data set includes: stacking the node features at consecutive multiple time steps into a three-dimensional feature tensor according to a preset time window length; dividing the risk level based on the ratio of the predicted convergence value to the preset allowed value, and labeling the risk level label of each node in the future specified time period for each time window to construct a standardized spatio-temporal data set containing feature tensors and label tensors.

[0016] Further, the training process of the spatio-temporal graph neural network model includes: dividing the spatio-temporal data set into a training set, a validation set and a test set in proportion; training by using a weighted multi-task loss function, the loss function including a regression loss term for deformation value prediction and a classification loss term for risk level prediction, wherein the classification loss term gives different weights to samples of different risk levels, and the weight ratio of the regression loss term to the classification loss term in the total loss is a preset ratio.

[0017] Further, based on the spatial proximity and the geological similarity, the weighted graph structure representing the correlation between sections is established, wherein: the spatial proximity rule includes connecting each node to multiple adjacent section nodes and calculating the connection weight according to the mileage difference between nodes; the geological similarity rule includes calculating the similarity of the spatial geometric features between nodes, and when the similarity exceeds a preset threshold, establishing a connection between the nodes, and taking the similarity as the connection weight.

[0018] Furthermore, in S6, the spatiotemporal graph neural network model includes at least one spatiotemporal block, each spatiotemporal block including: a spatial convolutional layer, a temporal gating layer, and a multi-scale temporal convolutional layer; and each spatiotemporal block sets a residual path, achieves feature dimension matching through a 1×1 convolutional kernel, and completes node feature update after activation by the ReLU activation function.

[0019] Furthermore, the spatial convolutional layer performs the following: a linear transformation on the original node features of node i to obtain the transformed node features. And the node features obtained after transforming the original node features of neighbor node j. Based on the node characteristics of node i Node characteristics of neighbor node j The attention coefficient between node i and its neighbor node j is calculated. : ; Where a is a 128-dimensional attention vector, Indicates transpose. The representation features are concatenated; attention weights are obtained through normalization. : in, Let exp() represent the attention coefficients between node i and any neighboring node k, and let exp() denote the exponential function. Then, for the node features of node i... renew: .

[0020] Furthermore, a fixed attention bias weight is applied to the nodes corresponding to the vault region.

[0021] Furthermore, the multi-scale temporal convolutional layer employs parallel dilated convolutional paths with different dilation rates to simultaneously extract short-term, medium-term, and long-term temporal features of node features.

[0022] Furthermore, in S3, the coarse registration of the point cloud based on the coordinates of the preset design control points in the tunnel includes: obtaining the geodetic coordinates of at least three preset control points and their scan coordinates in the point cloud; and, based on the geodetic coordinates and scan coordinates, initially aligning the point cloud to the geodetic coordinate system by solving the rigid transformation matrix.

[0023] Secondly, this application discloses a tunnel construction safety early warning system based on three-dimensional laser scanning, including a processor and a storage device; the processor performs read and write operations on the storage device, and the storage device stores a computer program for implementing the tunnel construction safety early warning method based on three-dimensional laser scanning.

[0024] The beneficial effects of this invention are: The spatiotemporal neural network model predicts future cross-sectional settlement risks, allowing sufficient time for risk management; 3D laser scanning is used as the core, integrating environmental and construction data to improve the accuracy of model predictions; an integrated system for data acquisition, processing, modeling, early warning, and feedback is constructed to improve management efficiency. The system will feed back the actual effects of each adjustment to the model for continuous learning and improvement. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of the process of a tunnel construction safety early warning method based on three-dimensional laser scanning according to an embodiment of this application. Detailed Implementation

[0026] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. 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.

[0027] refer to Figure 1 This application discloses a method and system for early warning of tunnel construction safety based on three-dimensional laser scanning.

[0028] The tunnel construction safety early warning method based on three-dimensional laser scanning according to the embodiments of this application includes the following steps: S1. Multi-source data acquisition: Point cloud data of the working face is acquired by a 3D laser scanner. The constructed section is scanned using a mobile SLAM (Simultaneous Localization and Mapping) system, which automatically generates point clouds of cross-sections with 1-meter spacing and convergence value calculation accuracy ≤ ±0.5mm. Construction parameters such as construction mileage, anchor spacing and length, and shotcrete thickness are obtained. Environmental monitoring data such as water level are collected in real time by a groundwater pressure sensor.

[0029] Specifically, the multi-source data includes the following operations: geological data is obtained by using a 3D laser scanner to acquire information such as lithology, joints, and faults at the tunnel face; deformation data is obtained by scanning the constructed section at a fixed time of 10:00 every day using a mobile SLAM system, and cross-sectional point clouds are extracted at 1-meter intervals along the tunnel axis with a convergence value calculation accuracy of ≤±0.5mm; environmental data is collected in real time by using a pre-embedded groundwater pressure sensor.

[0030] S2. Preprocessing of multi-source data: The collected point cloud data is processed by denoising, downsampling, and invalid region removal. The basic deformation value is calculated and the basic geological features are manually labeled.

[0031] Specifically, the 3D scan data is denoised using methods such as filtering from the PCL library (point cloud library). The number of neighboring points is set to 50, and the standard deviation is set to 3 to remove isolated noise that deviates from the overall point cloud distribution. This 3-fold standard deviation setting maximizes the balance between denoising effectiveness and feature preservation. Then, the point cloud data is labeled with its basic geological features, recording its lithology and the initial number of joint groups as a geological feature training set.

[0032] S3, Point cloud coordinates are unified: Based on the coordinates of the pre-set design control points in the tunnel, the point cloud is coarsely registered, and then finely registered using the ICP algorithm (three-dimensional point cloud registration algorithm) to unify the point clouds from multiple devices and time periods into the geodetic coordinate system.

[0033] Specifically, the coarse registration of the point cloud based on the coordinates of the pre-set design control points in the tunnel includes: obtaining precise geodetic coordinates (X1,Y1,Z1), (X2,Y2,Z2), and (X3,Y3,Z3) through the pre-set control points in the tunnel and connecting them with the real-time scan coordinates using a total station; matching the pre-set geodetic coordinates of the three control points with their real-time scan coordinates; and substituting them into the rigid transformation equation. In the formula, R is the rotation matrix and T is the translation vector. For geodetic coordinates, The coordinates are scanned in real time; then, the transformation matrix is ​​solved using the SVD algorithm. This achieves coarse alignment between two point clouds by mapping the coordinates of all points in the source point cloud through the transformation matrix, thus completing coarse registration.

[0034] Then, the ICP algorithm (3D point cloud registration algorithm) is used for fine registration, with a search radius of 5cm and the iteration termination condition being RMSE≤3mm (i.e., root mean square error≤3mm) or the number of iterations≤50.

[0035] S4. Deep Learning Feature Extraction: The PointNet++ semantic segmentation model (a deep learning model for processing 3D point cloud data) is trained based on the geological feature training set to extract the geometric features of the point cloud. The model uses the cross-entropy loss function and the Adam optimization algorithm, and iterates for 100 rounds to extract multi-dimensional features of each tunnel cross section from the 3D scan data (point cloud set).

[0036] For example, the PointNet++ model uses the point cloud of the working face and manually annotated geological features as the training set, divides the training set and the validation set in a 7:3 ratio, and iterates for 50 rounds using the cross-entropy loss function and the Adam optimization algorithm (an adaptive optimization method). Training stops when the recognition accuracy of the validation set is ≥85%, and geological parameters such as joint dip angle and rock mass integrity coefficient are output as the multidimensional features.

[0037] S5. Spatiotemporal dataset construction: Using the tunnel cross-section as the basic node, the multi-dimensional features of each node, along with the construction parameters and environmental monitoring data, are spliced ​​and integrated.

[0038] Specifically, each node first stores the data from the construction parameters in S1, such as basic attributes like mileage, geodetic coordinates, scanning timestamps, and construction stages. Then, it integrates the multi-dimensional features output by the PointNet++ model, such as 6-dimensional spatial geometric features like joint dip angle, rock mass integrity coefficient, and cross-sectional area, the deformation rate calculated by the mobile SLAM system (simultaneous localization and mapping system), and environmental parameters like groundwater pressure and anchor density. Finally, it forms the node's feature vector by splicing through channels and normalizes it to the [0,1] interval to eliminate the influence of dimensions.

[0039] Then, based on spatial proximity and geological similarity, a weighted graph structure representing the relationship between cross sections is established. The spatial proximity rule includes connecting each node to multiple adjacent cross section nodes and calculating the connection weight based on the mileage difference between nodes. The geological similarity rule includes calculating the similarity of spatial geometric features between nodes. When the similarity exceeds a preset threshold, a connection between nodes is established, and the similarity is used as the connection weight.

[0040] Specifically, the spatial proximity rule connects each node to nodes of three adjacent cross sections, with the weight calculated as "1 / distance difference between two nodes"; the geological similarity rule establishes a connection when the cosine similarity of spatial geometric features between nodes is ≥0.7, and the weight value is equal to the cosine similarity. All edges are organized into an edge index matrix and corresponding edge weight vector, and stored in a sparse matrix format.

[0041] In some embodiments, the node features of multiple consecutive time steps are stacked into a three-dimensional feature tensor according to a preset time window length. Risk levels are classified based on the ratio of the predicted convergence value to a preset allowable value, and risk level labels are assigned to each node within a specified future time period for each time window, thereby constructing a standardized spatiotemporal dataset containing feature tensors and label tensors. For example, node features of consecutive time steps are stacked into a [10×N×6] feature tensor in 10-day windows, where N is the number of valid nodes, ensuring that the features of each time step are consistent with the scan data of the corresponding date. Risk levels are classified according to "predicted convergence value / design allowable value," with values ​​<30% indicating low risk, 30%-70% indicating medium risk, and >70% indicating high risk. A [7×N×1] label tensor is assigned to each 10-day feature window corresponding to the next 7 days, constructing a standardized spatiotemporal dataset that meets the input requirements of the spatiotemporal graph neural network model.

[0042] S6. Construct a spatiotemporal graph neural network model: The spatiotemporal graph neural network model consists of three spatiotemporal blocks connected in sequence. Each spatiotemporal block contains a spatial convolutional layer corresponding to GAT (Graph Attention Network), a temporal gating layer corresponding to GRU (Gated Recurrent Unit), and a multi-scale temporal convolutional layer corresponding to TCN (Temporal Convolutional Network).

[0043] The spatial convolutional layer employs a 4-head attention mechanism, first performing a linear transformation on the features of each node. Where W is a 64-dimensional learnable weight matrix, The original node features of the i-th tunnel section node are transformed to obtain the transformed node features. Calculate the attention coefficient between node i and its neighbor node j. In the formula, is the node feature obtained after linear transformation of the neighbor node j; the specific process will not be repeated. a is a 128-dimensional attention vector. This represents the transpose of 'a'. Indicates feature splicing, It is the activation function. Then, the attention weights are obtained by normalization using the softmax function. ,in Let be the attention coefficient between the target node i and any neighboring node k, and exp() denotes the exponential function; in some preferred embodiments, an additional fixed attention bias of 0.2 is added to the dome node.

[0044] Then, the node features of node i Update to enhance key region features: , This is the activation function.

[0045] The time-gating layer uses a 64-dimensional hidden state, which is updated by the gate. : Control the proportion of historical information retained, among which, It is a parameter matrix. It is a bias vector. It is the hidden state of the previous time step. This is the current input. It's an activation function, a reset gate. : Controlling the extent to which new information is received, among which, and It resets the parameter matrix and bias vector of the gate; calculates the candidate states. ,in, This indicates the hidden state of the previous time step. With Reset Door By combining these factors to control the extent of their influence, the current state is ultimately obtained. It effectively captures the temporal dependence and mutation characteristics of deformation.

[0046] The multi-scale temporal convolutional layer employs three parallel dilated convolutional paths, each with a kernel size of 3 and dilation rates of 1, 2, and 4, corresponding to receptive fields of 3, 7, and 15, to achieve simultaneous extraction of short-term, medium-term, and long-term temporal features. Causal padding (e.g., padding length = (kernel size - 1) × dilation rate) ensures temporal causality and prevents future data leakage.

[0047] In some preferred embodiments, a residual path is set for each spatiotemporal block, feature dimension matching is achieved through a 1×1 convolution kernel, and node features are updated after ReLU activation, effectively alleviating the gradient vanishing problem.

[0048] The spatiotemporal graph neural network model is trained using the spatiotemporal dataset constructed above as input, and the dataset is divided into training, validation, and test sets in a 7:2:1 ratio. The model employs a weighted multi-task loss function: Huber loss is used for deformable value regression, and weighted cross-entropy is used for risk level classification. The weights for high-risk samples are set to 1.2, medium-risk samples to 0.5, and low-risk samples to 0.3.

[0049] For example, to address the training bias issue caused by the limited number of high-risk samples, the loss weight ratio for the two tasks is set to 0.6:0.4, with a total loss L = 0.6 × L. regression + 0.4×L classification ; among which, L regression For regression loss, L classification For classification loss.

[0050] The training process employs data augmentation strategies, including time-series interpolation, point cloud rotation of ±5°, and ±5% random noise. The number of training iterations is set to 300, the learning rate is set to 0.001, and an early stopping mechanism is incorporated to prevent overfitting and save training time.

[0051] Understandably, three spatiotemporal blocks are sequentially connected to form a complete spatiotemporal graph neural network structure. The output of each spatiotemporal block serves as the input to the next, enabling layer-by-layer feature extraction and transformation. Through the stacking of multiple spatiotemporal blocks, the model can progressively extract high-order spatiotemporal feature representations from the original input data, enhancing its ability to model complex spatiotemporal dynamic processes. Thus, by combining GAT spatial convolutional layers with dilated convolutional layers featuring causal padding, the model effectively captures spatial relationships and temporal evolution patterns in graph-structured data, simultaneously handling spatial dependencies between nodes and temporal evolution patterns of node features, making it suitable for various spatiotemporal prediction tasks.

[0052] S7. Tunnel Construction Safety Warning: Real-time collected and preprocessed 3D scanning data, construction parameters, and environmental monitoring data are input into a trained spatiotemporal neural network model. The model simultaneously learns the propagation law of tunnel cross-sectional features in the spatial graph structure and the evolution law in the time series, and outputs the prediction results of the deformation risk of each cross-section of the tunnel in a specified time period in the future. Based on the prediction results, safety warnings are issued to realize the early prediction and prevention of risks in the tunnel construction process.

[0053] The tunnel construction safety early warning system based on three-dimensional laser scanning according to an embodiment of this application includes a processor and a storage device; the processor performs read and write operations on the storage device, and the storage device stores a computer program for implementing the tunnel construction safety early warning method based on three-dimensional laser scanning.

[0054] The above description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the concept described herein through the above teachings or related technologies or knowledge. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A method for early warning of tunnel construction safety based on three-dimensional laser scanning, characterized in that, include: S1. Acquire multi-source data of the tunnel construction area, including three-dimensional scanning data, construction parameters and environmental monitoring data, wherein the three-dimensional scanning data is stored as a point cloud; S2. Preprocess the multi-source data; S3. Based on the coordinates of the preset design control points in the tunnel, the point cloud is coarsely registered, and then finely registered using a three-dimensional point cloud registration algorithm to unify the point cloud to the geodetic coordinate system. S4. Extract point cloud geometric features using a semantic segmentation model to obtain multi-dimensional features of each tunnel section; S5. Construct a spatiotemporal dataset, including: Using tunnel cross-sections as nodes, the multi-dimensional features of each node, along with the construction parameters and environmental monitoring data, are spliced ​​and fused to obtain the feature vector of the corresponding node. Furthermore, based on spatial proximity and geological similarity, a weighted graph structure representing the relationship between cross-sections is established. The node features of the nodes at multiple consecutive time steps are combined with the corresponding weighted graph structure in chronological order to construct a spatiotemporal dataset. S6. Train a spatiotemporal graph neural network model based on the spatiotemporal dataset; S7. Input the real-time collected data into the trained spatiotemporal neural network model to output the prediction results of the deformation risk of each section of the tunnel within a specified time period in the future, and issue a safety warning based on the prediction results.

2. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 1, characterized in that, In S5, the construction of the spatiotemporal dataset includes: According to the preset time window length, the node features of multiple consecutive time steps are stacked into a three-dimensional feature tensor; the risk level is divided based on the ratio of the predicted convergence value to the preset allowable value, and the risk level label of each node in the future specified time period is labeled for each time window, so as to construct a standardized spatiotemporal dataset containing feature tensors and label tensors.

3. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 2, characterized in that, The training process of the spatiotemporal graph neural network model includes: The spatiotemporal dataset is divided into a training set, a validation set, and a test set according to a certain ratio; The training is performed using a weighted multi-task loss function, which includes a regression loss term for predicting deformable values ​​and a classification loss term for predicting risk levels. The classification loss term assigns different weights to samples with different risk levels, and the weight ratio of the regression loss term to the classification loss term in the total loss is a preset ratio.

4. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 1, characterized in that, The weighted graph structure representing the relationship between cross sections is established based on spatial proximity and geological similarity, wherein: The spatial proximity rule includes: connecting each node to multiple adjacent cross-section nodes, and calculating the connection weight based on the mileage difference between nodes; The geological similarity-based rules include: calculating the similarity of spatial geometric features between nodes; establishing connections between nodes when the similarity exceeds a preset threshold; and using the similarity as the connection weight.

5. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 1, characterized in that, In S6, the spatiotemporal graph neural network model includes at least one spatiotemporal block, and each spatiotemporal block includes: a spatial convolutional layer, a temporal gating layer, and a multi-scale temporal convolutional layer; Furthermore, a residual path is set for each spatiotemporal block, feature dimension matching is achieved through a 1×1 convolution kernel, and node features are updated after activation by the ReLU activation function.

6. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 5, characterized in that, The spatial convolutional layer performs: A linear transformation is performed on the original node features of node i corresponding to the i-th tunnel section to obtain the transformed node features. And the node features obtained after transforming the original node features of neighbor node j. ; Based on the node characteristics of node i Node characteristics of neighbor node j The attention coefficient between node i and its neighbor node j is calculated. : ； Where a is a 128-dimensional attention vector, This represents the transpose of 'a'. Indicates feature splicing, For activation functions; Attention weights are obtained through normalization. : in, Let be the attention coefficient between node i and any neighbor node k, and exp() denotes the exponential function; Then, the node features of node i Update: ； In the formula This is the activation function.

7. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 6, characterized in that, A fixed attention bias weight is applied to the nodes corresponding to the vault region.

8. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 5, characterized in that, The multi-scale temporal convolutional layer employs parallel dilated convolutional paths with different dilation rates to simultaneously extract short-term, medium-term, and long-term temporal features of node features.

9. The method for early warning of tunnel construction safety based on three-dimensional laser scanning according to claim 1, characterized in that, In S3, the coarse registration of the point cloud based on the preset design control point coordinates in the tunnel includes: Obtain the geodetic coordinates of at least three preset control points and their scan coordinates in the point cloud; Based on the geodetic coordinates and scan coordinates, the point cloud is initially aligned to the geodetic coordinate system by solving the rigid transformation matrix.

10. A tunnel construction safety early warning system based on three-dimensional laser scanning, characterized in that, Includes processor and storage; The processor performs read and write operations on the memory, which stores a computer program for implementing the tunnel construction safety early warning method based on three-dimensional laser scanning as described in any one of claims 1-9.

Images