Tunnel composite catastrophe intelligent early warning method and system based on tendency digital twinning

Abstract

The invention provides a tunnel composite catastrophe intelligent early warning method and system based on tendency digital twinning, and belongs to the technical field of tunnel gushing water data processing analysis, and the method comprises the steps: obtaining the three-dimensional point cloud data of a tunnel structure and the design parameters of the tunnel structure, and building a digital twinning model based on the three-dimensional point cloud data and the design parameters of the tunnel structure; collecting monitoring data in a tunnel structure in real time and integrating the collected data into the digital twinborn model; the method comprises the following steps: modeling spatial-temporal features of monitoring data in a tunnel structure collected in real time by using a spatial-temporal diagram convolutional network, and outputting a spatial-temporal feature matrix, namely generating spatial-temporal feature representation of catastrophe factors; the spatial-temporal feature representation for generating the catastrophe factors is input to a Bayesian network, and the Bayesian network is used for further modeling a dependency relationship among different catastrophe factors and calculating a disaster occurrence probability; the digital twin model identifies a region of potential disaster within the tunnel based on the calculated probability of disaster occurrence.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of tunnel gushing water data processing and analysis, and particularly relates to a tunnel composite disaster intelligent early warning method and system based on tendency digital twinning. BACKGROUND

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

[0003] Tunnel engineering is an important part of transportation and infrastructure construction. With the continuous expansion of its scale and the increasing complexity, the risk of tunnel disasters is also increasing. Especially in complex geological conditions, the tunnel interior may be affected by multiple disaster factors such as groundwater seepage and stress changes. These factors often have a mutual dependence relationship and may cause composite disasters such as water bursting and landslides, which seriously threaten the safety of tunnel structures and the reliability of engineering operation.

[0004] Existing tunnel disaster monitoring technology mainly relies on a single data source or simple monitoring means, which cannot comprehensively and accurately reflect the relationship between complex disaster factors inside the tunnel. In addition, traditional monitoring systems also have great limitations in real-time data processing and disaster tendency prediction, lacking efficient prediction and early warning capabilities for disasters, making it difficult to meet the needs of multi-source data fusion and real-time disaster assessment in modern tunnel engineering.

[0005] With the development of digital twinning technology, it is possible to build realistic virtual models based on monitoring data of actual projects and update them in real time with sensor data, providing new possibilities for tunnel disaster monitoring. However, existing digital twinning technology still has some deficiencies in disaster tendency prediction, especially when facing composite disaster scenarios. How to analyze multi-source monitoring data in real time and make accurate predictions remains a difficult problem to be solved. At the same time, traditional disaster monitoring methods rely mainly on static data or lagging risk assessment, and cannot provide dynamic and closely integrated emergency response capabilities with the on-site environment. Therefore, there are problems of insufficient real-time and accuracy in tunnel composite disaster tendency prediction. SUMMARY

[0006] To overcome the deficiencies of the prior art, the present application provides a tunnel composite disaster intelligent early warning method based on tendency digital twinning, which combines digital twinning technology with disaster tendency prediction models and uses augmented reality (AR) technology to realize real-time disaster monitoring and assessment, effectively improving the response speed and reliability of the early warning system, especially suitable for disaster monitoring and emergency management in complex tunnel engineering.

[0007] To achieve the above purpose, one or more embodiments of the present application provide the following technical solutions: In a first aspect, a tunnel compound disaster intelligent early warning method based on a tendency digital twin is disclosed, comprising: obtaining three-dimensional point cloud data of a tunnel structure and design parameters of the tunnel structure, and constructing a digital twin model based on the three-dimensional point cloud data of the tunnel structure and the design parameters; real-time collection of monitoring data in the tunnel structure and integration of the collected data into the digital twin model; modeling the spatio-temporal features of the real-time collected monitoring data in the tunnel structure using a spatio-temporal graph convolution network, outputting a spatio-temporal feature matrix, i.e., generating a spatio-temporal feature representation of a disaster factor; inputting the generated spatio-temporal feature representation of the disaster factor into a Bayesian network, the Bayesian network being used to further model the dependency relationship between different disaster factors and calculate a disaster occurrence probability; the digital twin model identifies a potential disaster area in the tunnel based on the calculated disaster occurrence probability.

[0008] As a further technical solution, a three-dimensional laser is used to scan the tunnel to obtain three-dimensional point cloud data of the tunnel structure.

[0009] As a further technical solution, the constructed digital twin model displays the spatial position information of all monitoring devices and the real-time data fed back by the monitoring devices. The spatial position information of the monitoring devices includes the stake number, installation height, and depth of installation of the device inside the surrounding rock.

[0010] As a further technical solution, the collected data is integrated into the digital twin model, specifically comprising: real-time collection of monitoring data in the tunnel structure by monitoring devices arranged in the tunnel structure, and transmission of the data collected by the monitoring devices through an Internet of Things device and mapping with virtual monitoring points in the digital twin model.

[0011] As a further technical solution, the spatio-temporal graph convolution network is a spatio-temporal graph structure, modeling the tunnel monitoring points as nodes in the graph, and reflecting the spatial correlation between the nodes through edges. The spatio-temporal graph convolution network includes a graph convolution layer and a time convolution layer; the graph convolution layer is used to capture the spatial dependency relationship of stress or environmental data between different regions of the tunnel; and the time convolution layer is used to extract the time variation trend of the monitoring data, thereby generating a spatio-temporal feature representation of a disaster factor.

[0012] As a further technical solution, the Bayesian network constructs a causal relationship graph between disaster factors through nodes and directed edges, each node representing a disaster factor, including tunnel stress and underground water level, and the directed edges representing the causal relationship between different factors. The risk of each disaster factor is predicted according to current data through conditional probability calculation of the Bayesian network, wherein the Bayesian network can model the process that heavy rain causes the rise of underground water level and further affects the stress change of the tunnel as a probability dependent chain, and calculate the probability of tunnel structure damage.

[0013] As a further technical solution, further comprising: connecting the digital twin model to the AR device, superimposing the three-dimensional tunnel structure in the digital twin model, real-time monitoring data and disaster prediction results into the real scene, and the AR device enables the tunnel manager to directly view the potential risk area, monitoring device position and real-time data on site.

[0014] In a second aspect, a tunnel composite disaster intelligent early warning system based on propensity digital twin is disclosed, comprising: The digital twin model construction module is configured to: obtain three-dimensional point cloud data of the tunnel structure and design parameters of the tunnel structure, and construct a digital twin model based on the three-dimensional point cloud data of the tunnel structure and the design parameters; Real-time monitoring data in the tunnel structure is collected and the collected data is integrated into the digital twin model; The spatio-temporal feature representation module is configured to: model the spatio-temporal features of the real-time collected monitoring data in the tunnel structure by using a spatio-temporal graph convolution network, output a spatio-temporal feature matrix, and generate a spatio-temporal feature representation of the disaster factor; The disaster occurrence probability calculation module is configured to: input the generated spatio-temporal feature representation of the disaster factor into a Bayesian network, and the Bayesian network is used to further model the dependency relationship between different disaster factors and calculate the disaster occurrence probability; The disaster area identification module is configured to: the digital twin model identifies the area of potential disaster in the tunnel based on the calculated disaster occurrence probability.

[0015] The above one or more technical solutions have the following beneficial effects: The method of the present application combines spatio-temporal graph convolution network (ST-GCN) and Bayesian network to extract spatio-temporal features of multi-source monitoring data of the tunnel and model the causal relationship of disaster factors. ST-GCN is used to extract the spatio-temporal dynamic change features of the tunnel monitoring point data, capture the spatial correlation between different areas of the tunnel and its time change trend, and the Bayesian network is used to predict the interaction of each disaster factor and its influence on the safety of the tunnel through conditional probability calculation. Based on this, the present application can accurately predict the probability of disaster occurrence under multiple disaster situations of the tunnel and dynamically adjust the prediction results, ensuring the real-time and accuracy of the disaster propensity prediction.

[0016] The technical scheme can realize real-time monitoring and intelligent early warning of composite disasters, combines digital twin technology and an advanced disaster prediction model, and uses augmented reality (AR) technology to seamlessly integrate virtual monitoring results with the real environment, thereby solving the problem of tunnel disaster monitoring.

[0017] Advantages of the additional aspects of the application will be partially given in the following description, partially will become apparent from the following description, or will be learned by the practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings accompanying the specification of this application form a part thereof, serve to provide further understanding of the application, and together with the description of the exemplary embodiments of the application, serve to explain the application, and do not constitute improper limitations on the application.

[0019] Fig. 1 The figure is a whole structure diagram of a digital twin system of an embodiment of the application. Fig. 2 The figure is a flow chart of composite disaster risk prediction and emergency response of an embodiment of the application. DETAILED DESCRIPTION

[0020] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the application belongs.

[0021] It should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments according to the application.

[0022] In the case of no conflict, the embodiments in the application and the features in the embodiments can be combined with each other.

[0023] Embodiment one Referring to the accompanying Figs. 1-2 The embodiment discloses a tunnel composite disaster intelligent early warning method based on tendency digital twin, comprising the following steps: Step one: obtain three-dimensional point cloud data of the tunnel structure and design parameters of the tunnel structure, and construct a digital twin model based on the three-dimensional point cloud data of the tunnel structure and the design parameters; Step two: real-time acquisition of monitoring data in the tunnel structure and integration of the acquired data into the digital twin model; Step three: modeling the spatio-temporal features of the real-time acquired monitoring data in the tunnel structure using a spatio-temporal graph convolution network, outputting a spatio-temporal feature matrix, i.e. generating a spatio-temporal feature representation of the disaster factor; Step four: input the spatio-temporal feature representation of the generated disaster factors into a Bayesian network, which is used to further model the dependency between different disaster factors and calculate the disaster occurrence probability; Step five: the digital twin model identifies the potential disaster area in the tunnel based on the calculated disaster occurrence probability.

[0024] Step one specifically includes: 1-1) Basic construction of the digital twin model, including tunnel real scene model construction, monitoring device layout, and data display; 1-2) Real-time data integration and feedback of the digital twin model; 1-3) Compound disaster tendency prediction and risk area identification, including disaster risk area identification and real-time risk update; 1-4) Dynamic visualization of the disaster occurrence process, including dynamic disaster process simulation and user interactive experience; 1-5) Integration and application of digital twin and compound disaster prediction, including intelligent early warning and emergency response, and historical data analysis and future trend prediction.

[0025] In this embodiment, 1-1) the basic construction of the digital twin model, the specific process is: the core basis of the digital twin model is to construct the real scene model of the tunnel through three-dimensional point cloud data. This process can obtain accurate three-dimensional data of the tunnel structure through laser scanning or other three-dimensional scanning technology. Import these point cloud data using Unity 3D engine, combined with the geometric design data of the tunnel, to generate a highly realistic tunnel model.

[0026] Data types collected: three-dimensional point cloud data, tunnel design parameters, material properties (surrounding rock type, lining material), geological information.

[0027] Model construction process: combine point cloud data with design parameters to ensure that the virtual model is consistent with the structure of the actual tunnel, providing a reliable physical basis for subsequent dynamic simulation.

[0028] In this embodiment, the design parameters refer to the width and height information of the tunnel, the purpose is to ensure that the model constructed using point cloud data is consistent with the actual tunnel size, or the error is very small. Since point cloud data can only obtain a spatial size model, it cannot obtain material properties and geological information, therefore design parameters need to be added.

[0029] Monitoring device layout display: The digital twin model not only displays the static tunnel, but also includes the spatial location information of all monitoring devices and real-time data feedback. In Unity 3D, the devices need to be accurately laid out, and the location and real-time monitoring data of the monitoring devices need to be labeled in the three-dimensional model; Monitoring device location information: The stake number, installation height, and depth of the device installed in the surrounding rock of the device need to be labeled in detail, directly positioning the specific spatial location of the device, ensuring that the actual location of each monitoring device is accurately reflected in the digital model.

[0030] In step 1-2) Real-time data integration and feedback of digital twin model, the specific process is: The key advantage of the digital twin system is its real-time synchronization capability with the field data. Through continuous data collection of monitoring devices, the system can real-time feedback the current physical state of the tunnel and the working condition of the device, and integrate these data into the twin model. In this implementation patent, the monitoring devices include various sensors.

[0031] Real-time monitoring data display: Real-time monitoring data of various sensors (such as multi-point displacement meters, stress meters, and osmotic pressure meters) is directly fed back to the twin model through the interface. The system can visualize the monitoring results in the form of data windows, charts, or heat maps next to the location of the monitoring device, for example, real-time display of stress, displacement change, or osmotic pressure data.

[0032] Sensor data is transmitted through Internet of Things (IoT) devices and mapped to virtual monitoring points in the digital twin model. The data stream of each sensor can be input into the Unity 3D model through the MQTT (Message Queuing Telemetry Transport) data transmission protocol.

[0033] In step 1-3) Compound disaster tendency prediction and risk area identification, the specific process is: The compound disaster tendency prediction method is: Combined with the spatio-temporal graph convolution network (ST-GCN) and the Bayesian network, the compound disaster tendency prediction method is formed by modeling the probability dependence between the spatio-temporal feature extraction and the disaster factors. Specifically, ST-GCN is used to extract the spatio-temporal dynamic change features in the multi-source monitoring data monitored by various sensors, while the Bayesian network is used to capture the causal relationship between disaster factors and calculate the probability of disaster occurrence through conditional probability.

[0034] The digital twin model based on the spatio-temporal graph convolution network ST-GCN and the Bayesian network can display the prediction of disaster tendency, further realize the visualization of disaster occurrence probability, and even the scale and form of disaster occurrence.

[0035] First, the spatio-temporal graph convolutional network ST-GCN models the spatio-temporal features of the tunnel monitoring data to form the basis of the disaster tendency analysis.

[0036] The spatio-temporal graph structure of the spatio-temporal graph convolutional network ST-GCN models the tunnel monitoring points as nodes in the graph, where the nodes represent the arrangement positions of the monitoring devices, and the edges between the nodes reflect the spatial correlation. The spatio-temporal graph structure is a graph showing the spatial position relationship of the tunnel monitoring points. The above spatio-temporal graph convolutional network includes two layers of graph convolution and time convolution. The graph convolution layer is used to capture the spatial dependence relationship of stress or environmental data between different regions of the tunnel, and the time convolution layer is used to extract the time variation trend of the monitoring data, thereby generating the spatio-temporal feature representation of the disaster factors. Through this joint spatio-temporal modeling, the system can fully consider the dynamic changes of the environmental conditions inside and outside the tunnel, such as the gradual accumulation of stress or the long-term impact of rainfall increase on the tunnel structure.

[0037] In the present embodiment, for a given N monitoring points in the tunnel structure, an undirected weighted graph G=(V, E, A) is constructed, where V={v1, v2, …, vN} represents the N monitoring points; E represents the connection relationship between the monitoring points; A∈RN×N is an adjacency matrix that defines the connection strength between the points, and is calculated as follows: n N×N ; where x i , x j are the coordinates of the monitoring points i, j, and σ is a normalization factor. This method can ensure that the weights between adjacent sensors are high, while the connection between distant points is weak.

[0038] Through the convolution operation of the graph convolution layer of the GCN, information is propagated in the sensor network to extract the spatial topology features. The graph convolution operation is used to aggregate the information of the neighbor nodes to update the node features: ; where x is the node feature matrix of the l l th layer; is the trainable weight of the l l th layer; is the adjacency matrix with self-loop; is the degree matrix of x ; ; is the activation function.

[0039] ​​The node feature matrix above is derived from the attribute information of the nodes in the original data. Each node represents a monitoring point, and its corresponding features include monitoring information such as stress, displacement, and seepage pressure. These features are structured into a feature matrix as the initial input of the GCN model.

[0040] The adjacency matrix with self-loops is based on the adjacency matrix A of the graph plus the identity matrix (self-loops), where A The adjacency structure from the input graph data is obtained according to the graph model constructed in the actual application (such as spatial adjacency, functional connection, etc.).

[0041] After completing the spatial feature extraction, one-dimensional convolution (T-Conv) is used for time series feature extraction: ; where W t is the time convolution weight, and is a model trainable parameter that is automatically updated by the backpropagation algorithm during training. Its initial value is initialized using the Xavier or He initialization strategy, depending on the model architecture, represents one-dimensional convolution operation, b is the bias term, is the activation function. X is the original input data tensor.

[0042] After processing by the ST-GCN, the final output is the spatio-temporal feature matrix: ; where: H is the spatio-temporal feature matrix, which is used in the subsequent Bayesian network to establish the dependency relationship between different disaster factors; X is the original input data tensor; A is the adjacency matrix.

[0043] After obtaining the spatio-temporal features of the disaster factors, the Bayesian network is used to further model the dependency relationship between different disaster factors. The Bayesian network constructs a causal relationship graph between disaster factors through nodes and directed edges. Each node represents a disaster factor, such as tunnel stress, groundwater level, and directed edges represent the causal relationship between different factors. Through conditional probability calculation of the Bayesian network, the system can predict the risk of each disaster factor based on the current data. For example, the Bayesian network can model the process of heavy rain causing groundwater level rise and further affecting tunnel stress change as a probability dependency chain, and calculate the probability of tunnel structure damage.

[0044] The Bayesian network is a model based on probability reasoning, which can use conditional probability calculation to predict the risk of each disaster factor. The basic theoretical basis of the Bayesian network is Bayes' theorem: .

[0045] In catastrophe risk assessment, multiple catastrophe factors in the system are assumed With random variables and causal relationships, Bayesian networks can be represented as directed acyclic graphs (DAGs), where each node represents a random variable and each directed edge represents a causal relationship.

[0046] The joint probability distribution in a Bayesian network can be represented as: ; Where, represents the parent set of node , i.e. the direct antecedents that affect the variable.

[0047] In risk prediction, the goal is to calculate the probability of a specific catastrophe event R occurring given some observed data E, which requires calculating the posterior probability: .

[0048] If the conditional probabilities between catastrophe factors are known, Bayesian inference can be used for updating. For example, let's say a catastrophe factor has a conditional probability with catastrophe risk R as: ; Where the denominator can be calculated by the total probability formula: .

[0049] In Bayesian networks, maximum a posteriori estimation or expectation maximization methods can be used to infer incomplete data, thereby improving the prediction accuracy of catastrophe risk.

[0050] The combination of ST-GCN and Bayesian networks involves inputting the spatio-temporal features extracted by ST-GCN into the Bayesian network as the basis for the conditional probabilities of each catastrophe factor. The features extracted by the spatio-temporal convolutional network can more accurately represent the spatio-temporal dynamic changes of each catastrophe factor, and then the Bayesian network uses these spatio-temporal features to calculate the conditional probabilities between each catastrophe factor, thereby achieving joint probability prediction of catastrophe occurrence. This prediction method combines the spatio-temporal feature extraction capability of ST-GCN and the causal dependence modeling advantage of Bayesian networks, forming a highly accurate composite catastrophe prediction framework.

[0051] Through this method, the system can not only predict catastrophe risk based on historical data and real-time data, but also dynamically update the conditional probability distribution of the Bayesian network based on new monitoring data, and adjust the prediction results of catastrophe tendency in real time. In this way, the system can automatically adjust the assessment of future possible catastrophes when significant changes in tunnel stress or groundwater level are monitored, ensuring the real-time and accuracy of catastrophe tendency prediction.

[0052] In summary, by combining ST-GCN and Bayesian networks, the present application can simultaneously consider the dependence between spatio-temporal dynamic changes and disaster factors, significantly improving the accuracy of complex disaster tendency prediction.

[0053] Furthermore, the long-term accuracy and adaptability of the disaster tendency prediction model are improved through a self-learning mechanism. After each disaster prediction, the actual disaster occurrence is compared with the prediction results to adjust the model parameters and reduce prediction errors. Specifically, the system constructs a reward function to evaluate prediction accuracy and continuously optimizes the model through deep reinforcement learning. This feedback mechanism is based on the accumulation of historical data, gradually adjusting network weights and parameters to enable the model to adapt.

[0054] Regarding the construction of the reward function, a feedback mechanism is designed to evaluate the model's performance based on the difference between the prediction results and the actual occurrence. Specifically, the reward function will optimize the model's prediction accuracy to reduce prediction errors and improve long-term accuracy and adaptability. Through this feedback mechanism, the system can adjust the model parameters after each disaster prediction, gradually enhancing the model's adaptive ability.

[0055] For example, when the system detects a large error in a prediction, it will adjust the weights of relevant disaster factors and model parameters based on the actual occurrence. If a prediction indicates that the risk of tunnel structure stress imbalance is low, but a serious stress overload actually occurs, the model will increase the weight of the regional structure stress and optimize the stress transfer model to improve the accuracy of the prediction. At the same time, the system will update the disaster prediction model in real time through online learning. Whenever new monitoring data is input, the system will immediately adjust the model parameters to ensure that the model can adapt to new environmental data and update the prediction results in real time.

[0056] Risk area identification: The digital twin system can identify potential disaster areas in the tunnel based on the disaster occurrence probability calculated by ST-GCN and Bayesian networks. For example, a specific area of a tunnel may face the dual risks of water inrush and collapse due to rising groundwater levels and increased tunnel stress, which will be identified as a high-risk area.

[0057] Probability value display: The probability of disaster occurrence will be displayed in percentage form next to the risk area in the digital twin model. For example, in a certain tunnel section, the system will display a 35% probability of collapse within the next 24 hours. These probability values are dynamically updated as monitoring data is input, ensuring real-time understanding of the likelihood of disaster occurrence.

[0058] Color and shape differentiation: Different disaster risk areas can be identified by different colors, such as red for high-risk areas, yellow for medium-risk areas, and green for low-risk areas. Each potential disaster type (such as landslides, water bursts, etc.) can be distinguished by different graphics (such as triangles, circles).

[0059] Dynamic update: With the update of monitoring data, the Bayesian network can adjust the probability of disaster occurrence in real time, and the identified areas in the digital twin model will also change dynamically, ensuring real-time reflection of the latest disaster prediction results.

[0060] In addition, in this embodiment, the dynamic visualization of the disaster occurrence process is as follows: the combination of digital twin and AR can realize seamless connection between virtual and reality, providing real-time disaster monitoring and risk assessment solutions. By superimposing the three-dimensional tunnel structure in the digital twin model, real-time monitoring data, and disaster prediction results onto the real scene, AR technology enables tunnel managers to directly view potential risk areas, monitoring device locations, and real-time data on site. Such a combination greatly improves the efficiency and accuracy of emergency response, enabling managers to make faster and more accurate decisions in real environments. In addition, the powerful computing power of digital twin ensures the reliability of disaster prediction, while the convenient interaction of AR enhances the user's on-site operation experience. The combination of the two not only improves the practicality of the system, but also reduces the risk of misjudgment, making monitoring and early warning in complex disaster environments more intelligent and intuitive.

[0061] Regarding the connection method of the model and AR device: a cloud server can be used to process the digital twin model, ensuring that computing and real-time data processing will not be limited by performance. Data can be transmitted to the AR device through a wireless network to realize interaction between the model and reality.

[0062] Regarding data transmission and processing: fast and reliable data transmission protocols such as MQTT or WebSocket can be used to ensure that data transmission from the digital twin model to the AR device is real-time and stable.

[0063] Regarding interaction and updates: for user interaction with the AR device, the goal is to enable users to view disaster risk information in real time and respond accordingly. The AR device will display necessary information based on updates to the digital twin model, helping users make quick decisions.

[0064] The digital twin model not only displays the current risk status, but also simulates the occurrence and development process of future disasters. Users can further understand the detailed information and dynamic evolution process of potential disasters by clicking on high-risk areas.

[0065] Clickable identification of risk areas: Users can click on marked risk areas in the model to view detailed information about that area.

[0066] Detailed information display: Each risk area should display information about the type of catastrophe, probability of occurrence, and current status of spatio-temporal data. Catastrophe type: For example, show that the area is a water inrush, collapse, stress imbalance, or a composite area of multiple disasters; Catastrophe occurrence probability: Show the probability of catastrophe occurrence calculated by Bayesian network, specifically in the form of percentage. For example, "This area has a 35% probability of collapse within the next 24 hours"; Current monitoring data: Show the current real-time monitoring data of the area, including stress, displacement, groundwater level, temperature, and other multi-source sensor collection information. For example: "Current tunnel stress is 250kPa, groundwater level rises 10cm".

[0067] Dynamic update and feedback: When real-time monitoring data changes, users can see the dynamic changes in the risk status, detailed information, and catastrophe tendency of the area in the model.

[0068] Interactive functions can also show the dynamic development process of potential disasters. When users click on a risk area, the system can simulate the evolution of the catastrophe process through visualization.

[0069] Timeline sliding function: Set a timeline to allow users to slide the timeline to view the future trend of the disaster. Through the predicted future features of ST-GCN, show how the disaster gradually develops from small-scale changes to global catastrophe. For example, users can view the expansion range and speed of water inrush within the next 12 hours.

[0070] Disaster propagation path: Use animations or heat maps to show the propagation path and impact range of the disaster. For example, when water inrush occurs, the system can show the propagation path of the water flow from the water inrush point to other areas of the tunnel, and update the dynamic data such as water flow speed and water accumulation in real time.

[0071] Emergency plan suggestions: Based on risk scores and catastrophe occurrence probabilities, the system can give corresponding emergency suggestions according to the dynamic process of the disaster. For example, suggest reinforcing a certain section of the tunnel or evacuating personnel from the relevant area.

[0072] Integration and application of digital twin and composite catastrophe prediction, the specific process is: The digital twin system combines real-time data with the deep combination of composite catastrophe tendency prediction model to become a complete tunnel catastrophe management platform. The system inputs real-time data from monitoring devices, dynamically interacts with the prediction model, and visualizes and simulates disaster risks in the model.

[0073] The composite disaster prediction model is embedded in the numerical twin model in the embodiment, so that the digital twin model not only has the function of data display, but also can make disaster prediction combined with data, and the disaster prediction result and the disaster process can be visualized and displayed through the digital twin model.

[0074] Intelligent early warning and emergency response: when the disaster risk reaches a certain threshold, the digital twin model will automatically trigger an early warning, issue a warning to the manager through the visual interface, and provide an emergency response scheme according to the risk assessment.

[0075] Historical data analysis and future trend prediction: the system can store historical monitoring data to help analyze long-term trends. In addition, through composite disaster tendency prediction, the system can simulate possible future disaster scenarios to provide forward-looking support for tunnel safety maintenance.

[0076] In the embodiment, the digital twin model integrates three-dimensional point cloud data, tunnel design parameters, and monitoring device data to construct a realistic virtual tunnel model, and feeds back real-time monitoring data to the model to display the real-time changes of physical quantities such as stress, groundwater level, and osmotic pressure in the tunnel. With the help of the model, the system can reflect the real-time operation state of the tunnel interior, and identify potential risk areas combined with disaster tendency prediction results. At the same time, augmented reality (AR) technology is used to superimpose monitoring data and disaster warning information in the virtual model onto the real tunnel scene, so that users can directly view risk areas, monitoring device locations, and their data states on site through mobile devices or AR glasses, thereby greatly improving emergency response efficiency.

[0077] The advantage of the embodiment is that it realizes the real-time visualization of complex tunnel structures and the efficient integration of disaster prediction through digital twin technology, improves the convenience of on-site operations and the accuracy of decision-making through augmented reality technology, and can timely capture subtle changes in disaster factors and respond, thereby effectively reducing the risk of tunnel composite disasters.

[0078] The embodiment integrates spatio-temporal graph convolutional networks (ST-GCN) and Bayesian networks to analyze tunnel multi-source monitoring data in real time, capture the spatio-temporal dynamic changes of disaster factors, provide high-precision disaster tendency prediction, and update the prediction results in real time when the monitoring data changes. This ensures the real-time and accuracy of disaster prediction and provides more reliable support for tunnel disaster management.

[0079] The technical scheme of the embodiment combines real-time data of monitoring equipment with a virtual model through digital twinning technology, realizes integrated analysis of multi-source data, and combines Internet of Things (IoT) equipment and augmented reality (AR) technology. Tunnel managers can intuitively view risk areas and monitoring data in the actual environment, thereby greatly improving the efficiency and accuracy of on-site emergency decision-making.

[0080] The feedback and self-learning mechanism of the disaster prediction model of the embodiment gradually optimizes model parameters through accumulation of historical data, makes the prediction result more accurate, and reduces the risk of misjudgment that may be caused by relying on static data or lagging data in traditional monitoring methods. Through joint probability calculation of disaster factors, the application can identify potential disasters in complex environments and help managers make correct judgments through AR display.

[0081] The technical scheme of the embodiment not only can identify potential high-risk areas in real time, but also can dynamically display the process of disaster occurrence and expansion through visualization, and automatically provide emergency response suggestions according to risk assessment, so as to ensure that managers can take effective measures in time before the disaster occurs, and reduce the impact of the disaster on tunnel safety.

[0082] The technical scheme of the embodiment is applicable to various complex underground engineering projects, especially in complex disaster scenarios such as gushing water and collapse in tunnel engineering. Through the combination of digital twinning technology and AR, the system not only improves the intelligent level of disaster monitoring, but also greatly expands the application field of digital twinning technology in disaster prediction and risk management.

[0083] Embodiment two The purpose of the embodiment is to provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to realize the steps of the above method.

[0084] Embodiment three The purpose of the embodiment is to provide a computer readable storage medium.

[0085] A computer readable storage medium has a computer program stored thereon, and the program is executed by a processor to perform the steps of the above method.

[0086] Embodiment four The purpose of the embodiment is to provide a tunnel complex disaster intelligent early warning system based on propensity digital twinning, which includes: The digital twinning model construction module is configured to obtain three-dimensional point cloud data of a tunnel structure and design parameters of the tunnel structure, and construct a digital twinning model based on the three-dimensional point cloud data and the design parameters of the tunnel structure. collecting monitoring data in the tunnel structure in real time and integrating the collected data into the digital twin model; a spatio-temporal feature representation module configured to model spatio-temporal features of the monitoring data in the tunnel structure collected in real time by using a spatio-temporal graph convolution network, output a spatio-temporal feature matrix, i.e., generate a spatio-temporal feature representation of the disaster-causing factor; a disaster occurrence probability calculation module configured to input the spatio-temporal feature representation of the disaster-causing factor into a Bayesian network, the Bayesian network being used to further model the dependency relationship between different disaster-causing factors and calculate a disaster occurrence probability; a region identification module of the disaster configured to identify a region of a potential disaster in the tunnel based on the calculated disaster occurrence probability by the digital twin model.

[0087] Embodiment five The purpose of the present embodiment is to provide a computer program product containing instructions which, when run on a computer, cause the computer to perform the method and functions involved in any of the above embodiments. The steps and method embodiments of the above embodiments correspond to embodiment one, and the specific embodiments can refer to the related description part of embodiment one. The term "computer readable storage medium" should be understood to include a single medium or multiple media of one or more instruction sets; it should also be understood to include any medium capable of storing, encoding or carrying instruction sets for execution by a processor and causing the processor to perform any method in the present application.

[0088] Those skilled in the art should understand that the above-mentioned modules or steps of the present application can be realized by a general computer device, alternatively, they can be realized by device executable program codes, so that they can be stored in a storage device and executed by a computing device, or they can be made into individual integrated circuit modules, or a plurality of modules or steps can be made into a single integrated circuit module. The present application is not limited to any specific combination of hardware and software.

[0089] The above describes the specific embodiments of the present application in combination with the accompanying drawings, but is not a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications or variations made by those skilled in the art on the basis of the technical solutions of the present application without creative labor are still within the scope of protection of the present application.

Claims

1. An intelligent early warning method for tunnel composite disasters based on tendency digital twins is characterized by: include: Obtaining three-dimensional point cloud data of the tunnel structure and design parameters of the tunnel structure, and constructing a digital twin model based on the three-dimensional point cloud data and design parameters of the tunnel structure; collecting monitoring data from the tunnel structure in real time and integrating the collected data into the digital twin model; The spatiotemporal features of the monitoring data collected in real time in the tunnel structure are modeled using a spatiotemporal graph convolutional network, and the spatiotemporal feature matrix is ​​output, that is, the spatiotemporal feature representation of the disaster factors is generated; The spatiotemporal feature representation of the generated disaster factors is input into a Bayesian network, which is used to further model the dependencies between different disaster factors and calculate the probability of disaster occurrence; The digital twin model identifies potential disaster areas within the tunnel based on the calculated probability of disaster occurrence.

2. The intelligent early warning method for tunnel composite disasters based on tendency digital twins according to claim 1 is characterized in that: Use 3D laser to scan the tunnel and obtain the 3D point cloud of the tunnel structure; The constructed digital twin model displays the spatial location information of all monitoring devices and their real-time feedback data; The spatial location information of the monitoring equipment includes: the equipment's pile number, installation height, and the depth at which the equipment is installed inside the surrounding rock.

3. The intelligent early warning method for tunnel composite disasters based on tendency digital twins according to claim 1 is characterized in that: Integrate the collected data into the digital twin model, specifically including: Monitoring data in the tunnel structure is collected in real time using monitoring equipment deployed in the tunnel structure. The data collected by the monitoring equipment is transmitted through the Internet of Things device and mapped with the virtual monitoring points in the digital twin model.

4. The intelligent early warning method for tunnel composite disasters based on tendency digital twins according to claim 1 is characterized in that: The spatiotemporal graph convolutional network is a spatiotemporal graph structure, which models tunnel monitoring points as nodes in the graph, and the edges between nodes reflect the spatial correlation; The spatiotemporal graph convolutional network includes a graph convolution layer and a temporal convolution layer; The graph convolution layer is used to capture the spatial dependency of stress or environmental data between different areas of the tunnel; the temporal convolution layer is used to extract the temporal variation trend of the monitoring data, thereby generating a spatiotemporal feature representation of the disaster factors.

5. The intelligent early warning method for tunnel composite disasters based on tendency digital twins according to claim 1 is characterized in that: The Bayesian network constructs a causal relationship diagram between disaster factors through nodes and directed edges. Each node represents a disaster factor, including tunnel stress and groundwater level, and the directed edges represent the causal relationship between different factors. Through conditional probability calculations using a Bayesian network, the risks of various catastrophic factors are predicted based on current data. The Bayesian network can model the process in which heavy rain causes rising groundwater levels, which in turn affects tunnel stress changes, as a probabilistic dependency chain and calculate the probability of tunnel structure damage.

6. The intelligent early warning method for tunnel composite disaster based on tendency digital twin according to claim 1 is characterized by: include: The digital twin model is connected to an AR device, and the three-dimensional tunnel structure, real-time monitoring data, and disaster prediction results in the digital twin model are superimposed on the real scene. The AR device enables tunnel managers to view potential risk areas, monitoring equipment locations, and real-time data directly on site.

7. The intelligent early warning system for tunnel composite disasters based on tendency digital twin is characterized by: include: The digital twin model construction module is configured to: obtain three-dimensional point cloud data of the tunnel structure and design parameters of the tunnel structure, and construct a digital twin model based on the three-dimensional point cloud data and design parameters of the tunnel structure; collecting monitoring data from the tunnel structure in real time and integrating the collected data into the digital twin model; The spatiotemporal feature representation module is configured to: use a spatiotemporal graph convolutional network to model the spatiotemporal features of the monitoring data collected in real time in the tunnel structure, and output a spatiotemporal feature matrix, that is, to generate a spatiotemporal feature representation of the disaster factors; The disaster probability calculation module is configured to: generate a spatiotemporal feature representation of disaster factors and input it into a Bayesian network, wherein the Bayesian network is used to further model the dependency relationship between different disaster factors and calculate the probability of disaster occurrence; The disaster area identification module is configured as follows: the digital twin model identifies the potential disaster areas in the tunnel based on the calculated probability of disaster occurrence.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are performed.

Images