Tunnel digital twin three-dimensional intelligent control platform

Abstract

The application relates to the technical field of tunnel intelligent management, and particularly relates to a tunnel digital twin three-dimensional intelligent control platform. A tunnel acquisition module is used for acquiring tunnel image data uploaded by an image acquisition device and tunnel point cloud data collected by a laser device, and a tunnel three-dimensional model corresponding to a tunnel physical entity is constructed according to the tunnel image data and the tunnel point cloud data; a device association module is used for associating and fusing sensing devices in the tunnel with the tunnel three-dimensional model to obtain a tunnel digital twin; a vehicle detection module is used for acquiring vehicle driving data collected by sensing devices in the tunnel and a position of the vehicle, and a real-time digital object corresponding to a vehicle physical entity is generated in a position corresponding to the tunnel digital twin according to the vehicle driving data and the position of the vehicle; and a large-screen display module is used for displaying the tunnel digital twin containing the real-time digital object of the vehicle and vehicle driving data of the vehicle through a visual large screen.

Description

Technical Field

[0001] This invention relates to the field of intelligent tunnel management technology, specifically to a tunnel digital twin three-dimensional intelligent control platform. Background Technology

[0002] With economic development and the continuous improvement of people's living standards, the number of vehicles is constantly increasing, and highway construction is becoming more and more sophisticated. Among them, tunnels are an important method of construction for mountainous areas and cross-sea / river highways. The mileage of tunnels in operation is gradually increasing, and they are important links for highways and urban road traffic. Tunnels not only have high traffic volume, but also, as semi-enclosed environments, they have more traffic accidents than ordinary road sections and are extremely prone to secondary accidents, causing serious accident losses and traffic delays, thus becoming a bottleneck for the safe and smooth operation of highways.

[0003] For tunnel monitoring, video surveillance typically captures images, and various sensors collect vehicle data, which is then uploaded to a server for monitoring. However, due to the dim lighting inside tunnels, it's difficult to reconstruct the true scene using only images and sensor data. Current technologies combine digital twins with tunnel monitoring. Digital twins fully utilize physical models, sensor updates, and historical operational data, integrating multi-disciplinary, multi-physical, multi-scale, and multi-probability simulation processes to create a virtual map that reflects the entire lifecycle of the corresponding physical equipment. By establishing a tunnel digital twin, vehicle data is reconstructed within the digital twin to reflect the actual situation inside the tunnel. However, unlike factory digital twins or precision equipment digital twins which only require digital modeling to reflect the equipment's operation, tunnel digital twins need to reflect vehicle movement within the tunnel. Since vehicles inside a tunnel are not static, modeling and reconstructing the digital object for each entering vehicle would place excessive demands on computing power, creating an unbearable load and hindering widespread application. Summary of the Invention

[0004] The technical problem solved by this invention is to provide a three-dimensional intelligent control platform for tunnel digital twins, which can reduce the equipment requirements for recreating vehicles inside the tunnel in tunnel digital twins.

[0005] The basic solution provided by this invention is a tunnel digital twin 3D intelligent control platform, which includes a tunnel acquisition module, an equipment association module, a vehicle detection module, and a large screen display module.

[0006] The tunnel acquisition module is used to acquire tunnel image data uploaded by the image acquisition device and tunnel point cloud data acquired by the laser device, and to construct a 3D model of the tunnel corresponding to the physical entity of the tunnel based on the tunnel image data and tunnel point cloud data.

[0007] The device association module associates and fuses the sensing devices inside the tunnel with the three-dimensional model of the tunnel to obtain a digital twin of the tunnel;

[0008] The vehicle detection module is used to acquire vehicle driving data and vehicle location collected by sensing devices in the tunnel, and to generate a real-time digital object corresponding to the physical entity of the vehicle in the tunnel digital twin based on the vehicle driving data and vehicle location. The vehicle detection module includes a type detection module and an object generation module.

[0009] The type detection module has several vehicle models pre-set, which are used to identify the vehicle type and ticket number based on the image data detected by the image acquisition device;

[0010] The object generation module retrieves the corresponding vehicle model based on the vehicle type and generates a real-time digital object in the tunnel digital twin, and binds the license plate number to the real-time digital object;

[0011] The large-screen display module is used to display a digital twin of a tunnel containing real-time digital objects of vehicles and their driving data through a visual large screen.

[0012] The principle and advantages of this invention are as follows: First, tunnel images are measured using an image acquisition device, and point cloud data is measured using a laser device. The tunnel image data and point cloud data are then fused to establish a corresponding 3D tunnel model. The sensing devices within the tunnel are then fused with the 3D tunnel model to obtain a digital twin of the tunnel. For vehicles within the tunnel, based on the vehicle driving data detected by the sensing devices and the vehicle's location, the corresponding digital object is reconstructed in the digital twin. Simultaneously, for modeling the digital objects, the vehicle type and license plate number are obtained through image acquisition. The vehicle model corresponding to the measured vehicle type is retrieved from a pre-set model library; vehicles of the same type share the same vehicle model. The license plate number is bound to the vehicle model for differentiation. Finally, the tunnel digital twin, containing real-time vehicle digital objects and vehicle driving data, is displayed on a large visualization screen.

[0013] Compared to existing technologies, this solution does not recreate the actual vehicle model in the tunnel digital twin by measuring the vehicle's actual model. Instead, it pre-sets general models for various types of vehicles and selects the corresponding general model to recreate the vehicle in the tunnel digital twin based on the measured vehicle type. In this way, there is no need to recreate the vehicle in the tunnel based on its actual model; it can be directly retrieved from the pre-set model library, thereby reducing the computing power requirements for modeling vehicle digital objects in the tunnel digital twin.

[0014] Furthermore, it also includes road segmentation, and the vehicle detection module further includes a road segment detection module;

[0015] The road segmentation module is used to divide a tunnel into several identified road segments based on its length.

[0016] The road segment detection module is preset with a vehicle number threshold. It is also used to obtain the number of vehicles on each identified road segment and to determine the relationship between the number of vehicles on the identified road segment and the vehicle number threshold.

[0017] The object generation module is also used to generate digital objects corresponding to all vehicles on the identified road segment on the tunnel digital twin road segment corresponding to the identified road segment when the number of vehicles is less than the preset vehicle number threshold, and to select a number of identified vehicles from the identified road segment and mark other vehicles as unidentified vehicles when the number of identified vehicles is less than the vehicle number threshold, and to generate digital objects of identified vehicles on the tunnel digital twin road segment corresponding to the identified road segment.

[0018] The large screen display module is also used to mark the corresponding identification road segments, and to mark the relative parameters of the vehicle driving data of marked vehicles and unmarked vehicles, and to display the actual number of vehicles on the identification road segment.

[0019] The tunnel is divided into several identification segments, and a threshold for the number of vehicles on each segment is set. If the number of vehicles on a segment is less than the threshold, i.e., the number of vehicles on the segment is low, digital objects are generated for all vehicles on that segment. If the number of vehicles on a segment is greater than the threshold, i.e., the number of vehicles on the segment is high, identified vehicles are selected from those vehicles on that segment, and digital objects for these identified vehicles are generated only in the tunnel's digital twin. The relative parameters between the identified and unidentified vehicles are then used for labeling.

[0020] When there are many vehicles in a road segment, digital objects are not generated for all vehicles. Instead, only a subset of vehicles are selected to generate digital objects. The information of other vehicles is reflected through relative parameters between the identified and unidentified vehicles, such as the relative speed between the unidentified and identified vehicles, the distance between them, and the number of parking spaces between them. Compared to generating digital objects for all vehicles, selecting only a subset for display when there are many vehicles reduces the likelihood of display lag and lowers the load on servers and other equipment.

[0021] Furthermore, the object generation module is also used to obtain the vehicle type of each vehicle in the identification road segment where the number of vehicles is greater than the vehicle number threshold, count the number of vehicles included in each vehicle type, calculate the proportion of vehicles of each vehicle type, and select vehicles of the corresponding proportion as the identified vehicles based on the proportion.

[0022] When selecting vehicles for identification, vehicles of the corresponding proportion are chosen as the identification vehicles based on the proportion of each vehicle type in the identified road segment. This allows the display of the identification vehicles to reflect the proportion of each type of vehicle in the identified road segment when viewed on a large visual screen.

[0023] Furthermore, the road segment detection module is also used to determine whether the number of vehicles in the next identification road segment is higher than that in the current identification road segment before the identified vehicle enters the next identification road segment;

[0024] The object generation module is also used to continue using the identified vehicle as the identified vehicle for the next identified road segment when the number of vehicles in the next identified road segment is higher than that in the current identified road segment.

[0025] When a vehicle enters the next identification segment, the number of vehicles in the next identification segment is identified. If the number of vehicles in the next identification segment is higher than the number of vehicles in the current identification segment, then the number of vehicles in the next identification segment also exceeds the vehicle number threshold. Therefore, vehicles must also be selected in the next identification segment to generate corresponding digital objects. Since the identified vehicles reflect vehicles that are about to enter or have already entered the next identification segment from the previous identification segment, vehicles that have already entered the next identification segment are continued to be identified as vehicles in the next segment and displayed as digital objects in the tunnel digital twin corresponding to the next identification segment.

[0026] Furthermore, the object generation module is also used to obtain the proportion of vehicle types of identified vehicles entering the next identified road segment within a unit of time when the number of vehicles in the identified road segment exceeds the vehicle number threshold, and the number of vehicles in the preceding and following identified road segments does not exceed the vehicle number threshold, and when identified vehicles in the identified road segment with a number of vehicles exceeding the vehicle number threshold enter the next identified road segment. If the proportion of identified vehicles entering the next identified road segment to each vehicle type in the identified road segment is within a preset fluctuation threshold, the proportion of vehicle type selected by the identified vehicle is not changed. If it is outside the fluctuation threshold, the proportion of vehicle type in the identified road segment is re-obtained to select the identified vehicle.

[0027] If the number of vehicles in the identification road segment before and after the identification road segment exceeds the vehicle number threshold, and the number of vehicles in the identification road segment before and after the identified vehicle leaves the identification road segment, the proportion of the identified vehicle type leaving the identification road segment within a unit time is obtained. If it is the same as the proportion of the vehicle type in the identification road segment, then vehicles of the same proportion in the identification road segment are selected as the identified vehicles. If the proportion is different, the proportion of the vehicle type in the identification road segment is obtained again to select the identified vehicles, so as to ensure that the identified vehicles can truly reflect the proportion of the vehicle types in the road segment.

[0028] Furthermore, it also includes a risk identification module;

[0029] The risk identification module is used to identify high-risk events and their types within the tunnel based on vehicle driving data.

[0030] The large-screen display module is also used to mark the time and location of high-risk events in the tunnel digital twin through a visual large screen.

[0031] Based on the detected data, risk events and their types are identified, and these risk events are marked on a large visual screen for easy viewing.

[0032] Furthermore, the risk identification module includes a type identification module, a vehicle temperature identification module, a vehicle speed identification module, and a large screen display module;

[0033] The type recognition module is pre-set with high-risk vehicle types. It is used to identify vehicle types based on the image data collected by the monitoring equipment and to determine whether the identified vehicle type is a high-risk vehicle.

[0034] The vehicle temperature recognition module has a preset temperature threshold, which is used to identify vehicles whose temperature is higher than the preset temperature threshold as high-risk vehicles based on the vehicle temperature collected by the temperature detection device.

[0035] The vehicle speed recognition module has a preset speed threshold, which is used to identify vehicles whose speed exceeds the preset speed threshold as high-risk vehicles based on the vehicle speed collected by the vehicle speed detection device.

[0036] The large-screen display module is used to label the digital objects of high-risk vehicles, the lanes where high-risk vehicles are located, and the vehicle driving data of high-risk vehicles in the tunnel digital twin according to the risk level of the vehicles.

[0037] Digital objects with high vehicle temperature, high speed, or dangerous vehicle type are marked to facilitate relevant personnel to focus on and track high-risk vehicles. Attached Figure Description

[0038] Figure 1 This is a logic block diagram of an embodiment of a tunnel digital twin three-dimensional intelligent control platform according to the present invention. Detailed Implementation

[0039] The following detailed description illustrates the specific implementation method:

[0040] The basic implementation examples are as follows: Figure 1 As shown:

[0041] A tunnel digital twin 3D intelligent control platform includes a tunnel acquisition module, an equipment association module, a vehicle detection module, a large screen display module, and a road segmentation module.

[0042] The tunnel acquisition module is used to acquire tunnel image data uploaded by the image acquisition device and tunnel point cloud data acquired by the laser device. Based on the tunnel image data and tunnel point cloud data, a 3D model of the tunnel corresponding to the physical entity of the tunnel is constructed. Specifically, the tunnel image acquisition device is an intelligent camera inside the tunnel. The intelligent camera acquires images inside the tunnel to build a 3D tunnel model. The point cloud data is input into a preset 3D point cloud modeling software for shaping, obtaining the initial 3D model corresponding to the tunnel. The tunnel images are processed using a preset image processing algorithm to obtain the visible light surface image of the tunnel. The initial 3D tunnel model and the overall visible light surface image are then processed and superimposed to achieve the construction of the 3D tunnel model.

[0043] The device association module integrates the sensing devices within the tunnel with the tunnel's 3D model to obtain a digital twin of the tunnel. Specifically, based on sensing devices such as sensors, a corresponding environmental simulation program is set up for the tunnel's 3D model. The sensor devices transmit corresponding sensing data, such as temperature data and vehicle data, to the environmental simulation program corresponding to the tunnel's 3D model. Based on the sensing data, the environmental simulation program simulates the environment, thereby creating a digital twin of the tunnel's physical entity.

[0044] The vehicle detection module acquires vehicle driving data and vehicle location information collected by sensing devices within the tunnel. Based on this data, it generates a real-time digital object corresponding to the physical vehicle entity within the tunnel's digital twin. Specifically, sensing devices within the tunnel, such as speed detection devices and smart cameras, detect parameters such as vehicle speed, location, and lane position. The detected vehicle data is then bound to the vehicle and stored in the tunnel's digital twin to generate the corresponding digital object.

[0045] The vehicle detection module includes a type detection module and an object generation module.

[0046] The vehicle type detection module has several pre-set vehicle models and is used to identify vehicle types and ticket numbers based on image data detected by the image acquisition equipment. Specifically, the intelligent camera at the front end acquires vehicle images inside the tunnel, and the vehicle types are analyzed using a pre-set image recognition algorithm. In this embodiment, the identified vehicle types include: automobiles (small cars, microcars, compact cars, mid-size cars, high-end cars, luxury cars, sedans, CDVs, MPVs, SUVs, etc.), trucks (micro-trucks, light trucks, medium trucks, heavy trucks), off-road vehicles (light off-road vehicles, medium off-road vehicles, heavy off-road vehicles, super heavy off-road vehicles), dump trucks (light dump trucks, medium dump trucks, heavy dump trucks, mining dump trucks), tractors (semi-trailer tractors, full trailer tractors), and buses (micro-buses, light buses, medium buses, large buses, extra-large buses).

[0047] The object generation module retrieves the corresponding vehicle model based on the vehicle type and generates a real-time digital object within the tunnel digital twin, then binds the license plate number to the real-time digital object. Using a built-in model library, each vehicle type has a pre-defined general model. Based on the identified vehicle type, the module retrieves the corresponding vehicle model from the library, assigns the identified license plate number as an identifier to the vehicle model, and generates its digital object within the tunnel digital twin. Simultaneously, the detected vehicle data is bound to the digital object.

[0048] The large-screen display module is used to display the digital twin of the tunnel, which includes real-time digital objects of vehicles and their driving data, on a large visual screen. The large visual screen displays the driving status of the tunnel digital twin and the vehicle digital objects within it, providing a direct view of the actual situation inside the tunnel.

[0049] The road segmentation module is used to divide the tunnel into several identification segments based on the tunnel length. Specifically, the tunnel is divided into several equal segments; in this embodiment, each segment is divided into an identification segment every 1 km.

[0050] The road segment detection module has a preset vehicle number threshold and is also used to obtain the number of vehicles on each identified road segment and determine the relationship between the number of vehicles on the identified road segment and the vehicle number threshold.

[0051] The object generation module is also used to generate digital objects corresponding to all vehicles on the identified road segment on the tunnel digital twin road segment corresponding to the identified road segment when the number of vehicles is less than a preset vehicle number threshold, and to select a number of identified vehicles from the identified road segment and mark other vehicles as unidentified vehicles when the number of identified vehicles is less than the vehicle number threshold, and to generate digital objects of identified vehicles on the tunnel digital twin road segment corresponding to the identified road segment.

[0052] Specifically, the number of vehicles in each identified road segment is detected. When the number of vehicles in the identified road segment is less than the preset vehicle threshold, that is, the number of vehicles in the identified road segment is small, then a digital twin of all vehicles in the identified road segment will be generated in the digital twin corresponding to the identified road segment.

[0053] When the number of vehicles in the identified road segment exceeds a preset threshold, meaning there are many vehicles in that segment, generating digital objects for all vehicles in the corresponding tunnel digital twin would put a heavy load on the server and cause lag during viewing. Therefore, when the number of vehicles in the identified road segment exceeds the preset threshold, only the identified vehicles are selected to generate digital objects. The preset vehicle threshold can be set based on equipment conditions. The large-screen display module is also used to label the corresponding identified road segments and obtain relative parameters of the driving data between identified and unidentified vehicles for labeling, and to display the actual number of vehicles in the identified road segment. After selecting the identified vehicle, other vehicles are marked as unidentified vehicles, and the relative parameters between the unidentified and identified vehicles are obtained. This allows the identified vehicle to reflect the characteristics of the unidentified vehicles, such as the distance to the identified vehicle, the relative speed, the parking space ahead of the identified vehicle, and the specific vehicle type. When reflecting the parameters of the unidentified vehicle object through the identified vehicle, the closest identified vehicle is preferred. At the same time, the actual number of vehicles in the identified road segment is displayed on the large visualization screen.

[0054] The object generation module is also used to obtain the vehicle types of each vehicle in the identified road segment where the number of vehicles exceeds a vehicle number threshold, count the number of vehicles included in each vehicle type, calculate the proportion of each vehicle type, and select vehicles of the corresponding proportion as identified vehicles based on the proportion. When selecting identified vehicles, the selection is based on the proportion of the identified vehicle types. For example, if 30 cars, 10 trucks, and 5 buses are identified, with a ratio of 6:2:1, then 6 cars, 2 trucks, and 1 bus can be selected as identified vehicles. Corresponding digital objects are generated in the tunnel digital twin. The selection prioritizes vehicles located at different positions on the identified road segment to ensure that the identified vehicles fully cover the identified road segment.

[0055] The road segment detection module is also used to determine whether the number of vehicles in the next identification road segment is higher than that in the current identification road segment before the identified vehicle enters the next identification road segment;

[0056] The object generation module is also used to continue using the identified vehicle as the identified vehicle in the next identified road segment when the number of vehicles in the next identified road segment is higher than that in the current identified road segment. Specifically, if the number of vehicles in the next identified road segment is higher than that in the current identified road segment, when the identified vehicle enters the next identified road segment, it continues to be used as the identified vehicle to generate a digital object in the tunnel digital twin.

[0057] When a vehicle enters the next identification segment, the number of vehicles in the next identification segment is identified. If the number of vehicles in the next identification segment is higher than the number of vehicles in the previous identification segment, then the number of vehicles in the next identification segment also exceeds the vehicle number threshold. Therefore, vehicles must also be selected in the next identification segment to generate corresponding digital objects. Since the identified vehicles reflect vehicles that are about to enter or have already entered the next identification segment from the previous identification segment, vehicles that have already entered the next identification segment are continued to be identified as vehicles in the next segment and displayed as digital objects in the tunnel digital twin corresponding to the next identification segment.

[0058] The object generation module is also used to obtain the proportion of vehicle types of identified vehicles entering the next identified road segment within a unit of time when the number of vehicles in the identified road segment exceeds the vehicle number threshold, and the number of vehicles in the preceding and following identified road segments does not exceed the vehicle number threshold, and when identified vehicles in the identified road segment with a number of vehicles exceeding the vehicle number threshold enter the next identified road segment. If the proportion of identified vehicles entering the next identified road segment and the proportion of each vehicle type in the identified road segment are within a preset fluctuation threshold, the proportion of the selected vehicle type is not changed. If it is outside the fluctuation threshold, the proportion of the vehicle type in the identified road segment is re-obtained to select the identified vehicle.

[0059] If the number of vehicles in the identification road segment before and after the identification road segment exceeds the vehicle number threshold, and the number of vehicles in the identification road segment before and after the identified vehicle leaves the identification road segment, the proportion of the identified vehicle type leaving the identification road segment within a unit time is obtained. If it is the same as the proportion of the vehicle type in the identification road segment, the identification road segment with the same proportion of vehicle type is selected. If the proportion is different, the proportion of the vehicle type in the identification road segment is obtained again to select the identified vehicle, so as to ensure that the identified vehicle can truly reflect the proportion of the vehicle type in the road segment.

[0060] Example 2

[0061] The difference between this embodiment and Embodiment 1 is that this embodiment also includes a risk identification module, which is used to identify high-risk events and event types in the tunnel based on vehicle driving data.

[0062] The large-screen display module is also used to mark the time and location of high-risk events in the tunnel digital twin through a visual large screen.

[0063] The risk identification module includes a type identification module, a vehicle temperature identification module, a vehicle speed identification module, and a large screen display module.

[0064] The type recognition module has preset vehicle types for high-risk vehicles. It is used to identify vehicle types based on the image data collected by the monitoring equipment and determine whether the identified vehicle type is a high-risk vehicle.

[0065] The vehicle temperature recognition module has a preset temperature threshold. It is used to identify vehicles whose temperature is higher than the preset temperature threshold based on the vehicle temperature collected by the temperature detection device.

[0066] The vehicle speed recognition module has a preset speed threshold, which is used to identify vehicles whose speed exceeds the preset speed threshold as high-risk vehicles based on the vehicle speed collected by the vehicle speed detection device.

[0067] The large-screen display module is used to label the digital objects of high-risk vehicles, the lanes where high-risk vehicles are located, and the vehicle driving data of high-risk vehicles in the tunnel digital twin according to the risk level of the vehicles.

[0068] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A tunnel digital twin three-dimensional intelligent control platform, characterized in that: It includes a tunnel data acquisition module, an equipment association module, a vehicle detection module, and a large-screen display module; The tunnel acquisition module is used to acquire tunnel image data uploaded by the image acquisition device and tunnel point cloud data acquired by the laser device, and to construct a 3D model of the tunnel corresponding to the physical entity of the tunnel based on the tunnel image data and tunnel point cloud data. The device association module associates and fuses the sensing devices inside the tunnel with the three-dimensional model of the tunnel to obtain a digital twin of the tunnel; The vehicle detection module is used to acquire vehicle driving data and vehicle location collected by sensing devices in the tunnel, and to generate a real-time digital object corresponding to the physical entity of the vehicle in the tunnel digital twin based on the vehicle driving data and vehicle location. The vehicle detection module includes a type detection module and an object generation module. The type detection module has several vehicle models pre-set, which are used to identify the vehicle type and ticket number based on the image data detected by the image acquisition device; The object generation module retrieves the corresponding vehicle model based on the vehicle type and generates a real-time digital object in the tunnel digital twin, and binds the license plate number to the real-time digital object; The large screen display module is used to display a digital twin of a tunnel containing real-time digital objects of vehicles and their driving data through a visual large screen; It also includes road segmentation, and the vehicle detection module further includes a road segment detection module; The road segmentation module is used to divide a tunnel into several identified road segments based on its length. The road segment detection module is preset with a vehicle number threshold. It is also used to obtain the number of vehicles on each identified road segment and to determine the relationship between the number of vehicles on the identified road segment and the vehicle number threshold. The object generation module is also used to generate digital objects corresponding to all vehicles on the identified road segment on the tunnel digital twin road segment corresponding to the identified road segment when the number of vehicles is less than the preset vehicle number threshold, and to select a number of identified vehicles from the identified road segment and mark other vehicles as unidentified vehicles when the number of identified vehicles is less than the vehicle number threshold, and to generate digital objects of identified vehicles on the tunnel digital twin road segment corresponding to the identified road segment. The large screen display module is also used to mark the corresponding identification road segments, and to mark the relative parameters of the vehicle driving data of marked vehicles and unmarked vehicles, and to display the actual number of vehicles on the identification road segment. The object generation module is also used to obtain the vehicle type of each vehicle in the identification road segment where the number of vehicles is greater than the vehicle number threshold, count the number of vehicles included in each vehicle type, calculate the proportion of vehicles of each vehicle type, and select vehicles of the corresponding proportion as the identified vehicles based on the proportion. The object generation module is also used to obtain the proportion of vehicle types of identified vehicles entering the next identified road segment within a unit of time when the number of vehicles in the identified road segment exceeds the vehicle number threshold, and the number of vehicles in the preceding and following identified road segments does not exceed the vehicle number threshold, and when identified vehicles in the identified road segment with a number of vehicles exceeding the vehicle number threshold enter the next identified road segment. If the proportion of identified vehicles entering the next identified road segment and the proportion of each vehicle type in the identified road segment are within a preset fluctuation threshold, the proportion of the selected vehicle type is not changed. If it is outside the fluctuation threshold, the proportion of the vehicle type in the identified road segment is re-obtained to select the identified vehicle.

2. The tunnel digital twin three-dimensional intelligent control platform according to claim 1, characterized in that: The road segment detection module is also used to determine whether the number of vehicles in the next identification road segment is higher than that in the current identification road segment before the identified vehicle enters the next identification road segment; The object generation module is also used to continue using the identified vehicle as the identified vehicle for the next identified road segment when the number of vehicles in the next identified road segment is higher than that in the current identified road segment.

3. The tunnel digital twin three-dimensional intelligent control platform according to claim 2, characterized in that: It also includes a risk identification module; The risk identification module is used to identify high-risk events and their types within the tunnel based on vehicle driving data. The large-screen display module is also used to mark the time and location of high-risk events in the tunnel digital twin through a visual large screen.

4. The tunnel digital twin three-dimensional intelligent control platform according to claim 3, characterized in that: The risk identification module includes a type identification module, a vehicle temperature identification module, a vehicle speed identification module, and a large screen display module; The type recognition module is pre-set with high-risk vehicle types. It is used to identify vehicle types based on the image data collected by the monitoring equipment and to determine whether the identified vehicle type is a high-risk vehicle. The vehicle temperature recognition module has a preset temperature threshold, which is used to identify vehicles whose temperature is higher than the preset temperature threshold as high-risk vehicles based on the vehicle temperature collected by the temperature detection device. The vehicle speed recognition module has a preset speed threshold, which is used to identify vehicles whose speed exceeds the preset speed threshold as high-risk vehicles based on the vehicle speed collected by the vehicle speed detection device. The large-screen display module is used to label the digital objects of high-risk vehicles, the lanes where high-risk vehicles are located, and the vehicle driving data of high-risk vehicles in the tunnel digital twin according to the risk level of the vehicles.

Images