A tunnel monitoring method, device and medium based on digital twin

Abstract

This specification discloses a tunnel monitoring method, equipment, and medium based on digital twins, applied in the field of traffic monitoring technology, to address the problem that existing monitoring methods are unable to predict accident risks in a timely manner. The method includes: dividing the tunnel under inspection into regions based on brightness changes to obtain three-dimensional point cloud data for each region, and establishing static and dynamic components for the tunnel under inspection; constructing three-dimensional models at different levels based on the static and dynamic components, and aligning the three-dimensional models at different levels to obtain a dynamic three-dimensional model; nesting and associating the monitoring parameters of the monitoring equipment with the three-dimensional model to obtain the corresponding digital twin model; determining traffic impact data based on the correlation between historical monitoring data and historical traffic events; tracking and monitoring the traffic impact data based on the digital twin model; and timely predicting and extrapolating one or more traffic events corresponding to the region where the traffic impact data is located based on the digital twin model to obtain the traffic risk for each region.

Description

Technical Field

[0001] The present invention relates to the field of traffic monitoring technology, and in particular to a digital twin tunnel monitoring method, device and medium. Background Art

[0002] With the development of economy and the improvement of people's living standards, the number of vehicles is increasing, and the highway construction is becoming more and more perfect. Among them, tunnel is a kind of passage dug underground or in the mountain. It is also an important way to build mountainous areas and cross-sea / river highways. It is an important throat of highway and urban road traffic. With the popularization of vehicles, tunnels not only have a large volume of traffic, but also are semi-closed environments. Therefore, there are more traffic accidents than ordinary sections, and it is very easy to cause secondary accidents. Therefore, monitoring the traffic conditions in tunnels has become an important means to reduce the accident rate.

[0003] At present, the monitoring of traffic flow and infrastructure conditions in tunnels is generally based on manual detection, that is, regular manual inspections, or monitoring based on sensors and cameras installed in the tunnel structure. However, the monitoring frequency of manual inspections is low. First, it is easy to miss inspections, and second, it is difficult to respond to sudden traffic incidents in a timely manner, which can easily lead to further development of traffic risks. The monitoring method based on sensors and cameras generally determines the occurrence of an incident and conducts emergency treatment after the incident occurs. In other words, it is difficult to monitor and predict possible traffic incidents in a timely manner, which makes it difficult to reduce the incidence of traffic incidents in tunnels. Summary of the invention

[0004] In order to solve the above technical problems, one or more embodiments of this specification provide a tunnel monitoring method, device, equipment and medium based on digital twins.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of this specification provide a tunnel monitoring method based on digital twins, the method comprising:

[0007] Dividing the area into a first area, a second area, and a third area according to the brightness change of the tunnel to be detected, so as to obtain three-dimensional point cloud data of the first area, the second area, and the third area;

[0008] Determine and establish static components and dynamic components of the tunnel to be inspected based on the three-dimensional point cloud data, so as to construct a first-layer three-dimensional model based on the static components and a second-layer three-dimensional model based on the dynamic components;

[0009] Aligning the first layer of three-dimensional model with the second layer of three-dimensional model based on the point cloud positions of the three-dimensional point cloud data to obtain a dynamic three-dimensional model of the tunnel to be inspected;

[0010] Acquire the position information of each monitoring device in the tunnel to be detected, and nest and associate the monitoring parameters of the monitoring device with the three-dimensional model based on the position information to obtain the digital twin model of the tunnel to be detected;

[0011] Determine the traffic impact data of the tunnel to be detected based on the correlation between the historical monitoring data of the tunnel to be detected and the historical traffic events, and track and monitor the traffic impact data based on the digital twin model;

[0012] If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events corresponding to the area where the traffic impact data is located are predicted and deduced based on the digital twin model to determine the traffic risks in each area.

[0013] Optionally, in one or more embodiments of the present specification, performing area division according to brightness changes of the tunnel to be detected to obtain a first area, a second area, and a third area specifically includes:

[0014] Acquire the sunrise time and sunset time of the tunnel to be detected, so as to determine the low illumination time range and the high illumination time range of the tunnel to be detected based on the sunrise time and the sunset time;

[0015] If the current time is in a high illumination time range, the tunnel entrance image and the tunnel exit image are acquired based on a preset image acquisition device;

[0016] Performing grayscale processing on the tunnel entrance image and the tunnel exit image to obtain a tunnel entrance grayscale image and a tunnel exit grayscale image, so as to determine the brightness value of each pixel in the tunnel entrance grayscale image and the tunnel exit grayscale image;

[0017] Determine a difference in brightness values ​​of adjacent pixels in the grayscale image of the tunnel entrance and the grayscale image of the tunnel exit, and determine a sudden pixel point in the grayscale image of the tunnel entrance and the grayscale image of the tunnel exit based on the difference;

[0018] Determine a region boundary between the grayscale image of the tunnel entrance and the grayscale image of the tunnel exit according to the position of the sudden pixel point, so as to respectively determine a high brightness region and a low brightness region of the grayscale image of the tunnel entrance, and a high brightness region and a low brightness region of the high brightness region and the low brightness region of the grayscale image of the tunnel exit according to the region boundary;

[0019] Merging the low brightness area with the inner area of ​​the tunnel to be detected as a first area, taking the high brightness area of ​​the grayscale image of the tunnel entrance as a second area, and taking the high brightness area of ​​the grayscale image of the tunnel exit as a third area;

[0020] If the current time is in a low illumination time range, the inner area of ​​the tunnel to be detected and the outer area of ​​the tunnel to be detected are taken as the first area.

[0021] Optionally, in one or more embodiments of the present specification, obtaining the three-dimensional point cloud data of the first area, the second area, and the third area specifically includes:

[0022] Acquire initial three-dimensional point cloud data of the first area, the second area, and the third area according to a preset point cloud acquisition device of the tunnel to be inspected;

[0023] Training a point cloud completion model based on the historical point cloud data of the tunnel to be inspected to obtain a point cloud completion model that meets the requirements;

[0024] The initial three-dimensional point cloud data is input into the point cloud completion model that meets the requirements to complete the initial three-dimensional point cloud data and obtain three-dimensional point cloud data of the first area, the second area and the third area.

[0025] Optionally, in one or more embodiments of the present specification, determining to establish static components and dynamic components of the tunnel to be detected based on the three-dimensional point cloud data, so as to construct a first-layer three-dimensional model based on the static components and to construct a second-layer three-dimensional model based on the dynamic components, specifically includes:

[0026] Determine the fixed static components of the tunnel to be detected based on the architectural data of the tunnel to be detected;

[0027] Extracting moving three-dimensional point cloud data in the three-dimensional point cloud data based on the position coordinates of the three-dimensional point cloud data in adjacent time periods, so as to establish a dynamic component of the tunnel to be detected based on the moving three-dimensional point cloud data;

[0028] Determining a newly added static component corresponding to the three-dimensional point cloud data based on a matching relationship between the remaining three-dimensional point cloud data outside the moving three-dimensional point cloud data and the fixed static component;

[0029] Determine the geometric features of the fixed static component and the newly added static component according to the three-dimensional point cloud data corresponding to the fixed static component and the newly added static component, so as to construct a first-layer three-dimensional model based on the geometric features; wherein the geometric features include: point position, normal vector, and curvature;

[0030] A second-layer three-dimensional model is constructed according to the position coordinates corresponding to the three-dimensional point cloud data of the dynamic component.

[0031] Optionally, in one or more embodiments of the present specification, obtaining the location information of each monitoring device in the tunnel to be detected, and nesting and associating the monitoring parameters of the monitoring device with the three-dimensional model based on the location information to obtain the digital twin model of the tunnel to be detected, specifically includes:

[0032] Acquire the position information of each monitoring device in the tunnel to be detected, and determine a first coordinate system corresponding to the position information;

[0033] Based on the difference data between the first coordinate system and the second coordinate system corresponding to the three-dimensional model, a conversion relationship between the first coordinate system and the second coordinate system is established, and based on the conversion relationship, the position information is converted to the second coordinate system to obtain the current position information; wherein the conversion relationship includes at least one or more of the following: a translation relationship, a rotation relationship, and a scaling relationship;

[0034] The current position information is mapped to the corresponding position of the three-dimensional model, and the monitoring parameters of the monitoring device are nested and associated with the corresponding current position information, a data connection is established between the monitoring device and the three-dimensional model, and a digital twin model of the tunnel to be detected is obtained.

[0035] Optionally, in one or more embodiments of the present specification, based on the correlation between the historical monitoring data of the tunnel to be detected and the historical traffic events, determining the traffic impact data of the tunnel to be detected, and tracking and monitoring the traffic impact data based on the digital twin model specifically include:

[0036] Determine the historical monitoring data corresponding to each historical traffic event, group the historical monitoring data according to the event type corresponding to each historical traffic event, and obtain a set of historical monitoring data corresponding to each event type;

[0037] Based on the event risk level corresponding to each historical monitoring data in the historical monitoring data set, the historical monitoring data set is secondary grouped to obtain a subset of historical monitoring data corresponding to each event risk level;

[0038] Determining a first correlation value of each historical monitoring data in each of the historical monitoring data subsets based on a subjective and objective weighting method;

[0039] Determine the second correlation value of each historical monitoring data according to the overlap of the monitoring data in each subset of the historical monitoring data, and determine the tunnel area corresponding to each historical monitoring data, so as to determine the weighting coefficient of each historical monitoring data based on the tunnel area; wherein the weighting coefficient of the first area is greater than the weighting coefficient of the second area, which is greater than the weighting coefficient of the third area;

[0040] Determine the correlation corresponding to each of the historical monitoring data according to the product of the first correlation value, the second correlation value and the weighting coefficient, so as to obtain the traffic impact data of the tunnel to be detected by screening based on the correlation;

[0041] The traffic impact data is marked so that the digital twin model tracks and monitors the traffic impact data based on the mark.

[0042] Optionally, in one or more embodiments of the present specification, determining the first weight value of each historical monitoring data in each of the historical monitoring data subsets based on a subjective and objective weighting method specifically includes:

[0043] Receive, based on a preset interface, a subjective weight ranking sequence of each of the historical monitoring data from each expert terminal;

[0044] Determine the scale value of adjacent historical monitoring data in each subjective weight sorting sequence based on a preset ratio scale, so as to determine the subjective judgment matrix corresponding to each historical monitoring data in the historical monitoring data subset based on the scale value;

[0045] Obtaining information entropy of each historical monitoring data in the historical monitoring data subset, so as to determine the objective weight corresponding to each historical monitoring data according to the information entropy;

[0046] Based on the linear weighting of the subjective judgment matrix and the objective weight, a first weight value of each historical monitoring data in the historical monitoring data subset is determined.

[0047] Optionally, in one or more embodiments of the present specification, if it is determined that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events corresponding to the area where the traffic impact data is located are predicted and deduced based on the digital twin model to determine the traffic risk of each area, specifically including:

[0048] If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, then obtaining the change information of the traffic impact data and the tunnel area corresponding to the traffic impact data, so that the digital twin model simulates the traffic impact data according to the change information, and obtains the preview result of the area where the traffic impact data is located; wherein the preview result includes the probability of occurrence of one or more traffic events;

[0049] Determining the event risk level corresponding to the traffic event according to the occurrence probability corresponding to each of the traffic events;

[0050] The traffic risk of each area is determined based on the number of traffic incidents in each area and the event risk level of each traffic incident.

[0051] One or more embodiments of this specification provide a tunnel monitoring device based on digital twins, the device comprising:

[0052] at least one processor; and,

[0053] a memory communicatively connected to the at least one processor; wherein,

[0054] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: execute any of the above-mentioned methods.

[0055] One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute any of the above-described methods.

[0056] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0057] Dividing the tunnel into different brightness areas based on brightness changes can make it easier to collect, analyze and compare monitoring data. It helps to collect statistics on accident rates, traffic flow and other data in different areas under different application scenarios, and provide data basis for formulating targeted traffic safety measures. Building a two-layer three-dimensional model based on static components and dynamic components can provide more comprehensive tunnel information, which is helpful for more detailed analysis and monitoring. At the same time, building two layers of three-dimensional models separately can update or modify the models of static or dynamic components separately as needed without affecting each other. Being able to monitor and reflect changes in the tunnel more timely can make the model more flexible. The association between the digital twin model and the monitoring parameters makes it possible to display monitoring data in a three-dimensional visualization environment, which helps to track, predict and deduce traffic events based on traffic impact data based on the digital twin model, so as to understand the development trend of traffic events such as traffic flow, speed, congestion, etc. in advance, determine the traffic risks in each area, and enable the traffic dispatch unit to have time to formulate targeted plans and adjust traffic strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0059] Figure 1 A schematic diagram of a tunnel monitoring method based on digital twins provided in an embodiment of this specification;

[0060] Figure 2 A schematic diagram of the structure of a tunnel monitoring device based on digital twins provided in an embodiment of this specification;

[0061] Figure 3 A schematic diagram of the internal structure of a non-volatile storage medium provided in an embodiment of this specification. DETAILED DESCRIPTION

[0062] The embodiments of this specification provide a tunnel monitoring method, device and medium based on digital twins.

[0063] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0064] like Figure 1 As shown, the embodiment of this specification provides a schematic diagram of a tunnel monitoring method based on digital twins. Figure 1 It can be seen that in one or more embodiments of this specification, a tunnel monitoring method based on digital twins is characterized in that the method includes:

[0065] S101: performing area division according to brightness changes of the tunnel to be detected to obtain a first area, a second area, and a third area, so as to obtain three-dimensional point cloud data of the first area, the second area, and the third area.

[0066] Since the tunnel is a passage dug underground or in the mountain, the car will experience brightness changes inside and outside the tunnel when entering and exiting the tunnel. And this tunnel brightness change will also be affected by the shadows cast by sunlight on the mountain, so that the low-brightness tunnel extension, that is, the car needs to change the brightness before it enters the tunnel. It can be understood that different brightness areas have different effects on traffic events due to the influence of brightness and human vision. Therefore, in order to improve the pertinence of monitoring, in the embodiment of this specification, the first area, the second area and the third area will be divided according to the brightness change of the tunnel to be detected, so as to obtain the three-dimensional point cloud data of the first area, the second area and the third area. After dividing the tunnel into different brightness areas, it is more convenient to collect, analyze and compare the monitoring data. It is helpful to count the accident rate, traffic flow and other data in different areas in different application scenarios, and provide a basis for formulating targeted traffic safety measures.

[0067] Specifically, in one or more embodiments of the present specification, the first area, the second area, and the third area are obtained by performing area division according to the brightness change of the tunnel to be detected, which specifically includes the following process:

[0068] First, the sunrise time and sunset time of the tunnel to be detected are obtained, so as to determine the low illumination time range and high illumination time range of the tunnel to be detected according to the sunrise time and sunset time. By considering the high illumination time range and the low illumination time range respectively, the change of tunnel brightness during the day and night or under different weather conditions can be better adapted. If it is currently in the high illumination time range, then the tunnel entrance image and the tunnel exit image are obtained according to the preset image acquisition device. The tunnel entrance image and the tunnel exit image are gray-scale processed to obtain the tunnel entrance gray-scale image and the tunnel exit gray-scale image to determine the brightness value of each pixel in the tunnel entrance gray-scale image and the tunnel exit gray-scale image. Then, the difference in the brightness values ​​of adjacent pixels in the tunnel entrance gray-scale image and the tunnel exit gray-scale image is determined, and the sudden change pixel points in the tunnel entrance gray-scale image and the tunnel exit gray-scale image are determined based on the difference. The regional demarcation line between the tunnel entrance gray-scale image and the tunnel exit gray-scale image is determined according to the position of the sudden change pixel point, so as to determine the high brightness area and the low brightness area of ​​the tunnel entrance gray-scale image, and the high brightness area and the low brightness area of ​​the tunnel exit gray-scale image according to the regional demarcation line. The low brightness area and the area inside the tunnel of the tunnel to be detected are merged as the first area, the high brightness area of ​​the grayscale image of the tunnel entrance is used as the second area, and the high brightness area of ​​the grayscale image of the tunnel exit is used as the third area. In the above process, the tunnel is divided into different brightness areas, especially the low brightness area and the area inside the tunnel are merged as the first area, which can centrally monitor and analyze areas that may have higher risks, and improve the pertinence and efficiency of monitoring. If the current time range is low illumination, the area inside the tunnel of the tunnel to be detected and the area outside the tunnel of the tunnel to be detected are used as the first area. That is to say, for the low illumination time range, the area inside the tunnel and the area outside the tunnel are used together as the first area, taking into account the situation of the entire tunnel and avoiding the limitation of focusing only on the inside or outside of the tunnel.

[0069] Specifically, in one or more embodiments of the present specification, in order to improve the accuracy of real-time monitoring, obtaining three-dimensional point cloud data of the first area, the second area, and the third area specifically includes the following process:

[0070] According to the preset point cloud acquisition equipment of the tunnel to be detected, the initial three-dimensional point cloud data of the first area, the second area and the third area are obtained; the point cloud completion model is trained based on the historical point cloud data of the tunnel to be detected to obtain a point cloud completion model that meets the requirements; the initial three-dimensional point cloud data is input into the point cloud completion model that meets the requirements to complete the initial three-dimensional point cloud data and obtain the three-dimensional point cloud data of the first area, the second area and the third area. The point cloud completion model is used to quickly complete the point cloud data that has not been collected or is missing in real time, which greatly improves the accuracy of the data. In addition, historical point cloud data is used when training the point cloud completion model, so that the model can learn geometric information related to the current tunnel scene and enhance the accuracy of the completion.

[0071] S102: Determine and establish static components and dynamic components of the tunnel to be inspected based on the three-dimensional point cloud data, so as to construct a first-layer three-dimensional model based on the static components and a second-layer three-dimensional model based on the dynamic components.

[0072] In order to more accurately reflect the actual situation in the tunnel and achieve targeted monitoring. In the embodiment of this specification, the static components and dynamic components of the tunnel to be detected are established according to the three-dimensional point cloud data, so that the first layer of the three-dimensional model is constructed according to the static components, and the second layer of the three-dimensional model is constructed according to the dynamic components. It can be understood that by dividing the components of the tunnel into static and dynamic, the actual situation of the tunnel can be more accurately reflected. The static components include the structure, walls, ground, etc. of the tunnel, while the dynamic components can include moving objects such as vehicles and pedestrians. The two-layer three-dimensional model constructed in this way can provide more comprehensive tunnel information and facilitate more detailed analysis and monitoring. Constructing the two layers of three-dimensional models separately at the same time can make the model more flexible. For example, the models of static or dynamic components can be updated or modified separately as needed without affecting each other. This is very useful for the maintenance and management of the tunnel, and can reflect the changes in the tunnel more promptly.

[0073] Specifically, in one or more embodiments of the present specification, determining and establishing static components and dynamic components of a tunnel to be inspected based on three-dimensional point cloud data, so as to construct a first-layer three-dimensional model based on the static components and a second-layer three-dimensional model based on the dynamic components, specifically includes:

[0074] First, the fixed static components of the tunnel to be detected are determined based on the building data of the tunnel to be detected. Then, according to the position coordinates of the three-dimensional point cloud data in the adjacent time, the moving three-dimensional point cloud data in the three-dimensional point cloud data is extracted to establish the dynamic components of the tunnel to be detected based on the moving three-dimensional point cloud data. By extracting the moving three-dimensional point cloud data, dynamic elements in the tunnel, such as vehicles or moving equipment, can be captured. This is very valuable for applications such as real-time monitoring and traffic flow analysis, and can provide more detailed and real-time tunnel information. Based on the matching relationship between the remaining three-dimensional point cloud data outside the moving three-dimensional point cloud data and the fixed static components, the newly added static components corresponding to the three-dimensional point cloud data are determined. Using the matching relationship to determine the newly added static components, it is possible to timely discover changes in the tunnel or newly built structures, which helps to achieve timely maintenance and situation updates for the monitored tunnel. According to the three-dimensional point cloud data corresponding to the fixed static components and the newly added static components, the geometric features of the fixed static components and the newly added static components are determined to construct the first layer of the three-dimensional model based on the geometric features. Among them, it should be noted that the geometric features include: point position, normal vector, curvature, etc. In addition, the second layer of the three-dimensional model is constructed according to the position coordinates corresponding to the three-dimensional point cloud data of the dynamic component. Static components and dynamic components are constructed as the first and second layers of 3D models, respectively, to facilitate independent analysis and processing of different types of components. This hierarchical structure makes the model more flexible and scalable, and different layers can be further refined and optimized according to specific needs.

[0075] S103: Aligning the first layer of three-dimensional model with the second layer of three-dimensional model based on the point cloud positions of the three-dimensional point cloud data to obtain a dynamic three-dimensional model of the tunnel to be inspected.

[0076] After obtaining the first layer 3D model and the second layer 3D model based on the above step S102, the dynamic 3D model of the tunnel to be detected is obtained. That is, by merging the information of the first layer and the second layer, a more complete dynamic 3D model can be constructed. In this way, the static structure and dynamic components of the tunnel can be comprehensively considered to provide a more comprehensive description of the tunnel. The point cloud position alignment process based on the 3D point cloud data can provide an accurate, complete and real-time dynamic 3D model of the tunnel to be detected, providing strong support for tunnel monitoring.

[0077] S104: Acquire the position information of each monitoring device in the tunnel to be inspected, and nest and associate the monitoring parameters of the monitoring device with the three-dimensional model based on the position information to obtain the digital twin model of the tunnel to be inspected.

[0078] In the embodiments of this specification, the location information of each monitoring device in the tunnel to be inspected is obtained, and the monitoring parameters of the detection device and the three-dimensional model are nested and associated according to the location information to obtain the digital twin model of the tunnel to be inspected. By associating the monitoring parameters of the monitoring device with the three-dimensional model, the monitoring data can be displayed in real time in the digital twin model. This enables users to intuitively understand the conditions of various locations in the tunnel, including structural health, environmental parameters, etc., so as to achieve comprehensive monitoring.

[0079] Specifically, in one or more embodiments of the present specification, the location information of each monitoring device in the tunnel to be detected is obtained, and the monitoring parameters of the monitoring device are nested and associated with the three-dimensional model based on the location information to obtain the digital twin model of the tunnel to be detected, which specifically includes:

[0080] In order to achieve accurate management, this specification first obtains the position information of each monitoring device in the tunnel to be detected, and determines the first coordinate system corresponding to the position information. Then, according to the difference data between the first coordinate system and the second coordinate system corresponding to the three-dimensional model, a conversion relationship between the first coordinate system and the second coordinate system is established, and the position information is converted to the second coordinate system based on the conversion relationship to obtain the current position information. Among them, it should be noted that the conversion relationship includes at least one or more of the following: translation relationship, rotation relationship, and scaling relationship. The differences between different coordinate systems are taken into account, and a conversion relationship is established. This makes it possible to integrate the position information from different monitoring devices, and no matter what coordinate system they use, they can be seamlessly connected with the three-dimensional model. By mapping the current position information to the corresponding position of the three-dimensional model, and nesting and associating the monitoring parameters of the monitoring device with the corresponding current position information, a data connection between the monitoring device and the three-dimensional model is established, and a digital twin model of the tunnel to be detected is obtained. The association of the digital twin model with the monitoring parameters enables the monitoring data to be displayed in a three-dimensional visualization environment. This helps to intuitively understand the state of the tunnel and conduct more in-depth data analysis and mining to discover potential problems and trends.

[0081] S105: Determine the traffic impact data of the tunnel to be detected based on the correlation between the historical monitoring data of the tunnel to be detected and the historical traffic events, and track and monitor the traffic impact data based on the digital twin model.

[0082] In order to be able to track and analyze risky traffic impact data, so as to timely grasp the event situation in the tunnel before the event occurs. In the embodiment of this specification, the traffic impact data of the tunnel to be detected is determined based on the correlation between the historical monitoring data and the historical traffic data of the tunnel to be detected, and the traffic impact data is tracked and monitored based on the digital twin model. This method of tracking and monitoring traffic impact data based on the digital twin model helps to achieve early warning of traffic incidents in the tunnel, real-time monitoring, optimize traffic management, improve safety, enhance emergency response capabilities and assist in decision-making support, which is of great significance for ensuring the safety and smoothness of traffic in the tunnel to be detected.

[0083] Specifically, in one or more embodiments of the present specification, based on the correlation between the historical monitoring data of the tunnel to be detected and the historical traffic events, the traffic impact data of the tunnel to be detected is determined, and the traffic impact data is tracked and monitored based on the digital twin model, specifically including:

[0084] Determine the historical monitoring data corresponding to each historical traffic event, and group each historical monitoring data according to the event type corresponding to each historical traffic event to obtain a set of historical monitoring data corresponding to each event type. At the same time, according to the event risk level corresponding to each historical monitoring data in the historical monitoring data set, perform secondary grouping on the historical monitoring data set to obtain a subset of historical monitoring data corresponding to each event risk level. By considering the historical traffic event type and event risk level, grouping and secondary grouping the historical monitoring data, it is possible to analyze traffic events of different types and risk levels more specifically, thereby determining the impact data corresponding to traffic events of different types and risk levels.

[0085] Then, the first correlation value of each historical monitoring data in each historical monitoring data subset is determined by subjective and objective weighting. This process can more comprehensively understand the impact of traffic events of different types and risk levels on the tunnel by grouping and regrouping the historical monitoring data by considering the types of historical traffic events and the risk levels of the events. According to the overlap of the monitoring data in each historical monitoring data subset, the second correlation value of each historical monitoring data is determined, and the tunnel area corresponding to each historical monitoring data is determined, so as to determine the weight coefficient of each historical monitoring data based on the tunnel area; wherein, it should be noted that the weight coefficient of the first area is greater than the weight coefficient of the second area and greater than the weight coefficient of the third area. According to the overlap of the monitoring data in the historical monitoring data subset, the second correlation value is determined, and the weight coefficient is determined in combination with the tunnel area, which further refines the correlation between the historical monitoring data and the traffic impact, and fully considers the brightness impact problem in different areas. Then, according to the product of the first correlation value, the second correlation value and the weight coefficient, the correlation corresponding to each historical monitoring data is determined, so as to obtain the traffic impact data of the tunnel to be detected based on the correlation screening. The traffic impact data is then marked so that the digital twin model can track and monitor the traffic impact data based on the mark. By filtering out the traffic impact data based on the degree of association, we can more accurately focus on the factors that have a significant impact on tunnel traffic and improve the pertinence of monitoring and analysis. The traffic impact data is marked so that the digital twin model can track and monitor based on the mark, which can reflect the changes in tunnel traffic conditions in real time, helping to identify problems and take measures in a timely manner.

[0086] Further, in one or more embodiments of the present specification, the determining of the first weight value of each historical monitoring data in each historical monitoring data subset based on the subjective and objective weighting method specifically includes the following process:

[0087] First, based on the preset interface, the subjective weight sorting sequence of each expert terminal for each historical monitoring data is received. By receiving the subjective weight sorting sequence of each expert terminal through the preset interface, the knowledge and experience of multiple experts can be fully utilized to reduce the influence of individual subjective bias. Then, the scale value of each adjacent historical monitoring data in each subjective weight sorting sequence is determined according to the preset proportional scale, so as to construct the subjective judgment matrix corresponding to each historical monitoring data in the historical monitoring data subset based on the transfer of the scale value. The information entropy of each historical monitoring data in the historical monitoring data subset is obtained to determine the objective weight corresponding to each historical monitoring data according to the information entropy. By using the information entropy to determine the objective weight of each historical monitoring data, the information content and uncertainty of the data itself can be reflected. Based on the linear weighting of the subjective judgment matrix and the objective weight, the first weight value of each historical monitoring data in the historical monitoring data subset is determined after effectively integrating the subjective and objective information.

[0088] S106: If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events corresponding to the area where the traffic impact data is located are predicted and deduced based on the digital twin model to determine the traffic risks of each area.

[0089] By tracking and monitoring traffic impact data through the digital twin model, information on traffic conditions can be obtained in real time. Once it is found that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events in the area where the traffic impact data is located are predicted and deduced based on the digital twin model, so as to understand the development trend of traffic events such as traffic flow, speed, congestion, etc. in advance, determine the traffic risks in each area, and enable the traffic dispatch unit to plan and adjust the traffic strategy in a targeted manner.

[0090] Specifically, in one or more embodiments of this specification, if it is determined that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events corresponding to the area where the traffic impact data is located are predicted and deduced based on the digital twin model to determine the traffic risk of each area, specifically including:

[0091] If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, then the change information of the traffic impact data and the tunnel area corresponding to the traffic impact data are obtained, so that the digital twin model simulates the traffic impact data according to the change information and obtains the preview results of the area where the traffic impact data is located. Among them, the preview results include the probability of occurrence of one or more traffic events. Then, the event risk level corresponding to the traffic event is determined according to the probability of occurrence corresponding to each traffic event. Then, according to the number of traffic events in each area and the event risk level of each traffic event, the traffic risk of each area is comprehensively evaluated and determined. By predicting and evaluating traffic risks in advance, preventive measures can be taken to avoid or reduce the occurrence of traffic accidents. In addition, dynamic adjustments and optimizations can be made based on real-time monitoring data to adapt to different traffic conditions and needs.

[0092] like Figure 2 As shown, the embodiment of this specification provides a schematic diagram of the internal structure of a tunnel monitoring device based on digital twins. Figure 2 It can be seen that in one or more embodiments of this specification, a tunnel monitoring device based on digital twins includes:

[0093] at least one processor; and,

[0094] a memory communicatively connected to the at least one processor; wherein,

[0095] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: execute any of the above-mentioned methods.

[0096] like Figure 3 As shown, the embodiment of this specification provides a schematic diagram of the internal structure of a non-volatile storage medium. Figure 3 It can be seen that in one or more embodiments of the present specification, a non-volatile storage medium stores computer executable instructions 301, and the computer executable instructions 301 can execute any of the above-mentioned methods.

[0097] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0098] The above specific embodiments of this specification are described. In some cases, the actions or steps recorded in this specification can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0099] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification should be included in the scope of this specification.

Claims

1. A tunnel monitoring method based on digital twins, characterized in that: The method comprises: Dividing the area into a first area, a second area, and a third area according to the brightness change of the tunnel to be detected, so as to obtain three-dimensional point cloud data of the first area, the second area, and the third area; Determine and establish static components and dynamic components of the tunnel to be inspected based on the three-dimensional point cloud data, so as to construct a first-layer three-dimensional model based on the static components and a second-layer three-dimensional model based on the dynamic components; Aligning the first layer of three-dimensional model with the second layer of three-dimensional model based on the point cloud positions of the three-dimensional point cloud data to obtain a dynamic three-dimensional model of the tunnel to be inspected; Acquire the position information of each monitoring device in the tunnel to be detected, and nest and associate the monitoring parameters of the monitoring device with the three-dimensional model based on the position information to obtain the digital twin model of the tunnel to be detected; Determine the traffic impact data of the tunnel to be detected based on the correlation between the historical monitoring data of the tunnel to be detected and the historical traffic events, and track and monitor the traffic impact data based on the digital twin model; If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events corresponding to the area where the traffic impact data is located are predicted and deduced based on the digital twin model to determine the traffic risks of each area; Based on the correlation between the historical monitoring data of the tunnel to be detected and the historical traffic events, traffic impact data of the tunnel to be detected is determined, and the traffic impact data is tracked and monitored based on the digital twin model, specifically including: Determine the historical monitoring data corresponding to each historical traffic event, group the historical monitoring data according to the event type corresponding to each historical traffic event, and obtain a set of historical monitoring data corresponding to each event type; Based on the event risk level corresponding to each historical monitoring data in the historical monitoring data set, the historical monitoring data set is secondary grouped to obtain a subset of historical monitoring data corresponding to each event risk level; Determining a first correlation value of each historical monitoring data in each of the historical monitoring data subsets based on a subjective and objective weighting method; Determine the second correlation value of each historical monitoring data according to the overlap of the monitoring data in each subset of the historical monitoring data, and determine the tunnel area corresponding to each historical monitoring data, so as to determine the weighting coefficient of each historical monitoring data based on the tunnel area; wherein the weighting coefficient of the first area is greater than the weighting coefficient of the second area, which is greater than the weighting coefficient of the third area; Determine the correlation corresponding to each of the historical monitoring data according to the product of the first correlation value, the second correlation value and the weighting coefficient, so as to obtain the traffic impact data of the tunnel to be detected by screening based on the correlation; Marking the traffic impact data so that the digital twin model tracks and monitors the traffic impact data based on the marking; Determining the first weight value of each historical monitoring data in each subset of the historical monitoring data based on a subjective and objective weighting method specifically includes: Receive, based on a preset interface, a subjective weight ranking sequence of each of the historical monitoring data from each expert terminal; Determine the scale value of adjacent historical monitoring data in each subjective weight sorting sequence based on a preset ratio scale, so as to determine the subjective judgment matrix corresponding to each historical monitoring data in the historical monitoring data subset based on the scale value; Obtaining information entropy of each historical monitoring data in the historical monitoring data subset, so as to determine the objective weight corresponding to each historical monitoring data according to the information entropy; Based on the linear weighting of the subjective judgment matrix and the objective weight, a first weight value of each historical monitoring data in the historical monitoring data subset is determined.

2. According to a tunnel monitoring method based on digital twinning according to claim 1, it is characterized in that: The step of performing area division according to the brightness change of the tunnel to be detected to obtain the first area, the second area and the third area specifically includes: Acquire the sunrise time and sunset time of the tunnel to be detected, so as to determine the low illumination time range and the high illumination time range of the tunnel to be detected based on the sunrise time and the sunset time; If the current time is in a high illumination time range, the tunnel entrance image and the tunnel exit image are acquired based on a preset image acquisition device; Performing grayscale processing on the tunnel entrance image and the tunnel exit image to obtain a tunnel entrance grayscale image and a tunnel exit grayscale image, so as to determine the brightness value of each pixel in the tunnel entrance grayscale image and the tunnel exit grayscale image; Determine a difference in brightness values ​​of adjacent pixels in the grayscale image of the tunnel entrance and the grayscale image of the tunnel exit, and determine a sudden pixel point in the grayscale image of the tunnel entrance and the grayscale image of the tunnel exit based on the difference; Determine a region boundary between the grayscale image of the tunnel entrance and the grayscale image of the tunnel exit according to the position of the sudden pixel point, so as to respectively determine a high brightness region and a low brightness region of the grayscale image of the tunnel entrance, and a high brightness region and a low brightness region of the grayscale image of the tunnel exit according to the region boundary; Merging the low brightness area with the inner area of ​​the tunnel to be detected as a first area, taking the high brightness area of ​​the grayscale image of the tunnel entrance as a second area, and taking the high brightness area of ​​the grayscale image of the tunnel exit as a third area; If the current time is in a low illumination time range, the inner area of ​​the tunnel to be detected and the outer area of ​​the tunnel to be detected are taken as the first area.

3. The tunnel monitoring method based on digital twin according to claim 1 is characterized in that: Acquiring three-dimensional point cloud data of the first area, the second area, and the third area specifically includes: Acquire initial three-dimensional point cloud data of the first area, the second area, and the third area according to a preset point cloud acquisition device of the tunnel to be inspected; Training a point cloud completion model based on the historical point cloud data of the tunnel to be inspected to obtain a point cloud completion model that meets the requirements; The initial three-dimensional point cloud data is input into the point cloud completion model that meets the requirements to complete the initial three-dimensional point cloud data and obtain three-dimensional point cloud data of the first area, the second area and the third area.

4. The tunnel monitoring method based on digital twin according to claim 1 is characterized in that: Determining and establishing static components and dynamic components of the tunnel to be inspected based on the three-dimensional point cloud data, so as to construct a first-layer three-dimensional model based on the static components and a second-layer three-dimensional model based on the dynamic components, specifically includes: Determine the fixed static components of the tunnel to be detected based on the architectural data of the tunnel to be detected; Extracting moving three-dimensional point cloud data in the three-dimensional point cloud data based on the position coordinates of the three-dimensional point cloud data in adjacent time periods, so as to establish a dynamic component of the tunnel to be detected based on the moving three-dimensional point cloud data; Determining a newly added static component corresponding to the three-dimensional point cloud data based on a matching relationship between the remaining three-dimensional point cloud data outside the moving three-dimensional point cloud data and the fixed static component; Determine the geometric features of the fixed static component and the newly added static component according to the three-dimensional point cloud data corresponding to the fixed static component and the newly added static component, so as to construct a first-layer three-dimensional model based on the geometric features; wherein the geometric features include: point position, normal vector, and curvature; A second-layer three-dimensional model is constructed according to the position coordinates corresponding to the three-dimensional point cloud data of the dynamic component.

5. The tunnel monitoring method based on digital twin according to claim 1 is characterized in that: Acquiring the location information of each monitoring device in the tunnel to be detected, and nesting and associating the monitoring parameters of the monitoring device with the three-dimensional model based on the location information to obtain the digital twin model of the tunnel to be detected, specifically including: Acquire the position information of each monitoring device in the tunnel to be detected, and determine a first coordinate system corresponding to the position information; Based on the difference data between the first coordinate system and the second coordinate system corresponding to the three-dimensional model, a conversion relationship between the first coordinate system and the second coordinate system is established, and based on the conversion relationship, the position information is converted to the second coordinate system to obtain the current position information; wherein the conversion relationship includes at least one or more of the following: a translation relationship, a rotation relationship, and a scaling relationship; The current position information is mapped to the corresponding position of the three-dimensional model, and the monitoring parameters of the monitoring device are nested and associated with the corresponding current position information, a data connection is established between the monitoring device and the three-dimensional model, and a digital twin model of the tunnel to be detected is obtained.

6. The tunnel monitoring method based on digital twin according to claim 1, characterized in that: If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, one or more traffic events corresponding to the area where the traffic impact data is located are predicted and deduced based on the digital twin model to determine the traffic risks of each area, specifically including: If it is determined that the traffic impact data exceeds the preset standard traffic parameter range, then obtaining the change information of the traffic impact data and the tunnel area corresponding to the traffic impact data, so that the digital twin model simulates the traffic impact data according to the change information, and obtains the preview result of the area where the traffic impact data is located; wherein the preview result includes the probability of occurrence of one or more traffic events; Determining the event risk level corresponding to the traffic event according to the occurrence probability corresponding to each of the traffic events; The traffic risk of each area is determined based on the number of traffic incidents in each area and the event risk level of each traffic incident.

7. A tunnel monitoring device based on digital twin, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: execute any of the methods described in claims 1-6.

8. A non-volatile storage medium storing computer executable instructions, wherein the computer executable instructions can: execute the method according to any one of claims 1 to 6.

Images