Tunnel pavement disease prediction system based on digital twinborn technology and construction method thereof

Abstract

The invention relates to the technical field of tunnel disease detection, in particular to a tunnel pavement disease prediction system based on a digital twinborn technology and a construction method thereof, and a tunnel digital module is used for constructing a digital twinborn model; the pavement disease updating module is used for constructing a digital twinborn database and updating twinborn pavement information of a digital twinborn model; the disease prediction module constructs a tunnel disease development model based on the pavement disease information in the digital twinborn model and the digital twinborn database, and is used for predicting the formation and development degree of tunnel pavement diseases; and the pavement condition visualization module displays the real-time state of the tunnel pavement and the information of the digital twinborn model based on the pavement disease updating module and the disease prediction module. A virtual model corresponding to an entity tunnel is created, and pavement disease formation and development are monitored, analyzed and predicted under the condition that tunnel operation is not affected; the intelligent and automatic level of tunnel management is optimized, and the safety and reliability of tunnel operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel disease detection, and in particular to a tunnel pavement disease prediction system based on digital twin technology and a construction method thereof. Background Art

[0002] Tunnel pavement, as the "face project" of tunnel construction, directly provides a driving interface for travelers. Its performance largely determines the operational safety and driving comfort of the tunnel. To achieve long-life service of tunnel pavement, in addition to the long life of the structural material itself, scientific management and maintenance are equally important. At present, research on the service status of long-life pavement throughout its life cycle is almost blank. How to accurately collect the service status data of the pavement structure, from the inside to the surface, to achieve intelligent perception of road structure safety and functional status throughout the life cycle and multi-source fusion warning, is one of the key issues that need to be urgently solved for the safe operation of long-life tunnel pavement. Therefore, timely detection of tunnel pavement defects and taking timely and correct maintenance measures are of great significance to extending the performance of tunnel pavement.

[0003] Traditional tunnel pavement detection has the following problems: (1) It is impossible to predict and judge in advance whether tunnel pavement damage will occur and the extent of the damage; (2) The static model of tunnel pavement detection built from historical data will continue to lose accuracy as it is put into use, and will eventually become completely ineffective. Summary of the invention

[0004] The present invention provides a tunnel pavement disease prediction system based on digital twin technology and a construction method thereof, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: A tunnel pavement disease prediction system based on digital twin technology, including: Tunnel digital module, used to build a digital twin model corresponding to the physical tunnel pavement; A pavement disease update module, used to collect tunnel pavement information and build a digital twin database, and update the twin pavement information of the digital twin model; A disease prediction module, which constructs a tunnel disease development model based on the digital twin model and the pavement disease information in the digital twin database, so as to predict the formation and development degree of tunnel pavement diseases; A pavement condition visualization module displays the real-time status of the tunnel pavement and the information of the digital twin model based on the pavement disease update module and the disease prediction module.

[0006] Furthermore, the pavement disease update module collects tunnel pavement information based on an IoT sensing system, wherein the IoT sensing system includes a temperature and humidity sensor, a strain sensor, a deformation joint displacement meter, an exhaust smoke sensor, a weighing system, and a video monitoring system; The temperature and humidity sensor is used to monitor the temperature and humidity parameters of the tunnel in service, the strain sensor is used to monitor the structural response parameters of the tunnel in service, the deformation joint displacement meter sensor is used to monitor the deformation parameters of the tunnel deformation joint, the exhaust gas and dust sensor is used to monitor the distribution of smoke and exhaust gas during the entire life cycle of the tunnel, the weighing system and the video monitoring system respectively detect the weight and number of axles of passing vehicles in the tunnel, and cooperate with the load sensor to monitor the axle load parameters of the tunnel in service.

[0007] Furthermore, the digital twin model includes a tunnel geometric model and a tunnel physical model, the tunnel geometric model includes spatial information of the tunnel and its road surface, and the tunnel physical model includes material properties and mechanical characteristics of the tunnel and its road surface.

[0008] Furthermore, the tunnel geometry model is set as an overall model including the tunnel pavement structure, the tunnel inner wall structure, the pavement layer structure and the leveling layer structure, which includes the tunnel pavement and the surrounding walls; The tunnel physical model is constructed by introducing material properties and tunnel mechanical properties based on the tunnel geometric model, and the digital twin model is obtained by associating the tunnel spatial conditions and physical and mechanical characteristics based on the dynamic mathematical approximate simulation of the tunnel physical model.

[0009] Furthermore, the tunnel digital module also includes a disease rule attribute model, which is used to analyze the real-time pavement disease information and compare it with the predicted information of the tunnel disease development model, and trigger the repair mechanism when the difference between the two is large; The tunnel disease development model is constructed based on the digital twin model and the pavement disease data analyzed by the disease rule attribute model, and the repair mechanism evaluates the actual condition of the pavement disease by artificially using prior knowledge to analyze and correct the tunnel disease development model.

[0010] Furthermore, the defect rule attribute model is established based on the rules summarized by the historical pavement defect information data in the digital twin database, as well as the standards and specifications in the tunnel field; The defect rule attribute model not only includes tunnel spatial information and mechanical characteristics associated with pavement defects, but also includes time information on the generation and development of pavement defects, which is used to guide the tunnel defect development model to understand and predict the formation and development of pavement defects.

[0011] A method for constructing a tunnel pavement defect prediction system based on digital twin technology, which is applied to the above-mentioned tunnel pavement defect prediction system based on digital twin technology, comprises the following steps: Construct tunnel digital modules based on tunnel physical space, digital space and twin data; Based on various monitoring devices deployed in the tunnel, a full-area and full-time IoT sensing system is established, and a road surface disease update module is constructed by associating the tunnel digital module; Building a disease prediction module based on the twin road surface advance development information obtained from the tunnel digital module and the road surface disease rule attributes; Based on the tunnel digital module and the IoT sensing system, the real-time information of the tunnel pavement and the twin pavement information are used to construct a pavement condition visualization module.

[0012] Furthermore, the digital twin model is constructed in the tunnel digital module. Specifically, based on Revit three-dimensional modeling and rendering software, a lightweight structural model is constructed according to the tunnel design drawings. Then, a hierarchical modeling method is adopted to model the tunnel wall, pavement layer, leveling layer, etc. The mechanical properties of the tunnel are dynamically simulated by mathematical approximation through the modeling software to reflect the spatial conditions and physical and mechanical characteristics of the tunnel. Based on the rules summarized from historical correlation data and the standards and specifications in the tunnel field, a defect rule attribute model is established.

[0013] Furthermore, the digital twin database is constructed based on the historical monitoring data of the tunnel entity collected by the IoT sensing system, and the pavement disease update module is constructed by associating the digital twin database with the digital twin model; The digital twin database is automatically updated based on the real-time monitoring data of the tunnel entity collected by the IoT sensing system, and the tunnel entity disease status information in the real-time monitoring data is automatically updated to the digital twin model.

[0014] Furthermore, based on the IoT sensing system, the real-time monitoring data of the tunnel entity is transmitted to the disease rule attribute model in the tunnel digital module, and the disease rule attribute model compares the pavement disease information of the tunnel entity with the prediction information of the tunnel disease development model. If the actual index differs greatly from the prediction index, the tunnel disease development model is manually corrected; The disease rule attribute model has a deep learning function. As the tunnel operation time increases, the formation and development rules of road surface diseases are summarized and added to the disease rule attribute model.

[0015] The beneficial effects of the present invention are: The present invention discloses a tunnel pavement disease prediction system based on digital twin technology and its construction method, and realizes accurate prediction and management of tunnel pavement diseases through digital twin technology. Digital twin technology specifically creates a virtual model corresponding to the physical tunnel, and cooperates with a full-domain and full-time IoT perception system composed of various types of sensors deployed at key positions of the physical tunnel to monitor, analyze and predict the formation and development of pavement diseases without affecting the operation of the tunnel; optimizes the intelligence and automation level of tunnel management, and improves the safety and reliability of tunnel operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a schematic diagram of the operating framework of the tunnel pavement disease prediction system in the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0021] The present invention discloses a tunnel pavement disease prediction system based on digital twin technology and its construction method, and realizes accurate prediction and management of tunnel pavement diseases through digital twin technology. Digital twin technology specifically creates a virtual model corresponding to the physical tunnel, and cooperates with a full-domain and full-time IoT perception system composed of multiple types of sensors deployed at key locations of the physical tunnel, so as to monitor, analyze and predict the formation and development of pavement diseases without affecting the operation of the tunnel.

[0022] Embodiment 1 In this embodiment, the tunnel pavement disease prediction system based on digital twin technology includes: The tunnel digital module is used to build a digital twin model corresponding to the physical tunnel pavement; the pavement disease update module is used to collect tunnel pavement information and build a digital twin database, and at the same time update the twin pavement information of the digital twin model; the disease prediction module builds a tunnel disease development model based on the digital twin model and the pavement disease information in the digital twin database, which is used to predict the formation and development degree of tunnel pavement diseases; the pavement condition visualization module displays the real-time status of the tunnel pavement and the information of the digital twin model based on the pavement disease update module and the disease prediction module.

[0023] During the specific implementation process, by establishing a mapping relationship between the tunnel entity and the tunnel model, a digital twin model of the tunnel characteristics is constructed, and the Internet of Things technology is used to build a pavement disease update module. The tunnel entity monitoring data is updated in real time in the digital twin model and digital twin database, to achieve the precise establishment of the digital twin model and the precise mapping of the full amount of data, ensuring that the disease prediction module predicts the formation and development of tunnel diseases with credibility and reference value.

[0024] In this embodiment, the pavement disease update module collects tunnel pavement information based on the Internet of Things sensing system. The Internet of Things sensing system includes temperature and humidity sensors, strain sensors, deformation joint displacement meters, exhaust gas and dust sensors, weighing systems and video monitoring systems; the temperature and humidity sensors are used to monitor the temperature and humidity parameters of the tunnel in service, the strain sensors are used to monitor the structural response parameters of the tunnel in service, and the pavement structure damage and performance degradation are analyzed later to find vulnerable sections and improve maintenance efficiency. The deformation joint displacement meter sensor is used to monitor the deformation parameters of the tunnel deformation joint, and the exhaust gas and dust sensor is used to monitor the distribution of dust and exhaust gas throughout the life cycle of the tunnel. The weighing system and the video monitoring system respectively detect the weight and number of axles of passing vehicles in the tunnel, and cooperate with the load sensor to monitor the axle load parameters of the tunnel in service.

[0025] Multi-source perception is the prerequisite for the construction of digital twin models. By deploying various types of sensors at key locations on the tunnel pavement, a full-domain and full-time IoT perception system is established to accurately monitor the service status of the tunnel in multiple dimensions and at multiple levels. Massive data such as images, videos, and various operation monitoring indicators can be fully acquired to achieve all-round perception of the environment, traffic loads, stress conditions, exhaust gas, etc., and obtain the full-domain and full-volume operation data of the tunnel in real time, providing a data foundation for the tunnel digital twin.

[0026] The evolution of tunnel service status is very complex. To accurately understand the tunnel service status, it is necessary to keep track of the overall development and subtle changes of the tunnel's key service parameters and realize the synchronous operation of the tunnel model and the tunnel entity in the twin environment. Through IoT perception, digital mapping and multi-dimensional modeling technology, the digital twin model is accurately established and the full amount of data is accurately mapped. At the same time, the pavement disease update module and the disease prediction module are optimized to enable the digital twin model to accurately simulate the tunnel service status, ensuring that the tunnel disease development model predicts the formation and development of tunnel diseases with credibility and reference.

[0027] In this embodiment, the digital twin model includes a tunnel geometric model and a tunnel physical model. The tunnel geometric model includes spatial information of the tunnel and its road surface, and the tunnel physical model includes material properties and mechanical characteristics of the tunnel and its road surface.

[0028] Among them, the tunnel geometric model is set as an overall model consisting of tunnel pavement structure, tunnel wall structure, pavement layer structure and leveling layer structure, including tunnel pavement and surrounding walls; the tunnel physical model is constructed based on the tunnel geometric model by introducing material properties and tunnel mechanical properties. The digital twin model is based on the dynamic mathematical approximate simulation of the tunnel physical model, and is obtained by associating the tunnel spatial conditions and physical and mechanical characteristics.

[0029] The tunnel digital module includes the tunnel geometry-physical model and the disease rule attribute model. Among them, the tunnel geometry uses modeling software to build a lightweight structural model according to the design drawings, mainly including the modeling of the tunnel wall, tunnel pavement, leveling layer, etc., which is used to reflect the spatial conditions of the tunnel; the tunnel physical characteristic model is composed of models that describe basic mechanical properties, including mechanical indicators mainly based on vertical compressive stress and transverse tensile stress, which are used to reflect physical and mechanical characteristics; the tunnel disease rule attribute model is established according to relevant theories and national standards in the tunnel field, including design theory, relevant local standards, maintenance theory and other theoretical knowledge. Its role is to provide theoretical support for the systematic analysis of possible diseases that may occur in the tunnel pavement in the future.

[0030] The performance status of tunnel pavement will change with the service time. The pavement disease update module continuously updates the disease data to reflect its actual performance status, and regularly outputs the type, location, degree and other information of the disease and incorporates it into the database. Sensors installed in the tunnel pavement are used to monitor key performance indicators in real time, such as stress and deformation, to detect abnormal conditions in time and record them; vehicles and their traffic information are collected through weighing systems and video monitoring systems as a supplement to disease data. Combined with the analysis of disease data over the years, the performance status and development trend of the tunnel pavement can be better understood, which is conducive to predicting the risks and hidden dangers that the tunnel pavement may face.

[0031] In this embodiment, the tunnel digital module also includes a disease rule attribute model, which is used to parse real-time pavement disease information and compare it with the predicted information of the tunnel disease development model, and trigger the correction mechanism when the difference between the two is large; the tunnel disease development model is constructed based on the digital twin model and the pavement disease data analyzed by the disease rule attribute model, and the correction mechanism evaluates the actual condition of the pavement disease through artificial use of prior knowledge and corrects the tunnel disease development model.

[0032] Furthermore, the defect rule attribute model is established based on the rules summarized by the historical pavement disease information data in the digital twin database, as well as the standards and specifications in the tunnel field; the defect rule attribute model not only includes the tunnel spatial information and mechanical characteristics associated with pavement diseases, but also includes the time information of the generation and development of pavement diseases, which is used to guide the tunnel disease development model to understand and predict the formation and development of pavement diseases.

[0033] Embodiment 2 The present invention discloses a method for constructing a tunnel pavement disease prediction system based on digital twin technology, comprising the following steps: A tunnel digital module is constructed based on the tunnel's physical space, digital space and twin data. A full-domain and full-time IoT perception system is established based on a variety of monitoring equipment installed in the tunnel, and a pavement disease update module is constructed by associating the tunnel digital module. A disease prediction module is constructed based on the twin pavement advance development information obtained from the tunnel digital module and the regular attributes of pavement diseases. A pavement condition visualization module is constructed based on the tunnel digital module and the IoT perception system, combining the real-time information of the tunnel pavement and the twin pavement information.

[0034] Among them, a digital twin model is constructed in the digital module of the tunnel. Specifically, based on the Revit 3D modeling and rendering software, a lightweight structural model is constructed according to the tunnel design drawings, and then the layered modeling method is used to model the tunnel wall, pavement layer, leveling layer, etc.; specifically, the simplified modeling of the main structures such as the tunnel wall, pavement, and leveling layer is carried out. After the model construction is completed, the model is exported to the Obj format, and the model is imported into Unity3D in the form of a resource file. In Unity3D, the satellite image data of the model and the real physical world are loaded into the scene, and the surrounding terrain, waters and other geographical environments are constructed based on satellite images. Texture mapping is performed on the tunnel to complete the construction of the twin scene; the dynamic mathematical approximate simulation of the mechanical properties of the tunnel is carried out through the modeling software to reflect the spatial conditions and physical and mechanical characteristics of the tunnel; Based on the rules summarized from historical correlation data and the standards and specifications in the tunnel field, a defect rule attribute model is established.

[0035] Furthermore, a digital twin database is constructed based on the historical monitoring data of the tunnel entity collected by the IoT sensing system, and a pavement disease update module is constructed by associating the digital twin database and the digital twin model; the digital twin database is automatically updated based on the real-time monitoring data of the tunnel entity collected by the IoT sensing system, and the tunnel entity disease status information in the real-time monitoring data is automatically updated to the digital twin model.

[0036] In the specific implementation process, firstly, a data online update module is established, and the Internet of Things technology is used to transmit the disease data to the digital twin database in the form of messages, and the system data is updated in real time; secondly, a pavement disease update module is established. Based on the IoT sensing system, the disease data is detected and the data of the digital twin model is updated in real time; at the same time, the uploaded real-time tunnel pavement disease information is input into the rule attribute model of the tunnel digital module. The real-time disease information includes the disease type, disease size, and disease location detection indicators.

[0037] Based on the Internet of Things perception system, the real-time monitoring data of the tunnel entity is transmitted to the disease rule attribute model in the tunnel digital module. The disease rule attribute model compares the pavement disease information of the tunnel entity with the predicted information of the tunnel disease development model. If the actual indicators are significantly different from the predicted indicators, the tunnel disease development model is manually corrected. The disease rule attribute model has a deep learning function. As the tunnel operation time increases, the formation and development laws of pavement diseases are summarized and added to the disease rule attribute model.

[0038] Among them, the tunnel rule attribute model compares the physical detection index of the pavement condition with the corresponding virtual entity index obtained by the twin calculation. If the physical detection index of the pavement condition differs greatly from the corresponding virtual entity index, the disease rule attribute model is triggered to use the relevant local standards, maintenance theory and other prior knowledge for analysis, accurately evaluate the physical pavement condition and correct the virtual entity operation program, delete the data that was previously calculated incorrectly or has expired in the digital twin model, and upload new physical detection indicators at the same time; thus, the pavement disease update module is established to form a logical closed loop of the tunnel pavement detection system. At the same time, the system reminds the staff to calibrate the disease prediction module; Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A tunnel pavement disease prediction system based on digital twin technology, characterized in that: include: Tunnel digital module, used to build a digital twin model corresponding to the physical tunnel pavement; A pavement disease update module, used to collect tunnel pavement information and build a digital twin database, and update the twin pavement information of the digital twin model; A disease prediction module, which constructs a tunnel disease development model based on the digital twin model and the pavement disease information in the digital twin database, so as to predict the formation and development degree of tunnel pavement diseases; A pavement condition visualization module displays the real-time status of the tunnel pavement and the information of the digital twin model based on the pavement disease update module and the disease prediction module.

2. The tunnel pavement disease prediction system based on digital twin technology according to claim 1 is characterized in that: The pavement disease update module collects tunnel pavement information based on the IoT sensing system, which includes a temperature and humidity sensor, a strain sensor, a deformation joint displacement meter, an exhaust smoke sensor, a weighing system and a video monitoring system; The temperature and humidity sensor is used to monitor the temperature and humidity parameters of the tunnel in service, the strain sensor is used to monitor the structural response parameters of the tunnel in service, the deformation joint displacement meter sensor is used to monitor the deformation parameters of the tunnel deformation joint, the exhaust gas and dust sensor is used to monitor the distribution of smoke and exhaust gas during the entire life cycle of the tunnel, the weighing system and the video monitoring system respectively detect the weight and number of axles of passing vehicles in the tunnel, and cooperate with the load sensor to monitor the axle load parameters of the tunnel in service.

3. The tunnel pavement disease prediction system based on digital twin technology according to claim 1 is characterized in that: The digital twin model includes a tunnel geometric model and a tunnel physical model. The tunnel geometric model includes spatial information of the tunnel and its road surface, and the tunnel physical model includes material properties and mechanical characteristics of the tunnel and its road surface.

4. The tunnel pavement disease prediction system based on digital twin technology according to claim 3 is characterized in that: The tunnel geometric model is set to be an overall model including the tunnel pavement structure, the tunnel inner wall structure, the pavement layer structure and the leveling layer structure, which includes the tunnel pavement and the surrounding wall; The tunnel physical model is constructed by introducing material properties and tunnel mechanical properties based on the tunnel geometric model, and the digital twin model is obtained by associating the tunnel spatial conditions and physical and mechanical characteristics based on the dynamic mathematical approximate simulation of the tunnel physical model.

5. The tunnel pavement disease prediction system based on digital twin technology according to claim 1 is characterized in that: The tunnel digital module also includes a disease rule attribute model, which is used to analyze the real-time road surface disease information and compare it with the predicted information of the tunnel disease development model, and trigger the repair mechanism when the difference between the two is large; The tunnel disease development model is constructed based on the digital twin model and the pavement disease data analyzed by the disease rule attribute model, and the repair mechanism evaluates the actual condition of the pavement disease by artificially using prior knowledge to analyze and correct the tunnel disease development model.

6. The tunnel pavement disease prediction system based on digital twin technology according to claim 5 is characterized in that: The disease rule attribute model is established based on the rules summarized by the historical pavement disease information data in the digital twin database, as well as the standards and specifications in the tunnel field; The defect rule attribute model not only includes tunnel spatial information and mechanical characteristics associated with pavement defects, but also includes time information on the generation and development of pavement defects, which is used to guide the tunnel defect development model to understand and predict the formation and development of pavement defects.

7. A method for constructing a tunnel pavement disease prediction system based on digital twin technology, characterized in that: The tunnel pavement disease prediction system based on digital twin technology applied to any one of claims 1 to 6 above comprises the following steps: Construct tunnel digital modules based on tunnel physical space, digital space and twin data; Based on various monitoring devices deployed in the tunnel, a full-area and full-time IoT sensing system is established, and a road surface disease update module is constructed by associating the tunnel digital module; Building a disease prediction module based on the twin road surface advance development information obtained from the tunnel digital module and the road surface disease rule attributes; Based on the tunnel digital module and the IoT sensing system, the real-time information of the tunnel pavement and the twin pavement information are used to construct a pavement condition visualization module.

8. The method for constructing a tunnel pavement defect prediction system based on digital twin technology according to claim 7, characterized in that: The digital twin model is constructed in the tunnel digital module. Specifically, based on the Revit three-dimensional modeling and rendering software, a lightweight structural model is constructed according to the tunnel design drawings. Then, a hierarchical modeling method is adopted to model the tunnel wall, pavement layer, leveling layer, etc. The mechanical properties of the tunnel are dynamically simulated by mathematical approximation through the modeling software to reflect the spatial conditions and physical and mechanical characteristics of the tunnel. Based on the rules summarized from historical correlation data and the standards and specifications in the tunnel field, a defect rule attribute model is established.

9. The method for constructing a tunnel pavement defect prediction system based on digital twin technology according to claim 7, characterized in that: Building the digital twin database based on the historical monitoring data of the tunnel entity collected by the IoT sensing system, and building the pavement disease update module by associating the digital twin database with the digital twin model; The digital twin database is automatically updated based on the real-time monitoring data of the tunnel entity collected by the IoT sensing system, and the tunnel entity disease status information in the real-time monitoring data is automatically updated to the digital twin model.

10. The method for constructing a tunnel pavement disease prediction system based on digital twin technology according to claim 8, characterized in that: Based on the IoT sensing system, the real-time monitoring data of the tunnel entity is transmitted to the disease rule attribute model in the tunnel digital module. The disease rule attribute model compares the pavement disease information of the tunnel entity with the prediction information of the tunnel disease development model. If the actual index differs greatly from the prediction index, the tunnel disease development model is manually corrected. The disease rule attribute model has a deep learning function. As the tunnel operation time increases, the formation and development rules of road surface diseases are summarized and added to the disease rule attribute model.

Images