Tunnel structure full life cycle health condition evaluation method and system

Abstract

The invention discloses a tunnel structure full life cycle health condition evaluation method and system. The method comprises the steps of obtaining different observation node structure stress information corresponding to tunnel joints in different seasons in a tunnel in unit time; acquiring crack width and development information in a preset time period of the tunnel in unit time; for tunnel joints in different seasons, full life cycle health condition prediction models corresponding to the tunnel joints, life cycle health condition information under different geological disasters, material aging and damage information and external load and environment influence information are obtained; inputting different observation node structure stress information corresponding to the tunnel joint into a full life cycle health condition prediction model to obtain a unit time prediction full life cycle health condition corresponding to the tunnel joint; and obtaining a full life cycle health condition evaluation result. The accuracy of the evaluation result is improved.

Description

Technical Field

[0001] The present invention relates to the field of tunnel monitoring, and in particular to a method and system for evaluating the health status of a tunnel structure throughout its life cycle. Background Art

[0002] With the acceleration of urbanization and the widespread use of underground space, tunnels, as important transportation and infrastructure, have become an important task for ensuring safety and extending their service life. The life cycle health assessment method for tunnel structures aims to monitor the safety and stability of their structures in real time by comprehensively assessing the health status of tunnels at various stages such as design, construction, operation, and maintenance. The core of this method is to comprehensively assess the health status of tunnels at different life cycle stages through data collection, model building, and risk analysis, and provide a scientific basis for subsequent maintenance and reinforcement. With the development of the Internet of Things, sensing technology, and data analysis technology, the health monitoring of tunnel structures has gradually shifted from traditional manual detection methods to automated and intelligent monitoring modes. This not only improves monitoring efficiency, but also provides real-time feedback on the health status of tunnels, providing data support for engineering decisions.

[0003] However, existing tunnel health assessment technologies have certain limitations, especially when using the traditional single-dimensional risk coefficient calculation method. Traditional methods usually rely on simple risk assessment models, calculate a single risk coefficient by comprehensively considering factors such as the tunnel's structure, environment, and load, and then judge whether the tunnel is in a safe state based on the coefficient. Although this single-dimensional assessment method can provide a rapid risk assessment in some cases, it often ignores the performance of the tunnel structure in a complex environment with multiple dimensions and factors. The health of the tunnel is not only related to the degree of physical damage to the structure itself, but also closely related to many factors such as the surrounding environment, construction quality, and operating status. The single-dimensional risk assessment method is prone to misjudgment and cannot fully reflect the complexity and diversity of the tunnel's health status.

[0004] In addition, traditional single-dimensional risk assessment methods often ignore the dynamic changes of tunnel structures and the differences in different life cycle stages. The health status of tunnels will change to varying degrees over time, changes in the external environment, and changes in usage loads. Traditional methods usually only evaluate at a certain moment or under specific conditions, which is difficult to fully reflect the status changes of the tunnel throughout its life cycle, and easily leads to insufficient early warning of potential problems. Summary of the invention

[0005] The present application provides a method and system for evaluating the health status of a tunnel structure throughout its life cycle to solve the problems raised by the above-mentioned background technology.

[0006] In terms of dynamic monitoring and health, this application provides a method for evaluating the health status of a tunnel structure throughout its life cycle, including: The structural stress information of different observation nodes corresponding to the tunnel connection of different seasons in the unit time tunnel is obtained through a multi-modal mechanical monitoring sensor device preset in the unit time tunnel; wherein the structural stress information of different observation nodes includes tensile stress, compressive stress, shear stress, bending stress and torsional stress; Obtain crack width and development information of the tunnel per unit time within a preset time period with different traffic volumes; For the tunnel connections in different seasons, a full life cycle health status prediction model corresponding to the tunnel connections, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information are obtained in the edge computing gateway cloud, and the structural stress information of different observation nodes corresponding to the tunnel connections is input into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connections, and the risk coefficient of the predicted full life cycle health status in different seasons is calculated based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information; The predicted full life cycle health status in different seasons is calculated according to the risk coefficient corresponding to the predicted full life cycle health status in different seasons, and the predicted full life cycle health status evaluation result in the unit time tunnel is obtained.

[0007] In a possible implementation, inputting the structural stress information of different observation nodes corresponding to the tunnel connection into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connection includes: Inputting the structural stress information of different observation nodes into the full life cycle health status prediction model; wherein the full life cycle health status prediction model includes a structural stress type identification layer, a tensile stress feature extraction layer, a compressive stress, shear stress, bending stress feature extraction layer, a torsional stress feature extraction layer, a feature fusion layer and a full connection layer; The structural stress type recognition layer respectively recognizes the types of structural stresses in different seasons of the structural stress information of different observation nodes, obtains the type recognition results of the structural stresses in different seasons, and inputs the structural stresses in different seasons into the corresponding feature extraction layer according to the type recognition results corresponding to the structural stresses in different seasons; The tensile stress feature extraction layer extracts features of the received tensile stress to obtain dynamic monitoring and health feature indicators; The compressive stress, shear stress, and bending stress feature extraction layer extracts features of the received compressive stress, shear stress, and bending stress to obtain structural safety performance feature indicators; The torsional stress feature extraction layer extracts features from the received torsional stress to obtain characteristic indicators of the tunnel vault section; The feature fusion layer fuses the dynamic monitoring and health feature index, the structural safety performance feature index, and the tunnel vault section feature index to obtain a fused feature index; The fully connected layer performs link prediction on the fusion feature indicator through a preset link prediction rule to obtain a link prediction result corresponding to the fusion feature indicator, and feeds back the link prediction result through a preset graph neural network model to obtain a full life cycle health status predicted per unit time.

[0008] In a possible implementation, the fracture width and development information includes a visualization diagram of hydrological parameters per unit time. The risk coefficient calculation of the predicted full life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information includes: For the hydrological parameter visualization diagrams of different seasons, the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams are determined by using preset hydrological parameter level classification rules; For the predicted full life cycle health status in different seasons, the dynamic monitoring and health settlement probability corresponding to the predicted full life cycle health status are determined according to the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams in different seasons and the material aging and damage information; For the predicted full life cycle health status in different seasons, determining the structural safety performance settlement probability corresponding to the predicted full life cycle health status based on the external load and environmental impact information; For the predicted full life cycle health status in different seasons, determining the tunnel vault section settlement probability corresponding to the predicted full life cycle health status based on the life cycle health status information under different geological disasters; For the predicted full life cycle health status in different seasons, the dynamic monitoring and healthy settlement probability, structural safety performance settlement probability and tunnel vault section settlement probability corresponding to the predicted full life cycle health status are weighted through the preset weight setting rules to obtain the risk coefficient calculation corresponding to the predicted full life cycle health status.

[0009] In a possible implementation, the material aging and damage information includes the settlement height corresponding to the health status of the whole life cycle in different seasons at different hydrological parameter levels of the hydrological parameters in different seasons, and the dynamic monitoring and healthy settlement probability corresponding to the predicted health status of the whole life cycle are determined according to the hydrological parameter level corresponding to the hydrological parameter visualization diagram in different seasons and the material aging and damage information, including: Determine the target settlement height corresponding to the predicted full life cycle health status at the hydrological parameter level corresponding to the hydrological parameter visualization diagram in different seasons in the material aging and damage information; The target settlement heights in different seasons are convoluted to obtain the dynamic monitoring and healthy settlement probability.

[0010] In a possible implementation, determining the tunnel vault section settlement probability corresponding to the predicted full life cycle health status based on the life cycle health status information under different geological disasters includes: Determine whether ground cracks have occurred based on the life cycle health status information under the different geological disasters; When it is judged that it has not occurred, determining that no settlement of the tunnel crown section has occurred; When it is judged to occur, the probability of the predicted full life cycle health status occurring is determined based on the life cycle health status information under the different geological disasters, and the probability is multiplied by the preset score to obtain the settlement probability of the tunnel vault section.

[0011] In a possible implementation, the method further includes: For the tunnel connection in different seasons, load judgment is performed on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section; The load judgment information of the reinforcement section in different seasons is combined with the health status evaluation result of the whole life cycle to obtain the load judgment information of the observation point, and the load judgment information of the observation point is stored in the edge computing gateway cloud.

[0012] In a possible implementation, performing load judgment on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section includes: Obtaining a corrosion degree assessment of the connection material corresponding to the tunnel connection; The characteristic material corrosion degree of the structural stress information of different observation nodes is evaluated by using a preset structural stress information material corrosion degree evaluation rule to obtain a structural stress material corrosion degree evaluation coefficient corresponding to the structural stress information; The structural stress material corrosion degree assessment coefficient is placed after the connection material corrosion degree assessment to obtain the reinforcement section load judgment information.

[0013] In a possible implementation, the load judgment of the reinforcement section in different seasons and the health status evaluation result of the whole life cycle are used to perform load judgment to obtain the load judgment information of the observation point, including: The load judgment information of the reinforcement section in different seasons is arranged in order from top to bottom through the preset classification rules to obtain the dynamic monitoring and healthy tunnel entrance section index; The index material corrosion degree is evaluated on the full life cycle health status evaluation result by using a preset index material corrosion degree evaluation rule to obtain a structural safety performance tunnel entrance section index; wherein the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are not associated with the same tunnel risk source; Determine whether the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are the same weight influence index; When judged to be the same, a correlation analysis is performed on the fatigue damage influence range of the dynamic monitoring and healthy tunnel entrance section index and the fatigue damage influence range of the structural safety performance tunnel entrance section index, and the fatigue damage influence range whose correlation coefficient reaches a preset value is determined as the calibrated fatigue damage influence range, and a correlation analysis is performed on the steel bar corrosion degree of the dynamic monitoring and healthy tunnel entrance section index and the steel bar corrosion degree of the structural safety performance tunnel entrance section index, and the steel bar corrosion degree whose correlation coefficient reaches a preset value is determined as the calibrated steel bar corrosion degree; Construct a dynamic monitoring and health reinforcement section index and a structural safety performance reinforcement section index; the dynamic monitoring and health reinforcement section index is the same as the structural safety performance reinforcement section index, the fatigue damage influence range of the dynamic monitoring and health reinforcement section index is greater than the calibrated fatigue damage influence range, the steel bar corrosion degree of the dynamic monitoring and health reinforcement section index is greater than the calibrated steel bar corrosion degree, the tunnel risk sources of the dynamic monitoring and health reinforcement section index in different seasons are the same, and the tunnel risk source of the dynamic monitoring and health reinforcement section index is not associated in the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index; The tunnel risk sources of different seasons of the dynamic monitoring and health tunnel entrance section index are used to replace the tunnel risk sources of the dynamic monitoring and health reinforcement section index at the corresponding position to obtain the dynamic monitoring and health exit section index, and the tunnel risk sources of different seasons of the structural safety performance tunnel entrance section index are used to replace the tunnel risk sources of the structural safety performance reinforcement section index at the corresponding position to obtain the structural safety performance exit section index; The dynamic monitoring and health exit section index is convolved with the structural safety performance exit section index to obtain the load judgment information of the observation point.

[0014] In terms of structural safety performance, this application provides a tunnel structure full life cycle health status evaluation system, including: A module for acquiring structural stress information of different observation nodes, which is used to acquire structural stress information of different observation nodes corresponding to tunnel connections of different seasons in the tunnel per unit time through a preset multi-modal mechanical monitoring sensor device in the tunnel per unit time; wherein the structural stress information of different observation nodes includes tensile stress, compressive stress, shear stress, bending stress and torsional stress; A crack width and development information acquisition module is used to obtain crack width and development information of the tunnel in a preset time period with different traffic flows per unit time; A risk coefficient calculation module is used to obtain, for the tunnel connection in different seasons, a full life cycle health status prediction model corresponding to the tunnel connection, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information in the edge computing gateway cloud, and input the structural stress information of different observation nodes corresponding to the tunnel connection into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connection, and calculate the risk coefficient of the predicted full life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information; The cloud-based information storage module of the edge computing gateway is used to calculate the risk coefficient corresponding to the predicted full life cycle health status in different seasons, classify the predicted full life cycle health status in different seasons, and obtain the full life cycle health status evaluation result within a unit time tunnel. Beneficial Effects

[0015] The present application provides a method for evaluating the health status of a tunnel structure throughout its life cycle. The greatest advantage of this method is that it can realize real-time and dynamic monitoring of the health status of the tunnel structure. In particular, through the combination of intelligent sensors, Internet of Things technology and big data analysis, it can collect multi-dimensional data such as the physical state, environmental conditions, load information, etc. of the tunnel in real time, and perform intelligent processing and analysis. Compared with traditional manual detection and single evaluation methods, this method can comprehensively evaluate the health changes of the tunnel throughout its life cycle, timely discover potential safety hazards, and effectively avoid accidents caused by sudden structural damage or aging. In addition, the full life cycle evaluation not only focuses on the current health status of the tunnel, but also can combine historical data to predict trends and predict possible problems in the future, thereby providing a scientific basis for the maintenance and reinforcement of the tunnel and optimizing resource allocation. Through this method, tunnel managers can formulate maintenance, reinforcement and replacement plans in advance to ensure the long-term safe operation of the tunnel, extend its service life, and reduce maintenance costs and the occurrence of accidents. In general, the method for evaluating the health status of the tunnel structure throughout its life cycle improves the accuracy, scientificity and operability of tunnel safety management through a multi-dimensional and data-driven approach, and promotes the intelligent and refined development of tunnel construction and management. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 A schematic diagram of a process for evaluating the health status of a tunnel structure throughout its life cycle provided in an embodiment of the present application; Figure 2 A block diagram of the structure modules of a tunnel structure full life cycle health status evaluation system provided in an embodiment of the present application; DETAILED DESCRIPTION

[0018] It should be noted that, in the absence of conflict, the embodiments and features described in the embodiments of the present application may be combined with each other. The present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0019] like Figure 1 As shown, a method for evaluating the health status of a tunnel structure throughout its life cycle is provided in an embodiment of the present application, comprising: Step S101, obtaining structural stress information of different observation nodes corresponding to tunnel connections in different seasons in the unit time tunnel through a multimodal mechanical monitoring sensor device preset in the unit time tunnel; wherein the structural stress information of different observation nodes includes tensile stress, compressive stress, shear stress, bending stress and torsional stress.

[0020] Step S102: Obtain crack width and development information of the tunnel in a preset time period with different vehicle flows per unit time.

[0021] Step S103: For the tunnel connections in different seasons, a full life cycle health status prediction model, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information corresponding to the tunnel connections are obtained in the edge computing gateway cloud, and the structural stress information of different observation nodes corresponding to the tunnel connections is input into the full life cycle health status prediction model to obtain the predicted full life cycle health status per unit time corresponding to the tunnel connections, and the risk coefficient of the predicted full life cycle health status in different seasons is calculated based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information.

[0022] Step S104, the predicted full life cycle health conditions in different seasons are classified according to the risk coefficient calculation corresponding to the predicted full life cycle health conditions in different seasons to obtain a full life cycle health condition evaluation result within a unit time tunnel.

[0023] In this embodiment, as described in step S101 above, the structural stress information of different seasons and different time points in the tunnel is collected in real time through the preset multi-modal mechanical monitoring sensor device in the tunnel per unit time. These sensors are installed at each observation node of the tunnel to comprehensively monitor the structural health of the tunnel joint. Specifically, the structural stress information of the observation node includes various mechanical stresses such as tensile stress, compressive stress, shear stress, bending stress and torsion stress. Tensile stress and compressive stress mainly reflect the deformation characteristics of the tunnel structure under the action of external forces. Tensile stress stretches the structure and compressive stress compresses the structure. Especially in the early stage after tunnel excavation, these stress values ​​are crucial to assessing the safety of the tunnel. Shear stress describes the sliding and deformation between two adjacent planes inside the structure, which usually occurs in the transition area of ​​the tunnel wall or joint, and is a key consideration for the stability of the tunnel structure. Bending stress involves the response of the structure under the action of bending force, especially the tunnel roof or curved part. Monitoring of bending stress can help discover potential damage caused by uneven load or structural aging. Torsional stress mainly reflects the response of the tunnel structure when it is subjected to torsional loads. Especially when the tunnel is affected by irregular loads, torsional stress may cause local stress concentration or structural deformation. Through multimodal mechanical monitoring sensor devices, these stress information can be comprehensively collected, which can not only evaluate the health status of tunnel joints under different seasons and environmental conditions, but also effectively detect possible damage or fatigue of the tunnel structure during long-term use, providing a scientific basis for the safe operation of the tunnel.

[0024] As described in step S102 above, the crack width and development information of the tunnel per unit time in a preset time period with different vehicle flows is obtained. Specifically, the crack width and development information is obtained through the official website of the Crack Width and Development Bureau. The crack width and development information includes but is not limited to changes in temperature, humidity, wind speed and rainfall in the preset time period.

[0025] As described in the above step S103, for the tunnel connections in different seasons, the full life cycle health status prediction model corresponding to the tunnel connections, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information are obtained in the edge computing gateway cloud, and the structural stress information of different observation nodes corresponding to the tunnel connections is input into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connections, and the risk coefficient of the predicted full life cycle health status in different seasons is calculated based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information. Specifically, firstly, the target text corresponding to the tunnel connection is obtained in the edge computing gateway cloud through the evaluation of the degree of material corrosion at the connection of the tunnel; wherein, the target text includes a full life cycle health status prediction model, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information. The full life cycle health status prediction model is a pre-trained deep learning model. The material aging and damage information includes the settlement height corresponding to the full life cycle health status in different seasons under different hydrological parameter levels of hydrological parameters in different seasons. The external load and environmental impact information includes the risk coefficient calculation of hazards caused by the full life cycle health status in different seasons. The material aging and damage information and the external load and environmental impact information are obtained through experiments. The life cycle health status information under different geological disasters records the settlement type and time of each life cycle health status in the tunnel connection; then, the structural stress information of different observation nodes corresponding to the tunnel connection is input into the life cycle health status prediction model to obtain the unit time predicted life cycle health status corresponding to the tunnel connection; finally, the risk coefficient of the predicted life cycle health status in different seasons is calculated based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information. It can be understood that by calculating the risk coefficient of the predicted life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information, the risk coefficient calculation of the predicted life cycle health status in different seasons is realized in multiple dimensions, which helps to improve the accuracy of the risk coefficient calculation results, and then improve the effectiveness of the evaluation results.

[0026] As described in the above step S104, the predicted life-cycle health conditions in different seasons are classified according to the risk coefficient calculation corresponding to the predicted life-cycle health conditions in different seasons, and the life-cycle health condition evaluation result in the tunnel per unit time is obtained. Specifically, the predicted life-cycle health conditions corresponding to all tunnel connections are classified according to the calculated risk coefficients, and the predicted life-cycle health conditions with high scores are ranked in front, and the predicted life-cycle health conditions with low scores are ranked in the back. In this way, a list can be obtained to tell the staff which settlements in the tunnel per unit time are the most urgent and need to be handled as a priority. This list is the final life-cycle health condition evaluation result.

[0027] The method provided in this embodiment, on the one hand, can comprehensively obtain various structural stress information at the tunnel joint by using tensile stress, compressive stress, shear stress, bending stress and torsional stress. These different types of structural stress information complement each other, providing multi-dimensional data from macro to micro, from surface to internal, which is helpful to comprehensively identify and detect possible life cycle health conditions. On the other hand, the risk factor calculation method for predicting the health condition of the whole life cycle in different seasons integrates the information of crack width and development, life cycle health condition information under different geological disasters, material aging and damage information and external load and environmental impact information per unit time dimension, and realizes a more accurate risk assessment of each predicted life cycle health condition. The multi-dimensional risk factor calculation method improves the accuracy of risk factor calculation, helps to more scientifically determine the priority processing order of predicting the health condition of the whole life cycle, and avoids the misjudgment that may be caused by the traditional single-dimensional risk factor calculation.

[0028] In some embodiments, inputting the structural stress information of different observation nodes corresponding to the tunnel connection into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connection includes: Inputting the structural stress information of different observation nodes into the full life cycle health status prediction model; wherein the full life cycle health status prediction model includes a structural stress type identification layer, a tensile stress feature extraction layer, a compressive stress, shear stress, bending stress feature extraction layer, a torsional stress feature extraction layer, a feature fusion layer and a full connection layer; The structural stress type recognition layer respectively recognizes the types of structural stresses in different seasons of the structural stress information of different observation nodes, obtains the type recognition results of the structural stresses in different seasons, and inputs the structural stresses in different seasons into the corresponding feature extraction layer according to the type recognition results corresponding to the structural stresses in different seasons; The tensile stress feature extraction layer extracts features of the received tensile stress to obtain dynamic monitoring and health feature indicators; The compressive stress, shear stress, and bending stress feature extraction layer extracts features of the received compressive stress, shear stress, and bending stress to obtain structural safety performance feature indicators; The torsional stress feature extraction layer extracts features from the received torsional stress to obtain characteristic indicators of the tunnel vault section; The feature fusion layer fuses the dynamic monitoring and health feature index, the structural safety performance feature index, and the tunnel vault section feature index to obtain a fused feature index; The fully connected layer performs link prediction on the fusion feature indicator through a preset link prediction rule to obtain a link prediction result corresponding to the fusion feature indicator, and feeds back the link prediction result through a preset graph neural network model to obtain a full life cycle health status predicted per unit time.

[0029] The method provided in this embodiment can enable the life cycle health prediction model to identify and classify different types of structural stress information by setting a structural stress type identification layer. The accuracy of structural stress processing is improved, so that each type of structural stress information can enter the corresponding feature extraction layer, ensuring the effectiveness and accuracy of feature extraction. The feature extraction layer of each structural stress is specially designed for this type of structural stress, so that the feature information of this structural stress type can be extracted to the maximum extent, improving the prediction accuracy of the life cycle health prediction model.

[0030] In some embodiments, the crack width and development information includes a unit time hydrological parameter visualization diagram, and the risk coefficient calculation of the predicted full life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information includes: For the hydrological parameter visualization diagrams of different seasons, the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams are determined by using preset hydrological parameter level classification rules; For the predicted full life cycle health status in different seasons, the dynamic monitoring and healthy settlement probability corresponding to the predicted full life cycle health status are determined according to the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams in different seasons and the material aging and damage information; specifically, the material aging and damage information includes the settlement heights corresponding to the full life cycle health status in different seasons at different hydrological parameter levels of the hydrological parameters in different seasons. When determining the dynamic monitoring and healthy settlement probability corresponding to the predicted full life cycle health status according to the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams in different seasons and the material aging and damage information, first, the target settlement heights corresponding to the predicted full life cycle health status at the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams in different seasons are respectively determined in the material aging and damage information, and then, the target settlement heights in different seasons are convolved to obtain the dynamic monitoring and healthy settlement probability; For the predicted full life cycle health status in different seasons, determining the structural safety performance settlement probability corresponding to the predicted full life cycle health status based on the external load and environmental impact information; specifically, calculating the risk coefficient corresponding to the predicted full life cycle health status in the external load and environmental impact information as the structural safety performance settlement probability; For the predicted full life cycle health status in different seasons, the settlement probability of the tunnel vault section corresponding to the predicted full life cycle health status is determined based on the life cycle health status information under the different geological disasters; specifically, whether ground cracks have occurred is determined based on the life cycle health status information under the different geological disasters; when it is determined that it has not occurred, the risk coefficient of the full life cycle health status of the tunnel vault section is determined to be 0; when it is determined that it has occurred, the probability of occurrence of the predicted full life cycle health status is determined based on the life cycle health status information under the different geological disasters, and the probability is multiplied by a preset score to obtain the settlement probability of the tunnel vault section; wherein, when determining the probability of occurrence of the predicted full life cycle health status based on the life cycle health status information under the different geological disasters, first, the target historical full life cycle health status that is the same as the predicted full life cycle health status is determined in the life cycle health status information under the different geological disasters, and then, the number of occurrences of the target historical full life cycle health status is determined in the life cycle health status information under the different geological disasters, and finally, the ratio between the number of occurrences of the target historical full life cycle health status and the total number of occurrences of the full life cycle health status in the life cycle health status information under the different geological disasters is taken as the probability; For the predicted full life cycle health status in different seasons, the dynamic monitoring and health settlement probability, structural safety performance settlement probability and tunnel vault section settlement probability corresponding to the predicted full life cycle health status are weighted by the preset weight setting rules to obtain the risk coefficient calculation corresponding to the predicted full life cycle health status. Among them, the dynamic monitoring and health settlement probability corresponds to the dynamic monitoring and health weight, the structural safety performance settlement probability corresponds to the structural safety performance weight, and the tunnel vault section settlement probability corresponds to the tunnel vault section weight. The dynamic monitoring and health weight is greater than the tunnel vault section weight, and the structural safety performance weight is greater than the dynamic monitoring and health weight.

[0031] The method provided in this embodiment realizes the multi-dimensional calculation of the risk coefficient of the predicted health status throughout the life cycle, which helps to improve the accuracy of the risk coefficient calculation results, and further improve the effectiveness of the evaluation results.

[0032] In some embodiments, the method further comprises: For the tunnel connection in different seasons, load judgment is performed on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section; The load judgment information of the reinforcement section in different seasons is combined with the health status evaluation result of the whole life cycle to obtain the load judgment information of the observation point, and the load judgment information of the observation point is stored in the edge computing gateway cloud.

[0033] The step of performing load judgment on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section includes: Obtaining a corrosion degree assessment of the connection material corresponding to the tunnel connection; The characteristic material corrosion degree of the structural stress information of different observation nodes is evaluated by using a preset structural stress information material corrosion degree evaluation rule to obtain a structural stress material corrosion degree evaluation coefficient corresponding to the structural stress information; The structural stress material corrosion degree assessment coefficient is placed after the connection material corrosion degree assessment to obtain the reinforcement section load judgment information.

[0034] The load judgment information of the reinforcement section in different seasons is subjected to load judgment with the health status evaluation result of the whole life cycle to obtain the load judgment information of the observation point, including: The load judgment information of the reinforcement section in different seasons is arranged in order from top to bottom through the preset classification rules to obtain the dynamic monitoring and healthy tunnel entrance section index; The index material corrosion degree is evaluated on the full life cycle health status evaluation result by using a preset index material corrosion degree evaluation rule to obtain a structural safety performance tunnel entrance section index; wherein the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are not associated with the same tunnel risk source; Determine whether the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are the same weight influence index; When judged to be the same, a correlation analysis is performed on the fatigue damage influence range of the dynamic monitoring and healthy tunnel entrance section index and the fatigue damage influence range of the structural safety performance tunnel entrance section index, and the fatigue damage influence range whose correlation coefficient reaches a preset value is determined as the calibrated fatigue damage influence range, and a correlation analysis is performed on the steel bar corrosion degree of the dynamic monitoring and healthy tunnel entrance section index and the steel bar corrosion degree of the structural safety performance tunnel entrance section index, and the steel bar corrosion degree whose correlation coefficient reaches a preset value is determined as the calibrated steel bar corrosion degree; Construct a dynamic monitoring and health reinforcement section index and a structural safety performance reinforcement section index; the dynamic monitoring and health reinforcement section index is the same as the structural safety performance reinforcement section index, the fatigue damage influence range of the dynamic monitoring and health reinforcement section index is greater than the calibrated fatigue damage influence range, the steel bar corrosion degree of the dynamic monitoring and health reinforcement section index is greater than the calibrated steel bar corrosion degree, the tunnel risk sources of the dynamic monitoring and health reinforcement section index in different seasons are the same, and the tunnel risk source of the dynamic monitoring and health reinforcement section index is not associated in the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index; The tunnel risk sources of different seasons of the dynamic monitoring and health tunnel entrance section index are used to replace the tunnel risk sources of the dynamic monitoring and health reinforcement section index at the corresponding position to obtain the dynamic monitoring and health exit section index, and the tunnel risk sources of different seasons of the structural safety performance tunnel entrance section index are used to replace the tunnel risk sources of the structural safety performance reinforcement section index at the corresponding position to obtain the structural safety performance exit section index; The dynamic monitoring and health exit section index is convolved with the structural safety performance exit section index to obtain the load judgment information of the observation point.

[0035] The method provided in this embodiment, on the one hand, performs load judgment on the structural stress information of the tunnel connection and its corresponding different observation nodes to obtain the load judgment information of the reinforcement section, and further performs load judgment on the load judgment information of the reinforcement section in different seasons and the health status evaluation results of the whole life cycle, thereby realizing the systematic association between data, so that relevant information can be accurately and systematically stored and managed in the edge computing gateway cloud. This systematic data management method improves the efficiency of data retrieval and provides a solid data foundation for subsequent analysis and decision-making.

[0036] like Figure 2 As shown, a tunnel structure full life cycle health status evaluation system includes: The module for acquiring structural stress information of different observation nodes is used to acquire structural stress information of different observation nodes corresponding to tunnel connections of different seasons in the tunnel per unit time through a multimodal mechanical monitoring sensor device preset in the tunnel per unit time; wherein, the structural stress information of different observation nodes includes tensile stress, compressive stress, shear stress, bending stress and torsional stress.

[0037] The crack width and development information acquisition module is used to obtain the crack width and development information of the tunnel per unit time within a preset time period with different vehicle flows.

[0038] The risk coefficient calculation module is used to obtain the full life cycle health status prediction model, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information corresponding to the tunnel connection in different seasons in the edge computing gateway cloud, and input the structural stress information of different observation nodes corresponding to the tunnel connection into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connection, and calculate the risk coefficient of the predicted full life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information.

[0039] The cloud-based information storage module of the edge computing gateway is used to calculate the risk coefficient corresponding to the predicted full life cycle health status in different seasons, classify the predicted full life cycle health status in different seasons, and obtain the full life cycle health status evaluation result within a unit time tunnel.

[0040] It should be noted that technical personnel in the relevant technical field can clearly understand that, for the convenience and conciseness of description, the specific working processes of the system and different season modules described above can refer to the corresponding processes in the aforementioned embodiment of the health status evaluation method for the entire life cycle of a tunnel structure, and will not be repeated here.

[0041] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for evaluating the health status of a tunnel structure throughout its life cycle, characterized in that: The method includes: The structural stress information of different observation nodes corresponding to the tunnel connection in different seasons in the unit time tunnel is obtained through a multi-modal mechanical monitoring sensor device preset in the unit time tunnel; the structural stress information of different observation nodes includes tensile stress, compressive stress, shear stress, bending stress and torsional stress; Obtain crack width and development information of the tunnel per unit time within a preset time period with different traffic volumes; For the tunnel connections in different seasons, a full life cycle health status prediction model corresponding to the tunnel connections, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information are obtained in the edge computing gateway cloud, and the structural stress information of different observation nodes corresponding to the tunnel connections is input into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connections, and the risk coefficient of the predicted full life cycle health status in different seasons is calculated based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information; The predicted full life cycle health status in different seasons is calculated according to the risk coefficient corresponding to the predicted full life cycle health status in different seasons, and the predicted full life cycle health status evaluation result in the unit time tunnel is obtained.

2. A method for evaluating the health status of a tunnel structure throughout its life cycle according to claim 1, characterized in that: The method further comprises: For the tunnel connection in different seasons, load judgment is performed on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section; Perform load judgment on the reinforcement section load judgment information in different seasons and the health status evaluation result of the whole life cycle to obtain the observation point load judgment information, and store the observation point load judgment information in the edge computing gateway cloud; The step of performing load judgment on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section includes: Obtaining a corrosion degree assessment of the connection material corresponding to the tunnel connection; The characteristic material corrosion degree of the structural stress information of different observation nodes is evaluated by using a preset structural stress information material corrosion degree evaluation rule to obtain a structural stress material corrosion degree evaluation coefficient corresponding to the structural stress information; The structural stress material corrosion degree assessment coefficient is placed after the connection material corrosion degree assessment to obtain the reinforcement section load judgment information; The load judgment information of the reinforcement section in different seasons is used to judge the load with the health status evaluation result of the whole life cycle to obtain the load judgment information of the observation point, including: The load judgment information of the reinforcement section in different seasons is arranged in order from top to bottom through the preset classification rules to obtain the dynamic monitoring and healthy tunnel entrance section index; The index material corrosion degree is evaluated on the full life cycle health status evaluation result by using a preset index material corrosion degree evaluation rule to obtain a structural safety performance tunnel entrance section index; wherein the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are not associated with the same tunnel risk source; Determine whether the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are the same weight influence index; When judged to be the same, a correlation analysis is performed on the fatigue damage influence range of the dynamic monitoring and healthy tunnel entrance section index and the fatigue damage influence range of the structural safety performance tunnel entrance section index, and the fatigue damage influence range whose correlation coefficient reaches a preset value is determined as the calibrated fatigue damage influence range, and a correlation analysis is performed on the steel bar corrosion degree of the dynamic monitoring and healthy tunnel entrance section index and the steel bar corrosion degree of the structural safety performance tunnel entrance section index, and the steel bar corrosion degree whose correlation coefficient reaches a preset value is determined as the calibrated steel bar corrosion degree; Construct a dynamic monitoring and health reinforcement section index and a structural safety performance reinforcement section index; the dynamic monitoring and health reinforcement section index is the same as the structural safety performance reinforcement section index, the fatigue damage influence range of the dynamic monitoring and health reinforcement section index is greater than the calibrated fatigue damage influence range, the steel bar corrosion degree of the dynamic monitoring and health reinforcement section index is greater than the calibrated steel bar corrosion degree, the tunnel risk sources of the dynamic monitoring and health reinforcement section index in different seasons are the same, and the tunnel risk source of the dynamic monitoring and health reinforcement section index is not associated in the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index; The tunnel risk sources of different seasons of the dynamic monitoring and health tunnel entrance section index are used to replace the tunnel risk sources of the dynamic monitoring and health reinforcement section index at the corresponding position to obtain the dynamic monitoring and health exit section index, and the tunnel risk sources of different seasons of the structural safety performance tunnel entrance section index are used to replace the tunnel risk sources of the structural safety performance reinforcement section index at the corresponding position to obtain the structural safety performance exit section index; The dynamic monitoring and health exit section index is convolved with the structural safety performance exit section index to obtain the load judgment information of the observation point.

3. A method for evaluating the health status of a tunnel structure throughout its life cycle according to claim 1, characterized in that: The step of inputting structural stress information of different observation nodes corresponding to the tunnel connection into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connection includes: Inputting the structural stress information of different observation nodes into the full life cycle health status prediction model; wherein the full life cycle health status prediction model includes a structural stress type identification layer, a tensile stress feature extraction layer, a compressive stress, shear stress, bending stress feature extraction layer, a torsional stress feature extraction layer, a feature fusion layer and a full connection layer; The structural stress type recognition layer respectively recognizes the types of structural stresses in different seasons of the structural stress information of different observation nodes, obtains the type recognition results of the structural stresses in different seasons, and inputs the structural stresses in different seasons into the corresponding feature extraction layer according to the type recognition results corresponding to the structural stresses in different seasons; The tensile stress feature extraction layer extracts features of the received tensile stress to obtain dynamic monitoring and health feature indicators; The compressive stress, shear stress, and bending stress feature extraction layer extracts features of the received compressive stress, shear stress, and bending stress to obtain structural safety performance feature indicators; The torsional stress feature extraction layer extracts features from the received torsional stress to obtain characteristic indicators of the tunnel vault section; The feature fusion layer fuses the dynamic monitoring and health feature index, the structural safety performance feature index, and the tunnel vault section feature index to obtain a fused feature index; The fully connected layer performs link prediction on the fusion feature indicator through a preset link prediction rule to obtain a link prediction result corresponding to the fusion feature indicator, and feeds back the link prediction result through a preset graph neural network model to obtain a full life cycle health status predicted per unit time.

4. A method for evaluating the health status of a tunnel structure throughout its life cycle according to claim 1, characterized in that: The crack width and development information includes a visualization diagram of hydrological parameters per unit time, The risk coefficient calculation of the predicted full life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information includes: For the hydrological parameter visualization diagrams of different seasons, the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams are determined by using preset hydrological parameter level classification rules; For the predicted full life cycle health status in different seasons, the dynamic monitoring and health settlement probability corresponding to the predicted full life cycle health status are determined according to the hydrological parameter levels corresponding to the hydrological parameter visualization diagrams in different seasons and the material aging and damage information; For the predicted full life cycle health status in different seasons, determining the structural safety performance settlement probability corresponding to the predicted full life cycle health status based on the external load and environmental impact information; For the predicted full life cycle health status in different seasons, determining the tunnel vault section settlement probability corresponding to the predicted full life cycle health status based on the life cycle health status information under different geological disasters; For the predicted full life cycle health status in different seasons, the dynamic monitoring and healthy settlement probability, structural safety performance settlement probability and tunnel vault section settlement probability corresponding to the predicted full life cycle health status are weighted through the preset weight setting rules to obtain the risk coefficient calculation corresponding to the predicted full life cycle health status.

5. A method for evaluating the health status of a tunnel structure throughout its life cycle according to claim 4, characterized in that: The material aging and damage information includes the settlement height corresponding to the health status of the whole life cycle in different seasons at different hydrological parameter levels of the hydrological parameters in different seasons. The dynamic monitoring and healthy settlement probability corresponding to the predicted health status of the whole life cycle are determined according to the hydrological parameter level corresponding to the hydrological parameter visualization diagram in different seasons and the material aging and damage information, including: Determine the target settlement height corresponding to the predicted full life cycle health status at the hydrological parameter level corresponding to the hydrological parameter visualization diagram in different seasons in the material aging and damage information; The target settlement heights in different seasons are convoluted to obtain the dynamic monitoring and healthy settlement probability.

6. A method for evaluating the health status of a tunnel structure throughout its life cycle according to claim 4, characterized in that: The determining of the tunnel vault section settlement probability corresponding to the predicted full life cycle health status based on the life cycle health status information under different geological disasters includes: Based on the life cycle health status information under the different geological disasters, it is determined whether ground cracks have occurred; when it is determined that no ground cracks have occurred, it is determined that no tunnel vault section settlement has occurred; when it is determined that the ground cracks have occurred, the probability of the predicted full life cycle health status occurring is determined based on the life cycle health status information under the different geological disasters, and the probability is multiplied by a preset score to obtain the probability of the tunnel vault section settlement.

7. A tunnel structure full life cycle health status evaluation system, characterized in that: include: A module for acquiring structural stress information of different observation nodes, which is used to acquire structural stress information of different observation nodes corresponding to tunnel connections of different seasons in the tunnel per unit time through a preset multi-modal mechanical monitoring sensor device in the tunnel per unit time; wherein the structural stress information of different observation nodes includes tensile stress, compressive stress, shear stress, bending stress and torsional stress; A crack width and development information acquisition module is used to obtain crack width and development information of the tunnel in a preset time period with different traffic flows per unit time; A risk coefficient calculation module is used to obtain, for the tunnel connection in different seasons, a full life cycle health status prediction model corresponding to the tunnel connection, life cycle health status information under different geological disasters, material aging and damage information, and external load and environmental impact information in the edge computing gateway cloud, and input the structural stress information of different observation nodes corresponding to the tunnel connection into the full life cycle health status prediction model to obtain the unit time predicted full life cycle health status corresponding to the tunnel connection, and calculate the risk coefficient of the predicted full life cycle health status in different seasons based on the crack width and development information, the life cycle health status information under different geological disasters, the material aging and damage information, and the external load and environmental impact information; The edge computing gateway cloud information storage module is used to calculate the predicted full life cycle health status in different seasons according to the risk coefficient corresponding to the predicted full life cycle health status in different seasons, and to obtain the full life cycle health status evaluation result in the tunnel per unit time. For the tunnel joints in different seasons, the tunnel joints and the structural stress information of different observation nodes corresponding to the tunnel joints are subjected to load judgment to obtain the reinforcement section load judgment information, and the reinforcement section load judgment information in different seasons is subjected to load judgment with the full life cycle health status evaluation result to obtain the observation point load judgment information, and the observation point load judgment information is stored in the edge computing gateway cloud; The step of performing load judgment on the tunnel connection and the structural stress information of different observation nodes corresponding to the tunnel connection to obtain load judgment information of the reinforcement section includes: Obtaining a corrosion degree assessment of the connection material corresponding to the tunnel connection; The characteristic material corrosion degree of the structural stress information of different observation nodes is evaluated by using a preset structural stress information material corrosion degree evaluation rule to obtain a structural stress material corrosion degree evaluation coefficient corresponding to the structural stress information; The structural stress material corrosion degree assessment coefficient is placed after the connection material corrosion degree assessment to obtain the reinforcement section load judgment information; The load judgment information of the reinforcement section in different seasons is used to judge the load with the health status evaluation result of the whole life cycle to obtain the load judgment information of the observation point, including: The load judgment information of the reinforcement section in different seasons is arranged in order from top to bottom through the preset classification rules to obtain the dynamic monitoring and healthy tunnel entrance section index; The index material corrosion degree is evaluated on the full life cycle health status evaluation result by using a preset index material corrosion degree evaluation rule to obtain a structural safety performance tunnel entrance section index; wherein the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are not associated with the same tunnel risk source; Determine whether the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index are the same weight influence index; When judged to be the same, a correlation analysis is performed on the fatigue damage influence range of the dynamic monitoring and healthy tunnel entrance section index and the fatigue damage influence range of the structural safety performance tunnel entrance section index, and the fatigue damage influence range whose correlation coefficient reaches a preset value is determined as the calibrated fatigue damage influence range, and a correlation analysis is performed on the steel bar corrosion degree of the dynamic monitoring and healthy tunnel entrance section index and the steel bar corrosion degree of the structural safety performance tunnel entrance section index, and the steel bar corrosion degree whose correlation coefficient reaches a preset value is determined as the calibrated steel bar corrosion degree; Construct a dynamic monitoring and health reinforcement section index and a structural safety performance reinforcement section index; the dynamic monitoring and health reinforcement section index is the same as the structural safety performance reinforcement section index, the fatigue damage influence range of the dynamic monitoring and health reinforcement section index is greater than the calibrated fatigue damage influence range, the steel bar corrosion degree of the dynamic monitoring and health reinforcement section index is greater than the calibrated steel bar corrosion degree, the tunnel risk sources of the dynamic monitoring and health reinforcement section index in different seasons are the same, and the tunnel risk source of the dynamic monitoring and health reinforcement section index is not associated in the dynamic monitoring and health tunnel entrance section index and the structural safety performance tunnel entrance section index; The tunnel risk sources of different seasons of the dynamic monitoring and health tunnel entrance section index are used to replace the tunnel risk sources of the dynamic monitoring and health reinforcement section index at the corresponding position to obtain the dynamic monitoring and health exit section index, and the tunnel risk sources of different seasons of the structural safety performance tunnel entrance section index are used to replace the tunnel risk sources of the structural safety performance reinforcement section index at the corresponding position to obtain the structural safety performance exit section index; The dynamic monitoring and health exit section index is convolved with the structural safety performance exit section index to obtain the load judgment information of the observation point.

Images