A tunnel life cycle health monitoring method and system

Abstract

The present invention discloses a tunnel life cycle health monitoring method and system, which belongs to the technical field of tunnel health monitoring, wherein the method includes: collecting tunnel design information; establishing the basic life cycle of the tunnel according to the design information, monitoring sensor data through built-in sensors, establishing a time series monitoring data set, and compensating the basic life cycle through the time series monitoring data set; evaluating the coverage blind area of ​​built-in sensors based on layout information, structural information, and the equipment attenuation factor of built-in sensors, and real-time environmental information; performing important evaluation of the tunnel location based on structural information and geological information; configuring additional collection strategies through a first penalty factor and a second penalty factor, and executing additional data collection for the tunnel; updating the life cycle correction according to the additional data collection results, and completing tunnel health monitoring. This application solves the technical problem that the safety hazards of tunnels cannot be discovered in time due to monitoring lag and insufficient blind area coverage in tunnel monitoring technology.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel health monitoring, and in particular to a tunnel full life cycle health monitoring method and system. Background Art

[0002] As an important transportation facility, the safety, stability and durability of tunnels are crucial to ensuring smooth traffic and the safety of people's lives and property. As tunnels age, their structures may be affected by the natural environment, geological conditions, human factors and other factors, resulting in cracks, leakage, deformation and other problems, which in turn affect the safety performance of the tunnels. Therefore, it is of great significance to conduct health monitoring of tunnels throughout their life cycle and to promptly discover and deal with potential safety hazards in order to ensure the safe operation of tunnels.

[0003] Traditional tunnel monitoring methods mainly rely on regular inspections and manual testing, which has certain lags and limitations and cannot reflect the health of the tunnel in real time. In addition, manual testing is difficult to cover all parts of the tunnel, especially some hidden areas, which have monitoring blind spots.

[0004] In summary, the present application aims to solve the technical problems in existing tunnel health monitoring technologies, such as monitoring lag and insufficient blind spot coverage, which result in failure to timely discover tunnel safety hazards. Summary of the invention

[0005] The present application provides a tunnel life cycle health monitoring method and system, aiming to solve the technical problems in existing tunnel health monitoring technologies such as monitoring lag and insufficient blind spot coverage, which lead to failure to timely discover tunnel safety hazards.

[0006] In view of the above problems, the present application provides a tunnel life cycle health monitoring method and system.

[0007] The first aspect disclosed in the present application provides a method for health monitoring of a tunnel throughout its life cycle, the method comprising collecting design information of the tunnel, the design information comprising structural information of the tunnel and layout information of built-in sensors; establishing a basic life cycle of the tunnel according to the design information, and monitoring sensor data through built-in sensors to establish a time series monitoring data set, compensating the basic life cycle through the time series monitoring data set to generate an updated life cycle; acquiring real-time environmental information of the tunnel, evaluating the coverage blind area of ​​the built-in sensors based on the layout information, the structural information and the equipment attenuation factor of the built-in sensors and the real-time environmental information, and establishing a first penalty factor for mapping the tunnel position; performing an important evaluation of the tunnel position based on the structural information and geological information, and establishing a second penalty factor mapped to the tunnel position; configuring an additional collection strategy through the first penalty factor and the second penalty factor, and executing additional data collection of the tunnel based on the additional collection strategy; correcting the updated life cycle according to the additional data collection result, and completing the tunnel health monitoring based on the correction result.

[0008] Another aspect disclosed in the present application provides a tunnel life cycle health monitoring system, the system comprising a design information acquisition module: used to acquire design information of the tunnel, the design information comprising structural information of the tunnel and layout information of built-in sensors; an update life cycle generation module: used to establish a basic life cycle of the tunnel according to the design information, and to monitor sensor data through built-in sensors, establish a time series monitoring data set, compensate the basic life cycle through the time series monitoring data set, and generate an update life cycle; a first penalty factor establishment module: used to obtain real-time environmental information of the tunnel, evaluate the coverage blind area of ​​the built-in sensor based on the layout information, the structural information and the equipment attenuation factor of the built-in sensor, and the real-time environmental information, and establish a first penalty factor for tunnel position mapping; a second penalty factor establishment module: used to evaluate the importance of the tunnel position based on the structural information and geological information, and establish a second penalty factor mapped to the tunnel position; an additional collection strategy configuration module: used to configure an additional collection strategy through the first penalty factor and the second penalty factor, and perform additional data collection of the tunnel based on the additional collection strategy; an update life cycle correction module: used to correct the update life cycle according to the additional data collection result, and complete the tunnel health monitoring based on the correction result.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, the tunnel structure information and sensor layout information are collected to establish a basic life cycle, and the life cycle is updated through sensor monitoring data and time series data sets. The coverage blind area is evaluated by combining real-time environmental information and sensor attenuation factors to establish the first penalty factor; the location importance is evaluated based on structural and geological information to establish the second penalty factor. According to these two penalty factors, additional collection strategies are configured, additional data collection is performed, and the life cycle is corrected accordingly to complete tunnel health monitoring. The technical problems of monitoring lag and insufficient blind area coverage in existing tunnel health monitoring technologies, which lead to the failure to timely discover tunnel safety hazards, are solved. The technical effect of enhancing the accuracy and comprehensiveness of monitoring and improving the level of tunnel safety management is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic flow chart of a tunnel life cycle health monitoring method is provided for an embodiment of the present application;

[0013] Figure 2 A schematic diagram of a process for configuring an additional collection strategy in a tunnel life cycle health monitoring method is provided for an embodiment of the present application;

[0014] Figure 3 A structural schematic diagram of a tunnel life cycle health monitoring system is provided for an embodiment of the present application.

[0015] Explanation of the reference numerals: design information collection module 11 , update lifecycle generation module 12 , first penalty factor establishment module 13 , second penalty factor establishment module 14 , additional collection strategy configuration module 15 , update lifecycle correction module 16 . DETAILED DESCRIPTION

[0016] The overall idea of ​​the technical solution provided by this application is as follows:

[0017] The embodiments of the present application provide a method and system for health monitoring of a tunnel throughout its life cycle. By integrating the design information, real-time environmental data, and sensor monitoring data of the tunnel, a life cycle model of the tunnel is established and dynamically updated. First, the structural information and sensor layout information of the tunnel are collected to establish a basic life cycle model. The model is compensated and updated through real-time monitoring and time series data sets. Combining the sensor attenuation factor and real-time environmental information, the coverage blind area is evaluated and a first penalty factor is established; the importance is evaluated based on the structural and geological information, and a second penalty factor is established. These two penalty factors are used to configure and execute additional data collection, and the life cycle is corrected accordingly to complete the health monitoring of the tunnel and improve the accuracy and comprehensiveness of the monitoring.

[0018] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0019] Embodiment 1

[0020] like Figure 1 As shown, an embodiment of the present application provides a tunnel life cycle health monitoring method, the method comprising:

[0021] Step S100: collecting design information of the tunnel, wherein the design information includes structural information of the tunnel and layout information of built-in sensors.

[0022] Specifically: obtain tunnel design drawings and construction plans, including plan views, cross-sections, structural drawings, etc.; collect material descriptions and construction process documents to understand the performance of the materials used and the construction methods; sort and summarize this information to form a complete tunnel structure information database. The structural information refers to the specific design details of the tunnel, such as the geometric size, shape, material type, and support structure. For example, the length, diameter, wall thickness of the tunnel, the specifications of the concrete or steel used, and the plan layout and longitudinal section of the tunnel.

[0023] Obtain the layout plan and installation location diagram of the built-in sensors, and clarify the specific location and installation method of each sensor. Record the type and function of each sensor, such as strain gauges, temperature sensors, humidity sensors, accelerometers, etc. Among them, the layout location of the sensor should be determined according to the characteristics of the tunnel and the monitoring needs, and it needs to be laid out in key parts and sensitive areas of the tunnel. There are many ways to install sensors, such as adhesive, embedded, hanging, etc. The specific method needs to be determined according to the type of sensor and the layout location. The data collected by the sensor needs to be transmitted to the monitoring center for processing and analysis, so it is necessary to determine the appropriate data transmission method, such as wired transmission, wireless transmission, etc. Built-in sensors can monitor the deformation, pressure, temperature and other parameters of the tunnel in real time, providing important guarantees for the safe operation of the tunnel.

[0024] This step can establish a complete tunnel life cycle model by collecting and organizing the tunnel's structural information and the layout information of built-in sensors, and provide basic data support for subsequent sensor data monitoring and analysis.

[0025] Step S200: Establish a basic life cycle of the tunnel according to the design information, monitor sensor data through built-in sensors, establish a time series monitoring data set, compensate the basic life cycle through the time series monitoring data set, and generate an updated life cycle.

[0026] Specifically: using the collected tunnel design information (including structural information and sensor layout information), based on the tunnel design information, combined with geological conditions, environmental factors, material properties, etc., the design life of the tunnel, that is, the basic life cycle, is evaluated. It predicts the behavior and performance changes of the tunnel under normal use conditions, including structural deformation, material aging, potential stress concentration areas, etc.

[0027] Furthermore, various sensors (such as strain gauges, accelerometers, temperature sensors, etc.) built into the tunnel structure collect data on the physical state and environmental conditions of the tunnel in real time. These data may include parameters such as strain, vibration, temperature, humidity, etc. The collected data is transmitted to the monitoring center by wireless or wired means and stored in a database to form a time-series monitoring data set.

[0028] The data collected by the sensors are collated, cleaned and preprocessed to ensure the integrity and accuracy of the data. The time series data set refers to the time series monitoring data set formed by organizing the processed data in chronological order. These data sets reflect the physical state and environmental changes of the tunnel at different time points.

[0029] Analyze the time series monitoring data to identify abnormal changes or trends in the tunnel structure. For example, detected stress concentration, abnormal deformation or temperature anomalies. Compare the analysis results with the basic life cycle to identify the differences between the basic life cycle and the actual monitoring data. Based on these differences, compensate and correct the basic life cycle. If the monitoring data shows that the tunnel has abnormal conditions or potential risks, it may be necessary to shorten the basic life cycle; conversely, if the tunnel is in good operating condition, you can consider extending the basic life cycle. Generate an updated life cycle with compensated and corrected data. More accurately reflect the behavior and performance changes of the tunnel under actual use conditions.

[0030] This step realizes the dynamic update and compensation of the tunnel life cycle model by combining design information with actual monitoring data. The actual monitoring data collected by built-in sensors provides real-time and true tunnel status information. By integrating and analyzing this data, the generated updated life cycle can more accurately predict and reflect the health status of the tunnel, thereby improving the accuracy and reliability of monitoring, timely discovering and warning potential problems, and ensuring the safety and stability of the tunnel.

[0031] Step S300: Acquire real-time environment information of the tunnel, evaluate the coverage blind spot of the built-in sensor based on the layout information, the structure information, the device attenuation factor of the built-in sensor, and the real-time environment information, and establish a first penalty factor for tunnel position mapping.

[0032] Specifically: Use environmental monitoring equipment (such as temperature sensors, humidity sensors, gas concentration sensors, etc.) pre-installed in the tunnel to collect real-time environmental parameters such as temperature, humidity, and gas concentration in the tunnel. Ensure that the environmental monitoring equipment can transmit real-time data to the data processing center via wired or wireless means.

[0033] According to the sensor layout diagram or record during tunnel design, clarify the specific location, type and monitoring range of each built-in sensor. Understand the overall structure, cross-sectional shape, size and location of key supporting structures of the tunnel in order to evaluate the coverage and blind spots of sensor monitoring. Consider the performance degradation of built-in sensors as they grow in use, i.e., equipment attenuation. This can be quantified through regular calibration and testing. Set an attenuation factor for each built-in sensor based on the performance attenuation of the equipment. This factor can be a value between 0 and 1, indicating the ratio of the current performance of the sensor to the initial performance. The blind spot refers to an area that cannot be effectively monitored by the sensor due to reasons such as limited sensor monitoring range or tunnel structure obstruction. Based on the monitoring range of the sensor and the tunnel structure information, use spatial analysis technology (such as GIS) to identify the blind spot. Combined with real-time environmental information, evaluate whether the environmental parameters in the blind spot may exceed the safety threshold. Comprehensively consider the equipment attenuation factor to quantitatively evaluate the potential risks in the blind spot.

[0034] The first penalty factor is intended to reflect the degree of risk caused by the blind spots covered by built-in sensors at different locations in the tunnel. Based on the blind spot evaluation results, a risk level is assigned to each tunnel location. The risk level is converted into a specific penalty factor value. For example, the penalty factor for high-risk areas can be set to 1.5, the penalty factor for medium-risk areas to 1.2, and the penalty factor for low-risk areas to 1. These penalty factor values ​​will be used in subsequent tunnel location mapping or risk assessment models to more accurately reflect the safety status of each location in the tunnel.

[0035] Based on this step, the real-time environmental information of the tunnel can be effectively obtained, and the coverage blind areas of the built-in sensors can be evaluated, and then the first penalty factor of the tunnel location mapping can be established, providing strong data support for the operation and maintenance of the tunnel.

[0036] Step S400: Performing an importance evaluation of the tunnel location based on the structural information and geological information, and establishing a second penalty factor mapped to the tunnel location.

[0037] Specifically, the geological information includes: geological conditions, which comprehensively consider the geological conditions of the area where the tunnel is located, such as stratum lithology, geological structure (such as faults, folds, etc.), hydrogeological conditions, etc. These factors directly affect the stability and safety of the tunnel; unfavorable geological areas, special attention should be paid to unfavorable geological areas, such as weak interlayers, karst zones, landslides, etc. These areas often have higher safety risks and require special monitoring and reinforcement measures; groundwater and gas, analyze the groundwater conditions and gas content in the area where the tunnel passes. High water pressure and gas accumulation may pose a threat to tunnel safety.

[0038] Combining structural information and geological information, the risk levels of different locations in the tunnel can be divided into high-risk areas, medium-risk areas, and low-risk areas. Specific evaluation indicators are formulated, such as structural stability, complexity of geological conditions, distribution of unfavorable geological areas, etc. These indicators will be used to quantitatively evaluate the importance of tunnel locations.

[0039] The second penalty factor is used to reflect the importance of the tunnel location and its impact on the overall safety situation. The larger the value of the penalty factor, the more important the location is, requiring higher attention and stricter monitoring measures. The second penalty factor is calculated for each tunnel location based on the risk level classification and evaluation indicators. For example, the penalty factor for high-risk areas can be set to 1.5, 1.2 for medium-risk areas, and 1 for low-risk areas. In actual operation, the value of the second penalty factor can be adjusted in a timely manner according to changes in tunnel monitoring data and safety conditions. For example, when an abnormal situation occurs at a certain location, its penalty factor value can be temporarily increased to strengthen monitoring and early warning.

[0040] This step can make an important evaluation of the tunnel location based on the structural information and geological information of the tunnel, and establish a second penalty factor mapped with the tunnel location. It helps to more accurately evaluate the safety status of the tunnel and provide strong data support for the operation and maintenance of the tunnel.

[0041] Step S500: configuring an additional collection strategy through the first penalty factor and the second penalty factor, and performing additional data collection of the tunnel based on the additional collection strategy.

[0042] Specifically: The first penalty factor is derived based on the blind area evaluation of the built-in sensors, reflecting the risk level caused by insufficient sensor coverage at different locations in the tunnel. The second penalty factor is derived based on an important evaluation of the tunnel's structural and geological information, reflecting the importance of the tunnel's location and its impact on the overall safety situation.

[0043] Among them, configuring additional collection strategies includes: combining the first penalty factor and the second penalty factor to determine the data collection priority of each location in the tunnel. For example, for locations where both factors are high, a higher data collection priority should be given. According to the safety requirements of the tunnel and the results of risk assessment, select the parameters that need to be additionally collected. These parameters may include displacement, stress, strain, seepage, gas concentration, etc. According to the risk level and importance of each location, formulate different data collection frequencies. For high-risk and important locations, the collection frequency should be increased to obtain more real-time and accurate data. According to the actual situation of the tunnel and the needs of the collection parameters, select the appropriate collection method. This may include using higher-precision sensors, installing more monitoring points, using drones or robots for inspections, etc. Set warning thresholds for each collection parameter. When the collected data exceeds the threshold, the warning mechanism should be triggered so that timely countermeasures can be taken.

[0044] Deploy new sensors or other data collection devices at required locations according to the additional collection strategy. Configure the data collection system to ensure that the new devices can connect and transmit data correctly. Start additional data collection according to the set collection frequency and collection parameters. Analyze the collected data to evaluate the safety status of the tunnel. When the data exceeds the set threshold, trigger the early warning mechanism and take corresponding countermeasures.

[0045] For example, for high-risk and important locations: the first penalty factor is 1.5, and the second penalty factor is 1.5. Collection frequency: once an hour; collection parameters: displacement, stress, seepage; warning thresholds: displacement ±5mm, stress ±10MPa, seepage velocity>0.5m / day.

[0046] Medium risk and general location: first penalty factor 1.2, second penalty factor 1.0. Collection frequency: once every 4 hours; collection parameters: displacement, stress; warning threshold: displacement ±3mm, stress ±5MPa.

[0047] Based on this step, additional data collection strategies for the tunnel can be configured based on the first penalty factor and the second penalty factor, and these strategies can be effectively implemented to obtain more comprehensive and accurate data support, thereby providing strong guarantees for the operation and maintenance of the tunnel.

[0048] Step S600: update the life cycle correction according to the additional data collection result, and complete the tunnel health monitoring based on the correction result.

[0049] Specifically: According to the configured additional data collection strategy, use more accurate sensors, add monitoring points or use drones / robots to perform additional data collection. Ensure the accuracy and real-time nature of data collection to obtain the latest status information of key locations in the tunnel.

[0050] The collected additional data are collated, cleaned and preprocessed to ensure data quality. Descriptive statistical analysis, correlation analysis, trend analysis and other methods are used to deeply explore the patterns and trends in the data. Combine historical data with real-time data to evaluate the structural health status, deformation trends and potential risks of the tunnel.

[0051] Based on the results of the additional data analysis, the current state of the tunnel is accurately assessed. Special attention is paid to the key locations and sensitive areas of the tunnel, such as the vault, side walls, lining, etc. Based on the results of the current state assessment, the life cycle of the tunnel is corrected. If abnormal conditions such as severe deformation, crack expansion, or increased seepage are found in the tunnel, the life cycle should be appropriately shortened. If the tunnel is in good condition and the structure is stable, the life cycle can be appropriately extended. Set clear thresholds or standards for life cycle corrections. For example, when a key indicator of the tunnel exceeds a certain threshold, the life cycle correction mechanism is automatically triggered.

[0052] Combine built-in sensors and additional data acquisition equipment to establish a comprehensive tunnel health monitoring system. Ensure that the system can monitor the tunnel's structural health, environmental parameters, traffic conditions, etc. in real time. Monitor the tunnel in real time, paying attention to key indicators such as structural deformation, crack development, and seepage. Once an abnormal situation is found or the warning threshold is exceeded, the warning mechanism is immediately triggered to notify relevant personnel to take countermeasures. Regularly maintain and inspect the tunnel to ensure the normal operation of the monitoring equipment and the accuracy of the data. Regularly evaluate the health status of the tunnel, and adjust the monitoring strategy and life cycle correction plan based on the evaluation results.

[0053] Based on this step, the life cycle can be updated and corrected according to the additional data collection results, and the tunnel health monitoring work can be completed based on the correction results. It helps to timely discover the potential risks of the tunnel and take corresponding countermeasures to ensure the safe and stable operation of the tunnel.

[0054] Furthermore, step S100 of the present application further includes: establishing the actual coverage range of the built-in sensor, the formula is as follows:

[0055] C i =R i ·(1-OCF)·PF·(1-CF)·(1-DF)·(1-EF);

[0056] Among them, C iCharacterizes the actual coverage of the i-th built-in sensor, R i is the theoretical coverage of the i-th built-in sensor, OCF is the correction factor for the shielding of the internal structure of the tunnel, PF is the performance correction factor of the built-in sensor, CF is the correction factor for the curvature of the tunnel, DF is the time performance attenuation correction factor of the built-in sensor, and EF is the correction factor for the built-in sensor affected by environmental conditions; the blind spots are summarized according to the actual coverage to complete the coverage blind spot evaluation, and the formula is as follows:

[0057]

[0058] Among them, B is the summary result of the blind area, n is the total number of built-in sensors, and L is the total length of the tunnel.

[0059] Specifically: OCF considers the blocking effect of the tunnel's internal structure (such as supports, partitions, etc.) on the sensor signal; PF considers the actual performance of the sensor itself, which may be worse than the theoretical value due to manufacturing errors or quality problems; CF considers the impact of tunnel curvature on sensor signal transmission. The greater the curvature, the greater the correction factor; DF considers that the performance of the sensor may gradually decay over time; EF considers the impact of environmental factors such as temperature, humidity, and corrosive gases on sensor performance.

[0060] For each sensor i, calculate the theoretical coverage R i With actual coverage C i The difference between R i \C i The blind areas of all sensors are summed up by the union operation The total blind area range is obtained. The result is then intersected with the total length interval of the tunnel [0, L] to ensure that the blind area result is within the tunnel range.

[0061] The formula and steps ensure a comprehensive assessment of the blind areas of the tunnel's internal sensor monitoring. By combining the differences between theoretical coverage and actual coverage, the weak links and blind areas in the monitoring system can be identified, and the summary results B of these blind areas can provide an accurate coverage blind area evaluation. This result can be further used to optimize the sensor layout, improve the coverage and accuracy of the monitoring system, and ensure the safety and stability of the tunnel.

[0062] Further, such as Figure 2As shown, step S500 of the present application also includes: performing factor alignment of the first penalty factor and the second penalty factor based on the tunnel position mapping; judging whether the first penalty factor and the second penalty factor are at the same position according to the factor alignment result; if they are the first penalty factor and the second penalty factor at the same position, performing superimposed additional acquisition analysis of monitoring accuracy and establishing a superimposed additional acquisition strategy; if they are not the first penalty factor and the second penalty factor at the same position, establishing an independent additional acquisition strategy according to the separated first penalty factor and the second penalty factor; and completing the additional acquisition strategy configuration according to the superimposed additional acquisition strategy and the independent additional acquisition strategy.

[0063] Specifically, the factor alignment refers to the process of matching and corresponding the first penalty factor and the second penalty factor with the specific location of the tunnel. This process can ensure the accurate deployment of monitoring resources and formulate corresponding monitoring strategies according to the degree of tunnel health risk at different locations.

[0064] A detailed tunnel location map is required, which should accurately mark the various parts and key locations of the tunnel. Based on the results of the tunnel health assessment, determine the first and second penalty factors for different locations. Match each penalty factor to a specific location on the tunnel location map. This involves matching the factor value or level to the tunnel segment, key point or area. After completing the matching of factors to locations, it can be determined which locations have higher penalty factors, thereby determining the areas where monitoring accuracy needs to be increased.

[0065] After completing the factor alignment, it is necessary to determine whether the two penalty factors point to the same location or area of ​​the tunnel. If both penalty factors point to the same location or area, it means that the location or area needs to increase monitoring accuracy in multiple aspects.

[0066] If two penalty factors point to the same location or area, additional collection and analysis is required. This is because the location or area has risks or anomalies in multiple dimensions, so more monitoring equipment needs to be added or more sophisticated monitoring methods need to be adopted to improve the precision and accuracy of monitoring. Additional collection and analysis will consider multiple factors, such as the type, quantity, and installation location of monitoring equipment, to ensure the effectiveness and feasibility of the monitoring strategy.

[0067] Based on the results of the superimposed additional acquisition analysis, a specific superimposed additional acquisition strategy is formulated. This strategy will specify in detail what types of monitoring equipment should be added at what locations, and how to configure these devices to ensure the accuracy and effectiveness of monitoring.

[0068] If the two penalty factors do not point to the same location or area, it means that they represent the monitoring needs of different areas. In this case, it is necessary to formulate independent additional collection strategies for each penalty factor. These strategies will determine the type, quantity and installation location of monitoring equipment according to the specific situation and needs of each area.

[0069] Finally, the superimposed additional acquisition strategy and the independent additional acquisition strategy are integrated to form a complete additional acquisition strategy configuration. This configuration will cover the entire tunnel, ensuring that all areas that require increased monitoring accuracy are effectively monitored. At the same time, this configuration will also take into account the rational allocation and efficiency of resources to ensure the feasibility and economy of monitoring work.

[0070] Furthermore, step S500 of the present application also includes: establishing a collection location point according to the additional collection strategy; performing a strategy importance analysis on the additional collection strategy, and configuring a collection reserved interval according to the strategy importance analysis result; reconstructing the collection location point through the collection reserved interval, and completing additional data collection according to the reconstructed collection location point with the additional collection strategy.

[0071] Specifically: the specific locations where additional data collection is required are determined based on the additional collection strategy. These locations may be key parts of the tunnel structure, areas known to have potential risks, or newly added monitoring points based on monitoring needs.

[0072] After determining the collection locations, it is necessary to further perform importance analysis on the additional collection strategies for these locations. The importance analysis is based on multiple factors, such as the risk level of the location, the trend of changes in historical data, and the impact on the overall safety of the tunnel. Through importance analysis, it can be determined which locations have more important additional data collection and require more frequent monitoring or higher-precision data.

[0073] Based on the importance analysis, a reserved collection interval is configured for each collection location point. This includes the time interval for data collection (such as hourly, daily, weekly, etc.), the accuracy requirements for data collection (such as data resolution, measurement error, etc.), the duration of data collection (such as continuous collection or intermittent collection), etc. The configuration of the reserved interval is intended to ensure that data collection at important locations can be fully guaranteed by resources, while avoiding wasting resources at unimportant locations.

[0074] According to the configuration of the reserved interval, reconsider the data collection plan of certain locations, or increase / decrease the number of certain locations. Through this process, it can be ensured that the final collection location can maximize the needs of tunnel health monitoring while complying with resource allocation constraints. Finally, according to the reconstructed collection location and the corresponding additional collection strategy, start to perform additional data collection. It involves the use of various sensors, monitoring instruments and data processing technologies to collect status data, environmental data, etc. of the tunnel structure, and evaluate the health status and potential risks of the tunnel through data analysis.

[0075] This step optimizes the additional data collection plan through strategy importance analysis and configuration of reserved collection intervals to ensure the accuracy and effectiveness of tunnel health monitoring. At the same time, this plan also reflects the rational allocation and efficient use of monitoring resources.

[0076] Furthermore, step S600 of the present application also includes: calling the image data in the additional data acquisition result, grayscale processing the image data, performing sensitivity verification based on the LBP operator, and establishing a first sensitive area; performing edge detection on the image data, and establishing a second sensitive area based on the edge detection result; performing fusion of the first sensitive area and the second sensitive area, establishing an identification feature of the additional data acquisition result based on the fusion result, and updating the life cycle correction based on the identification feature.

[0077] Specifically: extract image data in the tunnel from the additional data collection, which may include high-resolution images of tunnel walls, supporting structures, etc. The grayscale processing refers to converting color images into grayscale images to simplify subsequent image processing steps. Grayscale processing reduces data dimensions and improves processing efficiency by converting the color information of each pixel into brightness information. LBP is an image processing operator used for texture analysis, which can effectively extract texture features of images. The LBP operator is used to analyze the texture patterns in grayscale images and identify areas in the image with significant texture changes. These areas are called first sensitive areas. Use the LBP operator to perform a sliding window operation in the image to calculate the texture features of each local area. According to the significance of the features, determine sensitive areas in the image where abnormalities or changes may exist.

[0078] Use edge detection algorithms (such as Canny, Sobel, etc.) to identify edges in the image where pixel values ​​change significantly. Edge detection can highlight the structural boundaries and contours in the image. These areas are called second sensitive areas. These areas may include the extension of cracks, the boundaries of water seepage areas, etc. In other words, the grayscale image is smoothed to reduce the impact of noise. The gradient of the image is calculated to identify edge pixels with large gradient changes. Through threshold segmentation, significant edge pixels are retained to form an edge map.

[0079] The first sensitive area identified by the LBP operator and the second sensitive area obtained by edge detection are fused. Image superposition, logical operations (such as AND, OR, etc.) or region merging technology are used to integrate the information of the two sensitive areas. The fusion result can more comprehensively reflect the abnormalities and structural changes in the image. Based on the fused sensitive areas, the key features of the image are extracted. These features include the shape, size, position, texture pattern, edge features, etc. of the area. The visual information of the fused area is converted into quantifiable feature data through feature extraction algorithms (such as HOG, SIFT, etc.).

[0080] The extracted identification features are used to correct the life cycle of the tunnel. Anomalies in the identification features are analyzed to assess the health status and potential problems of the tunnel structure. These analysis results are integrated into the life cycle model of the tunnel, involving the assessment of the health status of the tunnel, the prediction of the remaining life, and the formulation of maintenance plans. Through this process, it can be ensured that the tunnel can be maintained and managed in a timely and effective manner throughout its life cycle.

[0081] This step uses image processing technology to extract the structural and texture features of the tunnel, and combined with other monitoring data, it can more accurately assess the health status of the tunnel. This method improves the accuracy and reliability of tunnel health monitoring and ensures the safety and stability of the tunnel throughout its life cycle.

[0082] Furthermore, step S600 of the present application also includes: establishing a detection attention factor based on the fusion result, the detection attention factor being the acquisition attention factor of the fusion sensor after image acquisition under the additional acquisition strategy; establishing a fusion feature after constraining the fusion sensor through the acquisition attention factor; performing attention recognition of image data based on the fusion result to establish an image feature; and establishing an identification feature based on the fusion feature and the image feature.

[0083] Specifically: Based on the fusion results, a detection attention factor is established. The detection attention factor refers to the acquisition focus of the fusion sensor after image acquisition under the additional acquisition strategy. These factors reflect the areas and features that need special attention in tunnel monitoring. By analyzing the fusion results, it is determined which areas and features should be given more attention during the monitoring process. The detection attention factor may include the areas that different sensors should pay attention to during data acquisition, the priority of data acquisition, the frequency of data acquisition, etc.

[0084] The established detection attention factors are used to constrain the collection of fusion sensors. This means that during the data collection process, the sensor will perform the data collection task according to the guidance information in the detection attention factors to ensure the pertinence and efficiency of data collection. This can be achieved by adjusting the sensor's collection parameters (such as sampling frequency, resolution, coverage, etc.). After the collection constraints, the fusion sensor will collect a series of data. This data may come from different types of sensors, including image sensors, displacement sensors, stress sensors, etc. By fusing these data (for example, integrating data from different sensors into the same data set, or performing weighted averaging on similar data, etc.), fusion features can be established. Fusion features integrate data from multiple sensors and can more comprehensively and accurately reflect the health of the tunnel.

[0085] In addition to fusion features, it is also necessary to perform attention recognition on the image data in the fusion result. This usually involves identifying and analyzing key areas, outliers, or change trends in the image. Attention recognition is based on image processing technology (such as edge detection, texture analysis, etc.) or machine learning algorithms (such as convolutional neural networks, support vector machines, etc.). Based on attention recognition, image features are extracted. Image features include shape features, texture features, edge features, etc., which are used to describe the specific attributes and characteristics of key areas or outliers in the image. Through feature extraction algorithms, this information is converted into quantifiable feature vectors.

[0086] The identification features are integrated with the image features to establish the identification features. The identification features are key indicators used to characterize the health status of the tunnel and can reflect the anomalies and changes in the tunnel structure. The identification features are trained and classified through machine learning algorithms (such as support vector machines, neural networks, etc.) to establish a model for predicting and diagnosing the health status of the tunnel.

[0087] Specifically, when the sensor collects data, the sensor parameters are adjusted according to the detection attention factor to ensure the focus of data collection. The collected multi-source data is processed, including image processing, signal processing, etc. Fusion features and image features are extracted from the processed data. The fusion features and image features are combined to establish recognition features. The recognition features are trained using historical data to establish a prediction and diagnosis model. The model is used to analyze the newly collected data, evaluate the health status of the tunnel, and predict potential problems.

[0088] Based on this step, a comprehensive and accurate identification feature can be established for tunnel health monitoring and assessment. The comprehensive use of fusion features and image features improves the accuracy and reliability of the monitoring system and ensures the safety and stability of the tunnel throughout its life cycle.

[0089] Furthermore, the method described in the present application also includes: establishing a tunnel timing anomaly based on the correction result, and configuring a warning signal based on the tunnel timing anomaly, the tunnel timing anomaly is obtained by analyzing the correction result through long and short timing windows; and performing tunnel warning management based on the warning signal.

[0090] Specifically: During the tunnel health monitoring process, various data may be generated, including real-time monitoring data, historical data, etc. These data need to be processed and analyzed so that the abnormal state of the tunnel structure can be identified. The correction result refers to the data obtained after processing, correction and calibration of the original monitoring data. After filtering, denoising, interpolation and other processing steps, the quality and accuracy of the data are improved. The tunnel timing anomaly refers to the abnormal state or behavior of the tunnel structure in the time series. These anomalies may be caused by factors such as structural damage, environmental changes, and construction impacts. By analyzing the correction results, these timing anomalies can be identified. Identifying tunnel timing anomalies usually requires the use of statistical methods, machine learning algorithms, or expert systems. For example, a threshold can be set to detect whether the data exceeds the normal range, or pattern recognition technology can be used to detect abnormal patterns.

[0091] The long time series window is used to analyze the long-term trend of the tunnel. For example, it can be a time span of several months to several years, which helps to identify slow changes and long-term trends in the tunnel structure. The short time series window is used to capture short-term changes in the tunnel. For example, it can be a time span of several days to several weeks, which helps to identify sudden events and rapid changes. Through the comprehensive analysis of long and short time series windows, abnormal changes in the health status of the tunnel can be identified. Compare the data in different time windows to find abnormal points or abnormal trends, such as sudden stress changes, increased deformation, etc.

[0092] According to the identified time series anomalies, configure the corresponding warning signal. The level of the warning signal can be divided into different levels according to the severity of the anomaly, such as low, medium, and high. Configure the threshold of the warning signal to determine under what circumstances the warning is triggered. For example, a high-level warning is triggered when the deformation exceeds a certain set value. Warning management refers to the process of managing and controlling tunnel warning signals. The warning management system monitors the health status of the tunnel in real time, receives sensor data and analyzes results. When the system detects a warning signal, it immediately issues an alarm.

[0093] The early warning management system takes corresponding response measures according to the level and type of the early warning signal. For low-level warnings, it may only record and monitor, while for high-level warnings, immediate action is required, such as notifying relevant departments, implementing emergency inspections and repairs, etc. All early warning signals and response measures are recorded and an early warning log is established. Through the analysis of the early warning log, the early warning management strategy and system parameters are continuously optimized.

[0094] In this step, by establishing tunnel timing anomalies and configuring early warning signals, the tunnel life cycle health monitoring method can timely detect and warn potential health problems. By using long and short timing window analysis, the long-term trend and short-term changes of the tunnel are comprehensively considered to improve the accuracy and reliability of anomaly identification. The real-time monitoring and response mechanism of the early warning management system ensures that timely measures can be taken to ensure the safety and stability of the tunnel.

[0095] In summary, the tunnel life cycle health monitoring method provided by the embodiment of the present application has the following technical effects:

[0096] 1. By comprehensively considering the tunnel's design information, real-time environmental information and sensor monitoring data, the tunnel life cycle model is established and updated to improve the accuracy and dynamic response capability of tunnel health monitoring. Coverage of blind areas and importance evaluation ensures comprehensive monitoring and accurate monitoring of key areas. Additional collection strategies and data fusion further optimize monitoring accuracy and efficiency, ultimately improving the safety and management level of the tunnel.

[0097] 2. Based on the layout information, structural information, device attenuation factors of built-in sensors, and real-time environmental information, evaluate the sensor coverage blind spots and establish the first penalty factor for tunnel location mapping. Accurately identify monitoring blind spots, optimize sensor layout, and improve the comprehensiveness and accuracy of tunnel monitoring.

[0098] 3. Based on the additional collection strategy, establish the collection location points, conduct strategy importance analysis, configure the collection reserved interval, and complete the additional data collection. Through importance analysis and reserved interval configuration, optimize the location and frequency of data collection to ensure monitoring coverage of key areas.

[0099] 4. Establish detection attention factors based on fusion results, constrain fusion sensor collection, extract fusion features and image features, and establish identification features. By integrating fusion features and image features, the depth and breadth of data analysis can be improved to provide more accurate tunnel health assessment.

[0100] Embodiment 2

[0101] Based on the same inventive concept as the tunnel life cycle health monitoring method in the aforementioned embodiment, Figure 3 As shown, an embodiment of the present application provides a tunnel life cycle health monitoring system, the system comprising:

[0102] Design information collection module 11: used to collect design information of the tunnel, the design information including structural information of the tunnel and layout information of built-in sensors;

[0103] An update lifecycle generation module 12 is used to establish a basic lifecycle of the tunnel according to the design information, monitor sensor data through built-in sensors, establish a time series monitoring data set, compensate the basic lifecycle through the time series monitoring data set, and generate an update lifecycle;

[0104] The first penalty factor establishment module 13 is used to obtain real-time environment information of the tunnel, evaluate the coverage blind area of ​​the built-in sensor based on the layout information, the structure information, the device attenuation factor of the built-in sensor, and the real-time environment information, and establish a first penalty factor for tunnel position mapping;

[0105] A second penalty factor establishment module 14: used to perform an important evaluation of the tunnel position based on the structural information and the geological information, and establish a second penalty factor mapped with the tunnel position;

[0106] Additional collection strategy configuration module 15: configured to configure an additional collection strategy through the first penalty factor and the second penalty factor, and perform additional data collection of the tunnel based on the additional collection strategy;

[0107] The update life cycle correction module 16 is used to perform update life cycle correction according to the additional data collection result, and complete the tunnel health monitoring based on the correction result.

[0108] Furthermore, the system is also used for:

[0109] To establish the actual coverage of the built-in sensor, the formula is as follows:

[0110] C i =R i ·(1-OCF)·PF·(1-CF)·(1-DF)·(1-EF);

[0111] Among them, C i Characterizes the actual coverage of the i-th built-in sensor, R i is the theoretical coverage of the i-th built-in sensor, OCF is the correction factor for the shielding of the internal structure of the tunnel, PF is the performance correction factor of the built-in sensor, CF is the correction factor for the curvature of the tunnel, DF is the time performance attenuation correction factor of the built-in sensor, and EF is the correction factor for the influence of environmental conditions on the built-in sensor;

[0112] According to the actual coverage range, the blind spots are summarized to complete the coverage blind spot evaluation. The formula is as follows:

[0113]

[0114] Among them, B is the summary result of the blind area, n is the total number of built-in sensors, and L is the total length of the tunnel.

[0115] Furthermore, the system is also used for:

[0116] Performing factor alignment of the first penalty factor and the second penalty factor based on the tunnel position mapping;

[0117] Determine whether the first penalty factor and the second penalty factor are in the same position according to the factor alignment result;

[0118] If the first penalty factor and the second penalty factor are at the same position, then superposition and additional acquisition analysis of monitoring accuracy is performed to establish a superposition and additional acquisition strategy;

[0119] If the first penalty factor and the second penalty factor are not in the same position, an independent additional acquisition strategy is established according to the separated first penalty factor and the second penalty factor;

[0120] The additional acquisition strategy configuration is completed according to the superimposed additional acquisition strategy and the independent additional acquisition strategy.

[0121] Furthermore, the system is also used for:

[0122] Establishing a collection location point according to the additional collection strategy;

[0123] Performing a strategy importance analysis on the additional collection strategy, and configuring a collection reserved interval according to the strategy importance analysis result;

[0124] The acquisition position point is reconstructed through the acquisition reserved interval, and additional data acquisition is completed according to the reconstructed acquisition position point using the additional acquisition strategy.

[0125] Furthermore, the system is also used for:

[0126] Calling the image data in the additional data acquisition result, performing grayscale processing on the image data, performing sensitive verification based on the LBP operator, and establishing a first sensitive area;

[0127] Performing edge detection on the image data, and establishing a second sensitive area based on the edge detection result;

[0128] The first sensitive area and the second sensitive area are fused, an identification feature of the additional data acquisition result is established according to the fusion result, and an update life cycle correction is performed based on the identification feature.

[0129] Furthermore, the system is also used for:

[0130] Establishing a detection attention factor according to the fusion result, wherein the detection attention factor is an acquisition attention factor of the fusion sensor after image acquisition under the additional acquisition strategy;

[0131] After constraining the fusion sensor to collect data through the collection attention factor, a fusion feature is established;

[0132] Performing focus identification of image data according to the fusion result and establishing image features;

[0133] An identification feature is established according to the fusion feature and the image feature.

[0134] Furthermore, the system is also used for:

[0135] Establish a tunnel timing anomaly according to the correction result, and configure an early warning signal based on the tunnel timing anomaly, wherein the tunnel timing anomaly is obtained by analyzing the correction result through the long and short timing windows;

[0136] Tunnel early warning management is performed based on the early warning signal.

[0137] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0138] Furthermore, the first or second mentioned above may represent an order relationship, or may represent a specific concept, and / or may refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A tunnel life cycle health monitoring method, characterized in that: The method comprises: Collecting design information of the tunnel, wherein the design information includes structural information of the tunnel and layout information of built-in sensors; Establishing a basic life cycle of the tunnel according to the design information, monitoring sensor data through built-in sensors, establishing a time series monitoring data set, compensating the basic life cycle through the time series monitoring data set, and generating an updated life cycle; Acquire real-time environmental information of the tunnel, evaluate the coverage blind area of ​​the built-in sensor based on the layout information, the structural information, the device attenuation factor of the built-in sensor, and the real-time environmental information, and establish a first penalty factor mapped to the tunnel position, wherein the first penalty factor reflects the risk level caused by the sensor coverage blind area at different positions of the tunnel; Based on the structural information and geological information, an importance evaluation of the tunnel location is performed, and a second penalty factor mapped with the tunnel location is established, wherein the second penalty factor reflects the importance of the tunnel location and its impact on the overall safety status; The additional collection strategy is configured by the first penalty factor and the second penalty factor, and additional data collection of the tunnel is performed based on the additional collection strategy, wherein the additional collection strategy is configured including: determining the data collection priority of each position of the tunnel in combination with the first penalty factor and the second penalty factor; selecting parameters that need additional collection according to the security requirements and risk assessment results of the tunnel; formulating different data collection frequencies according to the risk level and importance of each position; selecting a suitable collection method according to the actual situation of the tunnel and the requirements for collection parameters; and setting a warning threshold for each collection parameter; Update the life cycle correction according to the additional data collection results, and complete the tunnel health monitoring based on the correction results; The evaluating of the coverage blind area of ​​the built-in sensor based on the deployment information, the structure information, the device attenuation factor of the built-in sensor, and the real-time environment information further includes: To establish the actual coverage of the built-in sensor, the formula is as follows: ； in, Characterization Actual coverage of built-in sensors, For the Theoretical coverage of built-in sensors, is the correction factor for the occlusion of the tunnel’s internal structure, is the performance correction factor of the built-in sensor, is the correction factor for tunnel curvature, is the time performance attenuation correction factor of the built-in sensor, It is the correction factor of the built-in sensor affected by environmental conditions; According to the actual coverage range, the blind spots are summarized to complete the coverage blind spot evaluation. The formula is as follows: ； in, To summarize the results for the blind area, is the total number of built-in sensors, is the total length of the tunnel. For each sensor i, calculate the theoretical coverage The actual coverage The difference between , summarize the blind areas of all sensors, and perform a union operation The total blind area is obtained and then compared with the total length of the tunnel. Intersect to ensure that the blind area results are within the tunnel range.

2. A tunnel life cycle health monitoring method as claimed in claim 1, characterized in that: The configuring of the additional collection strategy by using the first penalty factor and the second penalty factor also includes: Performing factor alignment of the first penalty factor and the second penalty factor based on the tunnel position mapping; Determine whether the first penalty factor and the second penalty factor are in the same position according to the factor alignment result; If the first penalty factor and the second penalty factor are at the same position, then superposition and additional acquisition analysis of monitoring accuracy is performed to establish a superposition and additional acquisition strategy; If the first penalty factor and the second penalty factor are not in the same position, an independent additional acquisition strategy is established according to the separated first penalty factor and the second penalty factor; The additional acquisition strategy configuration is completed according to the superimposed additional acquisition strategy and the independent additional acquisition strategy.

3. A tunnel life cycle health monitoring method as claimed in claim 1, characterized in that: The performing of additional data collection of the tunnel based on the additional collection strategy further includes: Establishing a collection location point according to the additional collection strategy; Performing a strategy importance analysis on the additional collection strategy, and configuring a collection reserved interval according to the strategy importance analysis result; The acquisition position point is reconstructed through the acquisition reserved interval, and additional data acquisition is completed according to the reconstructed acquisition position point using the additional acquisition strategy.

4. A tunnel life cycle health monitoring method as claimed in claim 1, characterized in that: The updating of the life cycle correction according to the additional data collection result also includes: Calling the image data in the additional data acquisition result, performing grayscale processing on the image data, performing sensitive verification based on the LBP operator, and establishing a first sensitive area; Performing edge detection on the image data, and establishing a second sensitive area based on the edge detection result; The first sensitive area and the second sensitive area are fused, an identification feature of the additional data acquisition result is established according to the fusion result, and an update life cycle correction is performed based on the identification feature.

5. A tunnel life cycle health monitoring method as claimed in claim 4, characterized in that: The step of establishing identification features of the additional data acquisition results based on the fusion results further includes: Establishing a detection attention factor according to the fusion result, wherein the detection attention factor is an acquisition attention factor of the fusion sensor after image acquisition under the additional acquisition strategy; After constraining the fusion sensor to collect data through the collection attention factor, a fusion feature is established; Performing focus identification of image data according to the fusion result and establishing image features; An identification feature is established according to the fusion feature and the image feature.

6. A tunnel life cycle health monitoring method as claimed in claim 1, characterized in that: The method further comprises: Establish a tunnel timing anomaly according to the correction result, and configure an early warning signal based on the tunnel timing anomaly, wherein the tunnel timing anomaly is obtained by analyzing the correction result through the long and short timing windows; Tunnel early warning management is performed based on the early warning signal.

7. A tunnel life cycle health monitoring system, characterized in that: The system is used to execute a tunnel life cycle health monitoring method as described in any one of claims 1 to 6, and the system comprises: Design information collection module: used to collect design information of the tunnel, including structural information of the tunnel and layout information of built-in sensors; Update life cycle generation module: used to establish the basic life cycle of the tunnel according to the design information, monitor the sensor data through the built-in sensor, establish a time series monitoring data set, compensate the basic life cycle through the time series monitoring data set, and generate an update life cycle; A first penalty factor establishment module: used to obtain real-time environmental information of the tunnel, evaluate the coverage blind area of ​​the built-in sensor based on the layout information, the structural information, the device attenuation factor of the built-in sensor, and the real-time environmental information, and establish a first penalty factor mapped to the tunnel position, wherein the first penalty factor reflects the risk level caused by the sensor coverage blind area at different positions of the tunnel; A second penalty factor establishment module: used for performing an important evaluation of the tunnel position based on the structural information and the geological information, and establishing a second penalty factor mapped with the tunnel position, wherein the first penalty factor reflects the risk level caused by the sensor coverage blind area at different positions of the tunnel; Additional collection strategy configuration module: used to configure additional collection strategies through the first penalty factor and the second penalty factor, and perform additional data collection of the tunnel based on the additional collection strategy, wherein configuring the additional collection strategy includes: determining the data collection priority of each location of the tunnel in combination with the first penalty factor and the second penalty factor; selecting parameters that need additional collection according to the security requirements and risk assessment results of the tunnel; formulating different data collection frequencies according to the risk level and importance of each location; selecting a suitable collection method according to the actual situation of the tunnel and the requirements for collection parameters; and setting an early warning threshold for each collection parameter; Update life cycle correction module: used to perform update life cycle correction according to the additional data collection results, and complete tunnel health monitoring based on the correction results.

Images