An intelligent operation and maintenance system for tunnel structure hierarchical health monitoring

Abstract

The present application discloses a hierarchical health monitoring intelligent operation and maintenance system for tunnel structures, including a data layer, an analysis layer, an application layer and a user layer; the data layer includes the physical data generated by the tunnel structure during operation and maintenance; the analysis layer is used to clean, reorganize and analyze the data obtained by the data layer, and then locate the weak sections of the tunnel structure and feed it back to the data layer for continuous monitoring; the application layer is used to display the analysis results and data of the analysis layer; the user layer is used to manage platform users. The beneficial effects of the present application: hierarchical lightweight monitoring of tunnels can be carried out, which can not only provide lightweight monitoring of the entire tunnel and achieve accurate positioning of weak sections, but also focus on monitoring weak sections, and timely provide intelligent warnings for abnormal structural conditions, providing targeted reference and guidance for its daily management and maintenance decisions, and ensuring the normal operation of the entire tunnel.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel safety monitoring, and in particular to an intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures. Background Art

[0002] Traditional tunnel structural health monitoring refers to installing sensors at key locations in the tunnel to conduct long-term online monitoring of various mechanical responses of the tunnel structure during the operation period, so as to achieve real-time evaluation and early warning of the health status of the tunnel structure and provide guidance for the safe operation and maintenance of the tunnel. With the increasing importance of tunnel operation and maintenance and the development of operation and maintenance concepts, traditional structural health monitoring methods face the following challenges:

[0003] (1) The method of selecting key positions is too subjective. The selection of key positions directly affects the scientificity and rationality of tunnel health monitoring. Currently, the selection of key positions mainly relies on the experience of practitioners, which is highly subjective.

[0004] (2) The life of sensors is short. Currently, the life of sensors used to monitor structural status generally does not exceed 5 years, which is far from the service life of the tunnel and requires frequent replacement. Summary of the invention

[0005] One of the objects of the present application is to provide a tunnel structure hierarchical health monitoring intelligent operation and maintenance system that can solve at least one defect in the above-mentioned background technology.

[0006] In order to achieve at least one of the above-mentioned purposes, the technical solution adopted in the present application is: a tunnel structure hierarchical health monitoring intelligent operation and maintenance system, including a data layer, an analysis layer, an application layer and a user layer; the data layer includes the physical data generated by the tunnel structure during operation and maintenance; the analysis layer is used to clean, reorganize and analyze the data in the data layer, and then locate the weak sections of the tunnel structure and feed back to the data layer for continuous monitoring; the application layer uses digital twin technology to display the analysis results and data of the analysis layer; the user layer is used to manage platform users.

[0007] Preferably, the data layer includes a first data layer and a second data layer; the first data layer includes tunnel structure dimension data, tunnel structure surface temperature data and tunnel longitudinal deformation data; the second data layer includes weak section positioning data, tunnel vault deformation data, tunnel longitudinal uneven settlement data and water seepage location data.

[0008] Preferably, the analysis layer includes a first analysis layer and a second analysis layer; the first analysis layer is suitable for cleaning and reorganizing the data of the first data layer, and analyzing the equivalent strength of the tunnel structure based on the retained longitudinal deformation data under the influence of the surface temperature of the tunnel structure, and then performing a degradation evaluation on the strength of the lining structure of the entire tunnel to mark the weak section and access the second data layer; the second analysis layer continuously monitors the structural health of the weak section based on the monitoring data of each monitoring item of the weak section, identifies the disease of the weak section based on the monitoring results, and cancels the weak section mark after the weak section is reinforced to re-access the first data layer for monitoring.

[0009] Preferably, the process of evaluating the degradation of the strength of the tunnel lining structure is as follows: based on the mechanical properties of concrete, a concrete performance data set is constructed through finite element simulation; the concrete performance data set is trained using a deep learning method to obtain a concrete performance evaluation model; the surface temperature data and longitudinal deformation data retained by the first analysis layer are input into the concrete performance evaluation model for inversion to obtain an elastic modulus evaluation value of the lining structure of the entire tunnel; the inversion result is compared with the design standard to determine the degree of degradation of the lining structure of the entire tunnel and mark the weak sections.

[0010] Preferably, the obtained concrete performance evaluation model needs to be corrected, and the modification process is as follows: the historical data of the temperature and longitudinal deformation of the tunnel are substituted into the concrete performance evaluation model as correction data; the output result of the concrete performance evaluation model is compared with the historical elastic modulus data of the tunnel; if the error between the two is less than or equal to the set threshold, it means that the obtained concrete performance evaluation model meets the accuracy requirements; if the error between the two is greater than the set threshold, an error analysis is performed and the concrete performance evaluation model is corrected based on the historical data.

[0011] Preferably, the data layer obtains the data of the first data layer through a tunnel weak section locating subsystem; the tunnel weak section locating subsystem includes a plurality of first visual detection units and a plurality of temperature detection units; the tunnel is divided into a plurality of adjacent monitoring sections along the longitudinal length direction, and the first visual detection unit and the temperature detection unit are correspondingly arranged in each of the monitoring sections; the temperature detection unit is suitable for collecting the surface temperature of the monitoring section; the first visual detection unit obtains the longitudinal deformation of the monitoring section by performing image acquisition on the monitoring points set at the end of the monitoring section.

[0012] Preferably, at least one monitoring point is provided at the end of the monitoring section, and the multiple monitoring points at the same end are arranged at equal intervals along the cross-sectional contour direction of the tunnel; the monitoring points at both ends of the monitoring section are installed with targets, and the first visual detection unit is suitable for performing image acquisition on the target at at least one end of the monitoring section, and then obtaining the longitudinal deformation amount corresponding to the monitoring section according to the imaging size change of the target.

[0013] Preferably, the data layer obtains the tunnel vault deformation data in the second data layer through the vault deformation monitoring subsystem, and the tunnel vault deformation data is represented by the vault sinking displacement; the vault deformation monitoring subsystem includes a first punctuation point arranged on the vault of the weak section, and a second visual detection unit installed on the ground; the second visual detection unit is suitable for performing image acquisition on the first punctuation point, and thereby obtaining the sinking displacement of the first punctuation point.

[0014] Preferably, the data layer obtains the longitudinal uneven settlement data of the tunnel in the second data layer through the uneven settlement monitoring subsystem; the uneven settlement monitoring subsystem includes multiple third visual detection units and multiple second punctuation marks; the second punctuation marks are respectively set at each settlement joint and / or expansion joint of the tunnel, and the third visual detection unit is arranged on the ground and located between adjacent second punctuation marks, so as to simultaneously capture images of two adjacent second punctuation marks, and then obtain the longitudinal uneven settlement data of the tunnel through the settlement displacement difference between adjacent second punctuation marks.

[0015] Preferably, the data layer obtains the water seepage position data in the second data layer through a water seepage position positioning subsystem; the water seepage position positioning subsystem includes multiple groups of fourth visual detection units respectively arranged at each joint position of the tunnel, and each group of multiple fourth visual detection units are arranged along both sides of the tunnel to respectively monitor the opposite wall areas; the fourth visual detection unit uses dual-spectrum thermal imaging technology to identify the position of the water seepage point and the water seepage area to obtain the water seepage position data.

[0016] Compared with the prior art, the beneficial effects of this application are:

[0017] (1) This application can conduct hierarchical lightweight monitoring of tunnels, which can not only provide lightweight monitoring of the entire tunnel and achieve accurate positioning of weak sections, but also focus on monitoring weak sections and provide timely intelligent warnings of abnormal structural conditions, thus providing targeted reference and guidance for daily management and maintenance decisions, and ensuring the normal operation of the entire tunnel.

[0018] (2) This application scientifically classifies monitoring and control indicators, achieving full-line monitoring while greatly reducing cost investment, helping to transform from traditional post-event response to preventive and precise maintenance, extending the service life of the tunnel and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The following is a schematic diagram of the workflow of this application.

[0020] Figure 2 This is a schematic diagram of the layout structure of the tunnel weak section positioning subsystem in this application.

[0021] Figure 3 Schematic diagram of the principle of longitudinal deformation calculation performed by the visual detection unit in this application.

[0022] Figure 4 Schematic diagram of the modification process of the concrete performance evaluation model in this application.

[0023] Figure 5 This is a schematic diagram of the layout structure of the vault deformation monitoring subsystem in this application.

[0024] Figure 6 This is a schematic diagram of the layout structure of the water seepage location positioning subsystem in this application. DETAILED DESCRIPTION

[0025] Below, the present application is further described in conjunction with specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0026] In the description of the present application, it should be noted that directional words, such as the terms "center", "lateral", "longitudinal", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", etc., indicating directions and positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of narrating the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and cannot be understood as limiting the specific scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0028] The terms "including" and "having" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0029] One of the preferred embodiments of the present application is as follows: Figure 1 As shown in the figure, a tunnel structure hierarchical health monitoring intelligent operation and maintenance system includes a data layer, an analysis layer, an application layer and a user layer. The data layer mainly includes the physical data generated by the tunnel structure during operation and maintenance. The analysis layer is used to clean, reorganize and analyze the physical data of the data layer, and then locate the weak sections of the tunnel structure and feed it back to the data layer for continuous monitoring. The application layer can use digital twin technology to digitally display the analysis results and data of the analysis layer. The user layer is used to manage platform users, such as setting permissions.

[0030] It can be understood that the tunnel structure hierarchical health monitoring intelligent operation and maintenance system of this application relies on digital twin technology to physically map and simulate the tunnel structure; a four-layer digital twin basic system architecture can be constructed, namely the data layer, analysis layer, application layer and user layer. These four layers of digital twin basic system architecture influence and interact with each other during the whole tunnel monitoring and operation and maintenance process, and jointly drive the correct operation of the tunnel hierarchical health monitoring intelligent operation and maintenance system.

[0031] It should be known that when conducting structural health monitoring of tunnels, if the health monitoring is performed on the entire structure of the tunnel, it will inevitably require high manpower and material costs. In the actual use of the tunnel, the structural strength of most tunnel sections can meet the strength requirements within the service life, and only a small number of weak sections will have structural abnormalities. Therefore, when conducting full-line health monitoring of the tunnel, the tunnel can be graded, that is, the tunnel can be divided into weak sections and non-weak sections. For non-weak sections, a relatively simple monitoring method can be used for maintenance, while for weak sections, key monitoring is required, so that timely identification and alarm can be carried out when diseases occur in weak sections.

[0032] It should also be known that the division of weak sections and non-weak sections of the tunnel can be judged by analyzing the degree of structural degradation of the tunnel based on the physical data of the tunnel during operation and maintenance. Compared with traditional methods, this application can provide monitoring of the entire tunnel to achieve accurate positioning of weak sections; it can also focus on monitoring weak sections and provide intelligent early warnings for abnormal structural conditions in a timely manner. It provides targeted reference and guidance for its daily management and maintenance decisions to ensure the normal operation of the entire tunnel. At the same time, this application scientifically classifies monitoring and control indicators, realizes full-line monitoring of the tunnel, and greatly reduces cost investment, which helps to transform from traditional post-event response to preventive and precise maintenance, extend the service life of the tunnel, and reduce maintenance costs.

[0033] In this embodiment, Figure 1 As shown, the physical data included in the data layer can be divided into structural data, system monitoring data and personnel detection data. According to the needs of system hierarchical management, it can be divided into the first data layer and the second data layer. The first data layer includes tunnel structure size data, tunnel structure surface temperature data and tunnel longitudinal deformation data. The second data layer includes weak section positioning data, tunnel vault deformation data, tunnel longitudinal uneven settlement data, water seepage location data and crack location data.

[0034] It should be noted that the data in the first data layer is mainly used to locate the weak section of the tunnel. Not all the data included in the second data layer need to be monitored for the weak section, and the necessary monitoring items can be selected according to the on-site conditions of the weak section. If the weak section is just insufficient in structural strength, it is only necessary to monitor the tunnel vault deformation data and the longitudinal uneven settlement data of the tunnel, and there is no need to monitor the water seepage location data and crack location data.

[0035] In this embodiment, Figure 1As shown in the figure, according to the hierarchical management needs of the system, the analysis layer can be divided into the first analysis layer and the second analysis layer according to the needs. Among them, the first analysis layer can clean and reorganize the monitoring data obtained from the first data layer; thus, the abnormal data can be excluded, leaving only the longitudinal deformation data of the tunnel structure under the influence of the surface temperature. Then the remaining data can be analyzed to obtain the equivalent strength of the tunnel structure; then the deterioration evaluation of the lining structure strength of the entire tunnel is carried out according to the existing structural strength detection data, and the abnormal result section is screened out for alarm; at the same time, the abnormal section can be marked as a weak section and connected to the second data layer for key monitoring. The second analysis layer can continuously monitor the structural health of the weak section according to the monitoring data of each monitoring item of the weak section; based on the monitoring results, the weak section is identified for disease, so that it can be identified in time when the disease occurs. After identifying the disease in the weak section, the personnel can conduct on-site confirmation and formulate a subsequent treatment plan. According to the formulated treatment plan, the weak section is structurally reinforced, and after the reinforcement is completed, the mark of the weak section can be cancelled, so that it can be re-connected to the first data layer as a non-weak section for routine monitoring of structural strength.

[0036] It should be known that data cleaning mainly involves formatting and deleting data with content errors, logical errors, meaningless data, and irrelevant data. Data reorganization mainly involves integrating data features using methods commonly used by technicians in this field, such as data normalization and data standardization.

[0037] In this embodiment, the degradation evaluation of the strength of the tunnel lining structure in the first analysis layer includes the following processes: based on the mechanical properties of concrete, a concrete performance data set is constructed through finite element simulation; the concrete performance data set is trained using a deep learning method to obtain a concrete performance evaluation model; the surface temperature data and longitudinal deformation data retained in the first analysis layer are input into the concrete performance evaluation model for inversion to obtain an elastic modulus evaluation value of the lining structure of the entire tunnel; the inversion result is compared with the design standard to determine the degree of degradation of the lining structure of the entire tunnel and mark the weak sections.

[0038] It can be understood that, for the establishment of the concrete performance evaluation model; first, a finite element model of the tunnel concrete structure can be established in the finite element software based on the known mechanical properties of concrete; then the temperature is used as the input of the model, and the deformation relationship is used as the output of the model; by listing as many temperature parameters as possible and inputting them into the model to output the corresponding deformation, a data set including different temperatures and the deformations that match them can be obtained, namely, a concrete performance data set. It should be known that the obtained concrete performance data already contains the longitudinal deformation corresponding to the different temperatures that may occur in the tunnel during use. Then, the concrete performance data set is trained by the deep learning model to obtain a concrete performance evaluation model, and the output of the concrete performance evaluation model is the elastic modulus E of the concrete structure. After obtaining the concrete performance evaluation model, the surface temperature data and longitudinal deformation data of the tunnel structure retained by the first analysis layer can be substituted into the concrete performance evaluation model to obtain the elastic modulus evaluation values ​​of each area of ​​the entire target tunnel. Finally, the obtained elastic modulus evaluation value is compared with the design standard of the tunnel lining to judge the degree of degradation of different areas of the entire tunnel.

[0039] It is important to know that after the first analysis layer sends the data of the first data layer into the concrete performance evaluation model, the concrete performance evaluation model can use a table-like lookup method to quickly match the input parameters with the concrete performance data set, and output the elastic modulus that has been calculated in advance according to the matched position, which can effectively improve the calculation speed of the model.

[0040] It should be known that the mechanical properties of concrete, that is, the initial elastic modulus E of concrete, can be obtained from the tunnel structure inspection report. The design standard of concrete can also be obtained from the tunnel structure inspection report. Generally speaking, the ultimate strength of the concrete structure that can operate normally can be used as the judgment threshold. Concrete structures with strengths lower than the ultimate strength of normal operation can be judged as abnormal, and vice versa.

[0041] In this embodiment, the concrete performance evaluation model obtained needs to be modified, such as Figure 4 As shown in the figure, the specific modification process is as follows: the historical data of tunnel temperature and longitudinal deformation are substituted into the concrete performance evaluation model as correction data; the output result of the concrete performance evaluation model is compared with the historical elastic modulus data of the tunnel; if the error between the two is less than or equal to the set threshold, it means that the obtained concrete performance evaluation model meets the accuracy requirements; if the error between the two is greater than the set threshold, an error analysis is performed and the concrete performance evaluation model is corrected based on the historical data.

[0042] It is understandable that the data in the concrete performance data set is obtained by finite element simulation, which is only theoretical deformation information obtained by theoretical calculation. In order to ensure that the obtained concrete performance evaluation model has sufficient accuracy, it is necessary to compare the actual value with the theoretical value to realize the correction of the concrete performance evaluation model. The historical data of the tunnel structure can be obtained from the tunnel structure monitoring report, and the temperature and deformation data of half a year to one year can be used as correction data.

[0043] In this embodiment, Figure 1 As shown in the figure, the content displayed by the application layer through digital twin technology includes the physical parameters of the tunnel, the tunnel twin model, the tunnel weak section twin model and equipment management information.

[0044] The physical parameters mainly include tunnel overview, tunnel structural parameters and the number of weak sections. Tunnel overview can show users the name, construction time and geographical location of the tunnel; tunnel structural parameters can show users information such as the length and width of the tunnel.

[0045] The contents of the tunnel twin model mainly include structural degradation evaluation, weak section location and alarm, and fire location and alarm. Specifically, the tunnel twin model displays the results of the structural degradation evaluation obtained by the first analysis layer on the first data layer. At the same time, it can also locate the occurrence of fire in the tunnel according to the sudden change in the strength of the lining structure. It should be known that the longitudinal deformation of the tunnel is affected by temperature. When a fire occurs, the surface temperature of the tunnel lining drops sharply, which will cause the data of the first data layer to mutate. Therefore, it can be judged that a fire has occurred in the tunnel, and the fire point can be located according to the tunnel position corresponding to the mutation data.

[0046] The contents of the weak section twin model include abnormal deformation alarm, water leakage alarm, crack location record and structural health evaluation. Specifically, the weak section twin model is to display the analysis structure of the second analysis layer on the second data layer. Based on the data of the second data layer, the second analysis layer can identify and display the vault deformation, longitudinal uneven settlement, water seepage location and crack information of the tunnel lining structure.

[0047] The content of equipment management mainly includes equipment model information, equipment installation information, equipment maintenance information, etc. Specifically, the data of the first data layer and the second data layer need to be monitored by specific equipment, and the equipment for monitoring needs to be managed. For convenience, the following will describe in detail the equipment used for monitoring the first data layer and the second data layer.

[0048] In this embodiment, the data of the first data layer and the second data layer can be acquired through the corresponding monitoring subsystem. Among them, the data of the first data layer is acquired through the weak section positioning subsystem, the vault deformation data of the second data layer is acquired through the vault deformation monitoring subsystem, the longitudinal uneven settlement data of the tunnel of the second data layer is acquired through the uneven settlement monitoring subsystem, and the water seepage position data of the second data layer is acquired through the water seepage position positioning subsystem. For easy understanding, the specific structure of each subsystem will be described in detail below.

[0049] 1. Weak section positioning subsystem.

[0050] like Figure 2 As shown, the tunnel weak section positioning subsystem includes multiple first visual detection units and multiple temperature detection units; the tunnel is divided into multiple adjacent monitoring sections along the longitudinal length direction, and the first visual detection unit and the temperature detection unit are arranged in each monitoring section accordingly; the temperature detection unit can collect the surface temperature of the monitoring section; the first visual detection unit acquires the longitudinal deformation of the monitoring section by performing image acquisition on the monitoring points set at the end of the monitoring section. After obtaining the temperature and longitudinal deformation data of each monitoring section of the entire tunnel lining, the first analysis layer can evaluate the degree of structural degradation of each monitoring section of the entire tunnel lining according to the acquired data, and locate the weak section and issue an alarm according to the evaluation results.

[0051] It should be noted that the structural strength of the tunnel lining is mainly determined by the elastic modulus E, and the factors affecting the elastic modulus are mainly temperature and longitudinal deformation; since the tunnel is generally a circular arch cross-section, the longitudinal deformation can also be regarded as axial deformation. Therefore, the monitoring of the structural strength of the tunnel lining is mainly the monitoring of the surface temperature and longitudinal deformation of the tunnel. Since the length of the tunnel is generally long, in order to facilitate monitoring and improve the accuracy of monitoring, the tunnel can be divided into multiple sections along the longitudinal or axial length direction, so that multiple monitoring sections with relatively short lengths can be obtained. Then, a monitoring point can be set at the end position of each monitoring section for the first visual detection unit to monitor the longitudinal deformation. The visual monitoring method is a non-contact method, which can effectively avoid the influence of tunnel deformation on the monitoring results to improve the monitoring accuracy. At the same time, a temperature detection unit is installed on each monitoring section for temperature collection. For each monitoring section, a temperature detection unit can be installed on the central surface of the monitoring section, or multiple temperature detection units can be installed at equal intervals along the longitudinal direction of the monitoring section.

[0052] It is understandable that the specific structure and working principle of the first visual detection unit and the temperature detection unit are well-known technologies to those skilled in the art; common first visual detection units include displacement monitoring camera devices such as gun cameras and ball cameras, and common temperature detection units include thermometers and temperature sensors. For the temperature detection unit, a thermometer can be used to capture the reading of the thermometer through a displacement monitoring camera and transmit the image data to the monitoring center for long-distance temperature data reading; for the temperature sensor, it can be directly transmitted to the monitoring center by signal transmission; the specific selection can be made according to the actual needs of those skilled in the art.

[0053] Specifically, this application uses non-contact measurement to monitor the longitudinal strain of the tunnel and the ambient temperature in sections and establish a relationship. It also analyzes the relationship between the longitudinal deformation and the degradation of the structural stiffness in sections, thereby locating the sections where tunnel diseases are prone to or have occurred, and conducting key monitoring. This process is low-cost, simple to operate, and can protect the entire tunnel section. In combination with existing non-contact monitoring, it can achieve accurate positioning of tunnel damage.

[0054] In this embodiment, Figure 2 As shown, in order to facilitate the first visual detection unit to monitor the longitudinal deformation of the tunnel, a target can be installed at the monitoring point; the first visual detection unit can capture a clear image by shooting the corresponding target. The first visual detection unit can continuously capture images of the target; and then the longitudinal deformation of the corresponding monitoring section can be calculated based on the change in the imaging size of the target in the images captured multiple times.

[0055] It should be known that the common method of directly monitoring an object using a visual method is to directly collect the deformation of the object; specifically, the initial position of the monitoring point of the object can be marked, and then the monitoring point can move with the deformation of the object during the deformation of the object. At this time, the deformation of the object can be obtained by comparing the current position of the monitoring point with the marked position. However, in actual use, since the shooting direction of the first visual detection unit is perpendicular to the deformation direction of the object and always remains stationary, a certain deflection angle will be generated between the first visual detection unit and the object during the deformation of the object, thereby affecting the accuracy of deformation collection; if you want to improve the accuracy, you need to use a corresponding algorithm to compensate, which will increase the calculation amount and cost of deformation collection, and the accuracy of the algorithm also directly affects the accuracy of deformation detection.

[0056] In this embodiment, the longitudinal displacement change from the target to the first visual detection unit, i.e., the longitudinal deformation of the monitoring segment, can be obtained by reverse deduction based on the different image sizes of the target as the distance from the monitoring segment to the first visual detection unit changes with the longitudinal deformation of the monitoring segment. For convenience, the following is a detailed description of the process of obtaining the longitudinal deformation of the monitoring segment by different target imaging sizes in this embodiment.

[0057] Specifically, Figure 3 As shown, the height of the target can be set as H, the longitudinal distance between the target and the lens of the displacement monitoring camera is L+ΔL, and the distance from the lens of the displacement monitoring camera to the internal imaging element is l. Initially, the target can be represented by a solid line frame, and the image height size of the target in the internal imaging element of the displacement monitoring camera is x 0 . With the longitudinal deformation of the monitoring segment, the target can move synchronously with the deformation of the monitoring segment. At this time, the target can be represented by a dotted frame; assuming that the target is approaching the displacement monitoring camera, and the approaching distance is ΔL, that is, the longitudinal deformation of the monitoring segment, then the longitudinal distance from the target to the lens of the displacement monitoring camera is L. Correspondingly, the image height size of the target in the imaging element inside the displacement monitoring camera is x.

[0058] According to the geometric relationship, the following relationship can exist:

[0059] x 0 / l=H / (L+ΔL), x / l=H / L.

[0060] Transforming the above relationship, we can get: Hl = x 0 (L+ΔL), Hl=xL.

[0061] Then according to x 0 (L+ΔL)= xL, the calculation formula of longitudinal deformation ΔL can be simplified as: ΔL=[(x / x 0 )-l]L.

[0062] It should be known that, from the above calculation formula, the calculation of the longitudinal deformation of the monitoring section has nothing to do with the height of the target and the distance from the lens of the displacement monitoring camera to the imaging element, but is only related to the imaging height of the target and the longitudinal distance from the displacement monitoring camera to the target. This can effectively simplify the calculation process and avoid the influence of other factors on the calculation results, and can effectively improve the monitoring accuracy of the longitudinal deformation of the monitoring section.

[0063] It should be noted that in the above calculation process, the vertical distance from the target to the displacement monitoring camera is assumed to be constant; since the tunnel is a circular arch structure with strong compressive resistance, the tunnel can be regarded as having no deformation in the vertical direction. Therefore, there is only a change in the distance in the longitudinal direction between the target and the displacement monitoring camera, which can maintain a high accuracy of the calculation result and the calculation process is relatively simple.

[0064] In this embodiment, only one monitoring point can be set at the end of the monitoring section; however, considering that the stress conditions at various positions along the cross-sectional contour of the tunnel may be inconsistent, that is, the longitudinal deformation at various positions along the cross-sectional contour of the tunnel may be inconsistent. Therefore, in order to maintain the accuracy of the monitoring results, multiple monitoring points can be set at the end of each monitoring section, and the multiple monitoring points are set at equal intervals along the cross-sectional contour of the tunnel. A specific example is Figure 2 As shown, each monitoring section is provided with two monitoring points along the cross-sectional contour direction, and the two monitoring points are symmetrically arranged. The targets installed at the two monitoring points at the same end are imaged by different first visual detection units to respectively calculate the corresponding longitudinal deformation amounts.

[0065] In this embodiment, based on the imaging relationship between the first visual detection unit and the target, there are multiple ways to install the first visual detection unit. For ease of understanding, two examples are used for detailed description below.

[0066] Example 1: Figure 2 As shown, the first visual detection unit can be installed at any position on the wall corresponding to the monitoring section, so that the first visual detection unit can capture images of the target installed at at least one end of the monitoring section.

[0067] It can be understood that the number of first visual detection units generally corresponds to the number of monitoring sections. For the case where the tunnel section between adjacent settlement joints includes multiple monitoring sections, targets can be installed at both ends of each monitoring section, and two adjacent monitoring sections share a monitoring point at adjacent positions.

[0068] Then, the first visual detection unit located between the monitoring segments can capture images of the target installed at one end of the monitoring segment, and in order to ensure that all monitoring segments are measured, the target positions for image capture in the two targets corresponding to each monitoring segment are consistent. At this time, the longitudinal deformation of a single monitoring segment can be obtained by summing the calculation results of two adjacent first visual detection units.

[0069] Of course, the first visual detection unit located between the monitoring sections can simultaneously capture images of the targets at both ends of the monitoring section, and the longitudinal deformation of the monitoring section can be obtained by adding the results of the first visual detection unit capturing images of the targets at both ends and inversely calculating. In the current situation, the first visual detection unit is preferably installed in the middle of the wall of the monitoring section so that the initial distances from the first visual detection unit to the targets at both ends of the monitoring section are the same.

[0070] Example 2: The first visual detection unit is installed at a monitoring point at one end of the monitoring section, so that the first visual detection unit can capture images of a target installed at a monitoring point at the other end of the monitoring section.

[0071] It can be understood that the longitudinal deformation of the monitoring segment can be regarded as the change in distance between the monitoring points at both ends. Therefore, the first visual detection unit can be installed at one end of the monitoring segment. In this way, when the monitoring segment undergoes longitudinal deformation, the change in distance between the first visual detection unit and the monitoring point at the other end of the monitoring segment can be regarded as the longitudinal deformation of the monitoring segment.

[0072] It should be known that both of the above examples can meet the requirements of this application, but in order to further improve the accuracy of collecting longitudinal deformation, the installation method of the first visual detection unit in this embodiment preferably adopts the method in which the first visual detection unit in the above example 1 simultaneously collects images of the targets at both ends of the monitoring section, so that the targets installed at each monitoring point can be captured by the two first visual detection units for mutual verification.

[0073] Those skilled in the art should know that there are joints in the tunnel during construction, and the joints can be divided into settlement joints and construction joints. Among them, the settlement joints cannot realize the transfer of longitudinal deformation between two adjacent tunnel sections, so as to avoid the longitudinal deformation interference of the tunnel sections on both sides of the settlement joints. The construction joint is the joint surface where the concrete is poured successively, and the longitudinal deformation of the adjacent tunnel sections can be transferred. Therefore, when arranging the monitoring system of the present application, it is only necessary to consider the settlement joints of the tunnel. The setting distance of the settlement joints can be comprehensively considered according to the length of the tunnel, the cross-sectional form, the geological conditions, the design load and other conditions. Therefore, according to the setting distance of the settlement joints, the monitoring section division method of the tunnel can be mainly divided into the following two methods.

[0074] Method 1: For settlement joints with shorter distances, the tunnel section between adjacent settlement joints can be directly set as the monitoring section. Then, n-1 settlement joints are required to form n continuous monitoring sections in the tunnel. Generally speaking, the value of n is greater than 1.

[0075] Method 2: For settlement joints with a long distance, such as Figure 2As shown, the tunnel can be first divided into n sections according to the number of settlement joints, and then the tunnel sections between adjacent settlement joints are divided into m sections according to appropriate lengths, so that the tunnel can have n×m monitoring sections.

[0076] It is understandable that both of the above two methods can meet the requirements of this application, and can be selected according to the actual needs of technicians in this field. The values ​​of n and m can be selected according to actual needs, for example Figure 2 As shown, the value of n is greater than 1, and the value of m is 3. The longitudinal deformation of the three monitoring sections corresponding to adjacent settlement joints can be marked as ΔL 1 , ΔL 2 and ΔL 3 , the corresponding temperatures are marked as ΔT 1 , ΔT 2 and ΔT 3 ; The elastic modulus corresponding to the three monitoring sections is E 1 、E 2 and E 3 , the elastic modulus is related to the ratio of the corresponding longitudinal deformation and temperature.

[0077] 2. Arch deformation monitoring subsystem.

[0078] like Figure 5 As shown, the vault deformation monitoring subsystem includes a first mark point set on the vault of the weak section, and a second visual detection unit installed on the ground. The second visual detection unit can collect images of the first mark point. As the vault of the weak section sinks and deforms, the position of the first mark point will also change accordingly, and then the second visual detection unit can obtain the sinking displacement of the first mark point, which is the vault deformation data.

[0079] It should be noted that the data of the first punctuation point and the second visual detection unit can be determined according to the number of weak sections, and each weak section is corresponding to at least one first punctuation point and a second visual detection unit. And the deformation of the arch is mainly sinking, so the deformation data of the arch is mainly collected by sinking displacement.

[0080] It should be known that the specific structure and working principle of the second visual detection unit are well-known technologies to those skilled in the art. Common second visual detection units include high-precision displacement monitoring camera devices such as gun cameras and ball cameras. The first punctuation point can be a physical target or a virtual punctuation point. The core is to use visual technology to achieve continuous monitoring of deformation.

[0081] Taking the first punctuation point installation target as an example, the initial coordinates of a point P on the target can be set to (x, y). As the arch sinks and deforms, the target will also move accordingly, and then the coordinates of a point P on the target will become (x1 ,y 1 ), then the sinking deformation of the arch Δy=yy 1 .

[0082] 3. Uneven settlement monitoring subsystem.

[0083] The uneven settlement monitoring subsystem includes multiple third visual detection units and multiple second punctuation marks. The second punctuation marks are set in the same way as the monitoring points in the weak section positioning subsystem, and can be set at each settlement joint and / or expansion joint position of the tunnel; and the third visual detection unit is arranged on the ground and is correspondingly located between two adjacent second punctuation marks, so that each third visual detection unit can simultaneously collect images of two adjacent second punctuation marks, and then obtain the longitudinal uneven settlement data of each weak section of the entire tunnel through the settlement displacement difference of the two adjacent second punctuation marks.

[0084] It should be known that the second punctuation point has the same structure as the first punctuation point, and can be a target with a physical body installed, or a virtual punctuation point. The uneven settlement amount is expressed in the same way as the aforementioned sinking deformation amount of the dome.

[0085] 4. Water seepage location positioning subsystem.

[0086] like Figure 6 As shown, the water seepage location positioning subsystem includes multiple groups of fourth visual detection units respectively arranged at each joint position of the tunnel, and the specific number of groups can be determined according to the water seepage location. Multiple fourth visual detection units of each group are arranged along both sides of the tunnel to monitor the opposite wall area respectively. The fourth visual detection unit can use dual-spectrum thermal imaging technology to identify the location of the water seepage point and the water seepage area to obtain the water seepage location data.

[0087] It should be known that the fourth visual detection unit can use a dual-spectrum thermal imaging camera or other equipment that uses dual-spectrum thermal imaging technology. The specific structure and working principle of the dual-spectrum thermal imaging camera are well known to those skilled in the art. The dual-spectrum thermal imaging technology can capture and locate the seepage position and the area affected by the seepage based on the temperature difference and color difference of the moist structure. Specifically, there is a significant difference in temperature and color between the seepage structure and the surrounding structure of the tunnel lining wall. Therefore, based on the temperature difference data and color difference data between the seepage structure and the surrounding structure, the seepage points of the tunnel lining can be monitored, the area affected by the seepage can be determined, and timely alarms can be issued.

[0088] It should also be noted that the specific number of the fourth visual detection units in each group can be selected according to the actual environmental conditions, and it is necessary to ensure that the joint section of the tunnel lining structure can be fully covered. Figure 6As shown, the number of fourth visual inspection units in each group is four, and they are symmetrically arranged on both sides of the tunnel. The collection directions of the two fourth visual inspection units on a single side are set in an idea way, that is, the fourth visual inspection unit located at the bottom collects data obliquely upward, and the fourth visual inspection unit located at the top collects data obliquely downward, and then by superimposing the collection areas of the two fourth visual inspection units, the half-side area of ​​the cross-section at the contact point of the tunnel can be fully covered. Of course, if the collection range of the fourth visual inspection unit is sufficient, only one fourth visual inspection unit can be installed on a single side.

[0089] The above describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited by the above embodiments, and the above embodiments and the specification only describe the principles of the present application. The present application may have various changes and improvements without departing from the spirit and scope of the present application, and these changes and improvements fall within the scope of the present application for which protection is sought. The scope of protection claimed by the present application is defined by the attached claims and their equivalents.

Claims

1. An intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures, characterized in that: include: Data layer; The data layer includes physical data generated by the tunnel structure during operation and maintenance; Analytical layer; The analysis layer is used to clean, reorganize and analyze the data of the data layer, thereby locating the weak sections of the tunnel structure and feeding back to the data layer for continuous monitoring; Application layer; The application layer uses digital twin technology to display the analysis results and data of the analysis layer; as well as User layer; The user layer is used to manage platform users; The data layer includes: The first data layer includes tunnel structure dimension data, tunnel structure surface temperature data, tunnel longitudinal deformation data and tunnel structure strength detection data; and The second data layer includes weak section location data, tunnel crown deformation data, and tunnel longitudinal uneven settlement data; The analysis layer includes: The first analysis layer is suitable for cleaning and reorganizing the data of the first data layer, and analyzing the equivalent strength of the tunnel structure according to the retained longitudinal deformation data under the influence of the surface temperature of the tunnel structure, and then evaluating the deterioration of the lining structure strength of the entire tunnel to mark the weak section and access the second data layer; and The second analysis layer continuously monitors the structural health of the weak section according to the monitoring data of each monitoring item of the weak section; identifies the disease of the weak section based on the monitoring results, and cancels the weak section mark after the weak section is reinforced to reconnect to the first data layer for monitoring; The process of evaluating the deterioration of tunnel lining structure strength is as follows: Based on the mechanical properties of concrete, a concrete performance data set is constructed through finite element simulation; The concrete performance data set is trained using deep learning methods to obtain a concrete performance evaluation model; The surface temperature data and longitudinal deformation data retained in the first analysis layer are input into the concrete performance evaluation model for inversion to obtain the elastic modulus evaluation value of the lining structure of the entire tunnel; The inversion results are compared with the design standards to determine the degree of deterioration of the tunnel lining structure and mark the weak sections; The construction of the concrete performance data set includes the following processes: establishing a finite element model of the tunnel concrete structure in the finite element software based on the known mechanical properties of concrete; taking the temperature as the input of the model and the deformation relationship as the output of the model; listing different temperature parameters and inputting them into the model to output the corresponding deformation, and then obtaining a data set including different temperatures and corresponding deformations as the concrete performance data set.

2. The intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures according to claim 1, characterized in that: After the concrete performance evaluation model is obtained, it needs to be modified. The modification process is as follows: Substitute the historical data of tunnel temperature and longitudinal deformation into the concrete performance evaluation model as correction data; Compare the output of the concrete performance evaluation model with the historical elastic modulus data of the tunnel; If the error between the two is less than or equal to the set threshold, it means that the obtained concrete performance evaluation model meets the accuracy requirements; If the error between the two is greater than the set threshold, an error analysis is performed and the concrete performance evaluation model is corrected based on historical data.

3. The intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures according to claim 1 or 2, characterized in that: The data layer obtains the data of the first data layer through the tunnel weak section positioning subsystem; The tunnel weak section positioning subsystem includes: A plurality of temperature detection units; the tunnel is divided into a plurality of adjacent monitoring sections along the longitudinal length direction, and the temperature detection units are arranged correspondingly in each of the monitoring sections to collect the surface temperature; as well as A plurality of first visual detection units; the first visual detection units are arranged correspondingly at each of the monitoring sections; the first visual detection units acquire the longitudinal deformation of the monitoring section by performing image acquisition on the monitoring points arranged at the ends of the monitoring sections.

4. The intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures according to claim 3, characterized in that: At least one monitoring point is arranged at the end of the monitoring section, and a plurality of monitoring points at the same end are arranged at equal intervals along the cross-sectional profile direction of the tunnel; The monitoring points at both ends of the monitoring section are installed with targets, and the first visual detection unit is suitable for collecting images of the target at at least one end of the monitoring section, and then obtaining the longitudinal deformation of the corresponding monitoring section according to the imaging size change of the target.

5. The intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures according to claim 3, characterized in that: The data layer obtains tunnel vault deformation data in the second data layer through the vault deformation monitoring subsystem, and the tunnel vault deformation data is represented by the vault sinking displacement; The vault deformation monitoring subsystem includes a first mark point set on the vault of the weak section, and a second visual detection unit installed on the ground; the second visual detection unit is suitable for collecting images of the first mark point, and then obtaining the sinking displacement of the first mark point.

6. The intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures according to claim 3, characterized in that: The data layer is passed through the uneven settlement monitoring subsystem to obtain the longitudinal uneven settlement data of the tunnel in the second data layer; The uneven settlement monitoring subsystem includes: A plurality of second punctuation points; the second punctuation points are respectively arranged at each settlement joint and / or expansion joint of the tunnel; and A plurality of third visual detection units; the third visual detection units are arranged on the ground and located between adjacent second marks, so as to simultaneously collect images of two adjacent second marks, and then obtain the longitudinal uneven settlement data of the tunnel through the sinking displacement difference of the adjacent second marks.

7. The intelligent operation and maintenance system for hierarchical health monitoring of tunnel structures according to claim 3, characterized in that: The data layer obtains the water seepage location data in the second data layer through the water seepage location positioning subsystem; The water seepage location positioning subsystem includes multiple groups of fourth visual detection units respectively arranged at each joint position of the tunnel, and multiple fourth visual detection units of each group are arranged along both sides of the tunnel to monitor the opposite wall area respectively; The fourth visual detection unit uses dual-spectrum thermal imaging technology to identify the location of the water seepage point and the water seepage area to obtain water seepage location data.

Images