Tunnel joint deformation diagnosis method, device, equipment and medium

Abstract

The invention relates to a tunnel joint deformation diagnosis method, device and equipment and a medium, and belongs to the technical field of tunnel monitoring, and the method comprises the steps: obtaining the strain information of a tunnel joint through an optical fiber sensor; inputting the strain information into a trained joint deformation mode recognition model to obtain a current deformation mode of the tunnel joint; the current deformation mode comprises at least one of opening and slab staggering; and determining a target deformation amount identification model corresponding to the current deformation mode, and inputting the strain information into the target deformation amount identification model to obtain a deformation amount corresponding to the current deformation mode. According to the invention, accurate monitoring of the deformation mode and the deformation amount of the tunnel joint can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel monitoring, and in particular to a tunnel joint deformation diagnosis method, device, equipment and medium. BACKGROUND

[0002] At present, the deformation monitoring of tunnel structures mainly relies on various conventional technical means. For example, a total station, a convergence meter and the like are used to periodically measure key points of a selected section manually to obtain convergence displacement; or a three-dimensional laser scanner is used to scan the inner wall of the tunnel, and the overall profile change of the section is analyzed through point cloud data comparison. In recent years, distributed optical fiber sensing technology has also been applied to tunnel monitoring. The main idea is to lay optical fibers along the ring or longitudinal direction of the tunnel, and by measuring the strain or temperature change of the optical fiber along the line, the overall deformation trend of the structure or the deformation of some specific positions such as the joint of the tunnel is monitored.

[0003] However, the deformation at the joint includes multiple modes, and the prior art cannot distinguish whether the deformation at the joint is joint opening, segment misalignment (shear) or both. Different deformation modes have completely different causes, degrees of danger and repair and reinforcement methods, and the prior art cannot provide more detailed and accurate basis for accurate repair of the joint. SUMMARY

[0004] Therefore, it is necessary to provide a tunnel joint deformation diagnosis method, device, equipment and medium to solve the problem that the prior art cannot provide more detailed and accurate basis for accurate repair of the joint.

[0005] In order to solve the above problems, in a first aspect, the present application provides a tunnel joint deformation diagnosis, and an optical fiber sensor is arranged at the position of the tunnel joint; the method comprises: obtaining strain information of the tunnel joint by the optical fiber sensor; inputting the strain information into a trained joint deformation mode recognition model to obtain a current deformation mode of the tunnel joint; the current deformation mode comprises at least one of opening and misalignment; determining a target deformation amount recognition model corresponding to the current deformation mode, and inputting the strain information into the target deformation amount recognition model to obtain a deformation amount corresponding to the current deformation mode.

[0006] In a possible implementation manner, different deformation modes correspond to different deformation amount recognition models; the method further comprises: obtaining strain sample data of the tunnel joint; the strain sample data is obtained through finite element simulation, physical model experiment and strain measurement of the tunnel joint; The strain sample data is labeled; the label includes a category label of a deformation mode and a deformation amount label corresponding to the category; The joint deformation mode recognition model and the deformation amount recognition model are trained respectively by the labeled strain sample data.

[0007] In a possible implementation, the strain sample data of the tunnel joint is obtained, including: The parameters of the finite element model of the tunnel are calibrated through the entity model experimental data; The strain sample data is obtained through finite element simulation according to the calibrated parameters of the finite element model.

[0008] In a possible implementation, the strain information includes strain information of a plurality of optical fiber sensors arranged along a target direction with the tunnel joint as the center; and the strain information is input into the trained joint deformation mode recognition model, including: The strain information of the plurality of optical fiber sensors is spliced according to the positions of the plurality of optical fiber sensors to obtain target strain information; The target strain information is input into the trained joint deformation mode recognition model; The strain information is input into the target deformation amount recognition model, including: The target strain information is input into the target deformation amount recognition model.

[0009] In a possible implementation, the tunnel joint includes joints between segments on the tunnel, and at least one optical fiber sensor array is arranged on the tunnel; and the segment width is a preset multiple of the deployment interval of the sensors on the optical fiber sensor array.

[0010] In a possible implementation, each of the optical fiber sensor arrays is arranged along a key side line on the tunnel; and the key side line includes a vault side line and a waist line.

[0011] In a possible implementation, the method further includes: Diagnostic information is generated; the diagnostic information includes a diagnosis time, a position of the tunnel joint, a current deformation mode and a deformation amount of the tunnel joint; Alarm information is generated according to the diagnostic information.

[0012] In a second aspect, the present application further provides a tunnel joint deformation diagnosis device, and an optical fiber sensor is arranged at a position of a tunnel joint; the device includes: A monitoring information acquisition module is configured to acquire strain information of a tunnel joint through the optical fiber sensor; The deformation pattern recognition module is used to input the strain information into the trained joint deformation pattern recognition model to obtain the current deformation pattern of the tunnel joint; the current deformation pattern includes at least one of opening and misalignment. The deformation determination module is used to determine the target deformation identification model corresponding to the current deformation mode, and input the strain information into the target deformation identification model to obtain the deformation corresponding to the current deformation mode.

[0013] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a program; the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the tunnel joint deformation diagnosis method described in any of the above claims.

[0014] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program, wherein the program or instructions, when executed by a processor, are capable of implementing the steps in any of the tunnel joint deformation diagnosis methods described above.

[0015] The beneficial effects of this invention are: This invention acquires strain information of tunnel joints using fiber optic sensors installed at the joint locations. This strain information is then input into a trained joint deformation pattern recognition model, accurately determining the current deformation pattern of the tunnel joint. Furthermore, this invention configures a corresponding deformation amount recognition model for each deformation pattern. Therefore, after determining the current deformation pattern, the strain information is further input into the target deformation amount recognition model corresponding to that pattern. This allows the target deformation amount recognition model to perform targeted analysis and recognition of the deformation features in the strain information, more accurately obtaining the deformation amount corresponding to the current deformation pattern. This provides detailed and precise maintenance data, including deformation pattern and deformation amount, for joint repair. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating an embodiment of the tunnel joint deformation diagnosis method provided by the present invention; Figure 2 For the present invention Figure 1 A flowchart illustrating an embodiment of S102; Figure 3A schematic diagram of a fiber sensor layout method provided by the present application is shown in the figure; Figure 4 A schematic diagram of a fiber sensor layout method provided by the present application is shown in the figure; Figure 5 A schematic diagram of the flow of another embodiment of the tunnel joint deformation diagnosis method provided by the present application is shown in the figure; Figure 6 A schematic diagram of the structure of one embodiment of the tunnel joint deformation diagnosis device provided by the present application is shown in the figure; Figure 7 A schematic diagram of the structure of one embodiment of the electronic device provided by the present application is shown in the figure. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more. The association relationship of the associated objects is described by "and / or", which means that there can be three relationships, for example: A and / or B can represent the three cases of A alone, A and B together, and B alone. The character " / ", generally represents that the associated objects before and after it are in an "or" relationship.

[0020] In the embodiments of the present application, "first", "second", and the like are used to distinguish similar objects, and are not used to describe a specific order or sequence, nor to indicate or imply relative importance or implicitly indicate the number of the indicated technical features. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of a kind and do not limit the number of objects, for example, the first object can be one or more.

[0021] In this document, reference to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood that the embodiments described herein can be combined with other embodiments.

[0022] Reference Figure 1, a flowchart of an embodiment of the tunnel joint deformation diagnosis method provided by the application is shown, and an optical fiber sensor is arranged at the position of the tunnel joint; the method comprises: S101, obtaining strain information of the tunnel joint by the optical fiber sensor.

[0023] The tunnel can be a subway tunnel, and specifically can be a shield tunnel in the subway tunnel. The shield tunnel refers to a tunnel formed by a construction method of using a shield machine, which is a large tunneling special equipment, to excavate and build a tunnel underground.

[0024] The shield tunnel is usually assembled by thousands of prefabricated segments, so there are a large number of joints between the segments.

[0025] The optical fiber sensor can be arranged at the joint position between the segments, so that the strain information at the joint can be obtained in real time by the optical fiber sensor.

[0026] S102, inputting the strain information into the trained joint deformation pattern recognition model to obtain a current deformation pattern of the tunnel joint; the current deformation pattern comprises at least one of opening and misalignment.

[0027] The joint deformation pattern recognition model can be a pre-trained classification model for recognizing the deformation pattern of the joint according to the strain information of the joint. The classification model can be a support vector machine (SVM), a decision tree, a random forest, or a deep learning model based on a convolutional neural network (CNN), etc. The deformation pattern includes only opening, or only misalignment or both opening and misalignment.

[0028] S103, determining a target deformation amount recognition model corresponding to the current deformation pattern, and inputting the strain information into the target deformation amount recognition model to obtain a deformation amount corresponding to the current deformation pattern.

[0029] Different deformation patterns correspond to different deformation amount recognition models, and the deformation amount recognition model can be a regression model, such as a Gaussian process regression model or a gradient boosting regression tree, or a deep learning model. The deformation amount recognition model can include at least one of a pre-trained opening amount recognition model and a misalignment amount recognition model.

[0030] When the current deformation pattern is opening, the strain information can be input into the opening amount recognition model to obtain the opening amount; when the current deformation pattern is misalignment, the strain information can be input into the misalignment amount recognition model to obtain the misalignment amount; and when the current deformation pattern is misalignment and opening, the strain information can be input into the misalignment amount recognition model and the opening amount recognition model respectively to obtain the misalignment amount and the opening amount.

[0031] The tunnel joint deformation diagnosis method provided in this embodiment can be applied to a tunnel joint deformation diagnosis system, which can be a software system running on a terminal device. The terminal device can be a tablet computer, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), mobile phone, etc. This embodiment does not impose any restrictions on the specific type of terminal device.

[0032] In summary, this embodiment acquires strain information of the tunnel joint using fiber optic sensors installed at the joint location. This strain information is then input into a trained joint deformation pattern recognition model, thereby accurately determining the current deformation pattern of the tunnel joint. Furthermore, this embodiment configures a corresponding deformation amount recognition model for each deformation pattern. Therefore, after determining the current deformation pattern, the strain information is further input into the target deformation amount recognition model corresponding to the current deformation pattern. This allows the target deformation amount recognition model to perform targeted analysis and recognition of the deformation features in the strain information, more accurately obtaining the deformation amount corresponding to the current deformation pattern. This provides detailed and precise maintenance data, including deformation pattern and deformation amount, for joint repair.

[0033] In some embodiments of the present invention, at least one fiber optic sensor array may be deployed on the tunnel; during customization and production, the deployment spacing of the sensors on this fiber optic sensor array is pre-designed to be a preset multiple of the standard tunnel segment width, wherein the preset multiple is an integer multiple. For example... Figure 2 The diagram illustrates a fiber optic sensor deployment method provided by this invention. The tube width is twice the deployment spacing of the sensors on the fiber optic sensor array. Figure 3 The diagram illustrates another fiber optic sensor deployment method provided by this invention. The width of the tube segment is one time the deployment spacing of the sensors on the fiber optic sensor array. The preset multiple can be determined based on the monitoring range, monitoring accuracy, etc. For example, if the monitoring range is small but the monitoring accuracy requirement is high, a larger preset multiple can be set; if the monitoring range is large but the monitoring accuracy requirement is low, a smaller preset multiple can be set.

[0034] The embodiment adopts a position matching design, so that when the fiber sensor array is installed in the tunnel, the center area of each segment joint is naturally and deterministically covered by at least one fiber sensor without complex field aiming or positioning. This is equivalent to automatically and standardizing forming a "joint-spanning monitoring unit" at the weakest joint position of all structures in the whole tunnel. Meanwhile, the position matching design has the following advantages: ①Maximum signal fidelity: Since the segment joint is the area with the most concentrated deformation, deterministically deploying the fiber sensor in this area can ensure that the strain signal collected has the highest strength and the best signal-to-noise ratio, providing the highest quality raw data for subsequent pattern recognition.

[0035] ②Uniformity of diagnostic reference: This design makes the "scale" for monitoring hundreds of joints in the whole tunnel completely uniform, which lays a solid foundation for transverse comparison between different joints and longitudinal trend analysis of the same joint.

[0036] ③Convenience of data processing: When processing continuous data streams, the subsequent algorithm can efficiently and accurately automatically segment and window the data according to this preset sensor distribution rule consistent with the segment blocking rhythm, greatly improving the calculation efficiency.

[0037] In some embodiments of the present application, each fiber sensor array can be laid along a key side line on the tunnel; the key measurement lines include the crown measurement line and the waist line measurement line.

[0038] In some embodiments of the present application, the strain information includes strain information of a plurality of fiber sensors laid along a target direction with the tunnel joint as the center; the step of inputting the strain information into the trained joint deformation pattern recognition model includes: splicing the strain information of the plurality of fiber sensors according to the positions of the plurality of fiber sensors to obtain target strain information; inputting the target strain information into the trained joint deformation pattern recognition model; The step of inputting the strain information into the target deformation amount recognition model includes: inputting the target strain information into the target deformation amount recognition model.

[0039] In this embodiment, when an excitation (such as train load, soil pressure change) acts on the tunnel, the fiber analyzer collects the strain information of all fiber sensors on the whole fiber sensor array at a high frequency and synchronously, forming a huge real-time data stream. Then, according to the preset tunnel structure information (i.e. the accurate mileage position of each joint), the continuous real-time data stream is automatically segmented or "windowed". Then, for the first ia joint, extract strain readings of a plurality of optical fiber sensors in a region adjacent to the joint and its two sides (the two sides refer to the two sides along the arrangement direction of the optical fiber sensor array) on both sides of the joint as the reference center, and arrange the group of readings in order of their physical positions, to form a characteristic vector (target strain information) of dimension m m

[0040] The vector completely describes the local strain distribution pattern of the first i joint at the current time.

[0041] The prior art mainly uses the single strain "reading" monitored at the position directly opposite the joint, that is, a scalar, to determine the deformation of the joint, and ignores the "distribution pattern" of the strain at the position, which is a higher dimension and more informative feature. The present embodiment generates target strain information that can represent the "distribution pattern" of the strain at the joint position, and then inputs the target strain information into the trained joint deformation pattern recognition model and the target deformation amount recognition model to recognize the deformation pattern and the deformation amount, which can make the recognition result more accurate.

[0042] In some embodiments of the present application, as shown in Figure 4 the tunnel joint deformation diagnosis method further comprises: S401, obtaining strain sample data of the tunnel joint; the strain sample data is obtained by finite element simulation, physical model experiment, and strain measurement on the tunnel joint.

[0043] S402, labeling the strain sample data; the label includes a class label of the deformation pattern and a deformation amount label corresponding to the class.

[0044] S403, training the joint deformation pattern recognition model and the deformation amount recognition model respectively by using the labeled strain sample data.

[0045] In the present embodiment, the strain sample data can be generated by three methods, and the specific generation process is as follows: ① Strain sample data generation based on finite element simulation (FEM). A precise three-dimensional mechanical model of the segmental joint is established in the finite element simulation software. By systematically applying n a plurality of different, known boundary conditions (such as different degrees of opening, misalignment, and combinations thereof), a plurality of corresponding characteristic vectors n are calculated. This method is used to generate strain sample data covering most working conditions at low cost and high efficiency.

[0046] ​​② Strain sample data generation and data augmentation based on entity model experiment. To verify the accuracy of the finite element simulation model and obtain high-fidelity data in the real world, the embodiment further includes performing entity model experiments. One or more 1:1 pipe joint physical models are built, and the optical fiber sensor array is deployed in the manner of the present application. Using jacks, actuators and other equipment, the pipe joint physical model is subjected to accurately measurable deformation, and the strain response of the optical fiber sensor array is synchronously collected to obtain the feature vector . These experimental data are regarded as the "gold standard" for calibrating the parameters of the finite element model. Then, according to the parameters of the calibrated finite element model, the finite element simulation can obtain more accurate strain sample data.

[0047] ③ Data calibration based on field measurement and manual inspection. To further improve the accuracy and robustness of the model in the real operating environment, the embodiment further includes learning from field measurement data. Regular manual inspection of the tunnel by professionals is performed, and contact displacement meters, crack width meters and other tools are used to accurately measure and record the state of the joints found to have deformation. Then, from the historical database of the optical fiber sensor monitoring system, the strain feature vector corresponding to the same time and same location as the inspection record is found .

[0048] Then, all simulation, experiment and field measurement data are labeled in a unified format. Two labels are provided for each feature vector: Class label y : indicating the deformation mode it belongs to, for example, the deformation modes include , , .

[0049] Magnitude label d : indicating the specific deformation size it corresponds to, for example .

[0050] The labeled data samples of simulation, experiment and field measurement data are fused together. A larger and more diverse mixed training set S is formed.

[0051]

[0052] This data set not only covers various theoretical working conditions, but also contains real-world noise and complex interference, which can greatly improve the generalization ability of the finally trained joint deformation mode recognition model and deformation amount recognition model.

[0053] In some embodiments of the present application, the tunnel joint deformation diagnosis method further comprises: Generate diagnostic information; the diagnostic information includes the diagnostic time, the location of the tunnel joint, the current deformation mode and deformation amount of the tunnel joint; Alarm information is generated based on diagnostic information.

[0054] For example, the diagnostic information could be {Location: 314 ring, Joint: No. 1, Pattern: Misalignment (shear), Deformation: 1.2mm}.

[0055] Alarm information can include diagnostic information, as well as alarm levels and maintenance recommendations. For example, if the alarm is "opening up," maintenance recommendations could include grouting or attaching steel plates for repair; if the alarm is "misaligned," maintenance recommendations could include stress relief and jacking to reset the position.

[0056] This embodiment can avoid the cost waste and safety hazards caused by blind repairs by timely feedback of alarm information.

[0057] Reference Figure 5 This paper illustrates a flowchart of a tunnel joint deformation diagnosis method provided by the present invention. The method acquires real-time data streams of the joint and the training set of the model through a data layer. The joint deformation pattern recognition model and deformation amount recognition model are trained by processing data from the model layer. The joint deformation pattern recognition model is a classification model, specifically an SVM model. The core idea of ​​SVM is to find the optimal hyperplane that can separate different categories of sample points with the maximum margin. For a binary classification problem (e.g., distinguishing between "misaligned" and "non-misaligned"), the optimization objective can be expressed as:

[0058] The constraints are:

[0059]

[0060] in, These are the parameters of the optimal hyperplane. It is the input feature vector. It is a slack variable, representing the first... j The degree to which each sample violates the interval constraint. It is a penalty coefficient used to balance maximizing the margin and classification error. For multi-class problems (such as three-class classification of "normal", "open", and "misaligned"), multiple binary classifiers can be combined using a "one-vs-one" or "one-vs-rest" strategy.

[0061] The deformation identification model is the SVR model, and the goal of SVR is to find a function To make it consistent with the true value The error is no more than is as small as possible within the range of

[0062] The constraint condition is:

[0063]

[0064]

[0065] wherein, defines an allowable error region, and only when the predicted value has an error greater than from the true value , the loss is calculated.

[0066] The processing and model layer is also used to input the feature vector i extracted in real time at the first joint into a trained classifier to obtain the most likely deformation mode category . According to the identified mode , the corresponding regression model is selected, and is input into the model to obtain the predicted deformation value .

[0067] Finally, the model recognition result is integrated into structured diagnostic information by applying the output layer and output for display.

[0068] Referring to Figure 6 , a structural schematic diagram of an embodiment of a tunnel joint deformation diagnosis device provided by the present application is shown, and an optical fiber sensor is arranged at the position of the tunnel joint; the device 600 comprises: a monitoring information acquisition module 601 configured to acquire strain information of the tunnel joint through the optical fiber sensor; a deformation mode recognition module 602 configured to input the strain information into a trained joint deformation mode recognition model to obtain a current deformation mode of the tunnel joint; the current deformation mode comprises at least one of opening and misalignment; a deformation amount determination module 603 configured to determine a target deformation amount recognition model corresponding to the current deformation mode, and input the strain information into the target deformation amount recognition model to obtain a deformation amount corresponding to the current deformation mode.

[0069] It should be noted that the implementation principle or implementation process of each module described above can refer to the embodiments of the foregoing method, which will not be described here.

[0070] Referring to Figure 7Fig. 7 shows an electronic device 700 according to an embodiment of the present application. The electronic device 700 comprises a processor 701, a memory 702 and a display 703. Figure 7 Only some components of the electronic device 700 are shown, but it should be understood that all the shown components are not required, and more or less components can be alternatively implemented.

[0071] The processor 701 can be a central processing unit (CPU), a microprocessor, or other data processing chip in some embodiments, for running program codes or processing data stored in the memory 702, such as the tunnel joint deformation diagnosis method of the present application.

[0072] In some embodiments, the processor 701 can be a single server or a group of servers. The group of servers can be centralized or distributed. In some embodiments, the processor 701 can be local or remote. In some embodiments, the processor 701 can be implemented in a cloud platform. In an embodiment, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0073] The memory 702 can be an internal storage unit of the electronic device 700 in some embodiments, such as a hard disk or a memory of the electronic device 700. The memory 702 can also be an external storage device of the electronic device 700 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 700.

[0074] Further, the memory 702 can include both the internal storage unit and the external storage device of the electronic device 700. The memory 702 is used to store application software and various data installed on the electronic device 700.

[0075] The display 703 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 703 is used to display information of the electronic device 700 and to display a visualized user interface. The components 701-703 of the electronic device 700 communicate with each other through a system bus.

[0076] In an embodiment, when the processor 701 executes the tunnel joint deformation diagnosis program in the memory 702, an optical fiber sensor is arranged at the position of the tunnel joint; the following steps can be implemented: Strain information of the tunnel joint is acquired by the optical fiber sensor; The strain information is input into the trained joint deformation mode recognition model to obtain a current deformation mode of the tunnel joint; the current deformation mode comprises at least one of opening and misalignment; A target deformation amount recognition model corresponding to the current deformation mode is determined, and the strain information is input into the target deformation amount recognition model to obtain a deformation amount corresponding to the current deformation mode.

[0077] It should be understood that, in addition to the above functions, the processor 701 can also implement other functions when executing the tunnel joint deformation diagnosis program in the memory 702, and specific descriptions can be made with reference to the descriptions of the previous method embodiments.

[0078] Further, the type of the electronic device 700 is not specifically limited, and the electronic device 700 can be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or the like. Exemplary embodiments of the portable electronic device include, but are not limited to, a portable electronic device running an IOS, android, microsoft, or other operating system. The above-mentioned portable electronic device can also be other portable electronic devices, such as a laptop computer having a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present application, the electronic device 700 can not be a portable electronic device, but a desktop computer having a touch-sensitive surface (e.g., a touch panel).

[0079] In one embodiment, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of any one of the tunnel joint deformation diagnosis methods described above.

[0080] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium. The computer readable storage medium includes a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.

[0081] The above description is only a preferred embodiment of the present application, and the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed by the present application can be easily conceived by those skilled in the art, and should be covered within the protection scope of the present application.

Claims

1. A method of tunnel joint deformation diagnosis, characterized by, The tunnel joint position is provided with a fiber sensor; the method comprises: Obtaining strain information of the tunnel joint through the fiber sensor; Inputting the strain information into a trained joint deformation mode recognition model to obtain a current deformation mode of the tunnel joint; the current deformation mode comprises at least one of opening and misalignment; Determining a target deformation amount recognition model corresponding to the current deformation mode, and inputting the strain information into the target deformation amount recognition model to obtain a deformation amount corresponding to the current deformation mode.

2. The tunnel joint deformation diagnostic method according to claim 1, characterized by, Different deformation modes correspond to different deformation amount recognition models; the method further comprises: Obtaining strain sample data of the tunnel joint; the strain sample data is obtained through finite element simulation, physical model experiment and strain measurement of the tunnel joint; Labeling the strain sample data; the label comprises a category label of the deformation mode and a deformation amount label corresponding to the category; Training the joint deformation mode recognition model and the deformation amount recognition model respectively through the labeled strain sample data.

3. The tunnel joint deformation diagnostic method of claim 2, wherein, The strain sample data of the tunnel joint comprises: Calibrating parameters of a finite element model of the tunnel through physical model experiment data; Obtaining strain sample data through finite element simulation according to the calibrated parameters of the finite element model.

4. The tunnel joint deformation diagnostic method of claim 1, wherein, The strain information comprises strain information of a plurality of fiber sensors arranged along a target direction with the tunnel joint as the center; inputting the strain information into the trained joint deformation mode recognition model comprises: Splicing the strain information of the plurality of fiber sensors according to the positions of the plurality of fiber sensors to obtain target strain information; Inputting the target strain information into the trained joint deformation mode recognition model; Inputting the target strain information into the target deformation amount recognition model. The tunnel joint comprises joints between pipe segments on the tunnel, and at least one fiber sensor array is arranged on the tunnel; 5. The tunnel joint deformation diagnostic method of claim 1, wherein, The pipe segment width is a preset multiple of the deployment interval of the sensors on the fiber sensor array. Each fiber sensor array is arranged along a key side line on the tunnel; the key side line comprises a vault side line and a waist line.

6. The tunnel joint deformation diagnostic method of claim 4, wherein, The method further comprises:

7. The tunnel joint deformation diagnostic method of claim 1, wherein, Generating diagnosis information; the diagnosis information comprises diagnosis time, the position of the tunnel joint, the current deformation mode and deformation amount of the tunnel joint; Generating alarm information according to the diagnosis information. The tunnel joint position is provided with a fiber sensor; the device comprises:

8. A tunnel joint deformation diagnostic apparatus characterized by comprising: A monitoring information acquisition module for obtaining strain information of the tunnel joint through the fiber sensor; A deformation mode recognition module for inputting the strain information into a trained joint deformation mode recognition model to obtain a current deformation mode of the tunnel joint; the current deformation mode comprises at least one of opening and misalignment; A deformation amount determination module for determining a target deformation amount recognition model corresponding to the current deformation mode, and inputting the strain information into the target deformation amount recognition model to obtain a deformation amount corresponding to the current deformation mode. ​ 9. An electronic device, comprising: comprising a memory and a processor, wherein, the memory, configured to store a program; the processor, coupled to the memory, configured to execute the program stored in the memory, so as to implement the steps in the tunnel joint deformation diagnosis method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer readable program or instruction for storing, the program or instruction being executed by a processor to implement the steps in the tunnel joint deformation diagnosis method according to any one of claims 1 to 7.

Images