Bridge displacement monitoring method, system and equipment and storage medium

Abstract

The invention provides a bridge displacement monitoring method, system and device and a storage medium. The method comprises the steps that vibration signal data of a bridge and target data are collected; establishing a finite element model of the bridge, and calculating the first three-order inherent frequency of the bridge based on the processed vibration signal data and the finite element model; performing multi-rate Kalman filtering fusion on the mean value and the processed target data to obtain fusion data; performing multiple labeling on the processed target data to obtain training target data, and training a MobileNet model based on the training target data to obtain a trained MobileNet model; and acquiring a spectrogram of the vibration signal data, and performing displacement analysis on the spectrogram and the fused data based on the trained MobileNet model. The bridge condition can be monitored from multiple angles, the monitoring accuracy can be effectively improved, the monitoring effect is improved, and the bridge safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and in particular to a bridge displacement monitoring method, system, equipment and storage medium. Background Art

[0002] Bridges are important facilities connecting cities and villages, and are also important infrastructure for modern transportation. Bridges generally refer to structures built across rivers, lakes, and seas to allow vehicles and pedestrians to pass smoothly. In order to adapt to the modern high-speed development of the transportation industry, bridges are also extended to buildings that cross mountain streams, poor geology, or meet other transportation needs to make travel more convenient.

[0003] The construction of bridges has brought us a lot of conveniences. However, after the completion of the bridge construction and put into use, it will be affected by loads in various directions, including the influence of the bridge's own weight, the influence of vehicles or pedestrians carried by the bridge, wind load, temperature load, etc., and different load intensities have different effects on the bridge. When these loads exceed the maximum bearing capacity of the bridge, it is easy to cause irreversible bridge damage and even lead to safety accidents.

[0004] In the prior art, when monitoring a bridge, an accelerometer is usually used to monitor the state of the bridge itself. However, it is difficult to ensure the accuracy and stability of the monitoring by only monitoring the state of the bridge itself through an accelerometer, and inaccurate data may be generated, resulting in poor monitoring results and difficulty in obtaining the safety of the bridge. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a bridge displacement monitoring method, system, device and storage medium to solve the deficiencies in the above-mentioned prior art.

[0006] In a first aspect, the present invention provides a bridge displacement monitoring method, the method comprising: Collecting vibration signal data and target data of the bridge, and processing the vibration signal data and the target data to obtain processed vibration signal data and processed target data; Establishing a finite element model of the bridge, and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model; Denoising the first three natural frequencies and averaging the denoised first three natural frequencies to calculate the mean of the first three natural frequencies, and fusing the mean with the processed target data by multi-rate Kalman filtering to obtain fused data; Annotating the processed target data twice to obtain training target data, and training the MobileNet model based on the training target data to obtain a trained MobileNet model; A frequency spectrum of the vibration signal data is obtained, and a displacement analysis is performed on the frequency spectrum and the fused data based on the trained MobileNet model.

[0007] Compared with the prior art, the beneficial effects of the present invention are as follows: by fusing the mean of the first three natural frequencies with the processed target data to obtain fused data, the bridge condition can be monitored from multiple angles, and the spectrum diagram and the fused data are subjected to displacement analysis by the trained MobileNet model, which can not only monitor the bridge condition from the vibration aspect, but also monitor the bridge through the self-stress condition of the bridge finite element model, thereby effectively improving the monitoring accuracy, improving the monitoring effect, and ensuring the safety of the bridge.

[0008] Furthermore, the steps of collecting vibration signal data of the bridge and collecting target data, and processing the vibration signal data and the target data include: Collecting vibration signal data of the bridge based on an accelerometer, and collecting image data of the bridge through a plurality of industrial cameras at different distances from the bridge combined with a plurality of total stations at different distances from the bridge, and establishing target data of the bridge based on the image data at a plurality of different distances; The vibration signal data is subjected to noise reduction processing, and the target data is subjected to data enhancement.

[0009] Furthermore, the step of establishing a finite element model of the bridge and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model includes: Establish the finite element model of the bridge based on the finite element software ANSYS; dividing the finite element model of the bridge into a plurality of finite element units to obtain a plurality of substructure models; The vibration signal data of the plurality of substructure models are obtained, and the first three natural frequencies of the bridge are calculated based on the vibration signal data of the plurality of substructure models.

[0010] Furthermore, the expression for calculating the mean of the first three-order natural frequencies is: ; In the formula, represents the mean, represents the averaging process, , , Represent the first-order frequency, second-order frequency, and third-order frequency respectively. Indicates scale.

[0011] Furthermore, the step of fusing the mean value with the processed target data by multi-rate Kalman filtering to obtain fused data includes: Performing multi-rate Kalman filtering on the processed target data to eliminate errors in the processed target data; The mean value and the processed target data are fused by RTS smoothing to obtain fused data.

[0012] Furthermore, the step of marking the processed target data twice includes: Performing initial labeling on the processed target data based on the automated labeling tool DarkLabel to regroup the processed target data to obtain coherent target data; The continuous target data are annotated for the second time based on the automated annotation tool DarkLabel to obtain the processed target data after multiple annotations.

[0013] Furthermore, the step of performing displacement analysis on the spectrum graph and the fused data based on the trained MobileNet model includes: Generate a fused data spectrum graph of the fused data; The frequency spectrum graph and the fused data frequency spectrum graph are compared based on the trained MobileNet model to obtain a comparison graph, and the displacement analysis of the bridge is performed according to the comparison graph.

[0014] In a second aspect, the present invention provides a bridge displacement monitoring system, the system comprising: An acquisition and processing module, used for acquiring vibration signal data of the bridge and acquiring target data, and processing the vibration signal data and the target data to obtain processed vibration signal data and processed target data; Establishing a calculation module for establishing a finite element model of the bridge, and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model; A calculation fusion module, used for denoising the first three natural frequencies and performing overall averaging on the denoised first three natural frequencies to calculate the mean of the first three natural frequencies, and fusing the mean with the processed target data by multi-rate Kalman filtering to obtain fused data; A labeling training module, used for labeling the processed target data twice to obtain training target data, and training the MobileNet model based on the training target data to obtain a trained MobileNet model; The acquisition and analysis module is used to acquire a frequency spectrum of the vibration signal data, and perform displacement analysis on the frequency spectrum and the fusion data based on the trained MobileNet model.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned bridge displacement monitoring method when executing the computer program.

[0016] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, which implements the above-mentioned bridge displacement monitoring method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a bridge displacement monitoring method in a first embodiment of the present invention; Figure 2 is a structural block diagram of a bridge displacement monitoring system in a second embodiment of the present invention; Figure 3 FIG. 4 is a schematic diagram of the hardware structure of an electronic device in a third embodiment of the present invention.

[0018] Description of main component symbols: 10. Acquisition and processing module; 20. Establishment of calculation module; 30. Calculation fusion module; 40. Labeling and training module; 50. Acquisition and analysis module; 60. Bus; 61. Processor; 62. Memory; 63. Communication interface.

[0019] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0020] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0021] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0023] See also Figure 1 , which shows a bridge displacement monitoring method in a first embodiment of the present invention, the method comprises steps S1 to S5: S1, collecting vibration signal data of the bridge and collecting target data, and processing the vibration signal data and the target data to obtain processed vibration signal data and processed target data; Specifically, the step S1 includes steps S11 to S12: S11, collecting vibration signal data of the bridge based on an accelerometer, and collecting image data of the bridge through a plurality of industrial cameras at different distances from the bridge combined with a plurality of total stations at different distances from the bridge, and establishing target data of the bridge according to the image data at the plurality of different distances; S12, performing noise reduction processing on the vibration signal data and data enhancement on the target data; It can be understood that by installing accelerometers at various locations on the bridge and obtaining vibration signal data of the bridge through the accelerometers, and by performing noise reduction processing on the vibration signal data, some useless data can be eliminated. In this embodiment, the target data of the bridge is collected by an industrial camera combined with a total station, and through data enhancement, the scale and diversity of the target data can be enhanced.

[0024] S2, establishing a finite element model of the bridge, and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model; Specifically, the step S2 includes steps S21 to S23: S21, establish the finite element model of the bridge based on the finite element software ANSYS; S22, dividing the finite element model of the bridge into a plurality of finite element units to obtain a plurality of substructure models; S23, obtaining vibration signal data of the plurality of substructure models, and calculating the first three natural frequencies of the bridge based on the vibration signal data of the plurality of substructure models; It can be understood that the finite element model of the bridge is established by the finite element software ANSYS, and the finite element model is divided into several small finite element units. Each finite element unit can be regarded as a simplified substructure. The mechanical response of the entire bridge can be obtained by combining several substructures. In this embodiment, the first three natural frequencies of the bridge can be obtained by the Butterworth-EEMD combination method.

[0025] It should be noted that ‌Butterworth-EEMD‌ is a signal processing method that combines ‌Butterworth filter‌ and ‌EEMD (Ensembled Empirical Mode Decomposition)‌. In specific implementation, ‌Butterworth filter first removes high-frequency noise and interference in the bridge vibration signal to ensure the accuracy of integrated empirical mode decomposition, and then adds Gaussian white noise to the vibration signal multiple times and performs EMD decomposition, and then performs overall averaging on the obtained intrinsic mode function to reduce modal aliasing and improve the accuracy of decomposition. In this way, the first three natural frequencies of the bridge can be obtained effectively and accurately.

[0026] S3, denoising the first three order natural frequencies and averaging the denoised first three order natural frequencies to calculate the mean of the first three order natural frequencies, and fusing the mean with the processed target data by multi-rate Kalman filtering to obtain fused data; In this embodiment, the expression for calculating the mean of the first three-order natural frequencies is: ; In the formula, represents the mean, represents the averaging process, , , Represent the first-order frequency, second-order frequency, and third-order frequency respectively. Indicates scale.

[0027] It should be explained that calculating the natural frequencies of the first three orders of the bridge can effectively eliminate high-frequency noise in the monitoring signal and avoid the situation where the monitoring results are unreliable due to accidental data. The use of multi-rate Kalman filtering can improve the accuracy of fusion, which can effectively improve the accuracy of monitoring.

[0028] Specifically, the step S3 includes steps S31 to S32: S31, performing multi-rate Kalman filtering on the processed target data to eliminate errors in the processed target data; It can be understood that filtering the processed target data by the Kalman filtering method can effectively eliminate the error data in the processed target data and avoid the error data from affecting the subsequent analysis of the bridge; S32, fusing the mean value and the processed target data by RTS smoothing to obtain fused data; It should be noted that the RTS smoothing method is to perform state prediction, measurement and error variance update in sequence to fuse the mean and the processed target data. In this embodiment, the expression of the RTS smoothing method is: ; In the formula, represents fused data, represents the mean, represents the prior variance matrix, represents the state vector estimate, represents the state vector, Represents a smoothed estimate.

[0029] S4, annotating the processed target data twice to obtain training target data, and training the MobileNet model based on the training target data to obtain a trained MobileNet model; Specifically, the step S4 includes step S41 to step S42: S41, performing initial labeling on the processed target data based on the automated labeling tool DarkLabel, so as to regroup the processed target data to obtain coherent target data; S42, performing a second labeling on the continuous target data based on the automated labeling tool DarkLabel to obtain the processed target data after multiple labeling; It can be understood that the target data processed through multiple annotations is more coherent and can enable the MobileNet model to better recognize during training, thereby improving the recognition and analysis effect of the MobileNet model.

[0030] S5, obtaining a frequency spectrum of the vibration signal data, and performing displacement analysis on the frequency spectrum and the fused data based on the trained MobileNet model; Specifically, the step S5 includes step S51 to step S52: S51, generating a fused data spectrum diagram of the fused data; S52, comparing the frequency spectrum and the fused data frequency spectrum based on the trained MobileNet model to obtain a comparison graph, and performing displacement analysis on the bridge according to the comparison graph; It can be understood that by comparing the spectrum graph and the fused data spectrum graph, a comparison graph can be obtained, that is, the data on the spectrum graph and the data on the fused data spectrum graph are compared on the same graph to obtain a comparison graph, and based on the data on the comparison graph, whether there is data that exceeds the safety threshold, the safety status of the bridge can be obtained.

[0031] In summary, the bridge displacement monitoring method in the above embodiment of the present invention obtains fused data by fusing the mean of the first three natural frequencies with the processed target data, so that the bridge condition can be monitored from multiple angles, and the displacement analysis of the spectrum diagram and the fused data is performed through the trained MobileNet model, which can not only monitor the bridge condition from the vibration aspect, but also monitor the bridge through the self-stress condition of the bridge finite element model, thereby effectively improving the monitoring accuracy, improving the monitoring effect, and ensuring the safety of the bridge.

[0032] Embodiment 2 The present invention also proposes a bridge displacement monitoring system, see Figure 2 , which shows a bridge displacement monitoring system in a second embodiment of the present invention, the system comprises: The acquisition and processing module 10 is used to acquire vibration signal data and target data of the bridge, and process the vibration signal data and the target data to obtain processed vibration signal data and processed target data; Establishing a calculation module 20, for establishing a finite element model of the bridge, and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model; A calculation fusion module 30 is used to denoise the first three natural frequencies and perform overall averaging on the denoised first three natural frequencies to calculate the mean of the first three natural frequencies, and perform multi-rate Kalman filtering fusion on the mean with the processed target data to obtain fused data; The expression for calculating the mean of the first three natural frequencies is: ; In the formula, represents the mean, represents the averaging process, , , Represent the first-order frequency, second-order frequency, and third-order frequency respectively. Indicates scale; A labeling training module 40 is used to label the processed target data twice to obtain training target data, and train the MobileNet model based on the training target data to obtain a trained MobileNet model; The acquisition and analysis module 50 is used to acquire the frequency spectrum of the vibration signal data, and perform displacement analysis on the frequency spectrum and the fusion data based on the trained MobileNet model.

[0033] In some optional embodiments, the acquisition processing module 10 includes: A collection unit, used to collect vibration signal data of the bridge based on an accelerometer, collect image data of the bridge through a plurality of industrial cameras at different distances from the bridge combined with a plurality of total stations at different distances from the bridge, and establish target data of the bridge according to the image data at a plurality of different distances; A processing unit is used to perform noise reduction processing on the vibration signal data and to perform data enhancement on the target data.

[0034] In some optional embodiments, the establishing calculation module 20 includes: Establishing units for building a finite element model of a bridge based on finite element software ANSYS; A segmentation unit, used for segmenting the finite element model of the bridge into a plurality of finite element units to obtain a plurality of substructure models; The acquisition calculation unit is used to obtain the vibration signal data of the plurality of substructure models, and calculate the first three natural frequencies of the bridge based on the vibration signal data of the plurality of substructure models.

[0035] In some optional embodiments, the calculation fusion module 30 includes: A filtering unit, configured to perform a multi-rate Kalman filter on the processed target data to eliminate errors in the processed target data; The fusion unit is used to fuse the mean value and the processed target data by RTS smoothing to obtain fused data.

[0036] In some optional embodiments, the annotation training module 40 includes: A first labeling unit, used for initially labeling the processed target data based on an automated labeling tool DarkLabel, so as to regroup the processed target data to obtain coherent target data; The second labeling unit is used to label the continuous target data for the second time based on the automatic labeling tool DarkLabel to obtain the processed target data after multiple labeling.

[0037] In some optional embodiments, the acquisition and analysis module 50 includes: A generating unit, used for generating a fused data spectrum diagram of the fused data; The comparison unit is used to compare the frequency spectrum diagram and the fused data frequency spectrum diagram based on the trained MobileNet model to obtain a comparison diagram, and perform displacement analysis on the bridge according to the comparison diagram.

[0038] The functions or operation steps implemented when the above modules and units are executed are generally the same as those in the above method embodiments, and will not be repeated here.

[0039] The bridge displacement monitoring system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0040] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0041] Embodiment 3 The present invention also provides an electronic device, see Figure 3 , which is a schematic diagram of the hardware structure of the electronic device in the third embodiment of the present invention.

[0042] The electronic device may include a processor 61 and a memory 62 storing computer program instructions.

[0043] Specifically, the processor 61 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the present application.

[0044] Among them, the memory 62 may include a large-capacity memory for data or instructions. For example, but not limitation, the memory 62 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 62 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 62 may be inside or outside the data processing device. In a specific embodiment, the memory 62 is a non-volatile memory. In a specific embodiment, the memory 62 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0045] The memory 62 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 61 .

[0046] The processor 61 implements the bridge displacement monitoring method of the first embodiment by reading and executing the computer program instructions stored in the memory 62 .

[0047] In some of the embodiments, the electronic device may further include a communication interface 63 and a bus 60. Figure 3 As shown, the processor 61, the memory 62, and the communication interface 63 are connected via a bus 60 and communicate with each other.

[0048] The communication interface 63 is used to realize the communication between the modules, devices, units and / or equipment in the present application. The communication interface 63 can also realize data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage and image / data processing workstations.

[0049] The bus 60 includes hardware, software or both, and couples the components of the device to each other. The bus 60 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 60 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 60 may include one or more buses. Although this application describes and illustrates a particular bus, this application contemplates any suitable bus or interconnect.

[0050] The device can acquire the bridge displacement monitoring system and execute the bridge displacement monitoring method of the first embodiment.

[0051] In addition, in combination with the bridge displacement monitoring method in the first embodiment, the present application may provide a storage medium for implementation. The storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the bridge displacement monitoring method in the first embodiment is implemented.

[0052] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0053] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A bridge displacement monitoring method, characterized in that: The method comprises: Collecting vibration signal data and target data of the bridge, and processing the vibration signal data and the target data to obtain processed vibration signal data and processed target data; Establishing a finite element model of the bridge, and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model; Denoising the first three natural frequencies and averaging the denoised first three natural frequencies to calculate the mean of the first three natural frequencies, and fusing the mean with the processed target data by multi-rate Kalman filtering to obtain fused data; Annotating the processed target data twice to obtain training target data, and training the MobileNet model based on the training target data to obtain a trained MobileNet model; A frequency spectrum of the vibration signal data is obtained, and a displacement analysis is performed on the frequency spectrum and the fused data based on the trained MobileNet model.

2. The bridge displacement monitoring method according to claim 1, characterized in that: The steps of collecting vibration signal data of the bridge and collecting target data, and processing the vibration signal data and the target data include: The vibration signal data of the bridge is collected based on the accelerometer, and the image data of the bridge is collected by combining a plurality of industrial cameras at different distances from the bridge with a plurality of total stations at different distances from the bridge, and the target data of the bridge is established according to the image data at the plurality of different distances; The vibration signal data is subjected to noise reduction processing, and the target data is subjected to data enhancement.

3. The bridge displacement monitoring method according to claim 1, characterized in that: The step of establishing a finite element model of the bridge and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model comprises: Establish the finite element model of the bridge based on the finite element software ANSYS; dividing the finite element model of the bridge into a plurality of finite element units to obtain a plurality of substructure models; The vibration signal data of the plurality of substructure models are obtained, and the first three natural frequencies of the bridge are calculated based on the vibration signal data of the plurality of substructure models.

4. The bridge displacement monitoring method according to claim 1, characterized in that: The expression for calculating the mean of the first three natural frequencies is: ； In the formula, represents the mean, represents the averaging process, , , Represent the first-order frequency, second-order frequency, and third-order frequency respectively. Indicates scale.

5. The bridge displacement monitoring method according to claim 1, characterized in that: The step of fusing the mean value with the processed target data by multi-rate Kalman filtering to obtain fused data comprises: performing a multi-rate Kalman filter on the processed target data to eliminate errors in the processed target data; The mean value and the processed target data are fused by RTS smoothing to obtain fused data.

6. The bridge displacement monitoring method according to claim 1, characterized in that: The step of marking the processed target data twice comprises: Performing initial labeling on the processed target data based on the automated labeling tool DarkLabel to regroup the processed target data to obtain coherent target data; The continuous target data are annotated for the second time based on the automated annotation tool DarkLabel to obtain the processed target data after multiple annotations.

7. The bridge displacement monitoring method according to claim 1, characterized in that: The step of performing displacement analysis on the spectrum graph and the fused data based on the trained MobileNet model comprises: Generate a fused data spectrum graph of the fused data; The frequency spectrum graph and the fused data frequency spectrum graph are compared based on the trained MobileNet model to obtain a comparison graph, and the displacement analysis of the bridge is performed according to the comparison graph.

8. A bridge displacement monitoring system, characterized in that: The system comprises: An acquisition and processing module, used for acquiring vibration signal data of the bridge and acquiring target data, and processing the vibration signal data and the target data to obtain processed vibration signal data and processed target data; Establishing a calculation module for establishing a finite element model of the bridge, and calculating the first three natural frequencies of the bridge based on the processed vibration signal data and the finite element model; A calculation fusion module, used for denoising the first three natural frequencies and performing overall averaging on the denoised first three natural frequencies to calculate the mean of the first three natural frequencies, and fusing the mean with the processed target data by multi-rate Kalman filtering to obtain fused data; A labeling training module, used for labeling the processed target data twice to obtain training target data, and training the MobileNet model based on the training target data to obtain a trained MobileNet model; The acquisition and analysis module is used to acquire a frequency spectrum of the vibration signal data, and perform displacement analysis on the frequency spectrum and the fusion data based on the trained MobileNet model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the bridge displacement monitoring method according to any one of claims 1 to 7 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the bridge displacement monitoring method according to any one of claims 1 to 7 is implemented.

Images