Bridge disease warning method, device, equipment, storage medium and computer product

Abstract

The present invention provides a method, device, equipment, storage medium and computer product for bridge disease warning, which relates to the technical field of electrical digital data processing. The method includes: obtaining the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera; calculating the current bridge health index of the target bridge based on the strain signal within the target time period, the vibration signal within the target time period, and the target image within the target time period; if the bridge health index is lower than the first threshold, it is determined that the target bridge is in a high-risk state; if the bridge health index is greater than or equal to the first threshold and less than the second threshold, it is determined that the target bridge is in a state of structural function degradation; wherein, the second threshold is greater than the first threshold; if the bridge health index is greater than the second threshold, it is determined that the target bridge is in a risk-free state. The present invention can timely and accurately determine whether the bridge is currently in a normal state and avoid accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical digital data processing, and in particular, to a method, device, equipment, storage medium and computer product for bridge disease warning. Background Art

[0002] As core nodes of the transportation network, bridges and tunnels are susceptible to diseases such as cracks, settlements, and leaks due to long-term environmental erosion, vehicle loads, material aging, etc. Traditional detection methods mainly rely on manual inspections or single-sensor monitoring, and have the following problems: poor timeliness: the manual inspection cycle is long, and it is difficult to capture sudden diseases in a timely manner; high false alarm rate: single sensors are easily affected by the environment, and the data reliability is insufficient; weak comprehensive judgment ability: the fusion analysis of multi-dimensional data (such as structural stress, temperature and humidity, images, etc.) is not realized. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, equipment, storage medium and computer product for bridge disease warning to solve the problems of poor timeliness, high false alarm rate and weak comprehensive judgment ability in existing bridge disease detection.

[0004] In a first aspect, embodiments of the present invention provide a method for bridge disease warning, including:

[0005] Obtain the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera; wherein, the target image is a bridge image including the strain sensor and the three-dimensional accelerometer.

[0006] Calculate the current bridge health index of the target bridge based on the strain signal in the target time period, the vibration signal in the target time period, and the target image in the target time period.

[0007] If the bridge health index is lower than the first threshold, it is determined that the target bridge is in a high-risk state.

[0008] If the bridge health index is greater than or equal to the first threshold and less than the second threshold, it is determined that the target bridge is in a state of structural function degradation; wherein, the second threshold is greater than the first threshold.

[0009] If the bridge health index is greater than the second threshold, it is determined that the target bridge is in a risk-free state.

[0010] In a possible implementation manner, calculating the current bridge health index of the target bridge based on the strain signal in the target time period, the vibration signal in the target time period, and the target image in the target time period includes:

[0011] For each moment in the target time period, identify the break points in the target image at that moment.

[0012] Based on the break points in the target image at each moment, determine the strain signals collected by the strain sensors within a preset range around the break point and the vibration signals collected by the three-dimensional accelerometers within a preset range around the break point, and denote them as the target strain signals and the target vibration signals.

[0013] According to the target strain signals and the target vibration signals, determine whether the break point is an abnormal point.

[0014] If the break points in the target images at multiple consecutive moments within the target time period are the same break point and are all determined to be abnormal points, then define this break point as the target point.

[0015] Based on the number of target points within the target time period, obtain the bridge health index.

[0016] In a possible implementation manner, obtaining the bridge health index based on the number of target points within the target time period includes:

[0017] Adopt the first formula to obtain the bridge health index.

[0018] The first formula is:

[0019]

[0020] Among them, represents the number of target points within the target time period, represents the bridge health index, represents a preset parameter.

[0021] In a possible implementation manner, determining whether the break point is an abnormal point according to the target strain signals and the target vibration signals includes:

[0022] Obtain the strain signal threshold and the vibration signal threshold.

[0023] If the target strain signal is greater than the strain signal threshold or the target vibration signal is greater than the vibration signal threshold, then determine that the break point is an abnormal point.

[0024] In a possible implementation manner, the method further includes:

[0025] Obtain the temperature and humidity signals of the temperature and humidity sensor.

[0026] Based on the temperature and humidity signals, in combination with the second formula, adjust the strain signal threshold and the vibration signal threshold.

[0027] The second formula is:

[0028]

[0029] Among them, represents the strain signal threshold before adjustment or the vibration signal threshold before adjustment, represents the temperature and humidity signal, represents the standard value of the temperature and humidity signal, represents the strain signal threshold after adjustment or the vibration signal threshold after adjustment.

[0030] In a possible implementation, obtaining the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera includes:

[0031] Obtaining the original data of the strain signal, the original data of the vibration signal, and the original data of the target image.

[0032] Performing noise reduction and normalization processing on the original data to obtain the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera.

[0033] In a second aspect, an embodiment of the present invention provides a bridge disease warning device, including:

[0034] A first processing module, configured to obtain the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera; wherein, the target image is a bridge image including the strain sensor and the three-dimensional accelerometer.

[0035] A second processing module, configured to calculate the current bridge health index of the target bridge based on the strain signal within the target time period, the vibration signal within the target time period, and the target image within the target time period.

[0036] A third processing module, configured to determine that the target bridge is in a high-risk state if the bridge health index is lower than the first threshold; determine that the target bridge is in a state of structural function degradation if the bridge health index is greater than or equal to the first threshold and less than the second threshold; wherein, the second threshold is greater than the first threshold; determine that the target bridge is in a risk-free state if the bridge health index is greater than the second threshold.

[0037] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method in the first aspect or any possible implementation manner of the first aspect above is implemented.

[0038] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method in the first aspect or any possible implementation manner of the first aspect above is implemented.

[0039] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program which, when executed by a processor, implements the method in the first aspect above or any possible implementation manner of the first aspect.

[0040] In the embodiments of the present invention, the bridge health index of the target bridge can be calculated in a timely manner through the strain signal of the strain sensor, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera. In addition to combining the strain signal and the vibration signal of the sensor, the physical reality image is also combined, enabling comprehensive analysis from multiple angles to analyze the current state of the bridge. Moreover, calculating the bridge health index based on the data within the target time period can more fully eliminate interference signals and improve the accuracy of the final warning. Since the data of the sensor and the camera are both real-time monitored data, the real-time performance of this solution is greatly improved, enabling real-time monitoring of the bridge and giving a timely warning when diseases occur in the current bridge. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a flowchart of the implementation of the bridge disease warning method provided by the embodiment of the present invention;

[0042] Figure 2 is a schematic structural diagram of the bridge disease warning device provided by the embodiment of the present invention;

[0043] Figure 3 is a schematic diagram of the electronic device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0045] See Figure 1 , which shows a flowchart of the implementation of the bridge disease warning method provided by the embodiment of the present invention, and is described in detail as follows:

[0046] Step 101: Obtain the strain signal of the strain sensor, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera in the target bridge; wherein, the target image is a bridge image including the strain sensor and the three-dimensional accelerometer.

[0047] In some specific embodiments, step 101 may include:

[0048] Obtain the original data of the strain signal, the original data of the vibration signal, and the original data of the target image.

[0049] Perform noise reduction and normalization processing on the original data to obtain the strain signal of the strain sensor, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera in the target bridge.

[0050] Specifically, the above process may specifically include:

[0051] 1. Data acquisition

[0052] Strain sensor data

[0053] Hardware setup: Install strain sensors at key positions on the bridge (such as the mid-span of the main girder, the bottom of the pier, etc.) to ensure that the sensors can accurately capture the stress changes in the structure.

[0054] Data recording: Connect the sensors through a data acquisition system (such as NI DAQ equipment) and record the original strain signals at a predetermined sampling frequency (such as 100 times per second). These data are usually stored in the form of text files or databases.

[0055] Vibration signal (3D accelerometer)

[0056] Hardware setup: Place the 3D accelerometer at key vibration detection points on the bridge (such as selecting one maximum deflection test section at each of the main span and side span of the main bridge).

[0057] Data recording: Also use the data acquisition system to record the original vibration signals output by the accelerometer.

[0058] Target image data

[0059] Camera setup: Configure the monitoring camera to ensure that it can cover the target area and clearly capture the parts to be monitored (such as the bridge surface or key structural parts and including strain sensors and 3D accelerometers).

[0060] Data recording: Capture images or video streams as needed through camera software or SDK and save them as image files (such as JPEG, PNG). These images will be used for subsequent visual analysis.

[0061] 2. Data preprocessing

[0062] Noise reduction processing

[0063] Strain signal and vibration signal: Use filtering techniques to remove noise. Common methods include median filtering, low-pass filtering, or wavelet transform. Selecting appropriate filter parameters (such as window size, cut-off frequency) is crucial to avoid losing useful information due to over-smoothing. For vibration signals, frequency domain analysis methods (such as fast Fourier transform FFT) can also be applied to identify and remove unnecessary high-frequency components.

[0064] Image data: Image noise reduction can be achieved using various methods, such as Gaussian blur, mean filtering, or more advanced non-local means filtering (NLM). These methods help reduce random noise in the image while trying to preserve edges and other important features.

[0065] Normalization processing

[0066] Strain signal and vibration signal: Common methods include Min-Max Normalization, which scales the data to the range [0, 1]; or Z-Score Standardization, which converts the data into a standard normal distribution form with a mean of 0 and a standard deviation of 1.

[0067] Image data: For images, normalization usually refers to converting pixel values from the integer range of 0 - 255 to the floating-point range of 0 - 1.

[0068] Exemplarily, a camera monitors a risk area for 24 hours a day. Using an image recognition algorithm, the camera can identify specific target objects or phenomena. A three-dimensional accelerometer can measure the tilt angle and acceleration information of an object. Based on the principle of the accelerometer, it calculates the tilt angle by detecting the acceleration component of the object in the gravitational field. At the same time, it can also sense the linear acceleration of the object and can work normally under various harsh environmental conditions, such as high temperature, low temperature, high humidity, strong vibration, etc. It can still maintain stable performance and accurate data output, reducing equipment failures and data errors caused by environmental factors.

[0069] Exemplarily, in order to better calculate the bridge health index of a bridge, the distribution positions of sensors (strain sensors and three-dimensional accelerometers) generally combine the specific structural form and force characteristics of the bridge and are set at positions prone to damage, which can improve the sensitivity of monitoring and handle faults in a timely manner before a failure occurs. Specifically, the generally referable positions are: the maximum positive moment section at the mid-span of the main girder, the maximum negative moment section of the main girder, the maximum compressive stress section of the pier, the stress concentration section at the tower-girder consolidation position, one maximum deflection test section is selected for each of the main span and side span of the main bridge, one maximum deflection test section is selected for each of the two approach bridges, and horizontal displacement measuring points are arranged at the top of each main bridge tower, etc. Strain sensors and three-dimensional accelerometers will be placed at these points. In addition, a camera for photographing the bridge will also be set. The pictures taken by this camera will capture the placed strain sensors and three-dimensional accelerometers. The pictures taken by the camera are small-range pictures, not images of the entire bridge. The small-range pictures are convenient for subsequent judgment of abnormal points.

[0070] Step 102: Calculate the current bridge health index of the target bridge based on the strain signal within the target time period, the vibration signal within the target time period, and the target image within the target time period.

[0071] In some specific embodiments, step 102 may include:

[0072] For each moment within the target time period, identify the break points in the target image at that moment.

[0073] Based on the break points in the target image at each moment, determine the strain signals collected by the strain sensors within a preset range around the break point and the vibration signals collected by the three-dimensional accelerometers within a preset range around the break point, denoted as the target strain signals and the target vibration signals.

[0074] According to the target strain signals and the target vibration signals, determine whether the break point is an abnormal point.

[0075] If the break points in the target images at multiple consecutive moments within the target time period are the same break point and are all identified as abnormal points, then define this break point as the target point.

[0076] Based on the number of target points within the target time period, obtain the bridge health index.

[0077] Exemplarily, an image recognition algorithm can be used to identify the break points in the target image, which can not only speed up the identification of break points but also improve the accuracy of break point identification.

[0078] Specifically, identifying the break points in the target image based on the image recognition algorithm can specifically include:

[0079] Preprocessing: First, the image needs to be preprocessed, which can include steps such as grayscale conversion, denoising (such as using Gaussian blur), and binarization. These steps help reduce noise interference and highlight potential break points.

[0080] Edge detection: Use edge detection algorithms (Canny operator, Sobel operator, etc.) to find the positions of the object contours in the image, thereby helping to locate the break points.

[0081] Feature extraction and description: Techniques such as HOG (Histogram of Oriented Gradients), SIFT (Scale-Invariant Feature Transform), or SURF (Speeded-Up Robust Features) can be used to extract key points and their descriptors.

[0082] Break point detection: Directly analyze the results after edge detection and find discontinuous places as potential break points.

[0083] Postprocessing: Further analyze and filter the detected break points, such as removing false alarms according to geometric shapes or application domain knowledge. Take the finally filtered results as the finally identified break points.

[0084] In some specific embodiments, obtaining a bridge health index based on the number of target points within a target time period may include:

[0085] Using a first formula to obtain the bridge health index.

[0086] The first formula may be:

[0087]

[0088] Wherein, represents the number of target points within the target time period, represents the bridge health index, represents a preset parameter.

[0089] In some specific embodiments, determining whether the fracture point is an abnormal point according to the target strain signal and the target vibration signal may include:

[0090] Obtaining a strain signal threshold and a vibration signal threshold.

[0091] If the target strain signal is greater than the strain signal threshold or the target vibration signal is greater than the vibration signal threshold, then determine that the fracture point is an abnormal point.

[0092] Step 103, if the bridge health index is lower than the first threshold, then determine that the target bridge is in a high-risk state; if the bridge health index is greater than or equal to the first threshold and less than the second threshold, then determine that the target bridge is in a state of structural function degradation; wherein, the second threshold is greater than the first threshold; if the bridge health index is greater than the second threshold, then determine that the target bridge is in a risk-free state.

[0093] Exemplarily, the method further includes:

[0094] Obtaining the temperature and humidity signals of the temperature and humidity sensor.

[0095] Based on the temperature and humidity signals, combining with a second formula to adjust the strain signal threshold and the vibration signal threshold.

[0096] The second formula is:

[0097]

[0098] Wherein, represents the strain signal threshold before adjustment or the vibration signal threshold before adjustment, represents the temperature and humidity signal, represents the standard value of the temperature and humidity signal, represents the strain signal threshold after adjustment or the vibration signal threshold after adjustment.

[0099] The above-mentioned bridge disease warning method can calculate the bridge health index of the target bridge in a timely manner through the strain signals of strain sensors, the vibration signals of three-dimensional accelerometers, and the target images captured by cameras. In addition to combining the strain signals and vibration signals of the sensors, it also combines physical reality images, enabling comprehensive analysis from multiple perspectives to analyze the current state of the bridge. Moreover, calculating the bridge health index based on the data within the target time period can more fully eliminate interference signals and improve the accuracy of the final warning. Since the data of the sensors and cameras are all real-time monitored data, the real-time performance of this solution is greatly improved, enabling real-time monitoring of the bridge and giving timely warnings when diseases occur in the current bridge.

[0100] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0101] The following is an apparatus embodiment of the present invention. For details not described in detail herein, reference can be made to the corresponding method embodiments above.

[0102] Figure 2 The structural schematic diagram of the bridge disease warning device provided by the embodiment of the present invention is shown. For the sake of convenience of description, only the parts related to the embodiment of the present invention are shown and are described in detail as follows:

[0103] As Figure 2 shown, the bridge disease warning device includes:

[0104] A first processing module 201, configured to obtain the strain signals of strain sensors, the vibration signals of three-dimensional accelerometers, and the target images captured by cameras in the target bridge; wherein, the target image is a bridge image including strain sensors and three-dimensional accelerometers.

[0105] A second processing module 202, configured to calculate the current bridge health index of the target bridge based on the strain signals within the target time period, the vibration signals within the target time period, and the target images within the target time period.

[0106] A third processing module 203, configured to determine that the target bridge is in a high-risk state if the bridge health index is lower than the first threshold; determine that the target bridge is in a state of structural function degradation if the bridge health index is greater than or equal to the first threshold and less than the second threshold; wherein, the second threshold is greater than the first threshold; determine that the target bridge is in a risk-free state if the bridge health index is greater than the second threshold.

[0107] In a possible implementation manner, the second processing module 202 may be configured to:

[0108] For each moment within the target time period, identify the break points in the target image at that moment.

[0109] Based on the break points in the target image at each moment, determine the strain signals collected by the strain sensors within a preset range around the break point and the vibration signals collected by the three-dimensional accelerometers within a preset range around the break point, denoted as the target strain signals and the target vibration signals.

[0110] According to the target strain signals and the target vibration signals, determine whether the break point is an abnormal point.

[0111] If the break points in the target images at multiple consecutive moments within the target time period are the same break point and are all identified as abnormal points, then define this break point as the target point.

[0112] Based on the number of target points within the target time period, obtain the bridge health index.

[0113] In a possible implementation, the second processing module 202 can be used to:

[0114] Adopt the first formula to obtain the bridge health index.

[0115] The first formula can be:

[0116]

[0117] Wherein, represents the number of target points within the target time period, represents the bridge health index, represents a preset parameter.

[0118] In a possible implementation, the second processing module 202 can be used to:

[0119] Obtain the strain signal threshold and the vibration signal threshold.

[0120] If the target strain signal is greater than the strain signal threshold or the target vibration signal is greater than the vibration signal threshold, then determine that the break point is an abnormal point.

[0121] In a possible implementation, the third processing module 203 can be used to:

[0122] Obtain the temperature and humidity signals of the temperature and humidity sensors.

[0123] Based on the temperature and humidity signals, in combination with the second formula, adjust the strain signal threshold and the vibration signal threshold.

[0124] The second formula can be:

[0125]

[0126] Among them, represents the strain signal threshold before adjustment or the vibration signal threshold before adjustment, represents the temperature and humidity signal, represents the standard value of the temperature and humidity signal, represents the strain signal threshold after adjustment or the vibration signal threshold after adjustment.

[0127] In a possible implementation manner, the first processing module 201 can be used to:

[0128] Obtain the original data of the strain signal, the original data of the vibration signal, and the original data of the target image.

[0129] Perform noise reduction and normalization processing on the original data to obtain the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera.

[0130] Figure 3 is a schematic diagram of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, the electronic device 5 of this embodiment includes: a processor 50 and a memory 51. The memory 51 stores a computer program 52. When the processor 50 executes the computer program 52, the steps in the above-mentioned various method embodiments are implemented. Or, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0131] Exemplarily, the computer program 52 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 51 and executed by the processor 50 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 52 in the electronic device 5.

[0132] The electronic device 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art can understand that Figure 3 merely an example of the electronic device 5, which does not constitute a limitation on the electronic device 5, and may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the electronic device 5 may further include input / output devices, network access devices, buses, etc.

[0133] The processor 50 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0134] The memory 51 may be an internal storage unit of the electronic device 5, such as the hard disk or memory of the electronic device 5. The memory 51 may also be an external storage device of the electronic device 5, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the electronic device 5. Further, the memory 51 may also include both the internal storage unit and the external storage device of the electronic device 5. The memory 51 is used to store the computer program 52 and other programs and data required by the electronic device 5. The memory 51 may also be used to temporarily store the data that has been output or will be output.

[0135] For the convenience and simplicity of description, only the above division of each functional module / unit is used as an example. In actual applications, the above functions may be allocated to different functional modules / units according to needs. The above modules / units may be implemented in the form of hardware, or may be implemented in the form of software, or may be implemented in the form of a combination of hardware and software.

[0136] The embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0137] The embodiment of the present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0138] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0139] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Without special instructions and logical conflicts, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0140] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A bridge disease early warning method, characterized in that: include: Acquire a strain signal of a strain sensor in a target bridge, a vibration signal of a three-dimensional accelerometer, and a target image captured by a camera; wherein the target image is an image of a bridge including a strain sensor and a three-dimensional accelerometer; Calculate a current bridge health index of a target bridge based on the strain signal within a target time period, the vibration signal within a target time period, and the target image within a target time period; If the bridge health index is lower than a first threshold, the target bridge is deemed to be in a high-risk state; If the bridge health index is greater than or equal to the first threshold and less than a second threshold, it is determined that the target bridge is in a state of structural function degradation; wherein the second threshold is greater than the first threshold; If the bridge health index is greater than the second threshold, it is determined that the target bridge is in a risk-free state; The calculating the current bridge health index of the target bridge based on the strain signal within the target time period, the vibration signal within the target time period and the target image within the target time period includes: For each moment in the target time period, identifying the breakpoint in the target image at that moment; Based on the fracture point in the target image at each moment, a strain signal collected by a strain sensor within a preset range around the fracture point and a vibration signal collected by a three-dimensional accelerometer within a preset range around the fracture point are determined, and recorded as a target strain signal and a target vibration signal; determining whether the break point is an abnormal point according to the target strain signal and the target vibration signal; If the breakpoints in the target images at multiple consecutive moments within the target time period are the same breakpoint and are all identified as abnormal points, then the breakpoint is defined as the target point; Based on the number of the target points within the target time period, a bridge health index is obtained.

2. The bridge disease early warning method according to claim 1 is characterized in that: The bridge health index is obtained based on the number of the target points within the target time period, including: Using the first formula, we get the bridge health index; The first formula is: in, Indicates the number of target points within the target time period, represents the bridge health index, Indicates preset parameters.

3. The bridge disease early warning method according to claim 1 is characterized in that: The step of determining whether the breakpoint is an abnormal point according to the target strain signal and the target vibration signal includes: Obtain strain signal threshold and vibration signal threshold; If the target strain signal is greater than the strain signal threshold or the target vibration signal is greater than the vibration signal threshold, the breakpoint is determined to be an abnormal point.

4. The bridge disease early warning method according to claim 3 is characterized in that: The method further comprises: Obtain temperature and humidity signals from the temperature and humidity sensor; Based on the temperature and humidity signal, in combination with a second formula, adjusting the strain signal threshold and the vibration signal threshold; The second formula is: in, Indicates the strain signal threshold before adjustment or the vibration signal threshold before adjustment. represents the temperature and humidity signal, Indicates the standard value of temperature and humidity signal. Indicates the adjusted strain signal threshold or the adjusted vibration signal threshold.

5. The bridge disease early warning method according to claim 1 is characterized in that: The step of obtaining the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer, and the target image captured by the camera includes: Acquiring the original data of the strain signal, the original data of the vibration signal, and the original data of the target image; The original data is subjected to denoising and normalization processing to obtain the strain signal of the strain sensor in the target bridge, the vibration signal of the three-dimensional accelerometer and the target image taken by the camera.

6. A bridge disease early warning device, characterized in that: include: A first processing module is used to obtain a strain signal of a strain sensor in a target bridge, a vibration signal of a three-dimensional accelerometer, and a target image captured by a camera; wherein the target image is an image of a bridge including a strain sensor and a three-dimensional accelerometer; A second processing module is used to calculate a current bridge health index of a target bridge based on the strain signal within a target time period, the vibration signal within a target time period, and the target image within a target time period; A third processing module is used to determine that the target bridge is in a high-risk state if the bridge health index is lower than a first threshold; if the bridge health index is greater than or equal to the first threshold and less than a second threshold, the target bridge is determined to be in a structural function degradation state; wherein the second threshold is greater than the first threshold; if the bridge health index is greater than the second threshold, the target bridge is determined to be in a risk-free state; The second processing module is further used for: For each moment in the target time period, identifying the breakpoint in the target image at that moment; Based on the fracture point in the target image at each moment, a strain signal collected by a strain sensor within a preset range around the fracture point and a vibration signal collected by a three-dimensional accelerometer within a preset range around the fracture point are determined, and recorded as a target strain signal and a target vibration signal; determining whether the break point is an abnormal point according to the target strain signal and the target vibration signal; If the breakpoints in the target images at multiple consecutive moments within the target time period are the same breakpoint and are all identified as abnormal points, then the breakpoint is defined as the target point; Based on the number of the target points within the target time period, a bridge health index is obtained.

7. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 5 when being executed by a processor.

Images