CN117948886A - Bridge health state monitoring method and system - Google Patents
Bridge health state monitoring method and system Download PDFInfo
- Publication number
- CN117948886A CN117948886A CN202211282716.6A CN202211282716A CN117948886A CN 117948886 A CN117948886 A CN 117948886A CN 202211282716 A CN202211282716 A CN 202211282716A CN 117948886 A CN117948886 A CN 117948886A
- Authority
- CN
- China
- Prior art keywords
- bridge
- displacement
- response time
- target
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000012544 monitoring process Methods 0.000 title claims abstract description 44
- 230000036541 health Effects 0.000 title claims abstract description 43
- 238000006073 displacement reaction Methods 0.000 claims abstract description 160
- 230000004044 response Effects 0.000 claims abstract description 102
- 238000004891 communication Methods 0.000 claims description 14
- 238000012806 monitoring device Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 6
- 238000010276 construction Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 230000005284 excitation Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003862 health status Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 241000283073 Equus caballus Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The application provides a bridge health state monitoring method, a system and a storage medium, wherein the bottom of a bridge is provided with at least two targets, and a camera for acquiring images at the targets is arranged at a bridge pier, and the method comprises the following steps: acquiring first displacement response time-course data at any one target point, and determining a first mahalanobis distance of the first displacement response time-course data according to the first displacement response time-course data and an autoregressive coefficient; and calculating a difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance, and outputting an early warning of the damage of the bridge when the difference value is greater than or equal to a preset threshold value. The infrared laser target point adopted by the application has lower cost, can adapt to various harsh working environments, omits a complex acquisition and transmission link of an acquisition instrument, and has the advantages of convenient construction, good reliability and high identification accuracy.
Description
Technical Field
The application relates to the technical field of monitoring systems, in particular to a bridge health state monitoring method and system.
Background
Most of the traditional bridge health state monitoring methods are to perform data analysis and health state evaluation on a bridge by arranging a high-precision vibration pickup on the bridge and acquiring acceleration response under environmental excitation. However, the high-precision vibration pickup has the advantages of complex structure, high price and severe application conditions, and generally needs to acquire and transmit data through a multi-channel acquisition instrument, so that the whole system has high price, complex structure and poor operability and reliability for the bridge health state evaluation requirement of acquiring data in real time for a long time.
Disclosure of Invention
The present application has been made to solve the above-described problems. According to an aspect of the present application, there is provided a bridge health status monitoring method, wherein at least two targets are provided at the bottom of the bridge, and a camera for capturing images at the targets is provided at the bridge pier, the method comprising:
acquiring first displacement response time-course data at any one target point, and determining a first mahalanobis distance of the first displacement response time-course data according to the first displacement response time-course data and an autoregressive coefficient;
And calculating a difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance, and outputting an early warning of the damage of the bridge when the difference value is greater than or equal to a preset threshold value.
In one embodiment of the present application, before the acquiring the first displacement response time-course data at the arbitrary target point, the method further includes:
And calculating the second mahalanobis distance.
In one embodiment of the present application, said calculating said second mahalanobis distance includes:
and under the healthy state of the bridge, constructing an autoregressive time sequence model through second displacement response time-course data of any one target point of the bridge, determining the autoregressive coefficient of the autoregressive time sequence model, and calculating the second mahalanobis distance of the second displacement response time-course data according to the second displacement response time-course data and the autoregressive coefficient.
In one embodiment of the present application, the acquiring the first displacement response time-course data at any one target point includes:
sending a request for acquiring the first displacement response time-course data to a cloud server;
and receiving the first displacement response time-course data sent by the cloud server.
In one embodiment of the present application, the acquiring the first displacement response time-course data at any one target point includes:
Acquiring a target image at any target point acquired by the camera, and determining the image displacement of the target image relative to the reference image; the reference image is an image of any target point of the bridge, which is acquired when the bridge is in a healthy state;
and determining first displacement response time course data of the bridge according to the image displacement.
In one embodiment of the application, the target is an infrared laser target.
In one embodiment of the application, the method further comprises: and determining the distance between the target point and the damage position of the bridge according to the difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance.
In one embodiment of the application, the method further comprises: and determining the position of the damaged position of the bridge according to the distance between at least two target points and the damaged position of the bridge.
According to another aspect of the present application, there is provided a bridge health status monitoring method, wherein at least two targets are provided at the bottom of the bridge, and a camera for capturing images at the targets is provided at the bridge pier, the method comprising:
Collecting a reference image of any target point of the bridge under the healthy state of the bridge;
At any moment, collecting a target image at any target point, and determining the image displacement of the target image relative to the reference image;
And according to the image displacement, determining displacement response time course data of the bridge at any moment, and sending the displacement response time course data to a cloud server for storage so that a client can evaluate the health state of the bridge by using the displacement response time course data.
In one embodiment of the application, determining an image displacement between the target image and the reference image comprises:
selecting a reference subregion of the reference image;
determining a target subarea corresponding to the reference subarea in the target image;
and determining the image displacement according to the gray value of the reference subarea and the gray value of the target subarea.
In one embodiment of the application, determining the image displacement from the gray value of the reference sub-region and the gray value of the target sub-region comprises:
Determining a correlation coefficient of the reference subregion and the target subregion;
according to the correlation coefficient, determining the whole pixel displacement of the target subarea relative to the reference subarea;
and determining the image displacement by using a curved surface fitting method according to the whole pixel displacement.
In one embodiment of the present application, determining displacement response time course data of the bridge at any time according to the image displacement includes:
and determining the displacement response time course data of the bridge at any moment according to the conversion coefficient of the image displacement and the displacement response time course data.
In one embodiment of the application, the sampling frequency of the reference image at any one target point of the bridge is between 25Hz and 35 Hz.
According to yet another aspect of the present application, there is provided a bridge health monitoring system, the system comprising a data acquisition device, a monitoring device in communication with the data acquisition device;
the data acquisition equipment comprises at least two targets arranged at the bridge and a camera for acquiring target images at each target;
The monitoring equipment is used for calculating displacement response time course data of the bridge according to the target point image, judging whether the bridge is damaged according to the displacement response data, and outputting early warning information when the bridge is damaged. .
According to a further aspect of the present application there is provided a storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the bridge health monitoring method described above.
According to the bridge health state monitoring method, system and storage medium, the target point is arranged at the bottom of the bridge, the first mahalanobis distance is calculated according to the image of the target point, then the difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance is calculated, whether the bridge is damaged or not is judged according to whether the difference value between the first mahalanobis distance and the second mahalanobis distance reaches the preset threshold value or not, the cost of the adopted infrared laser target point is low, the method can adapt to various severe working environments, the complex and complicated acquisition and transmission link of an acquisition instrument is omitted, and the method is convenient to construct, good in reliability and high in identification accuracy.
Drawings
The above and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 shows a schematic flow chart of a bridge health monitoring method according to an embodiment of the application;
FIG. 2 shows a schematic flow chart of a bridge health monitoring method according to an embodiment of the application;
FIG. 3 shows a schematic flow diagram of a bridge health monitoring method system according to an embodiment of the application;
fig. 4 shows a schematic diagram of a bridge health monitoring system according to an embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the application described in the present application, all other embodiments that a person skilled in the art would have without inventive effort shall fall within the scope of the application.
Based on the technical problems, the application provides a bridge health state monitoring method, wherein at least two targets are arranged at the bottom of a bridge, and a camera for acquiring images at the targets is arranged at a bridge pier, and the method comprises the following steps: acquiring first displacement response time-course data at any one target point, and determining the mahalanobis distance of the first displacement response time-course data according to the first displacement response time-course data and an autoregressive coefficient; and calculating a difference value between the mahalanobis distance and a second pre-stored mahalanobis distance, and outputting an early warning of damage to the bridge when the difference value is greater than or equal to a preset threshold value. The method and the device have the advantages that the first displacement response time course data and the autoregressive coefficient of the bridge in the healthy state are used as reference data, the second mahalanobis distance of the reference data is calculated, then the first mahalanobis distance is determined according to the second displacement response time course data and the autoregressive coefficient of the bridge in the preset time interval, whether the bridge is damaged or not is judged according to whether the difference value between the first mahalanobis distance and the second mahalanobis distance reaches the preset threshold value, the cost of the infrared laser target point adopted by the method and the device is low, the device can adapt to various severe working environments, the complex and complicated acquisition and transmission links of an acquisition instrument are omitted, and the method and the device are convenient to construct, good in reliability and high in identification accuracy.
Aspects of the bridge health monitoring method according to embodiments of the present application are described in detail below with reference to the accompanying drawings. The features of the various embodiments of the application may be combined with one another without conflict.
FIG. 1 shows a schematic flow chart of a bridge health monitoring method according to an embodiment of the application; the bottom of bridge is provided with two at least targets, pier department is provided with the camera that is used for gathering the image of target department. As shown in fig. 1, the bridge health monitoring method 100 according to the embodiment of the present application may include the following steps S101 and S102:
in step S101, first displacement response time-course data at any one target point is obtained, and a first mahalanobis distance of the first displacement response time-course data is determined according to the first displacement response time-course data and an autoregressive coefficient.
In one example of the application, the target is preferably an infrared laser target. Other types of targets may be employed in other embodiments. The application is described by taking an infrared laser target as an example.
In one embodiment of the present application, the acquiring the first displacement response time-course data at any one target point includes: a1, sending a request for acquiring the first displacement response time-course data to a cloud server; a2, receiving the first displacement response time-course data sent by the cloud server.
For example, in the present application, an architecture mode of a data acquisition device, a monitoring device (including a cloud server and a client) may be employed. The data acquisition equipment acquires first displacement response time-course data, the first displacement response time-course data is uploaded to the cloud server for processing, and then the client downloads the data from the cloud server for calculation when the data are needed. Specifically, an infrared laser target spot and a camera can be arranged at the bridge, a processor and a communication module can be further arranged, the camera can collect an infrared image at the infrared laser target spot, the processor processes the infrared image collected by the camera, first displacement response time interval data, namely physical displacement of the bridge, can be obtained, and then the first displacement response time interval data is uploaded to a cloud server by the communication module for storage. Wherein the communication module may be, but is not limited to, a 4G/5G communication module.
Because the cloud server has stored the first displacement response time-course data uploaded by the data acquisition device at this time, the client can directly send a request for taking the first displacement response time-course data to the cloud server, construct an autoregressive time sequence model according to the first displacement response time-course data at any one target point of the bridge, determine the autoregressive coefficient of the autoregressive time sequence model, and calculate the first mahalanobis distance according to the autoregressive coefficient. The calculation process is as follows:
assuming that the length of the bridge monitoring data sample is L, equally dividing the bridge monitoring data sample into K segments, wherein the data length of each segment is J, namely l=k×j, substituting the data sample to be determined (first displacement response time-course data) into formula (1) to obtain a first mahalanobis distance vector of the data sample to be determined, as follows:
Wherein MDD is a first Markov distance vector of a state to be determined, X Di is an element in a data sample to be determined, μ is a mean value of reference data, and Σ is a covariance of the reference data.
These can be used to construct an autoregressive time series model from the first displacement response time-course data and to determine the autoregressive coefficients of the autoregressive time series model, and then μ and Σ can be calculated from the autoregressive coefficients (i.e., the reference data), and specific processes can be referred to the following second equine distance vector calculation process.
Notably, the camera of the data acquisition device acquires the infrared image in real time, and the processor processes the infrared image in real time to obtain first displacement response time course data and uploads the first displacement response time course data to the cloud server in real time. Therefore, the cloud server stores the first displacement response time course data uploaded by the data acquisition equipment in real time. The client can acquire the second displacement response time interval data once in a preset time interval. For example, the preset time interval may be 1 hour.
In another embodiment of the present application, the acquiring the first displacement response time-course data at any one target point includes: b1, acquiring a target image at any target point acquired by the camera, and determining the image displacement of the target image relative to the reference image; the reference image is an image of any target point of the bridge, which is acquired when the bridge is in a healthy state; and B2, determining first displacement response time course data of the bridge according to the image displacement.
In the application, the architecture modes of the data acquisition device and the monitoring device can also be adopted. The cloud server and the client are not distinguished, and can be physically one device for storing data and calculating.
It should be noted that the architecture of the data collecting device and the monitoring device is a preferred embodiment of the present invention, and in other embodiments, the data collecting device and the monitoring device may be integrated into a whole or divided into finer architectures according to functions.
In one embodiment of the present application, before the acquiring the first displacement response time course data at the arbitrary target point, the method further includes: and calculating the second mahalanobis distance.
In one example, the calculating the second mahalanobis distance includes: and under the healthy state of the bridge, constructing an autoregressive time sequence model through second displacement response time-course data of any one target point of the bridge, determining the autoregressive coefficient of the autoregressive time sequence model, and calculating the second mahalanobis distance of the second displacement response time-course data according to the second displacement response time-course data and the autoregressive coefficient.
In one embodiment of the application, the process of constructing an autoregressive time series model and determining autoregressive coefficients of the autoregressive time series model is described by taking bridge lateral displacement data at one of the target points as an example.
Assuming that the displacement response time-course data of the bridge is { X t } (t=1, 2..once., N), an N-th order Autoregressive (AR) time-series model is built as follows:
Wherein X t is the value of the bridge displacement response time interval { X t } at the time t, n is the order of the AR time series model, Is an autoregressive coefficient (n-th order autoregressive coefficient is n in model), and represents the influence degree of the value x t-i before the time t on the value x t at the time t, a t represents zero mean and variance as/>Is a gaussian white noise of (c).
Wherein the order n of the AR time series model may be determined according to AIC criteria. The AIC criterion function is as follows:
wherein p is the order of the time sequence model, N is the length of the bridge displacement response result, As the variance of the model residual, when AIC takes the minimum, the corresponding p is the appropriate order of the model, i.e., n=p.
In the embodiment of the application, the autoregressive coefficient of the AR time series model can be used as the reference data of the bridge health state. The autoregressive coefficient of the AR time series model is obtained through a least square method. From formula (2):
wherein, formula (4) can be written in a matrix form as follows:
Wherein, A= [ x n+1 xn+1 …xN]T, a＝[xn+1 xn+1 … xN]T。
According to multiple regression theory, autoregressive coefficient matrixLeast squares estimation of (c) is:
in one embodiment of the present application, a second mahalanobis distance may be calculated according to the second displacement response time interval data and the autoregressive coefficients calculated above, where the second mahalanobis distance calculation formula is as follows:
MD＝(X-μ)TΣ-1(X-μ) (8)
wherein MD is the second Markov distance, X is an element in the data to be determined, μ is the mean value of the reference data, and Σ is the covariance of the reference data.
In order to achieve a better monitoring effect, assuming that the length of the bridge monitoring data sample is L, the bridge monitoring data sample is equally divided into K segments, the data length of each segment is J, namely l=kxj, and the reference data sample (the first displacement response time-course data) is substituted into the formula (8), so that a second mahalanobis distance vector of the reference data sample can be obtained, as follows:
wherein MDH is the second Marshall distance vector of the reference state, X Hi is an element in the reference state data sample, μ is the mean value of the reference data, Σ is the covariance of the reference data.
In the embodiment of the application, the autoregressive coefficient obtained by the first test after the bridge health monitoring system is installed can be obtainedAnd the bridge health state reference data are used as bridge health state reference data so as to calculate a first mahalanobis distance for the data to be determined, which are collected later.
Step S103, calculating a difference value between the first Marsdian distance and a pre-stored second Marsdian distance, and outputting an early warning of damage to the bridge when the difference value is greater than or equal to a preset threshold value.
The first displacement response time interval data at each infrared laser target point and the second displacement response time interval data at each infrared laser target point can be obtained through the method, and the first mahalanobis distance and the second mahalanobis distance at each infrared laser target point can be obtained according to the autoregressive coefficient. For at least more than two infrared laser targets arranged at the bridge, if the difference value between the first mahalanobis distance and the second mahalanobis distance at one target is greater than or equal to a preset threshold value, the bridge at the position is considered to be possibly damaged, and early warning information of damage of the bridge is sent.
In yet another embodiment of the present application, the method further comprises: and determining the distance between the target point and the damage position of the bridge according to the difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance.
From the pre-determined data, the difference (the difference between the first mahalanobis distance and the second mahalanobis distance) is inversely proportional to the distance (the distance between the target point and the damaged portion of the bridge), and therefore, the distance between the target point and the damaged portion of the bridge can be determined according to the inversely proportional relationship between the target point and the damaged portion of the bridge, and thus, the approximate position of the damaged portion of the bridge can be determined.
In one example, the method further comprises: and determining the position of the damaged position of the bridge according to the distance between at least two target points and the damaged position of the bridge. According to the geometric principle, the distances from the damage position to a plurality of target points are determined, circles/spheres are drawn by taking each target point as a center and the distances from the damage position to each target point as a radius, and then the intersection point between the circles/spheres is the damage position, so that the approximate position of the damage position can be determined. The bridge damage monitoring system can monitor the health state of the bridge, can determine the damage position of the bridge, and is convenient for operators to carry out safety precaution and daily maintenance on the bridge.
According to the application, the target point is arranged at the bottom of the bridge, the first mahalanobis distance is calculated according to the image at the target point, then the difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance is calculated, whether the bridge is damaged or not is judged according to whether the difference value between the first mahalanobis distance and the second mahalanobis distance reaches the preset threshold value, the cost of the adopted infrared laser target point is low, the method can adapt to various severe working environments, and the method omits a complex acquisition and transmission link of an acquisition instrument, and is convenient to construct, good in reliability and high in identification accuracy.
FIG. 2 shows a schematic flow chart of a bridge health monitoring method according to an embodiment of the application; the bottom of bridge is provided with two at least targets, pier department is provided with the camera that is used for gathering the image of target department. As shown in fig. 2, the bridge health monitoring method 200 according to the embodiment of the present application may include the following steps S201, S202 and S203:
in step S201, a reference image at any one target point of the bridge is acquired when the bridge is in a healthy state.
Generally, the state of a bridge that has just been built and has not been put into use is considered a healthy state. Thus, it is possible to acquire a reference image at any one target point of the bridge when the bridge has not been put into use.
The target point of the embodiment of the application can be an infrared laser target point, and correspondingly, the camera can be an infrared camera.
In one embodiment of the application, a camera may acquire infrared images at each infrared laser target point on the bridge under environmental stimulus in real time.
In a specific embodiment, the sampling frequency of the infrared images acquired by the camera is between 25Hz and 35Hz, for example 30Hz. And the camera continuously collects infrared images.
At any time, a target image at the arbitrary target point is acquired, and an image displacement of the target image relative to the reference image is determined at step S202.
In one embodiment of the application, determining an image displacement between the target image and the reference image comprises: b1, selecting a reference subarea of the reference image; b2, determining a target subarea corresponding to the reference subarea in the target image; and B3, determining the image displacement according to the gray value of the reference subarea and the gray value of the target subarea.
In one example, determining the image displacement from the gray value of the reference sub-region and the gray value of the target sub-region comprises: c1, determining a correlation coefficient of the reference subarea and the target subarea; c2, according to the correlation coefficient, determining the whole pixel displacement of the target subarea relative to the reference subarea; and C3, determining the image displacement by using a curved surface fitting method according to the whole pixel displacement.
Specifically, the processor may process the image captured by each target point in real time. Firstly, selecting an infrared image at any one infrared laser target point of a bridge in a healthy state (before the bridge is deformed) as a reference image, selecting a subarea in the reference image before the bridge is deformed as a reference subarea, assuming that the gray scale distribution is f (x, y), and then acquiring a target subarea in a target infrared image (namely an image after the bridge is deformed) at any one infrared laser target point, and assuming that the gray scale distribution is g (x, y). And assuming that the pixel distances of the bridge at the infrared target point, which move relatively before deformation after deformation, are dx and dy, wherein dx represents the transverse displacement and dy represents the vertical displacement. The gray values of the calculated areas before and after the deformation have the following relationship:
g(x*,y*)＝f(x-dx,y-dy) (10)
Calculating the similarity of the two subareas, and defining a correlation coefficient C as follows:
When the correlation coefficient C reaches the maximum value, the displacement of the target subarea, namely the real-time whole pixel displacement at any one infrared excitation target point, can be obtained, and then the subpixel displacements dx and dy, namely the image displacement, are obtained by using a curved surface fitting method. By this method, the image displacement at each infrared excitation target point can be obtained.
In step S203, according to the image displacement, displacement response time interval data of the bridge at any moment is determined, and the displacement response time interval data is sent to a cloud server for storage, so that the client side can evaluate the health state of the bridge by using the displacement response time interval data.
In one embodiment of the present application, determining displacement response time course data of the bridge at any time according to the image displacement includes: and determining the displacement response time course data of the bridge at any moment according to the conversion coefficient of the image displacement and the displacement response time course data.
Specifically, the actual physical displacement X and Y of the bridge are obtained by using a conversion coefficient K of the image displacement and the physical displacement calibrated in advance. Wherein x=k·dx, y=k·dy. Similarly, the displacement of the bridge portion at each infrared excitation target point can be obtained, and then the processor transmits the actual physical displacement data of the bridge to the cloud server for storage in real time through a communication module (e.g., a 4G communication module).
The infrared laser target point adopted by the application has lower cost, can adapt to various harsh working environments, omits a complex acquisition and transmission link of an acquisition instrument, and has the advantages of convenient construction, good reliability and high identification accuracy.
In yet another embodiment of the present application, a method for monitoring health status of a bridge is also provided. As shown in fig. 3, the bridge health monitoring method 300 according to the embodiment of the present application may include the following steps S301, S302, S303, S304, S305, S306, S307, S308, S309, and S310:
and step S301, installing an infrared target.
In one embodiment of the application, the infrared targets (namely infrared laser targets) can be uniformly arranged at the bottom of the bridge, and the fixing method is bolting, so that the targets can be ensured to be in close contact with the bridge; the camera is fixed at the pier body at one side, for example, the camera can be an industrial-grade camera, and the installation position of the camera needs to ensure that all targets at the bottom of the bridge are in the field of view of the camera. And then the infrared target spot and the camera are powered on, so that the infrared target spot emits infrared laser.
And step S302, shooting a target photo under environmental excitation.
In one embodiment of the application, when a bridge is used, for example, a vehicle drives over the bridge, the bridge may vibrate or even deform, and then the infrared image at the target point is photographed, so as to analyze the deformation degree of the bridge. In the embodiment of the application, the infrared image at the target point can be shot in real time so as to monitor the health state of the bridge in real time.
In step S303, the gray scale correlation coefficient extremum calculates the integer pixel displacement.
In one embodiment of the present application, the displacement of the whole pixel can be calculated according to the above-described formula (10) and formula (11).
Step S304, calculating sub-pixel displacement by surface fitting.
In one embodiment of the present application, the displacement of the sub-pixel may be calculated by using a curved surface fitting method in the conventional technology, which is not described herein.
In step S305, the sub-pixel displacement is converted into a target physical displacement. And obtaining the actual physical displacement of the bridge according to the conversion coefficient K of the image displacement and the physical displacement which are determined in advance.
Step S306, test data for the first time.
In one embodiment of the present application, no environmental stimulus may occur when the system of the present application is deployed, i.e., the bridge is in a healthy state, and no deformation occurs, so the first test data immediately after the deployment of the system of the present application may be used as reference data, or may be any one of the test data when the bridge is in a healthy state.
Step S307, the data is tested. After the system is put into use, the system is tested to obtain subsequent test data, namely, the shot target image, which can be used as data for analyzing whether the bridge is healthy.
Step S308, time series analysis. Specifically, from the first test data and the subsequent test data, first displacement response time-course data and second displacement response time-course data of the first test data and the subsequent test data may be calculated, respectively.
Step S309, markov distance calculation. In particular, an Autoregressive (AR) time series model may be constructed from the first test data and autoregressive coefficients derived. Then, based on the autoregressive coefficients, the first displacement response time-course data and the second displacement response time-course data, the mahalanobis distance between the two can be calculated respectively.
And step S310, health state assessment and early warning are carried out. Specifically, the calculated first mahalanobis distance and the calculated second mahalanobis distance can be compared, and when the difference value of the first mahalanobis distance and the second mahalanobis distance is larger than a preset threshold value, the health state of the bridge is considered to be problematic or damaged, and early warning information needs to be sent.
The above is merely an example, and in the specific implementation, the order of steps S306, S307, S308 and S309 above is not necessarily strictly performed in the above order, and the first displacement response time interval data, the autoregressive coefficient and the second mahalanobis distance thereof may be calculated when the first test data is obtained, and then the first displacement response time interval data, the autoregressive coefficient and the first mahalanobis distance may be directly used when the subsequent test data is obtained, which is not limited herein.
The infrared laser target point adopted by the application has lower cost, can adapt to various harsh working environments, omits a complex acquisition and transmission link of an acquisition instrument, and has the advantages of convenient construction, good reliability and high identification accuracy.
The bridge health monitoring system of the present application is described below in conjunction with fig. 4, where fig. 4 shows a schematic diagram of a bridge health monitoring system 400 according to an embodiment of the present application.
As shown in fig. 4, the bridge health monitoring system 400 includes: the system comprises a data acquisition device 41, a monitoring device 42 in communication with the data acquisition device.
The data acquisition equipment comprises at least two targets arranged at the bridge and a camera for acquiring target images at each target;
The monitoring equipment is used for calculating displacement response time course data of the bridge according to the target point image, judging whether the bridge is damaged according to the displacement response data, and outputting early warning information when the bridge is damaged.
In one embodiment of the application, the monitoring device 42 may include a cloud server 421 and/or a client 422.
The data acquisition device 41 is disposed at the bridge 43, and is configured to acquire displacement response time-course data of the bridge 43, and send the displacement response data to the cloud server for storage.
Specifically, the data acquisition device 41 includes: at least two infrared laser targets 411, a camera 412, a processor 413, a communication module 414, and a power system 415.
The infrared laser targets 411 are disposed at the bottom of the bridge 43, and all the infrared laser targets 411 are located in the field of view of the camera 412, where the infrared laser targets 411 are used for emitting infrared laser. In a specific embodiment, the plurality of infrared laser targets 411 are uniformly disposed at the bottom of the bridge 43.
The camera 412 is disposed at the pier body of the bridge 43, and is configured to collect infrared images at each of the infrared laser targets 411. In a specific embodiment, the camera 412 may be an industrial camera.
Wherein the processor 413 is configured to receive the infrared image collected by the camera 412, and calculate the displacement response time interval data of the bridge 43 according to the infrared image. In particular, the processor 413 may be a Central Processing Unit (CPU), an image processing unit (GPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other form of processing unit 4 with data processing capabilities and/or instruction execution capabilities.
The communication module 414 is configured to send the displacement response time interval data to the cloud server for storing. In a specific embodiment, the communication module may be a 4G communication module.
Wherein the power system 415 is connected to the at least two infrared laser targets 411, the camera 412, the processor 413, and the communication module 414 to supply power thereto.
In one embodiment of the present application, the cloud server 421 is configured to store the displacement response time-course data of the bridge.
In one embodiment of the present application, the client 422 is configured to obtain the displacement response data stored in the cloud server 421 at a preset time interval, determine whether the bridge is damaged according to the displacement response data, and output early warning information when the bridge 43 is damaged.
The cloud server 421 and the client 422 are also respectively configured with a power supply system, and can supply power to the power supply system.
Furthermore, according to an embodiment of the present application, there is also provided a storage medium on which program instructions are stored, which program instructions, when executed by a computer or a processor, are adapted to carry out the respective steps of the bridge health monitoring method of the embodiment of the present application. The storage medium may include, for example, a memory card of a smart phone, a memory component of a tablet computer, a hard disk of a personal computer, read-only memory (ROM), erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), USB memory, or any combination of the foregoing storage media.
The bridge health monitoring system and the storage medium provided by the embodiment of the application have the same advantages as the bridge health monitoring method because the bridge health monitoring method can be realized.
Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above illustrative embodiments are merely illustrative and are not intended to limit the scope of the present application thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the application. All such changes and modifications are intended to be included within the scope of the present application as set forth in the appended claims.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in order to streamline the application and aid in understanding one or more of the various inventive aspects, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the application. However, the method of the present application should not be construed as reflecting the following intent: i.e., the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
It will be understood by those skilled in the art that all of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be combined in any combination, except combinations where the features are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
Various component embodiments of the application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some of the modules according to embodiments of the present application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application can also be implemented as a system program (e.g., a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
The foregoing description is merely illustrative of specific embodiments of the present application and the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the scope of the present application. The protection scope of the application is subject to the protection scope of the claims.
Claims (15)
1. The bridge health state monitoring method is characterized in that at least two targets are arranged at the bottom of a bridge, a camera for acquiring images at the targets is arranged at a bridge pier, and the method comprises the following steps:
acquiring first displacement response time-course data at any one target point, and determining a first mahalanobis distance of the first displacement response time-course data according to the first displacement response time-course data and an autoregressive coefficient;
And calculating a difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance, and outputting an early warning of the damage of the bridge when the difference value is greater than or equal to a preset threshold value.
2. The method of claim 1, wherein prior to said obtaining the first displacement response time course data at the arbitrary target point, the method further comprises:
And calculating the second mahalanobis distance.
3. The method of claim 2, wherein the calculating the second mahalanobis distance comprises:
and under the healthy state of the bridge, constructing an autoregressive time sequence model through second displacement response time-course data of any one target point of the bridge, determining the autoregressive coefficient of the autoregressive time sequence model, and calculating the second mahalanobis distance of the second displacement response time-course data according to the second displacement response time-course data and the autoregressive coefficient.
4. The method of claim 1, wherein the acquiring first displacement response time course data at any one target point comprises:
sending a request for acquiring the first displacement response time-course data to a cloud server;
and receiving the first displacement response time-course data sent by the cloud server.
5. The method of claim 1, wherein the acquiring first displacement response time course data at any one target point comprises:
acquiring target images at the target points acquired by the camera, and determining the image displacement of the target images relative to the reference images; the reference image is an image of any target point of the bridge, which is acquired when the bridge is in a healthy state;
and determining first displacement response time course data of the bridge according to the image displacement.
6. The method of any one of claims 1-5, wherein the target is an infrared laser target.
7. The method according to any one of claims 1-5, further comprising: and determining the distance between the target point and the damage position of the bridge according to the difference value between the first mahalanobis distance and the pre-stored second mahalanobis distance.
8. The method of claim 7, wherein the method further comprises: and determining the position of the damaged position of the bridge according to the distance between at least two target points and the damaged position of the bridge.
9. The bridge health state monitoring method is characterized in that at least two targets are arranged at the bottom of a bridge, a camera for acquiring images at the targets is arranged at a bridge pier, and the method comprises the following steps:
Collecting a reference image of any target point of the bridge under the healthy state of the bridge;
At any moment, collecting a target image at any target point, and determining the image displacement of the target image relative to the reference image;
And according to the image displacement, determining displacement response time course data of the bridge at any moment, and sending the displacement response time course data to a cloud server for storage so that a client can evaluate the health state of the bridge by using the displacement response time course data.
10. The method of claim 9, wherein determining an image displacement between the target image and the reference image comprises:
selecting a reference subregion of the reference image;
determining a target subarea corresponding to the reference subarea in the target image;
and determining the image displacement according to the gray value of the reference subarea and the gray value of the target subarea.
11. The method of claim 10, wherein determining the image displacement from the gray value of the reference sub-region and the gray value of the target sub-region comprises:
Determining a correlation coefficient of the reference subregion and the target subregion;
according to the correlation coefficient, determining the whole pixel displacement of the target subarea relative to the reference subarea;
and determining the image displacement by using a curved surface fitting method according to the whole pixel displacement.
12. The method of claim 9, wherein determining displacement response time course data for the bridge at the any one time from the image displacement comprises:
and determining the displacement response time course data of the bridge at any moment according to the conversion coefficient of the image displacement and the displacement response time course data.
13. The method of claim 9, wherein the sampling frequency of the reference image at any one target point of the bridge is between 25Hz and 35 Hz.
14. The bridge health monitoring system is characterized by comprising a data acquisition device and a monitoring device which is in communication connection with the data acquisition device;
the data acquisition equipment comprises at least two targets arranged at the bridge and a camera for acquiring target images at each target;
The monitoring equipment is used for calculating displacement response time course data of the bridge according to the target point image, judging whether the bridge is damaged according to the displacement response data, and outputting early warning information when the bridge is damaged.
15. A storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the bridge health monitoring method of any one of claims 1 to 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211282716.6A CN117948886A (en) | 2022-10-19 | 2022-10-19 | Bridge health state monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211282716.6A CN117948886A (en) | 2022-10-19 | 2022-10-19 | Bridge health state monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117948886A true CN117948886A (en) | 2024-04-30 |
Family
ID=90790961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211282716.6A Pending CN117948886A (en) | 2022-10-19 | 2022-10-19 | Bridge health state monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117948886A (en) |
-
2022
- 2022-10-19 CN CN202211282716.6A patent/CN117948886A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luo et al. | Robust vision sensor for multi-point displacement monitoring of bridges in the field | |
| CN109477771B (en) | Structural health monitoring system for identifying damage through device based on augmented reality technology | |
| Fukuda et al. | Vision-based displacement sensor for monitoring dynamic response using robust object search algorithm | |
| CN109341903B (en) | Inhaul cable force measuring method based on edge recognition in computer vision | |
| Kuddus et al. | Target-free vision-based technique for vibration measurements of structures subjected to out-of-plane movements | |
| Poozesh et al. | Multicamera measurement system to evaluate the dynamic response of utility‐scale wind turbine blades | |
| Bartilson et al. | Target-less computer vision for traffic signal structure vibration studies | |
| US10803324B1 (en) | Adaptive, self-evolving learning and testing platform for self-driving and real-time map construction | |
| Jeong et al. | Automated wireless monitoring system for cable tension forces using deep learning | |
| CN106952303A (en) | Vehicle distance detecting method, device and system | |
| Jana et al. | Computer vision‐based real‐time cable tension estimation algorithm using complexity pursuit from video and its application in Fred‐Hartman cable‐stayed bridge | |
| Havaran et al. | Extracting structural dynamic properties utilizing close photogrammetry method | |
| Park et al. | Vision‐based natural frequency identification using laser speckle imaging and parallel computing | |
| JP2022550711A (en) | System and method for assessing asset operating condition | |
| Ho et al. | Multiscale acceleration-dynamic strain-impedance sensor system for structural health monitoring | |
| Chu et al. | Cable tension monitoring through feature-based video image processing | |
| JP7144141B2 (en) | Structural health monitoring system | |
| CN115761487A (en) | Method for quickly identifying vibration characteristics of small and medium-span bridges based on machine vision | |
| Wu et al. | Machine vision–based measurement approach for transverse vibrations of moving hoisting vertical ropes in mine hoists using edge location | |
| CN117076928A (en) | Bridge health state monitoring method, device and system and electronic equipment | |
| Brown et al. | Evaluation of a novel video-and laser-based displacement sensor prototype for civil infrastructure applications | |
| Abdullahi et al. | Accelerometer Based Structural Health Monitoring System on the Go: Developing Monitoring Systems with NI LabVIEW. | |
| CN117948886A (en) | Bridge health state monitoring method and system | |
| CN104391044B (en) | A kind of method for detecting vibration for detecting honeycomb corrosion damage | |
| Du et al. | A non-contact displacement measurement system based on a portable smartphone with digital image methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |