Bearing structure state monitoring method and device, storage medium and electronic device

Abstract

The invention provides a state monitoring method and device of a bearing structure, a storage medium and an electronic device, and the method comprises the steps: obtaining target vehicle load data of a target bearing structure in a target time period, and a dynamic parameter data set of preset dynamic parameters, the target vehicle load data represents spatial and temporal distribution of vehicle loads borne by the target bearing structure, and the preset dynamic parameters are parameters of the target bearing structure changing along with the borne vehicle loads; based on the target vehicle load data, dividing the dynamic parameter data set into multiple groups of parameter data based on the load weight; determining parameter values of preset state parameters of the structure state of the target bearing structure based on each group of parameter data in the multiple groups of parameter data to obtain a plurality of parameter values, fusing the plurality of parameter values to obtain a fused parameter value, and determining the structure state of the target bearing structure based on the fused parameter value, the preset state parameter is used for representing the structure state of the target bearing structure.

Description

Technical Field

[0001] The present invention relates to the technical field of structural health monitoring, and in particular, to a method and device for monitoring the state of a load-bearing structure, a storage medium, and an electronic device. Background Art

[0002] Load-bearing structures such as roads and bridges are affected by factors such as traffic loads and natural environments during operation, and thus structural damages and diseases occur. In order to ensure the safe operation of the structures, it is necessary to monitor the state of the load-bearing structures so as to timely detect problems of the load-bearing structures and take corresponding maintenance and repair measures. The monitoring contents include the degree of damage, fatigue condition, deformation condition, etc.

[0003] Currently, the state monitoring of load-bearing structures is carried out by manually detecting the states of various positions. It can be seen that the state monitoring method of load-bearing structures in the related art has problems of long time consumption for state detection and large consumption of human resources. Summary of the Invention

[0004] The main object of the present invention is to provide a method and device for monitoring the state of a load-bearing structure, a storage medium, and an electronic device, so as to solve the problems of long time consumption for state detection and large consumption of human resources in the state monitoring method of load-bearing structures in the related art.

[0005] To achieve the above object, according to one aspect of the present invention, a method for monitoring the state of a load-bearing structure is provided, including: obtaining target vehicle load data of a target load-bearing structure within a target time period, and obtaining a set of dynamic parameter data of preset dynamic parameters of the target load-bearing structure within the target time period, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target load-bearing structure within the target time period, and the preset dynamic parameters are parameters that change as the target load-bearing structure bears the vehicle load; based on the target vehicle load data, dividing the set of dynamic parameter data into multiple groups of parameter data, where different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals; based on each group of parameter data in the multiple groups of parameter data, respectively determining parameter values of preset state parameters of the structural state of the target load-bearing structure, obtaining multiple parameter values, fusing the multiple parameter values to obtain a fused parameter value, and determining the structural state of the target load-bearing structure based on the fused parameter value, where the preset state parameters are used to characterize the structural state of the target load-bearing structure.

[0006] According to another aspect of the present invention, there is provided a state monitoring device for a bearing structure, including: an acquisition unit configured to acquire target vehicle load data of a target bearing structure within a target time period, and acquire a set of dynamic parameter data of preset dynamic parameters of the target bearing structure within the target time period, wherein the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure within the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target bearing structure changes; a partitioning unit configured to partition the set of dynamic parameter data into multiple sets of parameter data based on the target vehicle load data, wherein different sets of parameter data in the multiple sets of parameter data correspond to different load weight intervals; a first execution unit configured to respectively determine parameter values of preset state parameters of the structural state of the target bearing structure based on each set of parameter data in the multiple sets of parameter data, obtain multiple parameter values, fuse the multiple parameter values to obtain a fused parameter value, and determine the structural state of the target bearing structure based on the fused parameter value, wherein the preset state parameter is used to characterize the structural state of the target bearing structure.

[0007] According to still another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the above-mentioned state monitoring method for a bearing structure when running.

[0008] According to still another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the above-mentioned processor executes the above-mentioned state monitoring method for a bearing structure through the computer program.

[0009] Applying the technical solution of the present invention, by adopting a method of monitoring the state of a bearing structure based on dynamic parameters, target vehicle load data of a target bearing structure within a target time period is obtained, and a set of dynamic parameter data of preset dynamic parameters of the target bearing structure within the target time period is obtained, wherein the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure within the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target bearing structure changes; based on the target vehicle load data, the set of dynamic parameter data is divided into multiple groups of parameter data, wherein different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals; based on each group of parameter data in the multiple groups of parameter data, the parameter values of preset state parameters of the structural state of the target bearing structure are respectively determined, multiple parameter values are obtained, the multiple parameter values are fused to obtain a fused parameter value, and the structural state of the target bearing structure is determined based on the fused parameter value, wherein the preset state parameter is used to characterize the structural state of the target bearing structure. Since under different states, there are differences in the dynamic parameters under the same load, state monitoring based on dynamic parameters does not require manual on-site detection, which can shorten the time-consuming of state detection and reduce the consumption of human resources; based on load grouping, the state prediction can be more accurate by combining the correlation between the load and the dynamic parameters, thereby improving the accuracy of prediction, and further solving the problems of long time-consuming state detection and large consumption of human resources in the state monitoring method of the bearing structure in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0011] Figure 1 FIG. shows a schematic diagram of the hardware environment of an embodiment of an optional method for monitoring the state of a bearing structure according to the present invention;

[0012] Figure 2 FIG. shows a schematic flowchart of an embodiment of an optional method for monitoring the state of a bearing structure according to the present invention;

[0013] Figure 3 FIG. shows a schematic diagram of an embodiment of an optional method for monitoring the state of a bearing structure according to the present invention;

[0014] Figure 4 FIG. shows a schematic diagram of an embodiment of another optional method for monitoring the state of a bearing structure according to the present invention;

[0015] Figure 5 FIG. shows a schematic diagram of an embodiment of yet another optional method for monitoring the state of a bearing structure according to the present invention;

[0016] Figure 6 Shows a schematic flowchart of an embodiment of a method for monitoring the state of another alternative load-bearing structure according to the present invention;

[0017] Figure 7 Shows a block diagram of the structure of an alternative state monitoring device for a load-bearing structure according to the present invention;

[0018] Figure 8 Shows a block diagram of the structure of an alternative electronic device according to the present invention. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually illustrative only and in no way limits the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0020] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0021] Unless otherwise specifically stated, the relative arrangements of the components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention. At the same time, it should be understood that for the sake of convenience of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationships. Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and devices should be regarded as part of the specification of the present application. In all the examples shown and discussed herein, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0022] According to one aspect of the embodiments of the present invention, a method for monitoring the state of a bearing structure is provided. Optionally, in this embodiment, the method for monitoring the state of the bearing structure described above may be applied to, for example, Figure 1 the hardware environment shown in FIG. including a monitoring device 102 and a server 104. As shown in Figure 1 FIG., the server 104 is connected to the monitoring device 102 through a network. A database may be set up on the server or independently of the server to provide data storage services for the server 104. Here, the monitoring device 102 may include a device for detecting preset dynamic parameters and a device for detecting vehicle loads.

[0023] The above network may include, but is not limited to, at least one of the following: a wired network, a wireless network. The above wired network may include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, a local area network. The above wireless network may include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity), Bluetooth.

[0024] The method for monitoring the state of the bearing structure in the embodiments of the present invention may be executed by the server 104, or may be executed by the monitoring device 102, or may also be jointly executed by the server 104 and the monitoring device 102. Taking the execution of the method for monitoring the state of the bearing structure in this embodiment by the server 104 as an example, Figure 2 FIG. shows a schematic flowchart of an embodiment of an optional method for monitoring the state of a bearing structure according to the present invention. As shown in Figure 2 FIG., the process of the method may include the following steps.

[0025] Step S202, obtain the target vehicle load data of the target bearing structure within the target time period, and obtain the dynamic parameter data set of the preset dynamic parameters of the target bearing structure within the target time period, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure within the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target bearing structure changes.

[0026] The method for monitoring the state of the bearing structure in this embodiment may be applied to the scenario of monitoring the state of the bearing structure. Here, the main functions of bearing structures such as bridges and roads are to bear and transmit forces and moments from external forces such as traffic loads, self-weights, earthquakes, and wind loads. In order to ensure the safe operation of the bearing structure, it is necessary to monitor the state of the bearing structure.

[0027] For example, according to the JT / T 1037-2022 "Technical Specification for Highway Bridge Structure Safety Monitoring System" issued by the Ministry of Transport, suspension bridges with a main span greater than or equal to 500m, cable-stayed bridges with a main span of 300m, beam bridges with a main span of 160m, arch bridges with a main span of 200m, and in-service bridges with a technical condition rating of Class 3 or Class 4 that require follow-up observation need to conduct structural monitoring. The monitoring content should include vehicle load information (including video image information on the vehicle weight, axle weight, number of axles, vehicle speed, traffic flow, and vehicle spatial distribution on all lanes). During the operation of the bridge, it will be affected by factors such as traffic loads and natural environments, and thus structural damage and diseases will occur. If the health status of the bridge structure cannot be monitored in a timely manner, it will pose potential safety hazards to the safe operation of the bridge.

[0028] Currently, the state monitoring of the load-bearing structure is carried out by manually detecting the states at various positions. It can be seen that the state monitoring method of the load-bearing structure in the related technology has problems such as long time-consuming for state detection and large consumption of human resources.

[0029] In order to solve at least some of the above problems, in this embodiment, since the dynamic parameters under the same load in different states will be different, by obtaining the dynamic parameters within the target time period and conducting state monitoring based on the dynamic parameters, there is no need for manual on-site detection, which can shorten the time-consuming for state detection and reduce the consumption of human resources; based on the load grouping, the state monitoring can be carried out more accurately by combining the correlation between the load and the dynamic parameters, thereby improving the accuracy of the monitoring.

[0030] In this embodiment, when conducting the monitoring of the load-bearing structure, the server can obtain the target vehicle load data of the target load-bearing structure detected by the monitoring device, and obtain the dynamic parameter data set of the preset dynamic parameters of the target load-bearing structure.

[0031] Here, the target vehicle load data can be used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure. The spatio-temporal distribution of the vehicle load can refer to the load conditions of the vehicle at different times and in different spaces. The spatio-temporal distribution can describe the variation law of the vehicle load, that is, how the load quantity of the vehicle changes at different time and space positions. The target vehicle load data can include but are not limited to: vehicle type, vehicle weight (load weight), vehicle axle weight (the vertical load generated by the vehicle tires on the bearing structure when the vehicle passes through the bearing structure, and the axle weights of different axles of different vehicles may be different), vehicle axle number (the number of axles the vehicle has, and vehicles with different axle numbers have different effects on the load distribution of the bearing structure), vehicle axle distance (the horizontal distance between two adjacent axles at the front and rear of the vehicle, and vehicles with different axle distances have different effects on the load distribution of the bearing structure), vehicle speed (the driving speed of the vehicle when it passes through the bearing structure, and vehicles at different speeds have different effects on the load distribution of the bearing structure), vehicle load distribution (the load distribution of the vehicle on different components of the bearing structure when passing through the bearing structure).

[0032] The target preset dynamic parameter is a parameter that changes as the target bearing structure bears the vehicle load. The preset dynamic parameter can be a parameter related to the load borne, which can be related to the load weight borne or not related to the load weight borne, and can include but are not limited to at least one of the following: strain, vibration, deflection.

[0033] Optionally, the target vehicle load data and the dynamic parameter data set obtained each time can be within the target time period, that is, the above target vehicle load data and the dynamic parameter data set can be obtained by the server in time segments, or the monitoring device outputs them to the server at fixed time intervals.

[0034] By obtaining the target vehicle load data of the target bearing structure within the target time period, the vehicle model (outer contour size, axle number, and axle spacing), total weight, driving speed, and driving trajectory (real-time position) can be obtained, and the load distribution of the bearing structure can be obtained at fixed time intervals.

[0035] For example, taking the target bearing structure as a bridge and the preset dynamic parameters including strain, vibration, and deflection as examples, in this embodiment, bridge damage can be inferred from the changes in the three physical quantities of strain, vibration, and deflection. When a vehicle passes over the bridge, the bridge is subjected to the action of a load, and the load will cause the bridge to generate strain. Strain is the amount of deformation that a material undergoes when subjected to an external force. For a bridge, excessive strain may lead to the destruction of the bridge. At the same time, the load will also cause the bridge to vibrate. Vibration refers to the periodic motion of an object when subjected to an external force. For a bridge, the vibration of the vehicle will be transmitted to the bridge, causing the bridge to vibrate, and the vibration will affect the stability and safety of the bridge. In addition, the load of the vehicle will also cause the bridge to generate deflection. Deflection refers to the bending deformation that the bridge undergoes when subjected to an external force. Excessive deflection may affect the service life and safety of the bridge.

[0036] Therefore, by obtaining the dynamic parameter data set of the preset dynamic parameters of the target bearing structure within the target time period, the bridge state can be monitored based on the dynamic parameter data set.

[0037] Step S204, based on the target vehicle load data, divide the dynamic parameter data set into multiple groups of parameter data, where different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals.

[0038] Considering that different load weights have different effects on the dynamic parameter data, in order to improve the accuracy of the state monitoring of the bearing device, the dynamic parameter data set can be divided into multiple groups of parameter data based on the target vehicle load data, where different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals.

[0039] For example, as Figure 3 , Figure 4 shown, in this embodiment, classification is performed according to the total load within the measurement area (loads below 3T can be excluded from the statistics). Figure 3 For non-classification, Figure 4 For classification by total load, the dynamic parameter data set is divided into two groups of parameter data corresponding to loads > 40T and loads ≤. That is, the changing situation of the preset dynamic data over time when the bearing structure is under a load > 40T is obtained, and the changing situation of the preset dynamic data over time when the bearing structure is under a load ≤ is obtained. Here, the number of groups of parameter data is not limited, and the setting of the load mass interval can be determined based on historical data. The value of the load weight interval in this embodiment is not limited.

[0040] Step S206: Based on each set of parameter data among multiple sets of parameter data, respectively determine the parameter values of the preset state parameters of the structural state of the target load-bearing structure, obtain multiple parameter values, fuse the multiple parameter values to obtain a fused parameter value, and determine the structural state of the target load-bearing structure based on the fused parameter value, where the preset state parameters are used to characterize the structural state of the target load-bearing structure.

[0041] Since the state of the load-bearing structure can be inferred from the changes in the preset dynamic parameters, based on each set of parameter data among multiple sets of parameter data, the parameter values of the preset state parameters of the structural state of the target load-bearing structure can be respectively determined. Here, the preset state parameters can be used to characterize the structural state of the target load-bearing structure. For example, whether there is damage, the degree of damage, etc.

[0042] By fusing multiple parameter values corresponding to different load weight intervals, a fused parameter value corresponding to the structural state of the load-bearing structure during the target time period can be obtained, and the structural state of the target load-bearing structure can be determined based on the fused parameter value. Optionally, the fusion can be to assign weights to the multiple parameter values corresponding to different load weight intervals and add them together, where the weight values are proportional to the load weights, or it can be other fusion methods considering the load weights. This embodiment does not limit this.

[0043] Through the above steps S202 to S206, obtain the target vehicle load data of the target load-bearing structure during the target time period, and obtain the dynamic parameter data set of the preset dynamic parameters of the target load-bearing structure during the target time period, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target load-bearing structure during the target time period, and the preset dynamic parameters are the parameters of the target load-bearing structure that change with the vehicle load borne; based on the target vehicle load data, divide the dynamic parameter data set into multiple sets of parameter data, where different sets of parameter data among the multiple sets of parameter data correspond to different load weight intervals; based on each set of parameter data among the multiple sets of parameter data, respectively determine the parameter values of the preset state parameters of the structural state of the target load-bearing structure, obtain multiple parameter values, fuse the multiple parameter values to obtain a fused parameter value, and determine the structural state of the target load-bearing structure based on the fused parameter value, where the preset state parameters are used to characterize the structural state of the target load-bearing structure, solving the problems in the state monitoring method of the load-bearing structure in the related art, such as long time-consuming for state detection and large human resource consumption, shortening the time-consuming for state detection and reducing human resource consumption.

[0044] In an exemplary embodiment, obtaining the target vehicle load data of the target load-bearing structure during the target time period includes:

[0045] S11. Obtain the load weight data of a set of vehicle loads detected by a weighing sensor. Here, the weighing sensor is used to detect the load weight of a vehicle load moving onto a target bearing structure, and a set of vehicle loads are the vehicle loads that are located on the target bearing structure for at least part of a target time period.

[0046] S12. Based on the set of acquisition images of an image acquisition component, perform target recognition and position tracking on each vehicle load in the set of vehicle loads to obtain the vehicle information of each vehicle load and the movement trajectory of each vehicle load. Here, the movement trajectory of each vehicle load is used to represent the change in the load position of each vehicle load on the target bearing structure over time.

[0047] S13. Based on the load weight data of each vehicle load, the vehicle information of each vehicle load, the movement trajectory of each vehicle load on the target bearing structure, and the shape information of the target bearing structure, determine the target vehicle load data of the target bearing structure in the target time period.

[0048] The weighing sensor is used to detect the load weight of a vehicle load moving onto a target bearing structure. The working principle of the weighing sensor is to determine the weight or mass of an object by measuring the strain or deformation generated by the object under force. Generally, inside the weighing sensor, there is an elastic element (such as a spring or a strain gauge). When an object is applied to the sensor, it causes the elastic element to deform or strain. The sensor infers the weight of the object by measuring the deformation or strain of the elastic element. In addition, the force-bearing situation of the vehicle load and the bearing structure is related. When a vehicle passes over the bearing structure, the load weight of the vehicle is transmitted to the bearing structure through the support structure of the bearing structure, thereby generating the force-bearing situation of the bearing structure.

[0049] The weighing sensor can be installed on the bearing structure to measure the vehicle load. The vehicle load measured by the weighing sensor can reflect the force-bearing situation of the bearing structure, such as information about the force distribution and the magnitude of the force on the bearing structure. Therefore, it can be understood that the load weight data of a set of vehicle loads detected by the weighing sensor is related to the shape information and the force distribution of the bearing structure.

[0050] A set of vehicle loads are the vehicle loads that are located on the target bearing structure for at least part of a target time period, and are the vehicle loads that have been borne by the target bearing structure during the target time period. That is, they are related to the load-bearing of the target bearing structure during the target time period. It can be determined by combining the vehicle loads detected by the load-bearing sensor and the results of position tracking. That is, it includes not only the vehicle loads detected by the weighing sensor during this time period, but also the vehicle loads detected previously and located on the target bearing structure during the target time period.

[0051] In order to obtain the spatio-temporal distribution of vehicle loads on the target bearing structure, after a set of load weight data of vehicle loads is obtained by the cloud server, target recognition and position tracking can be performed on each vehicle load in the set of vehicle loads based on the acquisition image set of the image acquisition component, so as to obtain the vehicle information of each vehicle load and the movement trajectory of each vehicle load, where the movement trajectory of each vehicle load is used to represent the change of the load position of each vehicle load on the target bearing structure over time.

[0052] Based on the load weight data of each vehicle load, the vehicle information of each vehicle load, the movement trajectory of each vehicle load on the target bearing structure, and the shape information of the target bearing structure, the target vehicle load data of the target bearing structure within the target time period is determined, that is, the spatio-temporal distribution of the vehicle loads borne by the target bearing structure within the target time period. Here, the vehicle information of each vehicle load may include, but is not limited to, the axle weight, the number of axles, the vehicle speed, the traffic flow, and the video image information of the vehicle spatial distribution, etc.

[0053] For example, in this embodiment, the dynamic weighing system and the video image monitoring system can be combined to detect the spatial distribution of bridge deck loads in real time based on the vehicle target tracking algorithm. The bridge deck dynamic weighing system weighs the vehicle loads in real time through the monitoring devices installed on different lanes, and based on the video image information and the bridge deck geometric information, uses the target position tracking algorithm to analyze the vehicle movement trajectory and calculate the position of the vehicle load on the bridge deck. Since the situations of vehicle overtaking and lane changing on the bridge deck are not frequent, the load positioning accuracy is relatively stable and can meet the subsequent application requirements. By using the bridge deck dynamic weighing system and the target position tracking algorithm together to realize the monitoring and positioning of vehicle loads, the stress conditions in each finite element area of the bridge can be monitored in real time, and the load gravity of each area of the bridge can be accurately quantified.

[0054] Through this embodiment, by combining the dynamic weighing system and the video image monitoring system, and detecting the spatial distribution of bridge deck loads in real time based on the vehicle target tracking algorithm, the state monitoring of the bearing structure can be realized according to the reference of the vehicle load spatial distribution on the bridge deck under the condition of ensuring normal traffic operation.

[0055] In an exemplary embodiment, the weighing sensor is a piezoelectric sensor; after obtaining a set of load weight data of vehicle loads detected by the weighing sensor within the target time period, the above method further includes:

[0056] S21, determining a compensation coefficient corresponding to each vehicle load based on the distance between each vehicle load and the piezoelectric sensor, where the compensation coefficient corresponding to each vehicle load is positively correlated with the distance between each vehicle load and the piezoelectric sensor;

[0057] S22. Compensate the load weight data of each vehicle load using the compensation coefficient corresponding to each vehicle load to obtain the compensated load weight data of each vehicle load.

[0058] Here, a piezoelectric sensor is a sensor that measures pressure using the piezoelectric effect. When a piezoelectric sensor is installed on a lane, when a vehicle passes by, the load of the vehicle is applied to the sensor, causing the sensor to generate pressure. The piezoelectric material inside the sensor will deform due to the applied pressure, and thus generate electric charges. The magnitude of this electric charge is proportional to the pressure applied to the sensor. By measuring the generated electric charges, the load information of the vehicle can be obtained. That is, the piezoelectric sensor measures the pressure applied to the sensor and uses the piezoelectric effect to convert the pressure into an electric charge signal, thereby measuring the vehicle load. The piezoelectric sensor has the characteristics of high sensitivity and fast response speed.

[0059] Considering that the distance between the sensor and the vehicle will affect the measurement accuracy and sensitivity of the sensor. When the distance between the vehicle and the sensor changes, the distribution of the force received by the sensor will also change, resulting in deviations in the measurement results. The sensitivity of the sensor refers to the degree of response of the sensor to external forces, and the change in distance will cause the sensitivity of the sensor to change. To solve the above technical problems, compensation can be performed based on the distance between the sensor and the vehicle, thereby improving the accuracy and reliability of the measurement.

[0060] Here, the compensation coefficient corresponding to each vehicle load and the distance between each vehicle load and the piezoelectric sensor can be positively correlated, that is, the farther the distance, the larger the compensation coefficient. Compensating the load weight data of each vehicle load using the compensation coefficient corresponding to each vehicle load can obtain the compensated load weight data of each vehicle load.

[0061] For example, in this embodiment, coefficient compensation is performed on the load that is far from the sensor. The compensation method is formula (1):

[0062]

[0063] Where M is the statistical load, is the measured load, k is the compensation coefficient, which is proportional to the distance between the sensor and the load, and the value range is 0 < k < 0.2.

[0064] Through this embodiment, compensating the vehicle load measured by the piezoelectric sensor based on the distance between the vehicle load and the piezoelectric sensor can improve the measurement accuracy of the piezoelectric sensor.

[0065] In an exemplary embodiment, the preset dynamic parameters include strain, vibration, and deflection; obtaining a set of dynamic parameter data of the preset dynamic parameters of the target load-bearing structure within the target time period, including:

[0066] S31. Obtain the strain data of the target bearing structure within the target time period to obtain a strain data set, obtain the vibration data of the target bearing structure within the target time period to obtain a vibration data set, and obtain the deflection data of the target bearing structure within the target time period to obtain a deflection data set;

[0067] S32. Perform normalization processing on the strain data set, vibration data set, and deflection data set respectively to obtain a normalized strain data set, a normalized vibration data set, and a normalized deflection data set;

[0068] S33. Perform data fusion on the normalized strain data set, normalized vibration data set, and normalized deflection data set according to a preset weight coefficient matrix to obtain a multi-source fusion data set, where the dynamic parameter data set is the multi-source fusion data set.

[0069] Obtain the strain data, vibration data, and deflection data of the target bearing structure within the target time period to obtain a strain data set, a vibration data set, and a deflection data set. Among them, the deflection data is obtained by measuring with a wire displacement gauge, the vibration data is obtained by measuring with an accelerometer, and the strain data is obtained by measuring with a strain gauge.

[0070] Perform dimensionless processing according to the row vector in the time direction. The calculation formula is as formula (2):

[0071]

[0072] where, x t represents the original data row vector that changes with time. For example, the strain data set, vibration data set, and deflection data set, x max represents the maximum value in x t and x min represents the minimum value in x t .

[0073] Here, the dimensionless processing can refer to a processing that converts data so that it is not affected by units, and can eliminate the dimensional differences between different variables. Through dimensionless processing, different indicators or variables can be made comparable, which is convenient for data comparison and analysis. Common dimensionless methods include standardization, min-max normalization, mean-variance normalization, etc. In this embodiment, normalization is taken as an example for illustration. Normalization processing is to convert data of different scales and magnitudes into a unified standard range to eliminate the dimensional influence between different features, so that the data can be better compared and analyzed. Common normalization methods include linear normalization, Z-Score normalization, maximum-minimum normalization, etc.

[0074] Data fusion is to perform weighted integration on the processed data, and through a preset weight coefficient matrix (for example, a set of weight coefficient matrices fitted from historical data), the strain, vibration, and deflection data are weighted and integrated into new fusion information s t , which is used for subsequent bridge damage judgment. The fitting method is shown in formula (3):

[0075] s t = a·de t + b·st t + c·vi t (3)

[0076] Where a, b, and c represent weights, and de t , st t , vi t represent the row vectors of deflection data, strain data, and vibration data respectively.

[0077] Through this embodiment, by performing data cleaning and normalization processing on the response signals of multiple sensors (such as strain, vibration, temperature, and deflection sensors), and then performing information fusion in combination with the weight coefficient matrix, the availability of the data can be improved.

[0078] In an exemplary embodiment, before performing normalization processing on the strain data set, vibration data set, and deflection data set respectively, the above method further includes:

[0079] S41, perform a first fitting operation on the strain data set and the temperature data within the target time period to obtain the fitted strain data set, where the first fitting operation is used to eliminate the change in strain data caused by temperature;

[0080] S42, perform a second fitting operation on the vibration data set and the temperature data within the target time period to obtain the fitted vibration data set, where the second fitting operation is used to eliminate the change in vibration data caused by temperature;

[0081] S43, perform a third fitting operation on the deflection data set and the temperature data within the target time period to obtain the fitted deflection data set, where the third fitting operation is used to eliminate the change in deflection data caused by temperature;

[0082] S44, perform filtering processing on the fitted strain data set, fitted vibration data set, and fitted deflection data set respectively to obtain the filtered strain data set, filtered vibration data set, and filtered deflection data set, where the filtering processing is used to filter out data outside the specified frequency band.

[0083] Considering that strain, vibration, deflection and temperature have a strong linear correlation, in this embodiment, the recursive least squares method can be used to fit the temperature, strain, vibration acceleration amplitude and deflection over a relatively long period of time respectively, so as to eliminate the data changes caused by temperature.

[0084] Using the recursive least squares method to fit the data means finding an optimal mathematical model through the recursive least squares algorithm, so that the model is closest to the given data points. The recursive least squares method is an iterative algorithm that continuously adjusts the model parameters to minimize the difference between the model prediction value and the actual observed value. Specifically, the method first selects an initial model and then calculates the predicted values of the model for the data points. Next, the difference between the actual observed value and the predicted value is calculated and squared to obtain a sum of squared errors. Then, the model parameters are adjusted to minimize the sum of squared errors. This process is iterated until an optimal model is found that minimizes the sum of squared errors.

[0085] Filter the processed deflection, vibration and strain data (filter out obvious outliers, and then use the spectral analysis method to remove the data in the higher frequency part, only retaining the data in the specified frequency band). The spectral analysis method can include but is not limited to Fourier transform, and the high-frequency part of the data can be removed by removing the high-order data.

[0086] Through this embodiment, by fitting the strain data set, vibration data set and deflection data set to eliminate the data changes caused by temperature, and filtering the fitted data, the quality and usability of the data can be improved.

[0087] In an exemplary embodiment, the target load-bearing structure is divided into multiple load-bearing areas, and each group of parameter data corresponds to different groups of acquisition times in the acquisition time set of the dynamic parameter data set; based on each group of parameter data in the multiple groups of parameter data, determine the parameter values of the preset state parameters of the structural state of the target load-bearing structure respectively, and obtain multiple parameter values, including:

[0088] S51, take each group of parameter data as the current group of parameter data respectively, and perform the following parameter value determination operations to obtain the parameter values corresponding to each group of parameter data, where a group of acquisition times corresponding to the current group of parameter data is a group of current acquisition times:

[0089] Take each load-bearing area in the multiple load-bearing areas as the current load-bearing area respectively, and perform the following curvature determination operations to obtain the curvature corresponding to each current acquisition time in each group of current acquisition times of each load-bearing area, where the regional boundaries of the current load-bearing area in the driving direction of the target load-bearing structure are the first regional boundary and the second regional boundary respectively:

[0090] Integrate the parameter data from the first region boundary to the second region boundary in the current set of parameter data to obtain the current integral curve corresponding to the current load-bearing region;

[0091] According to the current integral curve, determine the curvature corresponding to the current load-bearing region and each current acquisition time, where the curvature corresponding to the current load-bearing region and each current acquisition time is the value of the current integral curve at each current acquisition time divided by the sum of the values of the current integral curve at a set of current acquisition times;

[0092] Among them, the parameter values corresponding to each set of parameter data include the curvature corresponding to each load-bearing region and each current acquisition time.

[0093] After dividing the dynamic parameter data set of the target load-bearing structure within the target time period into multiple sets of parameter data based on the load weight interval, at least one set of parameter data obtained can correspond to at least some moments within the target time period, and each set of parameter data corresponds to different sets of acquisition times in the acquisition time set of the dynamic parameter data set. By performing the following parameter value determination operations on each set of parameter data as the current set of parameter data respectively, the parameter values corresponding to each set of parameter data can be obtained, and the parameter values corresponding to each set of parameter data include the curvature corresponding to each load-bearing region and each current acquisition time.

[0094] For example, in this embodiment, the bridge deck can be divided into N regions. Taking the current load-bearing region as the nth region as an example, the integral curve D of the nth region of the bridge can be calculated n .

[0095] For the classified multi-source fusion data s t Draw a curve changing with time. At this time, the current integral curve D of the nth region n As shown in formula (4):

[0096]

[0097] Among them, and represent the left and right boundaries of the nth region respectively, that is, the first region boundary and the second region boundary.

[0098] Furthermore, according to the current integral curve, determine the curvature corresponding to the current load-bearing region and each current acquisition time, and calculate the curve change curvature of the integral curve of the nth region at time t As shown in formula (5):

[0099]

[0100] The larger the mutation value of the curvature, the greater the probability of damage at that position.

[0101] Through this embodiment, it is possible to determine whether there is damage to the bearing structure.

[0102] In an exemplary embodiment, after determining the curvature corresponding to each current acquisition time for the current bearing area according to the current integral curve, the above method further includes:

[0103] S61. Take each current acquisition time as the current acquisition moment and perform the following curvature update operation to obtain the curvature corresponding to the updated current bearing area and each current acquisition time:

[0104] Use the distance weight coefficient matrix to integrate the curvature corresponding to the current bearing area and the current acquisition moment and the curvatures corresponding to a set of adjacent bearing areas and the current acquisition moment, to obtain the curvature corresponding to the updated current bearing area and the current acquisition moment;

[0105] Among them, a set of adjacent bearing areas includes the bearing areas that satisfy the proximity condition with the current bearing area among multiple bearing areas. The weight coefficient corresponding to the current bearing area in the distance weight coefficient matrix is a specified value, and the weight coefficient corresponding to each adjacent bearing area in the set of adjacent bearing areas is the value obtained by dividing the square of the reciprocal of the distance between each adjacent bearing area and the current bearing area by the sum of the squares of the reciprocals of the distances between each adjacent bearing area and the current bearing area.

[0106] Combining the multi-source sensor response information of adjacent multiple measurement points, for the curvature of the curve change of the nth area of the current bearing area at the current acquisition moment t and the curvatures of the curve changes of adjacent multiple areas at the moment t are integrated as the updated curvature of the curve change of the nth area at the moment t

[0107] Introduce the distance weight coefficient matrix to integrate the curvature changes of the damage curves of adjacent multiple areas. The spatial change curvature is as shown in formula (6):

[0108]

[0109] Among them, in the numerator of formula (6), is the curvature corresponding to the current bearing area and the current acquisition moment. At this time, i takes the fixed value corresponding to the current area. In the denominator, respectively corresponding to the curvature of each load-bearing area in all load-bearing areas of the load-bearing structure at the current acquisition moment. dw is as shown in formula (7) and represents the distance weight coefficient matrix. Here, the weight coefficient corresponding to the current load-bearing area in the distance weight coefficient matrix is a specified value. For example, when i = j, dw takes 1, and the weight coefficient corresponding to each adjacent load-bearing area in a group of adjacent load-bearing areas is the value obtained by dividing the square of the reciprocal of the distance between each adjacent load-bearing area and the current load-bearing area by the sum of the squares of the reciprocals of the distances between each adjacent load-bearing area and the current load-bearing area. That is, in formula (7), i takes the fixed value corresponding to the current area, and in the numerator, j takes the value corresponding to one of the adjacent load-bearing areas corresponding to the weight coefficient to be obtained in a group of adjacent load-bearing areas. d ij As shown in formula (8), it represents the distance between the monitoring point i and the remaining monitoring points j, and x and y represent the positions in the horizontal and vertical directions. p represents the total value of the area, that is, the number of load-bearing areas into which the target load-bearing structure is divided.

[0110]

[0111]

[0112] Optionally, in this embodiment, the curvature of the curve change of the nth area at each moment is averaged to obtain the curvature of the curve change of the nth area Then, it is integrated with the curvatures of the curve changes of multiple adjacent areas as the updated curvature of the curve change of the nth area

[0113] Combining the inference results in the horizontal (time dimension) and vertical (space dimension) directions, finally select as the damage evaluation index. The larger the change amplitude, the more it can reflect the existence of damage here.

[0114] Finally, sum up the damage indexes in different load weight intervals to obtain the total Then judge the damage according to the curvature change.

[0115] Optionally, based on the above evaluation index, combine the bridge design value and the relevant specifications in the "Technical Specification for Highway Bridge Structure Safety Monitoring System" to set the secondary threshold, and make small adjustments in combination with the actual engineering situation (bridge service life, vehicle type distribution, etc.).

[0116] Through this embodiment, through comparative analysis in the spatial dimension (lateral reasoning), a distance weight coefficient matrix is introduced to integrate the change curvatures of the integral curves of multiple adjacent regions. Based on the change amplitude of the integrated data, it is determined whether there is damage in the corresponding region, which can reduce the time consumption of the bearing structure state monitoring and reduce the labor cost.

[0117] In an exemplary embodiment, multiple parameter values are fused to obtain a fused parameter value, including:

[0118] S71, integrating the parameter values corresponding to the same bearing region among the parameter values corresponding to each group of parameter data to obtain the curvature corresponding to each bearing region and each acquisition time in the acquisition time set. Among them, the fused parameter value is the curvature corresponding to each bearing region and each acquisition time.

[0119] After classifying the preset dynamic parameters of the bearing regions of the bearing structure over time based on the load weight interval, by integrating the parameter values corresponding to the same bearing region among the parameter values corresponding to each group of parameter data, the curvature corresponding to each bearing region and each acquisition time in the acquisition time set is obtained. Among them, the fused parameter value is the curvature corresponding to each bearing region and each acquisition time.

[0120] Optionally, the integration method can be to assign weights to the change curvatures of different clustering results and add them together, and the weight value is proportional to the load weight.

[0121] Through this embodiment, based on the load grouping, the change curvatures of different clustering results are integrated to obtain the curvature corresponding to each bearing region and each acquisition time in the acquisition time set, and the state prediction can be performed more accurately by combining the correlation between the load and the curvature, thereby improving the accuracy of the prediction.

[0122] In an exemplary embodiment, after determining the structural state of the target bearing structure based on the fused parameter value, the above method further includes:

[0123] S81, when it is determined that the target bearing region among the multiple bearing regions is in an abnormal structural state at the target acquisition time in the acquisition time set, the position obtained by multiplying the position difference between the two region boundaries of the target bearing region by the target coefficient is determined as the position matching the abnormal structural state;

[0124] Among them, among multiple load-bearing areas, the load-bearing area before the target load-bearing area in the driving direction is the first load-bearing area, and the load-bearing area after the target load-bearing area is the second load-bearing area. The integral curve corresponding to the first load-bearing area and the target acquisition time is D1, the integral curve corresponding to the second load-bearing area and the target acquisition time is D2, and the target coefficient is (D1 - K*(D1 + D2)) / ((1 - 2K)*(D1 + D2)), where 0 < K < 1.

[0125] Considering that each target load-bearing area of the load-bearing structure may be relatively far apart, that is, the sensors at the two regional boundaries of the target load-bearing area (for example, sensors for monitoring strain, vibration, and deflection) are relatively sparse. In the case of determining that the target load-bearing structure is damaged, in order to achieve more accurate positioning, when it is determined that the target acquisition time of the target load-bearing area in the multiple load-bearing areas in the acquisition time set is in an abnormal structure state, the position obtained by multiplying the position difference between the two regional boundaries of the target load-bearing area by the target coefficient is determined as the position matching the abnormal structure state.

[0126] For example, for long-span bridges, due to the relatively sparse distribution of sensors, in order to achieve more accurate positioning, further damage location calculation needs to be carried out within the target load-bearing area.

[0127] Combined with Figure 5 , taking the x direction of the horizontal coordinate as an example (similarly for the vertical direction y), and respectively represent the left and right boundaries of the nth area (target load-bearing area), D n+1 = D1 represents the integral curve of the right adjacent area (the load-bearing area before the target load-bearing area in the driving direction is the first load-bearing area), D n-1 = D2 represents the integral curve of the left adjacent area (the load-bearing area after the target load-bearing area is the second load-bearing area), D n represents the integral curve of the current area (target load-bearing area), K is the proportional mean coefficient (usually taken as <0.2), then the damage position x value at this time is the formula (9):

[0128]

[0129] Since when D n > 0, D n-1 and D n+1 are usually also greater than 0, introducing K plays a filtering role to reduce the damage influence of farther points, and can make the obtained x value closer to the true value.

[0130] Through this embodiment, by combining the integral curves of adjacent areas to determine the specific damage position, the accuracy of damage positioning can be improved, thereby improving the damage handling efficiency and ensuring the safe operation of the load-bearing structure.

[0131] Optionally, in at least some embodiments of the present application, the load-bearing structure may be a bridge, and the structural state of the target load-bearing structure may be the damage state of the bridge, that is, a damaged state, an undamaged state, a slightly damaged state, a severely damaged state, and so on.

[0132] The following explains the state monitoring method of the load-bearing structure in the embodiments of the present invention with reference to optional examples. Taking the target load-bearing structure as a bridge and the preset dynamic parameters as strain, vibration, and deflection data as examples.

[0133] Different from the static detection scheme that requires blocking traffic operation, this method can perform damage monitoring under normal traffic conditions, which can improve transportation efficiency. At the same time, round-the-clock real-time monitoring can also detect damage more timely. Different from the scheme that uses a vehicle of a specified model and weight to pass through the bridge at a fixed low speed and then uses the sensor signal response as a damage index, this method has no requirements for vehicle type, speed, and weight, and can realize the monitoring function under random traffic flow conditions. Different from the method of directly using multi-source information fusion for bridge damage identification, this method combines a dynamic weighing system and a video image monitoring system, and based on the vehicle target tracking algorithm, it can detect the spatial distribution of the bridge deck load in real time, that is, analyze the sensor signal response under the condition of known vehicle load distribution within the sensor sensing area, and then identify the bridge damage condition.

[0134] The present invention provides a method for bridge damage monitoring and identification. Among them, monitoring refers to the acquisition and preprocessing of data from various sensor responses by combining data processing algorithms under normal traffic operation and known spatio-temporal distribution of vehicle loads on the bridge deck, and online recording of suspected abnormal data. And bridge damage identification includes two parts: damage judgment and damage location.

[0135] The main processing flow is as Figure 6As shown in the figure, vehicle load and position tracking refers to the use of conventional algorithms to calculate the spatial load distribution of each lane on the bridge deck in real time, facilitating the calculation of unit loads during subsequent finite element analysis. Multi-source information fusion refers to when a vehicle enters a certain finite element area, data cleaning and normalization processing are performed on the response signals of multiple sensors (such as strain, vibration, temperature, and deflection sensors), and then information fusion is carried out in combination with the weight coefficient matrix. Data clustering refers to multi-dimensional clustering of a large amount of vehicle data passing through the bridge deck according to different vehicle types, loads, speeds, and positions, and analyzing and reasoning the data of a single category after clustering. Damage judgment and location refer to multi-dimensional comparison of the data after the above analysis and drawing the time history envelope curve of the fusion information. According to the change of the integral curvature, it is judged whether there is damage to the bridge at this position and the degree of damage is calculated, and then the damage position is located according to the proportion calculation method of the damage degree of multiple measuring points. Here, the time history envelope curve refers to the curve of a certain variable changing with time within a certain time range, which can describe the change trend and characteristics of a certain variable in a system or process.

[0136] Through the present application, in the normal traffic scenario, by using the known bridge deck load distribution and the response of bridge deck sensor data, bridge damage is identified by analyzing abnormal data changes. Cluster the data generated by the vehicle type and vehicle weight of a single monitoring point, and then conduct horizontal and vertical comparative analysis on the time history envelope curve of the fusion information of the clustered data to judge whether there is damage to the bridge. After confirming the damage, further accurately locate the damage position according to the degree of damage.

[0137] According to another aspect of the embodiments of the present invention, there is also provided a state monitoring device for a load-bearing structure for implementing the above-mentioned state monitoring method of the load-bearing structure. As Figure 7 shown, the device may include:

[0138] An acquisition unit 702, configured to acquire target vehicle load data of a target load-bearing structure within a target time period, and acquire a set of dynamic parameter data of preset dynamic parameters of the target load-bearing structure within the target time period, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target load-bearing structure within the target time period, and the preset dynamic parameter is a parameter that the target load-bearing structure changes with the vehicle load borne;

[0139] A partitioning unit 704, connected to the acquisition unit 702, configured to partition the set of dynamic parameter data into multiple groups of parameter data based on the target vehicle load data, where different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals;

[0140] The first execution unit 706, connected to the division unit 704, is configured to respectively determine the parameter values of the preset state parameters of the structural state of the target bearing structure based on each set of parameter data in the multiple sets of parameter data, obtain multiple parameter values, fuse the multiple parameter values to obtain a fused parameter value, and determine the structural state of the target bearing structure based on the fused parameter value, where the preset state parameter is used to characterize the structural state of the target bearing structure.

[0141] It should be noted that the acquisition unit 702 in this embodiment can be used to execute the above step S202, the division unit 704 in this embodiment can be used to execute the above step S204, and the first execution unit 706 in this embodiment can be used to execute the above step S206.

[0142] Through the above modules, the target vehicle load data of the target bearing structure in the target time period is acquired, and the dynamic parameter data set of the preset dynamic parameters of the target bearing structure in the target time period is acquired, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure in the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target bearing structure changes; based on the target vehicle load data, the dynamic parameter data set is divided into multiple sets of parameter data, where different sets of parameter data in the multiple sets of parameter data correspond to different load weight intervals; the parameter values of the preset state parameters of the structural state of the target bearing structure are respectively determined based on each set of parameter data in the multiple sets of parameter data, multiple parameter values are obtained, the multiple parameter values are fused to obtain a fused parameter value, and the structural state of the target bearing structure is determined based on the fused parameter value, where the preset state parameter is used to characterize the structural state of the target bearing structure, which solves the problems of long time consumption and large human resource consumption in the state detection of the bearing structure in the related art, shortens the time consumption of the state detection, and reduces the human resource consumption.

[0143] In an exemplary embodiment, the acquisition unit includes:

[0144] The first acquisition module is configured to acquire the load weight data of a set of vehicle loads detected by a weighing sensor, where the weighing sensor is used to detect the load weight of the vehicle load moving onto the target bearing structure, and a set of vehicle loads is the vehicle load located on the target bearing structure at least part of the time in the target time period;

[0145] The first execution module is configured to perform target recognition and position tracking on each vehicle load in a set of vehicle loads based on the acquisition image set of the image acquisition component, to obtain the vehicle information of each vehicle load and the movement trajectory of each vehicle load, where the movement trajectory of each vehicle load is used to represent the change in the load position of each vehicle load on the target bearing structure over time;

[0146] A determination module, configured to determine target vehicle load data of a target load-bearing structure within a target time period based on load weight data of each vehicle load, vehicle information of each vehicle load, a movement trajectory of each vehicle load on the target load-bearing structure, and shape information of the target load-bearing structure.

[0147] In an exemplary embodiment, the weighing sensor is a piezoelectric sensor; the above device further includes:

[0148] A first determination unit, configured to, after obtaining load weight data of a set of vehicle loads detected by the weighing sensor within the target time period, determine a compensation coefficient corresponding to each vehicle load based on the distance between each vehicle load and the piezoelectric sensor, where the compensation coefficient corresponding to each vehicle load is positively correlated with the distance between each vehicle load and the piezoelectric sensor;

[0149] A compensation unit, configured to compensate the load weight data of each vehicle load by using the compensation coefficient corresponding to each vehicle load to obtain the compensated load weight data of each vehicle load.

[0150] In an exemplary embodiment, the preset dynamic parameters include strain, vibration, and deflection; the acquisition unit includes:

[0151] A second acquisition module, configured to acquire strain data of the target load-bearing structure within the target time period to obtain a strain data set, acquire vibration data of the target load-bearing structure within the target time period to obtain a vibration data set, and acquire deflection data of the target load-bearing structure within the target time period to obtain a deflection data set;

[0152] A processing unit, configured to perform normalization processing on the strain data set, the vibration data set, and the deflection data set respectively to obtain a normalized strain data set, a normalized vibration data set, and a normalized deflection data set;

[0153] A fusion unit, configured to perform data fusion on the normalized strain data set, the normalized vibration data set, and the normalized deflection data set according to a preset weight coefficient matrix to obtain a multi-source fusion data set, where the dynamic parameter data set is the multi-source fusion data set.

[0154] In an exemplary embodiment, the above device further includes:

[0155] A first fitting unit, configured to perform a first fitting operation on the strain data set and temperature data within the target time period before performing normalization processing on the strain data set, the vibration data set, and the deflection data set respectively to obtain a fitted strain data set, where the first fitting operation is used to eliminate the change in strain data caused by temperature;

[0156] A second fitting unit, configured to perform a second fitting operation on the vibration data set and the temperature data within the target time period to obtain a fitted vibration data set, where the second fitting operation is used to eliminate the change in vibration data caused by temperature;

[0157] A third fitting unit, configured to perform a third fitting operation on the deflection data set and the temperature data within the target time period to obtain a fitted deflection data set, where the third fitting operation is used to eliminate the change in deflection data caused by temperature;

[0158] A filtering unit, configured to perform filtering processing on the fitted strain data set, the fitted vibration data set, and the fitted deflection data set respectively to obtain a filtered strain data set, a filtered vibration data set, and a filtered deflection data set, where the filtering processing is used to filter out data outside a specified frequency band.

[0159] In an exemplary embodiment, the target bearing structure is divided into multiple bearing areas, and each set of parameter data corresponds to different sets of acquisition times in the acquisition time set of the dynamic parameter data set; the first execution unit includes:

[0160] A second execution module, configured to use each set of parameter data as the current set of parameter data to perform the following parameter value determination operation to obtain a parameter value corresponding to each set of parameter data, where a set of acquisition times corresponding to the current set of parameter data is a set of current acquisition times:

[0161] Taking each bearing area in the multiple bearing areas as the current bearing area respectively to perform the following curvature determination operation to obtain the curvature corresponding to each current acquisition time in a set of current acquisition times of each bearing area, where the area boundaries of the current bearing area in the driving direction of the target bearing structure are the first area boundary and the second area boundary respectively: performing integral processing on the parameter data from the first area boundary to the second area boundary in the current set of parameter data to obtain a current integral curve corresponding to the current bearing area; determining the curvature corresponding to the current bearing area and each current acquisition time according to the current integral curve, where the curvature corresponding to the current bearing area and each current acquisition time is the value of the current integral curve at each current acquisition time divided by the sum of the values of the current integral curve at a set of current acquisition times;

[0162] Wherein, the parameter value corresponding to each set of parameter data includes the curvature corresponding to each bearing area and each current acquisition time.

[0163] In an exemplary embodiment, the above device further includes:

[0164] A second execution unit, configured to, after determining the curvature corresponding to each current acquisition time of the current load-bearing area according to the current integral curve, use each current acquisition time as the current acquisition moment to perform the following curvature update operation to obtain the updated curvature corresponding to each current acquisition time of the current load-bearing area:

[0165] Integrate the curvature corresponding to the current load-bearing area and the current acquisition moment and the curvatures corresponding to a group of adjacent load-bearing areas and the current acquisition moment by using a distance weight coefficient matrix to obtain the updated curvature corresponding to the current load-bearing area and the current acquisition moment;

[0166] Wherein, a group of adjacent load-bearing areas includes the load-bearing areas that satisfy the proximity condition with the current load-bearing area among multiple load-bearing areas, the weight coefficient corresponding to the current load-bearing area in the distance weight coefficient matrix is a specified value, and the weight coefficient corresponding to each adjacent load-bearing area in a group of adjacent load-bearing areas is the value obtained by dividing the square of the reciprocal of the distance between each adjacent load-bearing area and the current load-bearing area by the sum of the squares of the reciprocals of the distances between each adjacent load-bearing area and the current load-bearing area.

[0167] In an exemplary embodiment, the first execution unit includes:

[0168] An integration module, configured to integrate the parameter values corresponding to the same load-bearing area among the parameter values corresponding to each group of parameter data to obtain the curvature corresponding to each load-bearing area and each acquisition time in the acquisition time set, wherein the fused parameter value is the curvature corresponding to each load-bearing area and each acquisition time.

[0169] In an exemplary embodiment, the above device further includes:

[0170] A second determination unit, configured to, after determining the structural state of the target load-bearing structure based on the fused parameter value, when it is determined that the target acquisition time of the target load-bearing area among multiple load-bearing areas in the acquisition time set is in an abnormal structural state, determine the position obtained by multiplying the position difference between the two regional boundaries of the target load-bearing area by the target coefficient as the position matching the abnormal structural state;

[0171] Wherein, among multiple load-bearing areas, the load-bearing area located before the target load-bearing area in the driving direction is the first load-bearing area, and the load-bearing area located after the target load-bearing area is the second load-bearing area. The integral curve corresponding to the first load-bearing area and the target acquisition time is D1, the integral curve corresponding to the second load-bearing area and the target acquisition time is D2, and the target coefficient is (D1 - K*(D1 + D2)) / ((1 - 2K)*(D1 + D2)), where 0 < K < 1.

[0172] In an exemplary embodiment, the load-bearing structure is a bridge, and the structural state of the target load-bearing structure is the damage state of the bridge.

[0173] It should be noted here that the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in the hardware environment as shown in Figure 1 and can be implemented by software or by hardware. Among them, the hardware environment includes a network environment.

[0174] According to another aspect of the embodiments of the present invention, a storage medium is also provided. Optionally, in this embodiment, the above storage medium can be used to execute the program code of any one of the above load-bearing structure state monitoring methods in the embodiments of the present invention.

[0175] Optionally, in this embodiment, the above storage medium can be located on at least one of the multiple network devices in the network shown in the above embodiment.

[0176] Optionally, in this embodiment, the storage medium is set to store program code for executing the following steps:

[0177] S1. Obtain the target vehicle load data of the target load-bearing structure in the target time period, and obtain the dynamic parameter data set of the preset dynamic parameters of the target load-bearing structure in the target time period, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target load-bearing structure in the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target load-bearing structure changes;

[0178] S2. Based on the target vehicle load data, divide the dynamic parameter data set into multiple groups of parameter data, where different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals;

[0179] S3. Based on each group of parameter data in the multiple groups of parameter data, respectively determine the parameter values of the preset state parameters of the structural state of the target load-bearing structure, obtain multiple parameter values, fuse the multiple parameter values to obtain a fused parameter value, and determine the structural state of the target load-bearing structure based on the fused parameter value, where the preset state parameter is used to characterize the structural state of the target load-bearing structure.

[0180] Optionally, the specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be elaborated herein.

[0181] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media such as USB flash drives, ROMs, RAMs, mobile hard disks, magnetic disks, or optical discs that can store program code.

[0182] According to another aspect of the embodiments of the present invention, an electronic device for implementing the above-mentioned method for monitoring the state of a bearing structure is further provided. The electronic device may be a server, a terminal, or a combination thereof.

[0183] Figure 8 is a structural block diagram of an optional electronic device according to an embodiment of the present invention, as Figure 8 shown, including a processor 802, a communication interface 804, a memory 806, and a communication bus 808. Among them, the processor 802, the communication interface 804, and the memory 806 communicate with each other through the communication bus 808. Among them,

[0184] The memory 806 is used to store computer programs;

[0185] The processor 802, when executing the computer program stored on the memory 806, implements the following steps:

[0186] S1, obtaining target vehicle load data of a target bearing structure within a target time period, and obtaining a set of dynamic parameter data of preset dynamic parameters of the target bearing structure within the target time period, where the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure within the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target bearing structure changes;

[0187] S2, based on the target vehicle load data, dividing the set of dynamic parameter data into multiple groups of parameter data, where different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals;

[0188] S3, respectively determining the parameter values of preset state parameters of the structural state of the target bearing structure based on each group of parameter data in the multiple groups of parameter data, obtaining multiple parameter values, fusing the multiple parameter values to obtain a fused parameter value, and determining the structural state of the target bearing structure based on the fused parameter value, where the preset state parameter is used to characterize the structural state of the target bearing structure.

[0189] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0190] The memory may include RAM, or may also include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0191] As an example, the above-mentioned memory 806 may but is not limited to include the acquisition unit 702, the division unit 704, and the first execution unit 706 in the state monitoring device of the above-mentioned bearing structure. In addition, it may also include but is not limited to other module units in the state monitoring device of the above-mentioned bearing structure, which will not be elaborated in this example.

[0192] The above-mentioned processor may be a general-purpose processor, which may include but is not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it may also be a DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0193] Optionally, specific examples in this embodiment may refer to the examples described in the above-mentioned embodiment, and will not be elaborated here.

[0194] Those of ordinary skill in the art can understand that Figure 8 The structure shown is only schematic. The device for implementing the state monitoring method of the above-mentioned bearing structure may be a terminal device, and the terminal device may be a terminal device such as a Mobile Internet Device (MID), PAD, etc. Figure 8 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may also include more or fewer components (such as a network interface, a display device, etc.) than those shown Figure 8 here, or have a different configuration from that shown Figure 8 here.

[0195] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, ROM, RAM, a magnetic disk, or an optical disc, etc.

[0196] The serial numbers of the embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments.

[0197] If the integrated units in the above embodiments are implemented in the form of software function units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0198] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by orientation words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom", etc. is usually based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description. Without contrary explanation, these orientation words do not indicate and imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the protection scope of the present invention; the orientation words "inside, outside" refer to the inside and outside relative to the contour of each component itself.

[0199] For the convenience of description, spatial relative terms such as "above...", "over...", "on the upper surface of...", "above" can be used here to describe the spatial positional relationship between a device or feature shown in the figure and other devices or features. It should be understood that the spatial relative terms are intended to include different orientations in use or operation in addition to the orientation described in the figure for the device. For example, if the device in the figure is inverted, the device described as "above other devices or structures" or "over other devices or structures" will be positioned as "below other devices or structures" or "under other devices or structures" afterwards. Thus, the exemplary term "above..." can include both the orientation of "above..." and "below...". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and corresponding explanations are made for the spatial relative descriptions used here.

[0200] In addition, it should be noted that the use of words such as "first", "second" to limit components is only for the convenience of distinguishing the corresponding components. Without otherwise stating, the above words have no special meaning. Therefore, it cannot be understood as a limitation on the protection scope of the present invention.

[0201] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for state monitoring of a load-bearing structure, characterized in that, it includes: Obtain the target vehicle load data of the target load-bearing structure within a target time period, and obtain a set of dynamic parameter data of the preset dynamic parameters of the target load-bearing structure within the target time period, wherein the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target load-bearing structure within the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target load-bearing structure changes; Based on the target vehicle load data, divide the set of dynamic parameter data into multiple groups of parameter data, wherein different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals; Based on each group of parameter data in the multiple groups of parameter data, respectively determine the parameter values of the preset state parameters of the structural state of the target load-bearing structure, obtain multiple parameter values, fuse the multiple parameter values to obtain a fused parameter value, and determine the structural state of the target load-bearing structure based on the fused parameter value, wherein the preset state parameter is used to characterize the structural state of the target load-bearing structure.

2. The method according to claim 1, characterized in that, the obtaining of the target vehicle load data of the target load-bearing structure within a target time period includes: Obtain the load weight data of a group of vehicle loads detected by a weighing sensor, wherein the weighing sensor is used to detect the load weight of the vehicle load moving onto the target load-bearing structure, and the group of vehicle loads is the vehicle load located on the target load-bearing structure for at least part of the time within the target time period; Based on the set of acquisition images of the image acquisition component, perform target recognition and position tracking on each vehicle load in the group of vehicle loads to obtain the vehicle information of each vehicle load and the movement trajectory of each vehicle load, wherein the movement trajectory of each vehicle load is used to represent the change in the load position of each vehicle load on the target load-bearing structure over time; Based on the load weight data of each vehicle load, the vehicle information of each vehicle load, the movement trajectory of each vehicle load on the target load-bearing structure, and the shape information of the target load-bearing structure, determine the target vehicle load data of the target load-bearing structure within the target time period.

3. The method according to claim 2, characterized in that, the weighing sensor is a piezoelectric sensor; after obtaining the load weight data of a group of vehicle loads detected by the weighing sensor within the target time period, the method further includes: Based on the distance between each vehicle load and the piezoelectric sensor, determine a compensation coefficient corresponding to each vehicle load, wherein the compensation coefficient corresponding to each vehicle load is positively correlated with the distance between each vehicle load and the piezoelectric sensor; Use the compensation coefficient corresponding to each vehicle load to compensate the load weight data of each vehicle load to obtain the compensated load weight data of each vehicle load.

4. The method according to claim 1, It is characterized in that the preset dynamic parameters include strain, vibration and deflection; the obtaining of the dynamic parameter data set of the preset dynamic parameters of the target bearing structure within the target time period includes: obtaining the strain data of the target bearing structure within the target time period to obtain a strain data set, obtaining the vibration data of the target bearing structure within the target time period to obtain a vibration data set, and obtaining the deflection data of the target bearing structure within the target time period to obtain a deflection data set; performing normalization processing on the strain data set, the vibration data set and the deflection data set respectively to obtain the normalized strain data set, the normalized vibration data set and the normalized deflection data set; performing data fusion on the normalized strain data set, the normalized vibration data set and the normalized deflection data set according to a preset weight coefficient matrix to obtain a multi-source fusion data set, wherein the dynamic parameter data set is the multi-source fusion data set.

5. The method according to claim 4, It is characterized in that before the step of performing normalization processing on the strain data set, the vibration data set and the deflection data set respectively, the method further includes: performing a first fitting operation on the strain data set and the temperature data within the target time period to obtain the fitted strain data set, wherein the first fitting operation is used to eliminate the change in strain data caused by temperature; performing a second fitting operation on the vibration data set and the temperature data within the target time period to obtain the fitted vibration data set, wherein the second fitting operation is used to eliminate the change in vibration data caused by temperature; performing a third fitting operation on the deflection data set and the temperature data within the target time period to obtain the fitted deflection data set, wherein the third fitting operation is used to eliminate the change in deflection data caused by temperature; performing filtering processing on the fitted strain data set, the fitted vibration data set and the fitted deflection data set respectively to obtain the filtered strain data set, the filtered vibration data set and the filtered deflection data set, wherein the filtering processing is used to filter out data outside a specified frequency band.

6. The method according to any one of claims 1 to 5, It is characterized in that the target bearing structure is divided into multiple bearing areas, and each group of parameter data corresponds to different groups of acquisition times in the acquisition time set of the dynamic parameter data set; the obtaining of the parameter values of the preset state parameters for determining the structural state of the target bearing structure based on each group of parameter data in the multiple groups of parameter data includes: taking each group of parameter data as the current group of parameter data respectively to perform the following parameter value determination operation to obtain the parameter value corresponding to each group of parameter data, wherein a group of acquisition times corresponding to the current group of parameter data is a group of current acquisition times: For each of the multiple load-bearing regions, perform the following curvature determination operations with each load-bearing region as the current load-bearing region, to obtain the curvature corresponding to each current acquisition time in the set of current acquisition times for each load-bearing region, where the regional boundaries of the current load-bearing region in the driving direction of the target load-bearing structure are the first regional boundary and the second regional boundary respectively: Integrate the parameter data from the first regional boundary to the second regional boundary in the current set of parameter data to obtain the current integral curve corresponding to the current load-bearing region; Determine the curvature corresponding to the current load-bearing region and each current acquisition time according to the current integral curve, where the curvature corresponding to the current load-bearing region and each current acquisition time is the value of the current integral curve at each current acquisition time divided by the sum of the values of the current integral curve at the set of current acquisition times; Wherein, the parameter values corresponding to each set of parameter data include the curvature corresponding to each load-bearing region and each current acquisition time.

7. The method according to claim 6, characterized in that after determining the curvature corresponding to the current load-bearing region and each current acquisition time according to the current integral curve, the method further includes: Taking each current acquisition time as the current acquisition moment and performing the following curvature update operations to obtain the updated curvature corresponding to the current load-bearing region and each current acquisition time: Using the distance weight coefficient matrix to integrate the curvature corresponding to the current load-bearing region and the current acquisition moment and the curvatures corresponding to a set of adjacent load-bearing regions and the current acquisition moment, to obtain the updated curvature corresponding to the current load-bearing region and the current acquisition moment; Wherein, the set of adjacent load-bearing regions includes the load-bearing regions that satisfy the proximity condition with the current load-bearing region among the multiple load-bearing regions, the weight coefficient corresponding to the current load-bearing region in the distance weight coefficient matrix is a specified value, and the weight coefficient corresponding to each adjacent load-bearing region in the set of adjacent load-bearing regions is the square of the reciprocal of the distance between each adjacent load-bearing region and the current load-bearing region, divided by the sum of the squares of the reciprocals of the distances between each adjacent load-bearing region and the current load-bearing region.

8. The method according to claim 6, characterized in that The fusing the multiple parameter values to obtain the fused parameter value includes: Integrating the parameter values corresponding to the same load-bearing region in the parameter values corresponding to each set of parameter data to obtain the curvature corresponding to each load-bearing region and each acquisition time in the acquisition time set, where the fused parameter value is the curvature corresponding to each load-bearing region and each acquisition time.

9. The method according to claim 8, characterized in that after determining the structural state of the target load-bearing structure based on the fused parameter value, the method further includes: When it is determined that the target acquisition time of the target bearing area in the plurality of bearing areas is in an abnormal structural state during the acquisition time set, the position obtained by multiplying the position difference between the two area boundaries of the target bearing area by the target coefficient is determined as the position matching the abnormal structural state; Among them, in the plurality of bearing areas, the bearing area located before the target bearing area in the driving direction is the first bearing area, and the bearing area located after the target bearing area is the second bearing area. The integral curve corresponding to the target acquisition time of the first bearing area is D1, and the integral curve corresponding to the target acquisition time of the second bearing area is D2. The target coefficient is (D1 - K*(D1 + D2)) / ((1 - 2K)*(D1 + D2)), where 0 < K < 1.

10. The method according to any one of claims 1 to 5 or claims 7 to 9, characterized in that, the bearing structure is a bridge, and the structural state of the target bearing structure is the damage state of the bridge.

11. A state monitoring device for a bearing structure, characterized in that, comprising: an acquisition unit, configured to acquire target vehicle load data of a target bearing structure during a target time period, and acquire a set of dynamic parameter data of preset dynamic parameters of the target bearing structure during the target time period, wherein the target vehicle load data is used to represent the spatio-temporal distribution of the vehicle load borne by the target bearing structure during the target time period, and the preset dynamic parameter is a parameter that changes as the vehicle load borne by the target bearing structure changes; a division unit, configured to divide the set of dynamic parameter data into multiple groups of parameter data based on the target vehicle load data, wherein different groups of parameter data in the multiple groups of parameter data correspond to different load weight intervals; a first execution unit, configured to respectively determine parameter values of preset state parameters of the structural state of the target bearing structure based on each group of parameter data in the multiple groups of parameter data, obtain a plurality of parameter values, fuse the plurality of parameter values to obtain a fused parameter value, and determine the structural state of the target bearing structure based on the fused parameter value, wherein the preset state parameter is used to characterize the structural state of the target bearing structure.

12. A computer-readable storage medium, characterized in that, the computer-readable storage medium includes a stored program, wherein the program, when running, executes the method according to any one of claims 1 to 10.

13. An electronic device, comprising a memory and a processor, characterized in that, a computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 10 through the computer program.

Images