Bridge state monitoring method, evaluation method and equipment based on cloud edge cooperation and multi-index fusion, and storage medium

Abstract

The invention provides a bridge state monitoring method, an evaluation method and equipment based on cloud edge cooperation and multi-index fusion, and a storage medium. The monitoring method comprises the following steps: acquiring a plurality of monitoring physical quantities corresponding to each monitoring point of a target bridge in a monitoring period according to the position of the monitoring point; performing Kalman filtering processing on a plurality of monitoring values of each monitoring physical quantity of each monitoring point; constructing an index matrix taking an average value of all the filtered monitoring values as an element; obtaining a health assessment score of each monitoring point based on the index matrix and the weight matrix; obtaining a Sharpley value of each monitoring physical quantity of the abnormal monitoring point; and obtaining the average change rate of the monitoring physical quantity corresponding to the maximum Sharpley value and the center distance between the abnormal monitoring point and the corresponding camera, and re-determining and adjusting the sampling frequency of the sensor of the abnormal monitoring point and the sampling visual angle of the camera. By adopting the monitoring method provided by the invention, more efficient and more accurate monitoring of the target bridge can be realized.

Description

Technical Field

[0001] The present invention relates to the field of bridge monitoring technology, and in particular to a bridge status monitoring method, evaluation method, device and storage medium based on cloud-edge collaboration and multi-indicator fusion. Background Art

[0002] With the rapid development of modern transportation infrastructure, bridges are key components of the transportation network, and their structural safety and stability are crucial to ensuring smooth traffic operation. However, bridge structures are easily damaged by long-term erosion by the natural environment and the impact of traffic loads, especially under extreme weather conditions (such as strong winds, heavy rains, earthquakes, etc.), and safety hazards are more prominent. Therefore, real-time monitoring of bridge status has become a daily task in bridge management and maintenance.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] Most existing bridge monitoring systems rely on a centralized architecture, and all data collected by the monitoring device needs to be transmitted to a central server through the network for processing and analysis. This model often faces problems such as insufficient transmission bandwidth resources, high data transmission delays, and excessive computing load when facing large-scale, multi-source data, making it difficult to achieve real-time monitoring of bridges. At the same time, once an abnormality occurs in a certain area of ​​the bridge, since the existing monitoring device always uses a fixed mode, the monitoring accuracy of the abnormal condition may not be sufficient, resulting in inadequate and untimely monitoring.

[0005] Therefore, a bridge condition monitoring method, evaluation method, equipment and storage medium based on cloud-edge collaboration and multi-indicator fusion are needed to at least partially solve the above technical problems. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a bridge status monitoring method, an evaluation method, a device and a storage medium based on cloud-edge collaboration and multi-indicator fusion to solve at least one of the problems in the prior art.

[0007] In a first aspect, an embodiment of the present invention provides a bridge status monitoring method based on cloud-edge collaboration and multi-index fusion, the monitoring method comprising:

[0008] Based on the monitoring device arrays set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge within the monitoring period are obtained; wherein the monitoring device array of each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal and at least one sensor;

[0009] Performing Kalman filtering on multiple monitoring values ​​corresponding to each monitoring physical quantity acquired by the at least one sensor at different acquisition timings within the monitoring period at each monitoring point through the edge computing terminal to obtain multiple filtered monitoring values ​​corresponding to each monitoring physical quantity, and further obtaining an average value of the filtered monitoring values ​​of each monitoring physical quantity at each monitoring point within the monitoring period;

[0010] The indicator matrix with the average value of all filtered monitoring values ​​as elements is constructed in the same order;

[0011] Obtain the health assessment score of each monitoring point within the monitoring period based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge, and compare the health assessment score of each monitoring point within the monitoring period with the upper and lower control thresholds determined based on the corresponding historical data;

[0012] If the health assessment score is within the upper and lower control thresholds, a first signal indicating that the bridge is normal is sent to the bridge control center through the edge computing terminal; if the health assessment score is not within the upper and lower control thresholds, the edge computing terminal compresses the filtered monitoring values ​​of multiple monitoring physical quantities at the abnormal monitoring point, and sends the compressed filtered monitoring values, monitoring point video information and a second signal indicating the abnormality of the bridge to the bridge control center;

[0013] Obtain the Shapley value φ(σ) of each monitored physical quantity at the abnormal monitoring point, and determine the monitored physical quantity corresponding to the maximum Shapley value.

[0014]

[0015] Wherein, σ represents any one of the monitored physical quantities obtained by the abnormal monitoring point, N is the set of monitored values ​​of all monitoring points of the target bridge, S is any subset of all monitored values ​​of the abnormal monitoring point excluding σ monitored physical quantities, S∪{σ} represents the set after adding any one of the monitored values ​​of σ physical quantities to the subset S, |N| and |S| are the number of monitored values ​​in each set, |N|! and |S|! represent the number of permutations, and v(S) represents the health assessment score obtained based on the subset indicator matrix formed by the average value of the filtered monitored values ​​corresponding to the monitored values ​​of the subset S and the weight matrix;

[0016] The average change rate of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera are obtained respectively, and the sampling frequency of the sensor for collecting the monitored physical quantity corresponding to the maximum Shapley value of the abnormal monitoring point and the sampling angle of the camera are re-determined and adjusted.

[0017] In a second aspect, an embodiment of the present invention provides a bridge status assessment method based on cloud-edge collaboration and multi-index fusion, the assessment method comprising:

[0018] Based on the monitoring device arrays set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge within the monitoring period are obtained; wherein the monitoring device array of each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal and at least one sensor;

[0019] The edge computing terminal performs Kalman filtering on a plurality of monitoring values ​​corresponding to each monitoring physical quantity acquired by the at least one sensor at different acquisition timings within a monitoring period at each monitoring point, obtains a plurality of filtered monitoring values ​​corresponding to each monitoring physical quantity, and further obtains an average value of the filtered monitoring values ​​of each monitoring physical quantity at each monitoring point within the monitoring period;

[0020] The same order is used to establish an indicator matrix with the average value of the filtered monitoring values ​​as an element;

[0021] Based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge, the health assessment score of the target bridge within the monitoring period is obtained;

[0022] Based on the deviation and change of the monitored physical quantities obtained at all monitoring points of the target bridge, obtain the abnormal evaluation score of the target bridge during the monitoring period;

[0023] A state evaluation value of the target bridge is obtained based on the health evaluation score and the abnormality evaluation score of the target bridge, wherein the size of the state evaluation value represents the health of the target bridge, and the smaller the state evaluation value is, the healthier the target bridge is.

[0024] In a third aspect, an embodiment of the present invention further provides a monitoring device, the monitoring device comprising:

[0025] A memory for storing computer executable instructions;

[0026] The processor is used to implement the monitoring method of the above technical solution when executing the computer executable instructions stored in the memory.

[0027] In a fourth aspect, an embodiment of the present invention further provides an evaluation device, the evaluation device comprising:

[0028] A memory for storing computer executable instructions;

[0029] The processor is used to implement the evaluation method of the above technical solution when executing the computer executable instructions stored in the memory.

[0030] In a fifth aspect, an embodiment of the present invention further provides a storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the monitoring method or evaluation method of the above technical solution.

[0031] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0032] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention. The components in the drawings are not drawn to scale, but are only for illustrating the principles of the present invention. In order to facilitate the illustration and description of some parts of the present invention, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present invention. In the drawings:

[0034] Figure 1 It is a flow chart of a bridge status monitoring method based on cloud-edge collaboration and multi-index fusion according to an embodiment of the present invention;

[0035] Figure 2 It is a flow chart of a bridge status assessment method based on cloud-edge collaboration and multi-index fusion according to an embodiment of the present invention;

[0036] Figure 3 is a schematic diagram of a monitoring device according to an embodiment of the present invention;

[0037] Figure 4 FIG. 4 is a schematic diagram of a monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0039] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0040] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0041] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0042] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0043] First, refer to Figure 1 A bridge condition monitoring method 100 based on cloud-edge collaboration and multi-index fusion according to an embodiment of the present application is described. Figure 1 As shown, the monitoring method 100 may include steps S110 to S190, which are specifically as follows:

[0044] In step S110, based on an array of monitoring devices set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge during the monitoring period are obtained; wherein the array of monitoring devices at each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal and at least one sensor.

[0045] In step S120, Kalman filtering is performed on multiple monitoring values ​​corresponding to each monitored physical quantity acquired by the at least one sensor at different acquisition timings at each monitoring point within the monitoring period through the edge computing terminal to obtain multiple filtered monitoring values ​​corresponding to each monitored physical quantity, and further obtain the average value of the filtered monitoring values ​​of each monitored physical quantity at each monitoring point within the monitoring period.

[0046] In step S130, an indicator matrix is ​​constructed with the average value of all filtered monitoring values ​​as an element in the same order.

[0047] In step S140, a health assessment score of each monitoring point within the monitoring period is obtained based on the indicator matrix and a weight matrix composed of each monitored physical quantity of the target bridge.

[0048] In step S150, based on the health assessment score of each monitoring point in the monitoring period, it is determined whether each monitoring point is abnormal according to the upper and lower control thresholds determined according to the corresponding historical data.

[0049] In step S160, if the health assessment score is within the upper and lower control thresholds, a first signal indicating that the bridge is normal is sent to the bridge control center through the edge computing terminal.

[0050] In step S170, if the health assessment score is not within the upper and lower control thresholds, the filtered monitoring values ​​of multiple monitoring physical quantities of the abnormal monitoring point are compressed through the edge computing terminal, and the compressed filtered monitoring values, monitoring point video information and a second signal characterizing the bridge abnormality are sent to the bridge control center.

[0051] In step S180, the Shapley value φ(σ) of each monitored physical quantity at the abnormal monitoring point is obtained, and the monitored physical quantity corresponding to the maximum Shapley value is determined.

[0052]

[0053] Wherein, σ represents any one of the monitoring physical quantities obtained by the abnormal monitoring point, N is the set of monitoring values ​​of all monitoring points of the target bridge, S is any subset of all monitoring values ​​of the abnormal monitoring point excluding σ monitoring physical quantities, S∪{σ} represents the set after adding any one of the monitoring values ​​of σ physical quantities to the subset S, |N| and |S| are the number of monitoring values ​​in each set, |N|! and |S|! represent the number of permutations, and v(S) represents the health assessment score obtained based on the subset indicator matrix formed by the average value of the filtered monitoring values ​​corresponding to the monitoring values ​​of the subset S and the weight matrix.

[0054] In step S190, the average change rate of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera are obtained respectively, and the sampling frequency of the sensor for collecting the monitored physical quantity corresponding to the maximum Shapley value of the abnormal monitoring point and the sampling viewing angle of the camera are determined and adjusted.

[0055] In an embodiment of the present application, first, a plurality of monitoring physical quantities corresponding to the positions of the monitoring points at each monitoring point of the target bridge during the monitoring period are obtained based on the array of monitoring devices, and a plurality of monitoring values ​​corresponding to each monitoring physical quantity obtained at each monitoring point are subjected to Kalman filtering through an edge computing terminal to obtain a plurality of corresponding filtered monitoring values, and an average value of the filtered monitoring values ​​is obtained, and then an indicator matrix with the average value of the filtered monitoring values ​​as an element is constructed, and a health assessment score of each monitoring point during the monitoring period is obtained based on the indicator matrix and the weight matrix, thereby determining whether each monitoring point is abnormal, and if the monitoring point is normal, a signal indicating that the bridge is normal is sent to the bridge control center through the edge computing terminal. If the monitoring point is abnormal, the bridge control center will receive a first signal indicating a normal condition. If the monitoring point is abnormal, the bridge control center will receive a compressed and filtered monitoring value, monitoring point video information, and a second signal indicating the bridge abnormality. The bridge control center will then obtain the Shapley value of each monitored physical quantity at the abnormal monitoring point, determine the monitored physical quantity corresponding to the maximum Shapley value, obtain the average rate of change of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period, and the center distance between the abnormal monitoring point and the corresponding camera, redetermine the sampling frequency of the sensor that collects the monitored physical quantity corresponding to the maximum Shapley value at the abnormal monitoring point, and the sampling angle of view of the camera. Finally, the corresponding sensors and cameras will be monitored and adjusted based on the redetermined sampling frequency of the sensor and sampling angle of view of the camera.

[0056] From the description of the above process, it can be seen that according to the monitoring method 100 of the embodiment of the present application, the edge computing technology based on the edge computing terminal is used to filter the collected monitoring values ​​at the monitoring point end and obtain the health assessment score of each monitoring point. When the monitoring point (bridge structure) is normal, it is only necessary to send a first signal representing the normal state of the bridge to the bridge control center. When the monitoring point is found to be abnormal, the compressed filtered monitoring values, the monitoring point video information and the second signal representing the abnormality of the bridge are transmitted for in-depth analysis by the bridge control center. Such a hierarchical transmission mechanism optimizes the data flow and saves bandwidth resources, while ensuring the timely transmission of key information in emergency situations and reducing the transmission amount of irrelevant data, thereby improving the response speed and processing efficiency. At the same time, the dynamic adjustment of the camera viewing angle and the adaptive control function of the sensor sampling frequency are integrated to accurately adjust the shooting angle of the camera for the abnormal monitoring point, lock the abnormal area, and dynamically optimize the sampling frequency of the sensor to improve the monitoring accuracy of the abnormal area and the timeliness and efficiency of data acquisition.

[0057] Among them, Figure 1 In the embodiment, step S170 and step S180 are shown to be arranged to be performed sequentially, which is only an example. It is understood that the order of step S170 and step S180 may not be limited. For example, step S180 may be performed before step S170, or both may be performed in parallel and simultaneously.

[0058] The contents of the above steps of the monitoring method 100 according to the embodiment of the present application will be described in detail below.

[0059] For common bridges, in order to achieve real-time monitoring of the bridge status, sensors are generally arranged at various key locations. For example, high-precision sensors are installed on the pier foundation and main beam of the bridge to monitor a variety of structural parameters. Specifically, for the pier foundation, water flow pressure sensors and displacement sensors are installed to obtain pier impact force data and pier displacement data to monitor the impact force and displacement changes of water flow on the pier foundation and evaluate the stability and anti-scouring performance of the foundation; strain sensors and acceleration sensors are arranged in the support area, mid-span position, beam end nodes and the connection between the crossbeam and the main beam of the main beam to obtain beam stress data and beam vibration data for real-time monitoring of the stress state and vibration response of the beam body to prevent structural damage caused by excessive load or fatigue. Among them, for cable-stayed bridges or suspension bridges, in addition to the above description, strain sensors and displacement sensors can also be arranged at the top of the cable tower, anchorage, cable clamp and the connection point between the cable and the bridge deck to obtain cable displacement data and cable deformation data, accurately monitor the cable tension changes and the displacement and deformation of the connection point to ensure the safety and stability of the cable system. The specific sensor installation plan will not be described in detail here.

[0060] It should be noted that the sensor at each monitoring point in the embodiment of the present application can obtain monitoring values ​​of multiple different physical quantities at each monitoring point. For example, the sensor can obtain data of two, three, four, etc. different physical quantities at each monitoring point. Therefore, the sensor at each monitoring point can be a plurality of sensors with a single monitoring function, or an all-in-one sensor capable of measuring multiple physical quantities.

[0061] At the same time, considering the significant differences in structural stress and deformation characteristics between single-span bridges and multi-span bridges, the sensor layout schemes are different. For single-span bridges, sensors are mainly arranged at the support and mid-span positions to monitor the support reaction force and mid-span deflection to ensure the overall stiffness and stability of the structure. For multi-span bridges, sensors need to be arranged at the mid-span, support, piers and connection parts between spans to ensure the coordination of the multi-span structure and avoid stress concentration and structural damage caused by differential deformation between spans.

[0062] In an embodiment of the present application, in step S110, based on the array of monitoring devices set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the location of each monitoring point of the target bridge during the monitoring period are obtained. The array of monitoring devices at each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal, and at least one sensor.

[0063] Specifically, for the convenience of understanding and description, taking a cable-stayed bridge or suspension bridge as an example, it is assumed that 10 monitoring points are set at the pier foundation and main beam of the bridge, and 20 monitoring points are set at the top of the pylon, the anchorage, the cable clamp and the connection point between the cable and the bridge deck. A water flow pressure sensor and a displacement sensor are installed at each monitoring point of the pier foundation of the bridge to obtain the pier impact force data and the pier displacement data. Strain sensors and acceleration sensors are installed at each monitoring point of the main beam to obtain the beam stress data and the beam vibration data. Strain sensors and displacement sensors are arranged at the top of the pylon, the anchorage, the cable clamp and the connection point between the cable and the bridge deck to obtain the cable displacement data and the cable deformation data. That is, 30 monitoring points are set at the target bridge, and a total of 6 monitoring physical quantities are obtained.

[0064] In a monitoring cycle, such as 10 minutes, 30 minutes or one hour, a sensor at each monitoring point acquires a total of 30 monitoring data of the corresponding monitoring physical quantity at a sampling interval Δt. For example, the water flow pressure sensor at the monitoring point No. 1 on the pier foundation of the bridge acquires 30 pier impact force data, and the displacement sensor also acquires 30 pier displacement data. The water flow pressure sensor at the monitoring point No. 4 on the pier foundation of the bridge also acquires 30 pier impact force data, and the displacement sensor also acquires 30 pier displacement data. The strain sensor at the monitoring point No. 7 on the main beam acquires 30 beam stress data, and the acceleration sensor also acquires 30 beam vibration data. The strain sensor at the monitoring point No. 15 on the top of the cable tower acquires 30 cable displacement data, and the displacement sensor also acquires 30 cable deformation data. The strain sensor at the monitoring point No. 23 on the cable clamp also acquires 30 cable displacement data, and the displacement sensor also acquires 30 cable deformation data.

[0065] In an embodiment of the present application, in step S120, the edge computing terminal performs Kalman filtering on multiple monitoring values ​​corresponding to each monitored physical quantity acquired by the at least one sensor at different acquisition timings within the monitoring period at each monitoring point, obtains multiple filtered monitoring values ​​corresponding to each monitored physical quantity, and further obtains the average value of the filtered monitoring values ​​of each monitored physical quantity at each monitoring point within the monitoring period.

[0066] In order to ensure real-time performance and response speed and ensure data accuracy, the edge computing terminal (existing technology equipment) at each monitoring point performs Kalman filtering on multiple monitoring values ​​corresponding to the corresponding multiple monitoring physical quantities to obtain multiple filtered monitoring values ​​corresponding to each monitoring physical quantity.

[0067] Specifically,

[0068]

[0069] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0070] in, It represents the monitoring value z of a monitoring physical quantity obtained by the sensor at the same sampling interval for the kth time within the monitoring cycle. k The monitored value after filtering, K k is the Kalman gain, H is the state matrix, H T is the transposed matrix, R is the noise covariance matrix, P k|k-1 is the state estimation error covariance matrix at the acquisition time.

[0071] Based on the multiple filtered monitoring values ​​corresponding to each monitored physical quantity, the average value of the filtered monitoring values ​​of each monitored physical quantity at each monitoring point in the monitoring period is further obtained. That is, all the filtered monitoring values ​​are added and then divided by k, so as to obtain the average value of the filtered monitoring values ​​of each monitored physical quantity at each monitoring point in the monitoring period.

[0072] In the embodiment of the present application, in step S130, the same order is used to construct an indicator matrix X whose elements are the average values ​​of all filtered monitoring values. Specifically,

[0073]

[0074] Where n is the total number of monitoring points, m is the number of types of monitored physical quantities obtained at all monitoring points of the target bridge, It is the average value of the filtered monitoring value of the jth monitoring physical quantity at the ith monitoring point.

[0075] Still taking the cable-stayed bridge or suspension bridge as an example, the total number of monitoring points n is 30, and the number of types of monitored physical quantities m is 6. Each row of the indicator matrix X can be arranged in sequence with pier impact force data, pier displacement data, beam stress data, beam vibration data, cable displacement data, and cable deformation data. Zero is assigned to non-existent physical quantities. For example, the monitoring point number 1 at the pier foundation of the bridge is to Both are 0.

[0076] In the embodiment of the present application, in step S140, the health assessment score Y of each monitoring point in the monitoring period is obtained based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge. i .

[0077] Health assessment scores at monitoring pointsi , can indicate the data health of the monitoring point in this monitoring period. Specifically,

[0078] Y i =X i ·W T

[0079]

[0080] W=[ω1,ω2,…,ω j ,…,ω m ]

[0081] Among them, ω j represents the weight of the jth monitored physical quantity, W T is the transposed matrix of W.

[0082] in,

[0083]

[0084] In an embodiment of the present application, in step S150, based on the health assessment score of each monitoring point within the monitoring period and the upper and lower control thresholds determined according to the corresponding historical data, it is determined whether each monitoring point is abnormal.

[0085] Among them, the upper and lower control thresholds of each monitored physical quantity are determined based on the corresponding historical data and are respectively certain values.

[0086] In an embodiment of the present application, in step S160, if the health assessment score is within the upper and lower control thresholds, a first signal indicating that the bridge is normal is sent to the bridge control center through the edge computing terminal.

[0087] Specifically, if the health assessment score is within the upper and lower control thresholds, it means that the bridge is in normal condition. The edge computing terminal only sends the first signal indicating that the bridge is normal to the bridge control center, without sending a large amount of real-time monitoring values ​​of various monitoring physical quantities and monitoring point video information to the bridge control center. Information transmission is efficient and has a small burden.

[0088] In the embodiment of the present application, if the health assessment score is not within the upper and lower control thresholds in step S170, the edge computing terminal compresses the filtered monitoring values ​​of the various monitoring physical quantities of the abnormal monitoring point, and sends the compressed filtered monitoring values, monitoring point video information and the second signal representing the bridge abnormality to the bridge control center.

[0089] If the health assessment score is not within the upper and lower control thresholds, it indicates that the bridge is abnormal. First, in order to significantly reduce the network bandwidth occupancy, especially in the case of limited bandwidth or poor network environment, to ensure efficient data transmission, the edge computing terminal is used to compress the filtered monitoring values ​​of various monitoring physical quantities of abnormal monitoring points to reduce the data volume. Then, the edge computing terminal sends the compressed filtered monitoring values, monitoring point video information and the second signal representing the bridge abnormality to the bridge control center to provide bridge abnormality and provide data for analysis.

[0090] In an embodiment of the present application, in step S180 , the Shapley value φ(σ) of each monitored physical quantity of the abnormal monitoring point is obtained, and the monitored physical quantity corresponding to the maximum Shapley value is determined.

[0091] When an abnormality occurs at a monitoring point, in order to improve the efficiency and accuracy of sensor monitoring without increasing the burden too much, a sensitivity analysis is performed on the monitoring physical quantity data obtained by different sensors at the abnormal monitoring point to evaluate the contribution of each monitoring physical quantity to the abnormality of the monitoring point, that is, to evaluate the influence of each monitoring physical quantity on the formation of the abnormality of the monitoring point.

[0092] Specifically,

[0093]

[0094] Wherein, σ represents any one of the monitoring physical quantities obtained by the abnormal monitoring point, N is the set of monitoring values ​​of all monitoring points of the target bridge, S is any subset of all monitoring values ​​of the abnormal monitoring point excluding σ monitoring physical quantities, S∪{σ} represents the set after adding any one of the monitoring values ​​of σ physical quantities to the subset S, |N| and |S| are the number of monitoring values ​​in each set, |N|! and |S|! represent the number of permutations, and v(S) represents the health assessment score obtained based on the subset indicator matrix formed by the average value of the filtered monitoring values ​​corresponding to the monitoring values ​​of the subset S and the weight matrix.

[0095] When the Shapley value of a certain monitored physical quantity at an abnormal monitoring point is determined to be the largest, it means that the data of the monitored physical quantity is most likely to be abnormal.

[0096] In an embodiment of the present application, in step S190, the average change rate of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera are respectively obtained, and the sampling frequency of the sensor for collecting the monitored physical quantity corresponding to the maximum Shapley value of the abnormal monitoring point and the sampling angle of view of the camera are re-determined and adjusted.

[0097] Continuing from the above, when it is determined that the data of a certain monitored physical quantity is most likely to be abnormal, the average change rate of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera are obtained respectively. Among them, the average change rate of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period is

[0098]

[0099] Among them, z k It represents the monitoring value of the monitored physical quantity collected by the sensor for the kth time at the sampling interval Δt within the monitoring period.

[0100] Then, the sampling frequency f of the sensor for monitoring the physical quantity corresponding to the maximum Shapley value collected at the abnormal monitoring point is re-determined. new and the camera’s sampling angle θ new , specifically:

[0101] f new =f base ×(1+α×ΔP)

[0102]

[0103] Among them, f base is the sampling frequency of the sensor that collects the maximum Shapley value corresponding to the monitored physical quantity in this monitoring period, θ base is the sampling angle of the camera in this monitoring period, D detect is the center distance between the abnormal monitoring point and the corresponding camera, D max is the maximum distance of the camera coverage, ΔP is the average rate of change of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period. α and β are the respective adjustment coefficients, which are constant values.

[0104] With the re-determined sampling frequency f new and the camera’s sampling angle θ new Monitor abnormal monitoring points to increase the monitoring frequency in abnormal situations to capture more detailed changes, and adjust the camera angle to focus the lens on the abnormal area to capture more relevant visual information.

[0105] Based on the above description, according to the monitoring method of the embodiment of the present application, it is possible to transmit data or signals in a hierarchical manner through edge computing technology based on edge computing terminals, thereby saving bandwidth resources, reducing the transmission amount of irrelevant data, and improving response speed and processing efficiency; at the same time, it integrates the dynamic adjustment of camera viewing angle and sensor sampling frequency control functions to improve the monitoring accuracy of abnormal areas and the timeliness and efficiency of data acquisition.

[0106] refer to Figure 3The embodiment of the present application also provides a monitoring device 300 for implementing the monitoring method 100 according to the embodiment of the present application. The monitoring device 300 includes a processor 310 and a memory 320. The monitoring device 300 may include one or more processors 310 and one or more memories 320. The memory 320 stores an executable program run by the processor 310, and when the executable program is run by the processor 310, the processor 310 executes the monitoring method 100 according to the embodiment of the present application described above.

[0107] The processor 310 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities.

[0108] The memory 320 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 310 may run the program instructions to implement the client functions (implemented by the processor) in the embodiments of the present application described herein and / or other desired functions. Various applications and various data may also be stored in the computer-readable storage medium, such as various data used and / or generated by the application, etc.

[0109] The monitoring device 300 may also include an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms. Figure 3 The components and structures of the monitoring device 300 shown are merely exemplary and non-limiting. The monitoring device 300 may also have other components and structures as required.

[0110] The input device may be a device used by a user to input instructions, and may include one or more of a keyboard, a mouse, a microphone, a touch screen, etc. In addition, the input device may also be any interface for receiving information.

[0111] The output device may output various information (eg, images or sounds) to the outside (eg, a user), and may include one or more of a display, a speaker, etc. In addition, the output device may also be any other device with an output function.

[0112] Exemplarily, the example monitoring device 300 for implementing the monitoring method 100 according to the embodiment of the present application can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (ultra-mobile personal computers, UMPCs), handheld computers, netbooks, personal digital assistants (personal digital assistants, PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (augmented reality, AR), virtual reality (virtual reality, VR) devices, smart home devices, car computers and other electronic devices, and the embodiments of the present application do not impose any restrictions on this.

[0113] Those skilled in the art can understand the specific operation of the monitoring device 300 for implementing the monitoring method 100 according to the embodiment of the present application in combination with the contents described above. For the sake of brevity, the specific details are not repeated here, and only some main operations of the processor 310 are described.

[0114] In one embodiment of the present application, when the executable program is executed by the processor 310, the processor 310 executes the following steps: based on the array of monitoring devices set at multiple monitoring points of the target bridge, obtain a plurality of monitoring physical quantities corresponding to the location of each monitoring point of the target bridge during the monitoring period according to the location of the monitoring point; perform Kalman filtering on a plurality of monitoring values ​​corresponding to each monitoring physical quantity obtained by the at least one sensor at different acquisition timings during the monitoring period at each monitoring point through an edge computing terminal to obtain a plurality of filtered monitoring values ​​corresponding to each monitoring physical quantity, and further obtain the average value of the filtered monitoring values ​​of each monitoring physical quantity at each monitoring point during the monitoring period; construct an indicator matrix with the average value of all filtered monitoring values ​​as elements in the same order; obtain the health assessment score of each monitoring point during the monitoring period based on the indicator matrix and the weight matrix composed of each monitoring physical quantity of the target bridge; The health assessment score of each monitoring point during the measurement period is used to determine whether each monitoring point is abnormal based on the upper and lower control thresholds determined by the corresponding historical data; if the health assessment score is within the range of the upper and lower control thresholds, the edge computing terminal sends a first signal indicating that the bridge is normal to the bridge control center; if the health assessment score is not within the range of the upper and lower control thresholds, the edge computing terminal compresses the filtered monitoring values ​​of multiple monitoring physical quantities of the abnormal monitoring point, and sends the compressed filtered monitoring values, monitoring point video information and a second signal indicating the bridge abnormality to the bridge control center; the Shapley value of each monitoring physical quantity of the abnormal monitoring point is obtained, and the monitoring physical quantity corresponding to the maximum Shapley value is determined; the average change rate of the monitoring physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera are obtained respectively, and the sampling frequency of the sensor for collecting the monitoring physical quantity corresponding to the maximum Shapley value of the abnormal monitoring point and the sampling angle of the camera are determined and adjusted.

[0115] The above exemplary shows the monitoring method 100 according to the embodiment of the present application. Figure 4 A monitoring system 400 provided in another aspect of an embodiment of the present application is described.

[0116] Reference Figure 4 The example monitoring system 400 for implementing the monitoring method of the embodiment of the present application is described. The monitoring system 400 may include an acquisition module 410, a filtering module 420, a matrix construction module 430, a health assessment score calculation module 440, a judgment and processing module 450, a Shapley value calculation module 460 and an adjustment module 470. Among them:

[0117] The acquisition module 410 is used to: based on the array of monitoring devices set at multiple monitoring points of the target bridge, acquire multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge during the monitoring period.

[0118] The filtering module 420 is used to: perform Kalman filtering on multiple monitoring values ​​corresponding to each monitoring physical quantity obtained by the at least one sensor at different acquisition time sequences at each monitoring point through the edge computing terminal, obtain multiple filtered monitoring values ​​corresponding to each monitoring physical quantity, and further obtain the average value of the filtered monitoring values ​​of each monitoring physical quantity at each monitoring point in the monitoring period.

[0119] The matrix construction module 430 is used to construct an indicator matrix with the average value of all filtered monitoring values ​​as an element in the same order.

[0120] The health assessment score calculation module 440 is used to obtain the health assessment score of each monitoring point within the monitoring period based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge.

[0121] The judgment and processing module 450 is used to: judge whether each monitoring point is abnormal based on the upper and lower control thresholds determined according to the corresponding historical data based on the health assessment score of each monitoring point during the monitoring period; if the health assessment score is within the upper and lower control thresholds, the edge computing terminal sends a first signal indicating that the bridge is normal to the bridge control center; if the health assessment score is not within the upper and lower control thresholds, the edge computing terminal compresses the filtered monitoring values ​​of multiple monitoring physical quantities of the abnormal monitoring point, and sends the compressed filtered monitoring values, monitoring point video information and a second signal indicating the abnormality of the bridge to the bridge control center.

[0122] The Shapley value calculation module 460 is used to obtain the Shapley value of each monitored physical quantity at the abnormal monitoring point and determine the monitored physical quantity corresponding to the maximum Shapley value.

[0123] The adjustment module 470 is used to respectively obtain the average rate of change of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera, and determine and adjust the sampling frequency of the sensor for collecting the monitored physical quantity corresponding to the maximum Shapley value of the abnormal monitoring point and the sampling angle of the camera.

[0124] The monitoring system 400 proposed in the embodiment of the present invention can transmit information according to different conditions, save bandwidth resources, and improve response speed and processing efficiency; at the same time, it can realize the dynamic adjustment of camera viewing angle and adaptive control function of sensor sampling frequency, thereby improving the monitoring accuracy of abnormal areas and the timeliness and efficiency of data acquisition.

[0125] refer to Figure 2 The present application also provides a bridge status assessment method 200 based on cloud-edge collaboration and multi-index fusion. Figure 2As shown, the evaluation method 200 may include steps S210 to S260, which are specifically as follows:

[0126] In step S210, based on an array of monitoring devices set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge during the monitoring period are obtained; wherein the array of monitoring devices at each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal and at least one sensor.

[0127] In step S220, the edge computing terminal performs Kalman filtering on multiple monitoring values ​​corresponding to each monitored physical quantity acquired by the at least one sensor at different acquisition timings at each monitoring point within the monitoring period, obtains multiple filtered monitoring values ​​corresponding to each monitored physical quantity, and further obtains the average value of the filtered monitoring values ​​of each monitored physical quantity at each monitoring point within the monitoring period.

[0128] In step S230, an indicator matrix X is established with the average value of the filtered monitoring values ​​as an element in the same order.

[0129] In step S240, a health assessment score of the target bridge within the monitoring period is obtained based on the indicator matrix and a weight matrix composed of each monitored physical quantity of the target bridge.

[0130] In step S250, based on the deviation and change of the monitored physical quantities obtained at all monitoring points of the target bridge, an abnormality assessment score of the target bridge within the monitoring period is obtained.

[0131] In step S260, a state evaluation value of the target bridge is obtained based on the health evaluation score and the abnormality evaluation score of the target bridge, wherein the size of the state evaluation value represents the health of the target bridge, and the smaller the state evaluation value is, the healthier the target bridge is.

[0132] According to the evaluation method 200 of the embodiment of the present application, steps S210 to S230 may refer to the relevant contents of the monitoring method 100 of the embodiment of the present application, and will not be described again here.

[0133] Steps S240 to S260 are described below, specifically as follows:

[0134] In step S240, based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge, the health assessment score Y of the target bridge within the monitoring period is obtained, specifically:

[0135] Y=X·W T

[0136] Among them, X is the indicator matrix, W TIt is the transposed matrix of the weight matrix W composed of each monitored physical quantity of the target bridge.

[0137] In step S250, based on the deviation and change of the monitored physical quantities obtained at all monitoring points of the target bridge, the abnormality assessment score of the target bridge within the monitoring period is obtained.

[0138] Specifically, the abnormal assessment score of the target bridge during the monitoring period is A,

[0139] A = γ·deviation score + η·rate of change score

[0140] Among them, γ and η are their respective weights and are constant values.

[0141] Regarding the deviation score, the following formula is used to obtain it:

[0142] Deviation score = ∑(Pj*ω j )

[0143]

[0144] z=[z1,z2,…z k …,z p ]

[0145] Among them, the average deviation value is the average value of all the deviation values ​​obtained. Pj represents the deviation score of the jth monitoring physical quantity of the target bridge, z represents the monitoring value sequence of the jth monitoring physical quantity collected by the sensor at the sampling interval Δt during the monitoring period, and Uj and Lj are the upper and lower control thresholds of the jth monitoring physical quantity, respectively. The maximum allowable deviation is the maximum allowable deviation of different monitoring physical quantities from the average deviation value to the boundary of the range [Lj,Uj], which is a fixed value.

[0146] Regarding the change rate score, the following formula is used to obtain it:

[0147] Change rate score = ∑(Vj*ω j )

[0148]

[0149] Wherein, Vj represents the change rate score of the jth monitored physical quantity of the target bridge. The average change rate is the average value of all the change rates obtained. The maximum change rate and the minimum change rate are the maximum and minimum values ​​of all the change rates obtained.

[0150] In step S26, the state evaluation value F of the target bridge is obtained according to the respective weights based on the health evaluation score Y and the abnormality evaluation score A of the target bridge. The size of the state evaluation value represents the health of the target bridge. The smaller the state evaluation value, the healthier the target bridge.

[0151] For example, the weights of health assessment score Y and abnormality assessment score A are 0.6 and 0.4 respectively.

[0152] F=0.6·Y+0.4·A

[0153] Similarly, the embodiment of the present application also provides an evaluation device (not shown) for implementing the evaluation method 200 according to the embodiment of the present application. The evaluation device also includes a processor and a memory. The specific content is not described here, and reference can be made to the relevant content of a monitoring device 300 for implementing the monitoring method 100 according to the embodiment of the present application provided in the embodiment of the present application.

[0154] In addition, according to an embodiment of the present application, the present application further provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is used to execute the corresponding steps of the monitoring method 100 of the embodiment of the present application or the corresponding steps of the evaluation method 200 of the embodiment of the present application. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0155] In addition, according to an embodiment of the present application, the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the monitoring method of the embodiment of the present application or implement the steps of the evaluation method of the embodiment of the present application.

[0156] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0157] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0159] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0160] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0161] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A bridge condition monitoring method based on cloud-edge collaboration and multi-index fusion, characterized in that: The monitoring method comprises: Based on the monitoring device arrays set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge within the monitoring period are obtained; wherein the monitoring device array of each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal and at least one sensor; Performing Kalman filtering on multiple monitoring values ​​corresponding to each monitoring physical quantity acquired by the at least one sensor at different acquisition timings within the monitoring period at each monitoring point through the edge computing terminal to obtain multiple filtered monitoring values ​​corresponding to each monitoring physical quantity, and further obtaining an average value of the filtered monitoring values ​​of each monitoring physical quantity at each monitoring point within the monitoring period; The indicator matrix with the average value of all filtered monitoring values ​​as elements is constructed in the same order; Based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge, the health assessment score of each monitoring point in the monitoring period is obtained; based on the health assessment score of each monitoring point in the monitoring period, the upper and lower control thresholds determined according to the corresponding historical data are used to determine whether each monitoring point is abnormal; If the health assessment score is within the upper and lower control thresholds, a first signal indicating that the bridge is normal is sent to the bridge control center through the edge computing terminal; if the health assessment score is not within the upper and lower control thresholds, the edge computing terminal compresses the filtered monitoring values ​​of multiple monitoring physical quantities at the abnormal monitoring point, and sends the compressed filtered monitoring values, monitoring point video information and a second signal indicating the abnormality of the bridge to the bridge control center; Obtain the Shapley value φ(σ) of each monitored physical quantity at the abnormal monitoring point, and determine the monitored physical quantity corresponding to the maximum Shapley value. Wherein, σ represents any one of the monitored physical quantities obtained by the abnormal monitoring point, N is the set of monitored values ​​of all monitoring points of the target bridge, S is any subset of all monitored values ​​of the abnormal monitoring point excluding σ monitored physical quantities, S∪{σ} represents the set after adding any one of the monitored values ​​of σ physical quantities to the subset S, |N| and |S| are the number of monitored values ​​in each set, |N|! and |S|! represent the number of permutations, and v(S) represents the health assessment score obtained based on the subset indicator matrix formed by the average value of the filtered monitored values ​​corresponding to the monitored values ​​of the subset S and the weight matrix; The average change rate of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period and the center distance between the abnormal monitoring point and the corresponding camera are obtained respectively, and the sampling frequency of the sensor for collecting the monitored physical quantity corresponding to the maximum Shapley value of the abnormal monitoring point and the sampling angle of the camera are re-determined and adjusted.

2. The monitoring method according to claim 1, characterized in that: The obtaining of a plurality of filtered monitoring values ​​corresponding to each monitored physical quantity specifically refers to: K k =P k|k-1 H T (HP k|k-1 H T +R) -1 in, It represents the monitoring value z of a monitoring physical quantity obtained by the sensor at the same sampling interval for the kth time within the monitoring cycle. k The monitored value after filtering, K k is the Kalman gain, H is the state matrix, R is the noise covariance matrix, P k|k-1 is the state estimation error covariance matrix at the acquisition time.

3. The monitoring method according to claim 1, characterized in that: The use of the same order to establish an indicator matrix X with the average value of the filtered monitoring values ​​as an element specifically refers to: Where n is the total number of monitoring points, m is the number of types of monitored physical quantities obtained at all monitoring points of the target bridge, It is the average value of the filtered monitoring value of the jth monitoring physical quantity at the ith monitoring point.

4. The monitoring method according to claim 3, characterized in that: The health assessment score Y of each monitoring point in the monitoring period is obtained based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge. i , specifically: Y i =X i ·W T W=[ω1,ω2,…,ω j ,…,oh m ] Among them, ω j represents the weight of the jth monitored physical quantity, W T is the transposed matrix of W.

5. The monitoring method according to claim 1, characterized in that: The sampling frequency f of the sensor for monitoring the physical quantity corresponding to the maximum Shapley value collected at the abnormal monitoring point is re-determined new and the camera’s sampling angle θ new , specifically: f new =f base ×(1+α×ΔP) Among them, f base is the sampling frequency of the sensor that collects the maximum Shapley value corresponding to the monitored physical quantity in this monitoring period, θ base is the sampling angle of the camera in this monitoring period, D detect is the center distance between the abnormal monitoring point and the corresponding camera, D max is the maximum distance covered by the camera, ΔP is the average rate of change of the monitored physical quantity corresponding to the maximum Shapley value during the monitoring period, and α and β are their respective adjustment coefficients.

6. A bridge condition assessment method based on cloud-edge collaboration and multi-index fusion, characterized in that: The evaluation methods include: Based on the monitoring device arrays set at multiple monitoring points of the target bridge, multiple monitoring physical quantities corresponding to the positions of each monitoring point of the target bridge within the monitoring period are obtained; wherein the monitoring device array of each monitoring point includes a camera for collecting video information of the monitoring point, an edge computing terminal and at least one sensor; Performing Kalman filtering on a plurality of monitoring values ​​corresponding to each monitoring physical quantity acquired by the at least one sensor at different acquisition timings within a monitoring period at each monitoring point through an edge computing terminal to obtain a plurality of filtered monitoring values ​​corresponding to each monitoring physical quantity, and further obtaining an average value of the filtered monitoring values ​​of each monitoring physical quantity at each monitoring point within the monitoring period; The same order is used to establish an indicator matrix with the average value of the filtered monitoring values ​​as an element; Based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge, the health assessment score of the target bridge within the monitoring period is obtained; Based on the deviation and change of the monitored physical quantities obtained at all monitoring points of the target bridge, obtain the abnormal evaluation score of the target bridge during the monitoring period; A state evaluation value of the target bridge is obtained based on the health evaluation score and the abnormality evaluation score of the target bridge, wherein the size of the state evaluation value represents the health of the target bridge, and the smaller the state evaluation value is, the healthier the target bridge is.

7. The evaluation method according to claim 6, characterized in that: The health assessment score Y of the target bridge within the monitoring period is obtained based on the indicator matrix and the weight matrix composed of each monitored physical quantity of the target bridge, specifically referring to: Y=X·W T Among them, X is the indicator matrix, W T is the transposed matrix of the weight matrix W composed of each monitored physical quantity of the target bridge; and / or The abnormal assessment score A of the target bridge within the monitoring period is obtained based on the deviation and change of the monitored physical quantities obtained at all monitoring points of the target bridge, specifically referring to: A = γ·deviation score + η·rate of change score Deviation score = ∑(Pj*ω j ) from=[from1,from2,…from k …,With p ] Change rate score = ∑(Vj*ω j ) Among them, Pj represents the deviation score of the j-th monitoring physical quantity of the target bridge, Vj represents the change rate score of the j-th monitoring physical quantity of the target bridge, z represents the monitoring value sequence of the j-th monitoring physical quantity collected by the sensor at a sampling interval Δt during the monitoring period, Uj and Lj are the upper and lower control thresholds of the j-th monitoring physical quantity, respectively, and γ and η are weights.

8. A monitoring device, characterized in that: The monitoring equipment includes: A memory for storing computer executable instructions; A processor, configured to implement the monitoring method according to any one of claims 1 to 5 when executing computer executable instructions stored in the memory.

9. An evaluation device, characterized in that The evaluation equipment comprises: A memory for storing computer executable instructions; The processor is used to implement the evaluation method described in claim 6 or 7 when executing the computer executable instructions stored in the memory.

10. A storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the monitoring method according to any one of claims 1 to 5, or the evaluation method according to any one of claims 6 to 7.

Images