A highway bridge hidden danger checking method and system based on multi-device cooperation

Abstract

The present application relates to the technical field of multi-terminal sensing synchronization, and relates to a highway bridge hidden danger investigation method and system based on multi-device cooperation, which comprises the following steps: receiving a bridge hidden danger investigation instruction, confirming a bridge to be investigated based on the bridge hidden danger investigation instruction, clock synchronizing m investigation devices to obtain m synchronized devices, using n sensors equipped in the synchronized devices to cooperatively collect data of the bridge to be investigated based on a preset cooperative collection protocol, obtaining n bridge collection data sets, time sequence synchronizing the n bridge collection data sets to obtain a bridge synchronization data set, calculating hidden danger values of investigation points corresponding to the bridge synchronization data set according to the bridge synchronization data set, cross-device fusing m hidden danger values according to the m investigation points to obtain fused hidden danger values, and judging an investigation result of the bridge to be investigated according to the fused hidden danger values and the m hidden danger values. The present application can improve the accuracy and reliability of cross-device fused highway bridge hidden danger investigation.

Description

Technical Field

[0001] This invention relates to the field of multi-terminal sensing synchronization technology, and in particular to a method and system for identifying potential hazards in highway bridges based on multi-device collaboration. Background Technology

[0002] With the continuous increase in traffic load and the long-term effects of environmental factors, bridge structures are prone to potential defects such as cracks, deformation, and corrosion. Failure to detect and address these defects in a timely manner could lead to serious safety accidents. Employing a multi-device collaborative approach allows for the simultaneous collection of bridge condition data at multiple inspection points, improving the comprehensiveness and real-time nature of the inspection. This provides a reliable basis for subsequent hazard assessment and maintenance decisions, effectively reducing bridge operational risks. Therefore, inspecting for potential hazards on highway bridges is of great significance for ensuring bridge structural safety and extending their service life.

[0003] Traditional methods for identifying potential hazards on highway bridges rely heavily on manual visual inspections or point-by-point measurements using single detection devices. This approach suffers from drawbacks such as low efficiency, strong subjectivity, and poor data consistency. Data collection times at different inspection points are inconsistent, making it difficult to reflect the overall condition of the bridge at any given moment. Furthermore, the independent operation of each device, lacking clock synchronization and data fusion mechanisms, easily leads to inaccurate hazard calculations or missed hazard assessments. In addition, traditional methods struggle to effectively correlate multi-source data, resulting in insufficient hazard identification capabilities across inspection points and hindering collaborative analysis and comprehensive judgment, thus impacting the accuracy and reliability of hazard identification. Therefore, improving the accuracy and reliability of cross-device fusion-based highway bridge hazard identification has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method for identifying potential hazards in highway bridges based on multi-device collaboration and a computer-readable storage medium. Its main purpose is to improve the accuracy and reliability of cross-device integrated identification of potential hazards in highway bridges.

[0005] To achieve the above objectives, the present invention provides a method for identifying potential hazards in highway bridges based on multi-device collaboration, comprising: Receive a bridge hazard investigation instruction, identify the bridge to be investigated based on the bridge hazard investigation instruction, and identify m investigation points and m investigation devices on the bridge to be investigated. The investigation points and investigation devices are one-to-one, and each investigation device is equipped with n sensors. By synchronizing the clocks of m inspection devices, m synchronization devices are obtained, where each synchronization device corresponds one-to-one with an inspection point. Perform the following operation on each of the m synchronization devices: Based on a preset collaborative acquisition protocol, the n sensors equipped with the synchronization device are used to collaboratively acquire data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The hazard values ​​are summarized to obtain m hazard values, where each hazard value corresponds one-to-one with an inspection point; Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

[0006] Optionally, the step of synchronizing the clocks of m investigation devices to obtain m synchronized devices includes: Confirm the device clock of each of the m investigated devices to obtain m device clocks to be calibrated, where each device clock corresponds one-to-one with an investigated device; Calculate the reference clock based on the clocks of m devices to be calibrated; For each of the m device clocks to be calibrated, perform the following operation: Calculate the absolute difference between the clock of the device to be calibrated and the reference clock to obtain the absolute clock difference, and compare the absolute clock difference with the preset clock difference threshold. If the absolute clock difference is less than or equal to the clock difference threshold, the investigation device corresponding to the absolute clock difference is used as the synchronization device; Otherwise, the clock of the troubleshooting device corresponding to the absolute clock difference is corrected using the reference clock to obtain the corrected device. The clock of the corrected device corresponding to the corrected device is confirmed. When the absolute difference between the clock of the corrected device and the reference clock is less than or equal to the clock difference threshold, the troubleshooting device corresponding to the absolute clock difference is used as the synchronization device. The number of synchronization devices is summarized to obtain m synchronization devices.

[0007] Optionally, the step of calculating the reference clock based on m clocks of devices to be calibrated includes: Compare m with a preset stratification threshold. If m is greater than the stratification threshold, cluster the m device clocks to be calibrated to obtain a groups of device clocks to be calibrated, where each group of device clocks to be calibrated contains multiple device clocks to be calibrated. Perform the following operation on each of the a clock groups of devices to be calibrated: Extract the clocks of the devices to be calibrated sequentially from the clock group of devices to be calibrated, and remove the clocks of the devices to be calibrated from the clock group of devices to be calibrated to obtain the remaining clock group of devices; Calculate the squared distance between the extracted clock of the device to be calibrated and the clock of the device to be calibrated in the remaining clock group, and obtain the squared clock distance value. Summarize the squared clock distance values ​​to obtain multiple squared clock distance values, where each squared clock distance value corresponds one-to-one with the clock of the device to be calibrated. The smallest clock distance squared value is selected from multiple clock distance squared values, and the clock of the device to be corrected corresponding to the smallest clock distance squared value is used as the reference clock for the cluster group. Summarize the cluster group reference clocks to obtain a cluster group reference clocks; The reference clock is identified from the reference clocks of cluster groups a.

[0008] Optionally, the method of using n sensors equipped with a synchronization device to collaboratively collect data from the bridges to be inspected, resulting in n bridge data sets, including: Obtain a bridge data acquisition configuration table with n sensors. The bridge data acquisition configuration table includes n data acquisition task nodes, and each data acquisition task node includes: acquisition frequency and acquisition time period. Each data acquisition task node has a different acquisition frequency but the same acquisition time period. Based on the n acquisition task nodes, the n sensors equipped with the synchronization device are task-bound to obtain n sensor task nodes, wherein the sensor task nodes include: sensors and acquisition task nodes; Perform the following operation on each of the n sensor task nodes: Using the sensors corresponding to the sensor task nodes, and according to the acquisition frequency and acquisition time period corresponding to the acquisition task nodes, the acquisition points corresponding to the synchronous devices in the bridge to be investigated are collected to obtain the bridge acquisition dataset. Summarize the bridge data collection datasets to obtain n bridge data collection datasets.

[0009] Optionally, the step of synchronizing the n bridge data sets in time to obtain a bridge synchronization dataset includes: Extract bridge data sets sequentially from n bridge data sets, and perform the following operations on the extracted bridge data sets: Set the current time, and identify the closest and furthest actual collection times from the bridge data collection dataset to obtain the collection end time and collection start time. Construct a data collection time interval with the start time of data collection as the start time of the interval and the end time of data collection as the end time of the interval. By summing the data collection time intervals, we obtain n data collection time intervals; Perform an intersection operation on n collection time intervals to obtain a synchronization time interval. Divide the synchronization time interval into b sub-intervals according to a preset time length, where each sub-interval contains the midpoint of the sub-interval. By using b sub-intervals to perform time-series synchronization on n bridge data sets, a bridge synchronization dataset is obtained.

[0010] Optionally, the step of using b sub-intervals to perform time-series synchronization of n bridge data sets to obtain a bridge synchronization dataset includes: Extract bridge data sets sequentially from n bridge data sets, and perform the following operations on the extracted bridge data sets: Extract sub-intervals sequentially from b sub-intervals, traverse the bridge acquisition data in the bridge acquisition dataset that falls within the sub-intervals, and obtain the interval acquisition dataset, wherein the interval acquisition dataset contains one or more bridge acquisition data. If the interval collection dataset contains only one bridge collection data, then the bridge collection data shall be used as the bridge cluster data; Otherwise, calculate the mean of all bridge data collected in the interval collection dataset to obtain bridge cluster data; Summarize the bridge cluster data to obtain b bridge cluster data, where each bridge cluster data corresponds one-to-one with a sub-interval; Summarize b bridge cluster data corresponding to each bridge data set in n bridge data sets to obtain c bridge cluster data sets, where c equals b multiplied by n; Based on b sub-intervals, the c bridge cluster data are divided into b bridge cluster data groups, where the sub-intervals corresponding to the bridge cluster data in each bridge cluster data group are the same. Perform the following operation on each of the b bridge cluster data groups: Calculate the mean of the bridge cluster data contained in the bridge cluster data group to obtain the bridge synchronization data, and summarize the bridge synchronization data to obtain the bridge synchronization dataset.

[0011] Optionally, calculating the hazard value of the inspection point corresponding to the bridge synchronous dataset based on the bridge synchronous dataset includes: Identify the types of the n sensors corresponding to the bridge synchronization dataset to obtain the sensor types; Using the sensor type, f sets of mapping relationships corresponding to the sensor type are retrieved from a pre-constructed hazard mapping table, wherein each set of mapping relationships contains a mapping interval and a mapping value; Bridge synchronization data are extracted sequentially from the bridge synchronization dataset. Using the bridge synchronization data, the corresponding mapping value is determined in the f groups of mapping relationships, wherein the bridge synchronization data is located within the mapping interval corresponding to the mapping value. Summarize the mapping values ​​to obtain a mapping value set, identify the largest mapping value from the mapping value set, and use the largest mapping value as the hidden danger value.

[0012] Optionally, the step of fusing the m hazard values ​​across devices based on the m inspection points to obtain the fused hazard value includes: The bridge structure of the bridge to be investigated is identified. Based on the bridge structure, the influence coefficient corresponding to each of the m investigation points is identified, resulting in m structural influence coefficients, where each structural influence coefficient corresponds one-to-one with an investigation point. Calculate the sum of m structural influence coefficients to obtain the comprehensive structural influence coefficient. Calculate the ratio of each of the m structural influence coefficients to the comprehensive structural influence coefficient to obtain m point weights, where each point weight corresponds one-to-one with the investigation point and the hidden danger value. The fused hazard value is calculated using the weights of m points and m hazard values, as shown in the following formula:

[0013] in, This represents the fusion risk value. This represents the value of the m hidden dangers. One potential hazard value, This represents the value of the m hidden dangers. The point weight corresponding to each potential hazard value.

[0014] Optionally, the step of determining the inspection result of the bridge to be inspected based on the fused hazard value and m hazard values ​​includes: The hazard indication value is calculated based on the combined hazard value and m individual hazard values, using the following formula:

[0015] in, This indicates the hazard indication value. This represents the fusion risk value. This indicates the preset threshold for potential hazards. This represents the value of the m hidden dangers. One potential hazard value, This indicates the preset threshold for single-point hazards. () indicates a preset indicator function that returns 1 if the condition is true, and 0 otherwise. Indicates the threshold identifier; If the hazard indicator value is not 0, the inspection results of the bridge to be inspected will be confirmed as having a hazard. Otherwise, the results of the investigation of the bridge to be investigated will be confirmed as having no hidden dangers.

[0016] To achieve the above objectives, the present invention also provides a highway bridge hazard investigation system based on multi-device collaboration, comprising: The inspection equipment deployment module is used to receive bridge hazard inspection instructions, identify the bridge to be inspected based on the bridge hazard inspection instructions, and identify m inspection points and m inspection equipment on the bridge to be inspected. The inspection points and inspection equipment are one-to-one, and each inspection equipment is equipped with n sensors. The equipment clock synchronization module is used to synchronize the clocks of m investigated devices to obtain m synchronized devices, where each synchronized device corresponds one-to-one with an investigated point. The collaborative acquisition module is used to collect data from the bridges to be investigated using n sensors equipped with the synchronization device based on a preset collaborative acquisition protocol, and to obtain n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by the actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The cross-device fusion module is used to aggregate hazard values ​​and obtain m hazard values, where each hazard value corresponds one-to-one with an investigation point; Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

[0017] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: Memory, storing at least one instruction; The processor executes the instructions stored in the memory to implement the above-described method for identifying potential hazards in highway bridges based on multi-device collaboration.

[0018] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for identifying potential hazards in highway bridges based on multi-device collaboration.

[0019] To address the problems described in the background art, this invention receives a bridge hazard investigation command, identifies the bridge to be investigated based on the command, and identifies m investigation points and m investigation devices on the bridge. Each investigation point corresponds one-to-one with an investigation device, and each investigation device is equipped with n sensors. The clocks of the m investigation devices are synchronized to obtain m synchronized devices, where each synchronized device corresponds one-to-one with an investigation point. This invention reduces the computational load of clock correction by performing hierarchical clustering synchronization of device clocks, and ensures that all investigation devices collect data under a unified time reference by adaptively adjusting the synchronization accuracy. Bridge data is used to lay the foundation for subsequent time-series alignment and cross-device fusion of bridge data, effectively improving the accuracy and timeliness of bridge hazard investigation. Based on a preset collaborative acquisition protocol, n sensors equipped with synchronous devices are used to collaboratively collect data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time. It can be seen that this invention standardizes multi-sensor collaborative acquisition through a bridge acquisition configuration table, setting different frequencies and the same time periods for the same type of sensors, realizing high-frequency capture of transient changes and low-frequency reduction of data. The redundancy and unified time period ensure time axis alignment, facilitating subsequent time-series synchronization and fusion, thus improving the accuracy and efficiency of bridge hazard investigation. Time-series synchronization of n bridge data sets is performed to obtain a bridge synchronization dataset. Hazard values ​​for the corresponding investigation points are calculated based on this bridge synchronization dataset. It is evident that this invention converts sensor-collected numerical data into hazard values ​​through a hazard mapping table, achieving a quantitative assessment of the degree of hazard at the investigation points for the bridge under investigation. The hazard values ​​are summarized to obtain m hazard values, where each hazard value corresponds one-to-one with an investigation point. Based on these m investigation points, the m hazard values ​​are cross-referenced. The process involves fusing data to obtain a fused hazard value. Based on this fused hazard value and m individual hazard values, the inspection result for the bridge to be inspected is determined, indicating either the presence or absence of a hazard. This process enables multi-device collaborative hazard inspection of highway bridges. The invention categorizes environmental factors by deviation rate (positive or negative) and dynamically adjusts the threshold using multiplication and summation operations. This allows the hazard threshold to adaptively reflect the impact of different environmental conditions on bridge detection data, solving the problem of false alarms or missed alarms caused by fixed thresholds under changing environmental conditions. This improves the accuracy and reliability of bridge hazard inspection under various environmental conditions. Therefore, this invention can improve the accuracy and reliability of cross-device fusion-based highway bridge hazard inspection. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a method for identifying potential hazards in highway bridges based on multi-device collaboration, provided in an embodiment of the present invention. Figure 2A functional module diagram of a highway bridge hidden danger investigation system based on multi-device collaboration provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the electronic device used to implement the multi-device collaborative highway bridge hidden danger investigation method according to an embodiment of the present invention.

[0021] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0022] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0024] This application provides a method for identifying potential hazards in highway bridges based on multi-device collaboration. The executing entity of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0025] Reference Figure 1 The diagram shown is a flowchart illustrating a method for identifying potential hazards in highway bridges based on multi-device collaboration, according to an embodiment of the present invention. In this embodiment, the method for identifying potential hazards in highway bridges based on multi-device collaboration includes: S1. Receive a bridge hazard investigation instruction, identify the bridge to be investigated based on the bridge hazard investigation instruction, and identify m investigation points and m investigation devices on the bridge to be investigated. The investigation points and investigation devices correspond one-to-one, and each investigation device is equipped with n sensors.

[0026] It should be explained that the bridge hazard investigation instruction is issued by personnel who wish to conduct hazard investigations on the bridge to be investigated. The bridge to be investigated is the target highway bridge for which hazard investigation is required. The investigation points are pre-determined key detection locations on the bridge to be investigated, based on the bridge's structural characteristics and hazard investigation requirements. For example, investigation points are typically set at critical structural stress points such as the mid-span section, support section, and 1 / 4 span section of the bridge. The investigation equipment is a detection device integrating multiple sensors, used to collect data from the bridge to be investigated at the corresponding investigation points. The sensors are sensor components equipped on the investigation equipment used for data collection from the bridge to be investigated; optionally, the types of sensors include, but are not limited to, acceleration sensors and displacement sensors.

[0027] For example, a municipal transportation bureau needs to conduct a hazard inspection of a prestressed concrete simply supported beam bridge that has been in operation for 15 years in the urban area. The bridge maintenance engineer issues a hazard inspection order, confirming that the bridge to be inspected is this prestressed concrete simply supported beam bridge. Based on the structural stress characteristics of the bridge to be inspected, five inspection points (m=5) are set at the mid-span section, the left 1 / 4 span section, the right 1 / 4 span section, the left support section, and the right support section. At the same time, one inspection device is configured at each inspection point, and each inspection device is equipped with three sensors (n=3).

[0028] It should be clarified that for the same inspection point, the n sensors equipped are of the same type, meaning that n identical sensors work together to collect bridge data on the same physical quantity. For different inspection points, the sensor types corresponding to the n sensors equipped at one point can be the same or different from the sensor types corresponding to the n sensors equipped at other inspection points, depending on the specific needs of the inspection point. For example, taking inspection points 1 and 2 as examples, inspection point 1 is equipped with 3 sensors of the same type, and inspection point 2 is equipped with 3 sensors of the same type, but the sensor types at inspection point 1 and inspection point 2 can be the same or different.

[0029] S2. Synchronize the clocks of m inspection devices to obtain m synchronized devices, where each synchronized device corresponds to one inspection point.

[0030] It should be understood that clock synchronization is the process of adjusting the device clocks of m inspection devices to a unified reference time base. The purpose is to ensure that different inspection devices collect bridge data under the same time reference system, thereby guaranteeing the consistency of the bridge data in the time dimension. The synchronized devices are inspection devices whose clocks, after clock synchronization processing, have deviations from the reference clock within an allowable range. Since multiple inspection devices are distributed at different locations on the bridge to be inspected, the internal clocks of each inspection device may have deviations. Without clock synchronization, the bridge data collected by different inspection devices cannot be precisely aligned in time, affecting the accuracy of subsequent timing synchronization and cross-device fusion. Therefore, the clock synchronization of m inspection devices to obtain m synchronized devices includes: Confirm the device clock of each of the m investigated devices to obtain m device clocks to be calibrated, where each device clock corresponds one-to-one with an investigated device; Calculate the reference clock based on the clocks of m devices to be calibrated; For each of the m device clocks to be calibrated, perform the following operation: Calculate the absolute difference between the clock of the device to be calibrated and the reference clock to obtain the absolute clock difference, and compare the absolute clock difference with the preset clock difference threshold. If the absolute clock difference is less than or equal to the clock difference threshold, the investigation device corresponding to the absolute clock difference is used as the synchronization device; Otherwise, the clock of the troubleshooting device corresponding to the absolute clock difference is corrected using the reference clock to obtain the corrected device. The clock of the corrected device corresponding to the corrected device is confirmed. When the absolute difference between the clock of the corrected device and the reference clock is less than or equal to the clock difference threshold, the troubleshooting device corresponding to the absolute clock difference is used as the synchronization device. The number of synchronization devices is summarized to obtain m synchronization devices.

[0031] It is understood that the clock of the device to be calibrated is the clock value of the device under investigation that has not yet undergone clock synchronization calibration. The reference clock is a unified time base calculated based on the clocks of all devices to be calibrated, used as a reference standard for clock synchronization. Specifically, the absolute clock difference is the absolute difference between the clock of the device to be calibrated and the reference clock, used to measure the degree of deviation between the clock of the device to be calibrated and the reference clock. The clock difference threshold is a pre-set upper limit for clock deviation, which can be determined according to the requirements of bridge hazard investigation for data acquisition time accuracy. For example, if the requirements for data acquisition time accuracy in bridge hazard investigation are very high, the clock difference threshold can be set to 1ms; conversely, if the requirements are lower, the clock difference threshold can be set to 10ms. When the absolute clock difference is less than or equal to the clock difference threshold, it indicates that the clock deviation of the device under investigation is within an acceptable range and no calibration is required. The clock calibration is the process of adjusting the device clock using the reference clock. The specific implementation process is as follows: a reference clock signal is sent to the device under investigation through a network time protocol or a precise time protocol, and the clock module of the device under investigation automatically adjusts its internal clock value according to the received reference clock signal. The calibrated device is the device under investigation that has undergone clock calibration processing. The corrected device clock is the device clock corresponding to the corrected device.

[0032] Further, the step of calculating the reference clock based on the m clocks of the devices to be calibrated includes: Compare m with a preset stratification threshold. If m is greater than the stratification threshold, cluster the m device clocks to be calibrated to obtain a groups of device clocks to be calibrated, where each group of device clocks to be calibrated contains multiple device clocks to be calibrated. Perform the following operation on each of the a clock groups of devices to be calibrated: Extract the clocks of the devices to be calibrated sequentially from the clock group of devices to be calibrated, and remove the clocks of the devices to be calibrated from the clock group of devices to be calibrated to obtain the remaining clock group of devices; Calculate the squared distance between the extracted clock of the device to be calibrated and the clock of the device to be calibrated in the remaining clock group, and obtain the squared clock distance value. Summarize the squared clock distance values ​​to obtain multiple squared clock distance values, where each squared clock distance value corresponds one-to-one with the clock of the device to be calibrated. The smallest clock distance squared value is selected from multiple clock distance squared values, and the clock of the device to be corrected corresponding to the smallest clock distance squared value is used as the reference clock for the cluster group. Summarize the cluster group reference clocks to obtain a cluster group reference clocks; The reference clock is identified from the reference clocks of cluster groups a.

[0033] In detail, the stratification threshold is a pre-set boundary value for the number of inspection devices, used to determine whether a stratified clustering method is needed to calculate the reference clock. The stratification threshold can be set according to the timeliness requirements of the bridge hazard inspection. When the timeliness requirements are relatively lenient, the stratification threshold can be appropriately increased; when the timeliness requirements are relatively strict, the stratification threshold can be appropriately decreased.

[0034] It should be clarified that when the number of devices to be investigated, *m*, is large (i.e., *m* is greater than the stratification threshold), if clustering is not performed and the pairwise squared distance values ​​are directly calculated for all *m* devices to be calibrated to select reference clocks, the computational workload increases quadratically with *m*, resulting in a very large computational load and reducing the timeliness of the investigation of potential hazards on the bridges to be investigated. The specific method of stratified clustering is as follows: first, the *m* devices to be calibrated are clustered into *a* groups (*a* is much smaller than *m*). Within each group, reference clocks for the clusters are selected separately. Finally, only the reference clocks from the *a* clusters are aggregated to obtain the reference clocks.

[0035] Understandably, clustering is the process of grouping clocks of devices to be calibrated with similar clock values ​​into a group. Optionally, this can be achieved using K-means clustering or hierarchical clustering algorithms. The device clock group to be calibrated is the grouping of device clocks obtained after clustering, where the clock values ​​within the same group are close to each other. The squared clock distance is the square of the difference between two device clocks to be calibrated, used to measure the degree of deviation between the two clocks. The cluster group reference clock is the device clock with the smallest sum of squared clock distances to other device clocks within each group, serving as the representative clock for that cluster group. The method for identifying the reference clock from the 'a' cluster group reference clocks is the same as the method for identifying the cluster group reference clock from the device clock group to be calibrated, and will not be repeated here. This invention reduces the computational load of clock correction by performing hierarchical clustering synchronization of device clocks. By adaptively adjusting the synchronization accuracy, it ensures that all inspection devices collect bridge data under a unified time reference, thereby laying the foundation for subsequent time-series alignment and cross-device fusion of bridge data and effectively improving the accuracy and timeliness of bridge hazard inspection.

[0036] S3. Based on the preset collaborative acquisition protocol, the n sensors equipped with the synchronization device are used to collaboratively acquire data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time.

[0037] It should be explained that the collaborative acquisition protocol is a pre-defined multi-sensor collaborative working rule used to standardize the acquisition methods of multiple sensors on the same inspection device, ensuring that each sensor acquires bridge data according to a predetermined acquisition frequency and time period. The collaborative data acquisition is the process by which multiple sensors on the inspection device simultaneously acquire data on the structural state parameters of the bridge to be inspected, under the constraints of the collaborative acquisition protocol. The bridge acquisition dataset is the collection of all bridge acquisition data acquired by a sensor within a specific acquisition time period. The bridge acquisition data refers to the state parameter values ​​of the bridge to be inspected acquired by the sensor at a specific acquisition moment. The actual acquisition time is the moment when the bridge acquisition data is actually acquired by the sensor.

[0038] Understandably, in order to standardize the collaborative data acquisition method of multiple sensors, it is necessary to define the acquisition task of each sensor through a data acquisition configuration table. Therefore, the method of using n sensors equipped with a synchronization device to collaboratively acquire data from the bridge to be inspected, resulting in n bridge acquisition datasets, including: Obtain a bridge data acquisition configuration table with n sensors. The bridge data acquisition configuration table includes n data acquisition task nodes, and each data acquisition task node includes: acquisition frequency and acquisition time period. Each data acquisition task node has a different acquisition frequency but the same acquisition time period. Based on the n acquisition task nodes, the n sensors equipped with the synchronization device are task-bound to obtain n sensor task nodes, wherein the sensor task nodes include: sensors and acquisition task nodes; Perform the following operation on each of the n sensor task nodes: Using the sensors corresponding to the sensor task nodes, and according to the acquisition frequency and acquisition time period corresponding to the acquisition task nodes, the acquisition points corresponding to the synchronous devices in the bridge to be investigated are collected to obtain the bridge acquisition dataset. Summarize the bridge data collection datasets to obtain n bridge data collection datasets.

[0039] It should be understood that the bridge data acquisition configuration table is a pre-defined sensor data acquisition task configuration file used to define the working parameters of each sensor during the collaborative data acquisition process. The data acquisition task node is the basic configuration unit in the bridge data acquisition configuration table, containing the acquisition frequency and acquisition period information for a specific sensor. The acquisition frequency is the number of times the sensor acquires bridge data per unit time. The acquisition period is the time range within which the sensor performs data acquisition. The task binding is the process of assigning acquisition task nodes to corresponding sensors. The sensor task node is a sensor that has been bound to an acquisition task node.

[0040] It should be clarified that the n sensors equipped at the same inspection point are of the same type and collect the same physical quantities, but each sensor has a different acquisition frequency and the same acquisition time period. The purpose of this setting is: different acquisition frequencies support high-frequency acquisition to capture rapid changes in bridge data, while also allowing low-frequency acquisition to reduce data redundancy; and a unified acquisition time period ensures that all bridge data has consistent start and end boundaries on the time axis, facilitating subsequent time-series alignment and fusion processing, thereby improving the accuracy and efficiency of bridge hazard inspection. This embodiment of the invention standardizes multi-sensor collaborative acquisition through a bridge acquisition configuration table. Sensors of the same type are assigned different frequencies and the same time period, enabling high-frequency capture of transient changes, low-frequency reduction of data redundancy, and a unified time period to ensure time axis alignment, facilitating subsequent time-series synchronization and fusion, thus improving the accuracy and efficiency of bridge hazard inspection.

[0041] S4. Synchronize the n bridge data sets in time to obtain a bridge synchronization dataset. Calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset.

[0042] It should be explained that the time-series synchronization is the process of aligning the bridge data collection datasets from n sensors along the time dimension. Because different sensors have different acquisition frequencies, the distribution density of their collected bridge data on the time axis varies. Time-series synchronization is needed to unify multiple datasets into the same time interval. The bridge synchronization dataset is the data set obtained after time-series synchronization processing, where all bridge synchronization data corresponds to the same time interval. The hazard value is a value calculated based on the bridge synchronization dataset and is used to measure the degree of hazard at the inspection point.

[0043] Understandably, due to differences in the acquisition frequencies of different sensors, even if different sensors acquire data during the same time period, the actual acquisition time of the first and last bridge synchronization data acquired by different sensors may differ in actual engineering due to factors such as equipment startup delays, clock drift, and packet loss. Therefore, it is necessary to first determine the common time interval of the bridge acquisition data corresponding to each sensor. The timing synchronization of the n bridge acquisition datasets yields the bridge synchronization dataset, which includes: Extract bridge data sets sequentially from n bridge data sets, and perform the following operations on the extracted bridge data sets: Set the current time, and identify the closest and furthest actual collection times from the bridge data collection dataset to obtain the collection end time and collection start time. Construct a data collection time interval with the start time of data collection as the start time of the interval and the end time of data collection as the end time of the interval. By summing the data collection time intervals, we obtain n data collection time intervals; Perform an intersection operation on n collection time intervals to obtain a synchronization time interval. Divide the synchronization time interval into b sub-intervals according to a preset time length, where each sub-interval contains the midpoint of the sub-interval. By using b sub-intervals to perform time-series synchronization on n bridge data sets, a bridge synchronization dataset is obtained.

[0044] It should be understood that the current time is the current moment when the timing synchronization operation is performed. The acquisition end time is the actual acquisition time closest to the current time in the bridge acquisition data set, that is, the moment when the sensor last acquired bridge acquisition data. The acquisition start time is the actual acquisition time furthest from the current time in the bridge acquisition data set, that is, the moment when the sensor first acquired bridge acquisition data. The acquisition time interval is a closed time range formed by the acquisition start time and acquisition end time, representing the effective bridge acquisition data coverage period of a sensor. The intersection operation is the operation of taking the common overlapping part of n acquisition time intervals, with the purpose of finding the time range in which all sensors have bridge acquisition data coverage. The synchronization time interval is the common intersection part of n acquisition time intervals, representing the time range in which all sensors have bridge acquisition data. The time length is a pre-set sub-interval division interval, and the setting of this time length needs to comprehensively consider the sensor's acquisition frequency and data processing accuracy requirements. The specific setting method is as follows: Find the highest acquisition frequency from the acquisition frequencies of n sensors. The time length is equal to the reciprocal of the highest acquisition frequency multiplied by a proportionality coefficient not greater than 1. This proportionality coefficient is manually set to balance the acquisition frequency and data processing accuracy; the smaller the proportionality coefficient, the finer the time division and the higher the synchronization accuracy. The sub-interval is the time period obtained by dividing the synchronization time interval into equal intervals. The median value of the sub-interval is the midpoint value of the sub-interval's time.

[0045] Furthermore, when performing time-series synchronization of bridge acquisition datasets using sub-intervals, it is necessary to handle the situation where multiple bridge acquisition datasets may exist within a sub-interval. Therefore, the step of using b sub-intervals to perform time-series synchronization of n bridge acquisition datasets to obtain a bridge synchronization dataset includes: Extract bridge data sets sequentially from n bridge data sets, and perform the following operations on the extracted bridge data sets: Extract sub-intervals sequentially from b sub-intervals, traverse the bridge acquisition data in the bridge acquisition dataset that falls within the sub-intervals, and obtain the interval acquisition dataset, wherein the interval acquisition dataset contains one or more bridge acquisition data. If the interval collection dataset contains only one bridge collection data, then the bridge collection data shall be used as the bridge cluster data; Otherwise, calculate the mean of all bridge data collected in the interval collection dataset to obtain bridge cluster data; Summarize the bridge cluster data to obtain b bridge cluster data, where each bridge cluster data corresponds one-to-one with a sub-interval; Summarize b bridge cluster data corresponding to each bridge data set in n bridge data sets to obtain c bridge cluster data sets, where c equals b multiplied by n; Based on b sub-intervals, the c bridge cluster data are divided into b bridge cluster data groups, where the sub-intervals corresponding to the bridge cluster data in each bridge cluster data group are the same. Perform the following operation on each of the b bridge cluster data groups: Calculate the mean of the bridge cluster data contained in the bridge cluster data group to obtain the bridge synchronization data, and summarize the bridge synchronization data to obtain the bridge synchronization dataset.

[0046] In detail, the interval acquisition dataset is the collection of all bridge acquisition data whose actual acquisition time falls within a certain sub-interval time range. When there is only one bridge acquisition data in a sub-interval, that bridge acquisition data is directly used as the clustering result for that sub-interval without the need for mean calculation. When there are multiple bridge acquisition data in a sub-interval, the bridge clustering data is calculated using an arithmetic mean. The purpose of using the arithmetic mean is that, since it is necessary to fuse the clustering results (bridge clustering data) of different sensors in the same sub-interval (and take the mean to obtain bridge synchronization data), the arithmetic mean can ensure that each bridge acquisition data contributes equally to the clustering result, avoiding the introduction of unnecessary weight bias. The bridge clustering data group is the collection of bridge clustering data corresponding to all sensors in the same sub-interval. The bridge synchronization data is the fused data value obtained by averaging all bridge clustering data in a bridge clustering data group. This invention achieves alignment and fusion of sensor data from different acquisition frequencies in the time dimension by collecting the intersection of time intervals and weighted clustering based on time distance, thus solving the problem of time synchronization of multi-sensor multi-frequency acquisition data.

[0047] Furthermore, after obtaining the bridge synchronization dataset, it is necessary to assess the degree of hazard at the corresponding inspection points based on the bridge synchronization data. Therefore, the step of calculating the hazard value of the inspection points corresponding to the bridge synchronization dataset based on the bridge synchronization dataset includes: Identify the types of the n sensors corresponding to the bridge synchronization dataset to obtain the sensor types; Using the sensor type, f sets of mapping relationships corresponding to the sensor type are retrieved from a pre-constructed hazard mapping table, wherein each set of mapping relationships contains a mapping interval and a mapping value; Bridge synchronization data are extracted sequentially from the bridge synchronization dataset. Using the bridge synchronization data, the corresponding mapping value is determined in the f groups of mapping relationships, wherein the bridge synchronization data is located within the mapping interval corresponding to the mapping value. Summarize the mapping values ​​to obtain a mapping value set, identify the largest mapping value from the mapping value set, and use the largest mapping value as the hidden danger value.

[0048] It is understood that the sensor type refers to the type of sensor corresponding to the bridge synchronous dataset. The hazard mapping table is a pre-built data lookup table used to map the bridge synchronous data collected by the sensors to hazard assessment scores. The hazard mapping table is constructed as follows: for each sensor type, based on relevant specifications and engineering experience for bridge structural safety assessment, bridge engineering experts determine the correspondence between the physical quantity monitored by the sensor and the bridge hazard level. The range of values ​​for the monitored physical quantity is divided into several continuous mapping intervals. Each mapping interval corresponds to a hazard level and is assigned a mapping value. The magnitude of the mapping value is positively correlated with the severity of the hazard. All mapping intervals and their mapping values ​​are organized into a key-value pair lookup table, which is the hazard mapping table. For example, for a certain sensor, the mapping range and corresponding mapping value can be set as follows: [0, 0.1) corresponds to 0 (no hidden danger), [0.1, 0.2) corresponds to 10 (minor hidden danger), [0.2, 0.3) corresponds to 30 (moderate hidden danger), [0.3, 0.5) corresponds to 60 (serious hidden danger), and [0.5, +∞) corresponds to 100 (dangerous hidden danger). When the bridge synchronization data collected by the sensor is 0.15, it falls into the range [0.1, 0.2), and the mapping value is 10.

[0049] It should be explained that the mapping relationship is the basic query unit in the hazard mapping table, containing a numerical range and the corresponding mapping value. The mapping range is the numerical range defined in the mapping relationship, used to determine the hazard level range to which the bridge's synchronous data belongs. The mapping value is the hazard assessment score corresponding to the mapping range; the larger the mapping value, the higher the hazard risk of the bridge to be investigated at the corresponding investigation point. The hazard value is the maximum value in the set of mapping values ​​corresponding to the same investigation point and the same type of sensor, reflecting the most serious hazard level detected by that type of sensor at that investigation point for the bridge to be investigated. This embodiment of the invention converts the numerical data collected by the sensor into hazard values ​​through the hazard mapping table, realizing a quantitative assessment of the hazard level of the bridge to be investigated at the investigation point.

[0050] S5. Summarize the hazard values ​​to obtain m hazard values, where each hazard value corresponds to a specific inspection point.

[0051] It should be explained that the m hidden danger values ​​are a set of hidden danger values ​​calculated and summarized for each of the m inspection points. Each hidden danger value reflects the degree of hidden danger of the bridge to be inspected at the corresponding inspection point.

[0052] S6. Based on the m inspection points, the m hidden danger values ​​are fused across devices to obtain the fused hidden danger value. Based on the fused hidden danger value and the m hidden danger values, the inspection result of the bridge to be inspected is determined. The inspection result is either that there is a hidden danger or that there is no hidden danger. Based on the inspection result, the hidden danger inspection of highway bridges based on multi-device collaboration is realized.

[0053] It should be explained that the cross-device fusion is a process of weighting and fusing the hazard values ​​of m different inspection points according to the importance of each inspection point in the bridge structure. The purpose is to comprehensively consider the hazard situation at various key locations of the bridge and obtain a fused hazard value that reflects the overall hazard status of the entire bridge. The fused hazard value is a comprehensive hazard assessment value obtained after cross-device fusion, used to measure the overall hazard level of the entire bridge to be inspected.

[0054] Understandably, different inspection points have varying degrees of importance in the bridge structure. The mid-span section typically bears the maximum bending moment, and its potential hazards have a greater impact on bridge safety. In contrast, the support sections primarily bear shear force, and their importance differs from that of the mid-span section. Therefore, it is necessary to determine the weight of each inspection point based on the bridge structure. The process of fusing m potential hazard values ​​across equipment based on the m inspection points yields a fused hazard value, including: The bridge structure of the bridge to be investigated is identified. Based on the bridge structure, the influence coefficient corresponding to each of the m investigation points is identified, resulting in m structural influence coefficients, where each structural influence coefficient corresponds one-to-one with an investigation point. Calculate the sum of m structural influence coefficients to obtain the comprehensive structural influence coefficient. Calculate the ratio of each of the m structural influence coefficients to the comprehensive structural influence coefficient to obtain m point weights, where each point weight corresponds one-to-one with the investigation point and the hidden danger value. The fused hazard value is calculated using the weights of m points and m hazard values, as shown in the following formula:

[0055] in, This represents the fusion risk value. This represents the value of the m hidden dangers. One potential hazard value, This represents the value of the m hidden dangers. The point weight corresponding to each potential hazard value.

[0056] It should be understood that the bridge structure refers to the structural type and construction form of the bridge to be investigated, including structural characteristics such as span arrangement, cross-sectional shape, and support conditions. Optional bridge structural types include, but are not limited to, simply supported beam bridges, continuous beam bridges, suspension bridges, and cable-stayed bridges. The structural influence coefficient is a coefficient determining the degree of influence of each investigation point on the overall safety of the bridge, based on the bridge's structural characteristics. The structural influence coefficient is determined by bridge engineering experts based on the structural mechanics analysis results and engineering experience. Generally, the structural influence coefficient at the mid-span section is the largest, followed by the 1 / 4 span section, and relatively smaller at the support sections. The comprehensive structural influence coefficient is the sum of m structural influence coefficients, used to normalize the calculation of the weight of each investigation point. The point weight is the proportion of weight each investigation point occupies in the calculation of the integrated hidden danger value, calculated by the ratio of the structural influence coefficient to the comprehensive structural influence coefficient, ensuring that the sum of all point weights is 1.

[0057] Furthermore, after obtaining the fused hazard value, it needs to be compared with a preset threshold to determine the hazard status of the bridge. Therefore, the step of determining the investigation result of the bridge to be investigated based on the fused hazard value and m hazard values ​​includes: The hazard indication value is calculated based on the combined hazard value and m individual hazard values, using the following formula:

[0058] in, This indicates the hazard indication value. This represents the fusion risk value. This indicates the preset threshold for potential hazards. This represents the value of the m hidden dangers. One potential hazard value, This indicates the preset threshold for single-point hazards. () indicates a preset indicator function that returns 1 if the condition is true, and 0 otherwise. Indicates the threshold identifier; If the hazard indicator value is not 0, the inspection results of the bridge to be inspected will be confirmed as having a hazard. Otherwise, the results of the investigation of the bridge to be investigated will be confirmed as having no hidden dangers.

[0059] In detail, the investigation results are the final judgment on the hazard status of the bridge under investigation based on the integrated hazard value and m hazard values, including two states: hazard exists and hazard does not exist. The integrated hazard value reflects the overall hazard situation of the bridge under investigation, while the m hazard values ​​reflect the hazard situation at a specific point on the bridge under investigation.

[0060] Understandably, the hazard indication value is obtained by adding two indication functions, where the indication function is... This indicator function is used to determine whether the overall fusion hazard value exceeds a preset hazard threshold. This method determines whether at least one inspection point has a hazard value exceeding a preset single-point hazard threshold. When both conditions are not met, g=0, indicating that the bridge under inspection has no hazards. When either condition is met or both conditions are met simultaneously, g≥1, indicating that the bridge under inspection has hazards. Even if the overall hazard value is within the acceptable range, if the hazard value at any inspection point exceeds the single-point hazard threshold, it indicates that the bridge under inspection has hazards. Conversely, even if all hazard values ​​are within the acceptable range, if the overall hazard value exceeds the acceptable range, it also indicates that the bridge under inspection has hazards. This judgment logic achieves dual monitoring of overall and local risks, avoiding the problem of underreporting of serious hazards in key areas due to weighted averaging. This embodiment of the invention determines the weight of each inspection point through a structural influence coefficient. Through dual judgment of overall and local risks, it can assess the comprehensive risk of the bridge and capture serious local hazards at any inspection point, avoiding underreporting caused by weighted averaging masking risks in key areas, thus improving the comprehensiveness and safety of hazard inspection for the bridge under inspection.

[0061] It should be explained that the hazard threshold is a pre-set threshold for determining the overall hazard value, used to distinguish whether there are hazards on the bridge under investigation. When the overall hazard value is greater than the hazard threshold, it indicates that the overall hazard level of the bridge under investigation exceeds the safety allowable range, and the investigation result confirms the existence of hazards. The single-point hazard threshold is a pre-set threshold for determining the hazard value of a single investigation point, used to distinguish whether there are hazards on the bridge under investigation at any investigation point from a local perspective. When the hazard value at a certain investigation point is greater than the single-point hazard threshold, it indicates that there are local hazards at that investigation point.

[0062] It is important to clarify that in the actual process of bridge hazard investigation, the bridge data collected by sensors is affected not only by the degradation or damage of the bridge structure itself, but also by environmental factors. For example, when there is heavy traffic and high wind speed on the bridge, the sensor readings will be higher due to load and wind vibration effects. Conversely, when there is less traffic and lower wind speed, the sensor readings are closer to the true condition of the bridge structure. If a fixed hazard threshold is directly used as the criterion for determining the hazard indication value, false alarms or missed alarms may occur under conditions of drastic changes in environmental factors. Therefore, it is necessary to dynamically set the hazard threshold according to the actual environmental conditions during the data collection period, so that the hazard threshold can reflect the impact of different environmental conditions on the sensor data.

[0063] Specifically, the method for setting the hazard threshold includes: Obtain environmental monitoring data nodes of the bridge to be investigated during the collection period. Each environmental monitoring data node includes z environmental monitoring index values, and each environmental monitoring index value corresponds to a different environmental factor. Obtain environmental baseline data nodes, wherein each environmental baseline data node includes z environmental monitoring baseline values, and each environmental monitoring baseline value corresponds one-to-one with an environmental monitoring indicator value; Environmental monitoring index values ​​are extracted sequentially from z environmental monitoring index values. Using the environmental monitoring index values, the corresponding environmental monitoring benchmark values ​​are retrieved from the z environmental monitoring benchmark values. The environmental factors corresponding to the environmental monitoring index values ​​are the same as the environmental factors corresponding to the environmental monitoring benchmark values. Subtract the environmental monitoring index value from the environmental monitoring benchmark value to obtain the index difference. Calculate the ratio of the index difference to the environmental monitoring benchmark value to obtain the environmental deviation rate, where the environmental monitoring index value is the minuend. If the environmental deviation rate is non-negative, then the environmental deviation rate is used as the positive environmental deviation rate; otherwise, the environmental deviation rate is used as the negative environmental deviation rate. The positive and negative environmental deviation rates are summarized separately to obtain x positive environmental deviation rates and y negative environmental deviation rates; The hazard threshold is calculated based on x positive environmental deviation rates and y negative environmental deviation rates, using the following formula:

[0064] in, This indicates the threshold for potential hazards. This indicates the preset baseline hazard threshold. Indicates shared ownership A positive environmental deviation rate express Among the positive environmental deviation rates, the first... A positive environmental deviation rate Indicates shared ownership A negative environmental deviation rate. express Among the negative environmental deviation rates, the first... A negative environmental deviation rate Indicates the threshold identifier. Indicates the reference identifier.

[0065] It should be explained that the environmental monitoring data nodes are sets of environmental state parameters acquired by environmental monitoring equipment deployed near the bridge to be investigated during the collection period. The environmental monitoring index values ​​are used to quantitatively describe the state level of a specific environmental factor during the collection period, and the environmental factors corresponding to the z environmental monitoring index values ​​are all different. Optionally, the types of environmental factors include, but are not limited to: wind speed and traffic load indicators.

[0066] It should be understood that the environmental monitoring benchmark value is used to describe the reference level of an environmental factor under standard testing conditions. The environmental benchmark data node is determined as follows: the bridge maintenance engineer selects the environmental conditions that cause the least interference to the sensor data collection as the standard testing condition based on the climate characteristics, traffic flow patterns, and relevant specifications for bridge structural safety assessment of the area where the bridge to be investigated is located, and records the index values ​​corresponding to the environmental factors (such as wind speed and traffic load indicators) under the standard testing condition as the environmental monitoring benchmark value.

[0067] Furthermore, the index difference is the difference between the environmental monitoring index value and the corresponding environmental monitoring benchmark value, used to measure the deviation of the actual monitored environment relative to the standard monitoring conditions. When the environmental monitoring index value is greater than or equal to the corresponding environmental monitoring benchmark value, the index difference is non-negative, indicating that the actual level of the environmental factor is higher than the standard monitoring conditions (e.g., actual wind speed is greater than the benchmark wind speed). When the environmental monitoring index value is less than the corresponding environmental monitoring benchmark value, the index difference is negative, indicating that the actual level of the environmental factor is not higher than the standard monitoring conditions. The environmental deviation rate is the ratio of the index difference to the corresponding environmental monitoring benchmark value, used to normalize environmental deviations of different dimensions into a dimensionless relative deviation.

[0068] Specifically, the positive environmental deviation rate is the deviation rate corresponding to a non-negative environmental deviation rate, indicating that the actual level of the environmental factor is higher than the standard testing conditions. The negative environmental deviation rate is the deviation rate corresponding to a negative environmental deviation rate, indicating that the actual level of the environmental factor is lower than the standard testing conditions.

[0069] It is understood that the benchmark hazard threshold is a pre-set benchmark value for hazard judgment used under standard inspection conditions, that is, the hazard threshold directly adopted when environmental conditions fully meet the standard inspection conditions. The benchmark hazard threshold is determined as follows: based on relevant specifications for bridge structural safety assessment and engineering practice experience, historical inspection data and maintenance records of similar bridges under standard inspection conditions are collected, the distribution of hazard values ​​corresponding to bridges with confirmed hazards is statistically analyzed, and the lower quartile of the hazard value distribution of the bridges with hazards is taken as the initial reference value of the benchmark hazard threshold. Finally, the bridge maintenance engineer makes fine adjustments according to the actual inspection accuracy requirements.

[0070] It should be explained that the calculation formula for the hazard threshold uses a multiplication operation for positive environmental deviation rates and a summation operation for negative environmental deviation rates. The reason is as follows: For positive environmental deviation rates (factors where the actual environmental level is not lower than the standard operating condition), multiplication is used because when multiple environmental factors simultaneously exceed the standard operating condition, there is a coupled amplification relationship between the interference effects of each factor on the sensor data. For example, when high wind speed and high traffic load occur simultaneously, the wind vibration effect and traffic load effect superimpose each other, causing the sensor reading to produce a nonlinear deviation exceeding that of a single factor. Multiplication amplifies this multi-factor synergistic interference, causing the hazard threshold to increase more rapidly as the deviation of the exceeding environmental factor increases. For negative environmental deviation rates (factors where the actual environmental level is lower than the standard operating condition), summation is used because when environmental factors are better than the standard operating condition, each environmental factor independently reduces the interference on the sensor data. When multiple factors are simultaneously better than the standard operating condition, their reduction effects are linearly superimposed. Summation ensures that the downward adjustment of the hazard threshold decreases linearly as the number and degree of environmental factors better than the standard operating condition increase, avoiding excessive downward adjustment of the hazard threshold. Optionally, the method for setting the single-point hazard threshold can refer to the method for setting the hazard threshold. This embodiment of the invention dynamically adjusts the hazard threshold by classifying the deviation rate of environmental factors into positive and negative categories and using multiplication and summation operations respectively. This allows the hazard threshold to adaptively reflect the impact of different environmental conditions on bridge inspection data, solving the problem that fixed thresholds are prone to false alarms or missed alarms under changing environmental conditions, and improving the accuracy and reliability of bridge hazard investigation under different environmental conditions.

[0071] To address the problems described in the background art, this invention receives a bridge hazard investigation command, identifies the bridge to be investigated based on the command, and identifies m investigation points and m investigation devices on the bridge. Each investigation point corresponds one-to-one with an investigation device, and each investigation device is equipped with n sensors. The clocks of the m investigation devices are synchronized to obtain m synchronized devices, where each synchronized device corresponds one-to-one with an investigation point. This invention reduces the computational load of clock correction by performing hierarchical clustering synchronization of device clocks, and ensures that all investigation devices collect data under a unified time reference by adaptively adjusting the synchronization accuracy. Bridge data is used to lay the foundation for subsequent time-series alignment and cross-device fusion of bridge data, effectively improving the accuracy and timeliness of bridge hazard investigation. Based on a preset collaborative acquisition protocol, n sensors equipped with synchronous devices are used to collaboratively collect data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time. It can be seen that this invention standardizes multi-sensor collaborative acquisition through a bridge acquisition configuration table, setting different frequencies and the same time periods for the same type of sensors, realizing high-frequency capture of transient changes and low-frequency reduction of data. The redundancy and unified time period ensure time axis alignment, facilitating subsequent time-series synchronization and fusion, thus improving the accuracy and efficiency of bridge hazard investigation. Time-series synchronization of n bridge data sets is performed to obtain a bridge synchronization dataset. Hazard values ​​for the corresponding investigation points are calculated based on this bridge synchronization dataset. It is evident that this invention converts sensor-collected numerical data into hazard values ​​through a hazard mapping table, achieving a quantitative assessment of the degree of hazard at the investigation points for the bridge under investigation. The hazard values ​​are summarized to obtain m hazard values, where each hazard value corresponds one-to-one with an investigation point. Based on these m investigation points, the m hazard values ​​are cross-referenced. The process involves fusing data to obtain a fused hazard value. Based on this fused hazard value and m individual hazard values, the inspection result for the bridge to be inspected is determined, indicating either the presence or absence of a hazard. This process enables multi-device collaborative hazard inspection of highway bridges. The invention categorizes environmental factors by deviation rate (positive or negative) and dynamically adjusts the threshold using multiplication and summation operations. This allows the hazard threshold to adaptively reflect the impact of different environmental conditions on bridge detection data, solving the problem of false alarms or missed alarms caused by fixed thresholds under changing environmental conditions. This improves the accuracy and reliability of bridge hazard inspection under various environmental conditions. Therefore, this invention can improve the accuracy and reliability of cross-device fusion-based highway bridge hazard inspection.

[0072] like Figure 2 The diagram shown is a functional block diagram of a highway bridge hidden danger investigation system based on multi-device collaboration provided in an embodiment of the present invention.

[0073] The multi-device collaborative highway bridge hazard investigation system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the multi-device collaborative highway bridge hazard investigation system 100 may include an investigation device deployment module 101, a device clock synchronization module 102, a collaborative data acquisition module 103, and a cross-device fusion module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device. The inspection equipment deployment module 101 is used to receive bridge hazard inspection instructions, identify the bridge to be inspected based on the bridge hazard inspection instructions, and identify m inspection points and m inspection equipment on the bridge to be inspected. The inspection points and inspection equipment correspond one-to-one, and each inspection equipment is equipped with n sensors. The device clock synchronization module 102 is used to synchronize the clocks of m investigation devices to obtain m synchronized devices, wherein each synchronized device corresponds to an investigation point. The collaborative acquisition module 103 is used to collect data from the bridges to be investigated using n sensors equipped with the synchronization device based on a preset collaborative acquisition protocol, and to obtain n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by the actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The cross-device fusion module 104 is used to summarize the hidden danger values ​​to obtain m hidden danger values, wherein each hidden danger value corresponds to a checkpoint. Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

[0074] In detail, the modules in the multi-device collaborative highway bridge hazard investigation system 100 described in this embodiment of the invention employ the same methods as described above. Figure 1 The method used is the same as the multi-device collaborative highway bridge hidden danger investigation method described in the article, and can produce the same technical effect, so it will not be repeated here.

[0075] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a method for identifying potential hazards in highway bridges based on multi-device collaboration, according to an embodiment of the present invention.

[0076] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a method program for identifying potential hazards in highway bridges based on multi-device collaboration.

[0077] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a method for investigating hidden dangers in highway bridges based on multi-device collaboration, but also to temporarily store data that has been output or will be output.

[0078] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a method for investigating hidden dangers in highway bridges based on multi-device collaboration) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0079] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0080] Figure 3 Only electronic devices with components are shown; those skilled in the art will understand that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0081] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0082] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0083] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0084] The program for identifying potential hazards in highway bridges based on multi-device collaboration, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following: Receive a bridge hazard investigation instruction, identify the bridge to be investigated based on the bridge hazard investigation instruction, and identify m investigation points and m investigation devices on the bridge to be investigated. The investigation points and investigation devices are one-to-one, and each investigation device is equipped with n sensors. By synchronizing the clocks of m inspection devices, m synchronization devices are obtained, where each synchronization device corresponds one-to-one with an inspection point. Perform the following operation on each of the m synchronization devices: Based on a preset collaborative acquisition protocol, the n sensors equipped with the synchronization device are used to collaboratively acquire data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The hazard values ​​are summarized to obtain m hazard values, where each hazard value corresponds one-to-one with an inspection point; Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

[0085] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0086] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0087] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Receive a bridge hazard investigation instruction, identify the bridge to be investigated based on the bridge hazard investigation instruction, and identify m investigation points and m investigation devices on the bridge to be investigated. The investigation points and investigation devices are one-to-one, and each investigation device is equipped with n sensors. By synchronizing the clocks of m inspection devices, m synchronization devices are obtained, where each synchronization device corresponds one-to-one with an inspection point. Perform the following operation on each of the m synchronization devices: Based on a preset collaborative acquisition protocol, the n sensors equipped with the synchronization device are used to collaboratively acquire data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The hazard values ​​are summarized to obtain m hazard values, where each hazard value corresponds one-to-one with an inspection point; Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

[0088] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0089] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0091] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for identifying potential hazards in highway bridges based on multi-device collaboration, characterized in that, The method includes: Receive a bridge hazard investigation instruction, identify the bridge to be investigated based on the bridge hazard investigation instruction, and identify m investigation points and m investigation devices on the bridge to be investigated. The investigation points and investigation devices are one-to-one, and each investigation device is equipped with n sensors. By synchronizing the clocks of m inspection devices, m synchronization devices are obtained, where each synchronization device corresponds one-to-one with an inspection point. Perform the following operation on each of the m synchronization devices: Based on a preset collaborative acquisition protocol, the n sensors equipped with the synchronization device are used to collaboratively acquire data from the bridges to be investigated, resulting in n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by its actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The hazard values ​​are summarized to obtain m hazard values, where each hazard value corresponds one-to-one with an inspection point; Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

2. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 1, characterized in that, The process of synchronizing the clocks of m investigation devices to obtain m synchronized devices includes: Confirm the device clock of each of the m investigated devices to obtain m device clocks to be calibrated, where each device clock corresponds one-to-one with an investigated device; Calculate the reference clock based on the clocks of m devices to be calibrated; For each of the m device clocks to be calibrated, perform the following operation: Calculate the absolute difference between the clock of the device to be calibrated and the reference clock to obtain the absolute clock difference, and compare the absolute clock difference with the preset clock difference threshold. If the absolute clock difference is less than or equal to the clock difference threshold, the investigation device corresponding to the absolute clock difference is used as the synchronization device; Otherwise, the clock of the troubleshooting device corresponding to the absolute clock difference is corrected using the reference clock to obtain the corrected device. The clock of the corrected device corresponding to the corrected device is confirmed. When the absolute difference between the clock of the corrected device and the reference clock is less than or equal to the clock difference threshold, the troubleshooting device corresponding to the absolute clock difference is used as the synchronization device. The number of synchronization devices is summarized to obtain m synchronization devices.

3. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 2, characterized in that, The step of calculating the reference clock based on the clocks of m devices to be calibrated includes: Compare m with a preset stratification threshold. If m is greater than the stratification threshold, cluster the m device clocks to be calibrated to obtain a groups of device clocks to be calibrated, where each group of device clocks to be calibrated contains multiple device clocks to be calibrated. Perform the following operation on each of the a clock groups of devices to be calibrated: Extract the clocks of the devices to be calibrated sequentially from the clock group of devices to be calibrated, and remove the clocks of the devices to be calibrated from the clock group of devices to be calibrated to obtain the remaining clock group of devices; Calculate the squared distance between the extracted clock of the device to be calibrated and the clock of the device to be calibrated in the remaining clock group, and obtain the squared clock distance value. Summarize the squared clock distance values ​​to obtain multiple squared clock distance values, where each squared clock distance value corresponds one-to-one with the clock of the device to be calibrated. The smallest clock distance squared value is selected from multiple clock distance squared values, and the clock of the device to be corrected corresponding to the smallest clock distance squared value is used as the reference clock for the cluster group. Summarize the cluster group reference clocks to obtain a cluster group reference clocks; The reference clock is identified from the reference clocks of cluster groups a.

4. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 3, characterized in that, The method involves using n sensors equipped with a synchronization device to collaboratively collect data from the bridges to be inspected, resulting in n bridge data sets, including: Obtain a bridge data acquisition configuration table with n sensors. The bridge data acquisition configuration table includes n data acquisition task nodes, and each data acquisition task node includes: acquisition frequency and acquisition time period. Each data acquisition task node has a different acquisition frequency but the same acquisition time period. Based on the n acquisition task nodes, the n sensors equipped with the synchronization device are task-bound to obtain n sensor task nodes, wherein the sensor task nodes include: sensors and acquisition task nodes; Perform the following operation on each of the n sensor task nodes: Using the sensors corresponding to the sensor task nodes, and according to the acquisition frequency and acquisition time period corresponding to the acquisition task nodes, the acquisition points corresponding to the synchronous devices in the bridge to be investigated are collected to obtain the bridge acquisition dataset. Summarize the bridge data collection datasets to obtain n bridge data collection datasets.

5. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 4, characterized in that, The process of synchronizing n bridge data sets in time to obtain a bridge synchronization dataset includes: Extract bridge data sets sequentially from n bridge data sets, and perform the following operations on the extracted bridge data sets: Set the current time, identify the closest and furthest actual collection times from the bridge data collection dataset, and obtain the collection end time and collection start time. Construct a data collection time interval with the start time of data collection as the start time of the interval and the end time of data collection as the end time of the interval. By summing the data collection time intervals, we obtain n data collection time intervals; Perform an intersection operation on n collection time intervals to obtain a synchronization time interval. Divide the synchronization time interval into b sub-intervals according to a preset time length, where each sub-interval contains the midpoint of the sub-interval. By using b sub-intervals to perform time-series synchronization on n bridge data sets, a bridge synchronization dataset is obtained.

6. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 5, characterized in that, The method of using b sub-intervals to perform time-series synchronization of n bridge data sets yields a bridge synchronization dataset, including: Extract bridge data sets sequentially from n bridge data sets, and perform the following operations on the extracted bridge data sets: Extract sub-intervals sequentially from b sub-intervals, traverse the bridge acquisition data in the bridge acquisition dataset that falls within the sub-intervals, and obtain the interval acquisition dataset, wherein the interval acquisition dataset contains one or more bridge acquisition data. If the interval collection dataset contains only one bridge collection data, then the bridge collection data shall be used as the bridge clustering data; Otherwise, calculate the mean of all bridge data collected in the interval collection dataset to obtain bridge cluster data; Summarize the bridge cluster data to obtain b bridge cluster data, where each bridge cluster data corresponds one-to-one with a sub-interval; Summarize b bridge cluster data corresponding to each bridge data set in n bridge data sets to obtain c bridge cluster data sets, where c equals b multiplied by n; Based on b sub-intervals, the c bridge cluster data are divided into b bridge cluster data groups, where the sub-intervals corresponding to the bridge cluster data in each bridge cluster data group are the same. Perform the following operation on each of the b bridge cluster data groups: Calculate the mean of the bridge cluster data contained in the bridge cluster data group to obtain the bridge synchronization data, and summarize the bridge synchronization data to obtain the bridge synchronization dataset.

7. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 6, characterized in that, The step of calculating the hazard value of the inspection point corresponding to the bridge synchronous dataset based on the bridge synchronous dataset includes: Identify the types of the n sensors corresponding to the bridge synchronization dataset to obtain the sensor types; Using the sensor type, f sets of mapping relationships corresponding to the sensor type are retrieved from a pre-constructed hazard mapping table, wherein each set of mapping relationships contains a mapping interval and a mapping value; Bridge synchronization data are extracted sequentially from the bridge synchronization dataset. Using the bridge synchronization data, the corresponding mapping value is determined in the f groups of mapping relationships, wherein the bridge synchronization data is located within the mapping interval corresponding to the mapping value. Summarize the mapping values ​​to obtain a mapping value set, identify the largest mapping value from the mapping value set, and use the largest mapping value as the hidden danger value.

8. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 7, characterized in that, The step of fusing m potential hazard values ​​across devices based on the m inspection points to obtain a fused potential hazard value includes: The bridge structure of the bridge to be investigated is identified. Based on the bridge structure, the influence coefficient corresponding to each of the m investigation points is identified, resulting in m structural influence coefficients, where each structural influence coefficient corresponds one-to-one with an investigation point. Calculate the sum of m structural influence coefficients to obtain the comprehensive structural influence coefficient. Calculate the ratio of each of the m structural influence coefficients to the comprehensive structural influence coefficient to obtain m point weights, where each point weight corresponds one-to-one with the investigation point and the hidden danger value. The fused hazard value is calculated using the weights of m points and m hazard values, as shown in the following formula: in, This represents the fusion risk value. This represents the m-th hazard value. One potential hazard value, This represents the m-th hazard value. The point weight corresponding to each potential hazard value.

9. The method for identifying potential hazards in highway bridges based on multi-device collaboration as described in claim 8, characterized in that, The determination of the investigation results of the bridge to be investigated based on the fusion hazard value and m hazard values ​​includes: The hazard indication value is calculated based on the combined hazard value and m individual hazard values, using the following formula: in, This indicates the hazard indication value. This represents the fusion risk value. This indicates the preset threshold for potential hazards. This represents the m-th hazard value. One potential hazard value, This indicates the preset threshold for single-point hazards. () indicates a preset indicator function that returns 1 if the condition is true, and 0 otherwise. Indicates the threshold identifier; If the hazard indicator value is not 0, the inspection results of the bridge to be inspected will be confirmed as having a hazard. Otherwise, the results of the investigation of the bridge to be investigated will be confirmed as having no hidden dangers.

10. A highway bridge hazard investigation system based on multi-device collaboration, characterized in that, The system includes: The inspection equipment deployment module is used to receive bridge hazard inspection instructions, identify the bridge to be inspected based on the bridge hazard inspection instructions, and identify m inspection points and m inspection equipment on the bridge to be inspected. The inspection points and inspection equipment are one-to-one, and each inspection equipment is equipped with n sensors. The equipment clock synchronization module is used to synchronize the clocks of m investigated devices to obtain m synchronized devices, where each synchronized device corresponds one-to-one with an investigated point. The collaborative acquisition module is used to collect data from the bridges to be investigated using n sensors equipped with the synchronization device based on a preset collaborative acquisition protocol, and to obtain n bridge acquisition datasets. Each bridge acquisition dataset contains multiple bridge acquisition data, and each bridge acquisition data is identified by the actual acquisition time. Synchronize n bridge data sets in time to obtain a bridge synchronization dataset, and calculate the hazard value of the inspection point corresponding to the bridge synchronization dataset based on the bridge synchronization dataset; The cross-device fusion module is used to aggregate hazard values ​​and obtain m hazard values, where each hazard value corresponds one-to-one with an investigation point; Based on the m inspection points, the m hazard values ​​are fused across devices to obtain the fused hazard value. The inspection result of the bridge to be inspected is determined based on the fused hazard value and the m hazard values. The inspection result is either that there is a hazard or that there is no hazard. Based on the inspection result, the hazard inspection of highway bridges based on multi-device collaboration is realized.

Images