Cloud-edge collaborative bridge crack detection method and system

Abstract

The cloud-edge collaborative bridge crack detection method and system of this application can determine whether the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match, and whether the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match. If the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match, and the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match, then the first bridge crack detection report and the second bridge crack detection report are determined to be related bridge crack detection reports. Thus, by combining the detection area and crack category of the bridge crack detection reports, it is determined whether the two sets of bridge crack detection reports are related bridge crack detection reports, thereby improving the accuracy of determining related bridge crack detection reports.

Description

Technical Field

[0001] This application relates to the field of bridge crack detection technology, and in particular to a cloud-edge collaborative bridge crack detection method and system. Background Technology

[0002] When performing bridge crack detection and analysis based on cloud-edge collaboration, improving the accuracy of determining associated bridge crack detection reports is one of the current technical challenges. Summary of the Invention

[0003] To address the technical problems existing in related technologies, this application provides a cloud-edge collaborative bridge crack detection method and system.

[0004] In a first aspect, embodiments of this application provide a cloud-edge collaborative bridge crack detection method, applied to a bridge crack detection system, the method comprising:

[0005] Obtain the first infrared thermal distribution and the first load-related variable from the first bridge crack detection report, and obtain the second infrared thermal distribution and the second load-related variable from the second bridge crack detection report;

[0006] Based on the first infrared thermal distribution and the second infrared thermal distribution, it is determined whether the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match. Based on the first load-related variable and the second load-related variable, it is determined whether the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match.

[0007] If the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match, and the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match, then the first bridge crack detection report and the second bridge crack detection report are determined to be associated bridge crack detection reports.

[0008] In some optional embodiments, determining whether the detection areas of the first bridge crack detection report and the second bridge crack detection report match based on the first infrared thermal distribution and the second infrared thermal distribution includes:

[0009] Determine the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution;

[0010] If the first Pearson correlation coefficient is greater than the first preset coefficient value, then it is determined that the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match.

[0011] The step of determining whether the crack categories in the first bridge crack detection report and the second bridge crack detection report match using the first load-related variable and the second load-related variable includes:

[0012] Determine the second Pearson correlation coefficient between the first load-related variable and the second load-related variable;

[0013] If the second Pearson correlation coefficient is greater than the second preset coefficient value, then the crack category in the first bridge crack detection report and the crack category in the second bridge crack detection report are determined to match.

[0014] In some optional embodiments, the step of determining that the first bridge crack detection report and the second bridge crack detection report are associated bridge crack detection reports in response to a match between the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report, and a match between the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report, includes:

[0015] A third Pearson correlation coefficient between the first bridge crack detection report and the second bridge crack detection report is determined using the first Pearson correlation coefficient and the second Pearson correlation coefficient.

[0016] If the third Pearson correlation coefficient is greater than the third preset coefficient value, then the first bridge crack detection report and the second bridge crack detection report are determined to be related bridge crack detection reports.

[0017] In some optional embodiments, the first infrared thermal distribution includes a third infrared thermal distribution for each first bridge crack detection entry in the first bridge crack detection report, and the second infrared thermal distribution includes a fourth infrared thermal distribution for each second bridge crack detection entry in the second bridge crack detection report, wherein each first bridge crack detection entry corresponds to one second bridge crack detection entry.

[0018] The acquisition of the first infrared thermal distribution of the first bridge crack detection report and the acquisition of the second infrared thermal distribution of the second bridge crack detection report include:

[0019] The first bridge crack detection report and the second bridge crack detection report are adjusted respectively to obtain the first adjusted bridge crack detection report and the second adjusted bridge crack detection report.

[0020] Both the first adjusted bridge crack detection report and the second adjusted bridge crack detection report are divided into multiple first bridge crack detection items and multiple second bridge crack detection items, respectively.

[0021] The third infrared thermal distribution of each first bridge crack detection item and the fourth infrared thermal distribution of the second bridge crack detection item corresponding to each first bridge crack detection item are obtained respectively.

[0022] In some optional embodiments, determining the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution includes:

[0023] The Pearson correlation coefficients between the third infrared thermal distribution of each first bridge crack detection item and the fourth infrared thermal distribution of the second bridge crack detection item corresponding to each first bridge crack detection item are determined respectively, resulting in multiple fourth Pearson correlation coefficients.

[0024] The average Pearson correlation coefficient of the plurality of fourth Pearson correlation coefficients is determined as the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution.

[0025] In some optional embodiments, the first infrared thermal distribution includes the first infrared thermal data and the first stress detection feedback data in the first bridge crack detection report, and the second infrared thermal distribution includes the second infrared thermal data and the second stress detection feedback data in the second bridge crack detection report.

[0026] The step of determining whether the detection areas of the first bridge crack detection report and the second bridge crack detection report match based on the first infrared thermal distribution and the second infrared thermal distribution includes:

[0027] Based on the first infrared thermal data and the second infrared thermal data, a first correlation confidence level between the first bridge crack detection report and the second bridge crack detection report is determined;

[0028] Based on the first stress detection feedback data and the second stress detection feedback data, a second correlation confidence level between the first bridge crack detection report and the second bridge crack detection report is determined.

[0029] The first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution is determined using the first correlation confidence level and the second correlation confidence level.

[0030] If the first Pearson correlation coefficient is greater than the first preset coefficient value, then the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report are determined to match.

[0031] In some optional embodiments, the first load-related variable of the first bridge crack detection report includes the third load-related variable of each first bridge crack detection report cluster in the first bridge crack detection report, and the second load-related variable of the second bridge crack detection report includes the fourth load-related variable of each second bridge crack detection report cluster in the second bridge crack detection report, wherein each first bridge crack detection report cluster corresponds to one second bridge crack detection report cluster.

[0032] Determining the second Pearson correlation coefficient between the first load-related variable and the second load-related variable includes:

[0033] The Pearson correlation coefficients between the third load-related variable of each first bridge crack detection report cluster and the fourth load-related variable of the second bridge crack detection report cluster corresponding to each first bridge crack detection report cluster are determined respectively, resulting in multiple fifth Pearson correlation coefficients.

[0034] The mean of the plurality of fifth Pearson correlation coefficients is determined as the second Pearson correlation coefficient between the first load-related variable and the second load-related variable.

[0035] In some optional embodiments, the method further includes:

[0036] Using the first load-related variable, the first infrared thermal distribution, the second load-related variable, and the second infrared thermal distribution, a text discrimination model is used to determine whether the first bridge crack detection report and the second bridge crack detection report are related bridge crack detection reports.

[0037] Secondly, this application also provides a bridge crack detection system, including a processor and a memory; the processor and the memory are communicatively connected, and the processor is used to read a computer program from the memory and execute it to implement the above-described method.

[0038] Thirdly, this application also provides a computer-readable storage medium having a program stored thereon that, when executed by a processor, implements the above-described method.

[0039] In this embodiment, the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report are used to determine whether they match. Furthermore, the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report are used to determine whether they match. If the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match, and the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match, then the first bridge crack detection report and the second bridge crack detection report are determined to be related bridge crack detection reports. This improves the accuracy of determining related bridge crack detection reports by combining the detection area and crack category of the bridge crack detection reports. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this application, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] Figure 1 This is a schematic flowchart of a cloud-edge collaborative bridge crack detection method provided in an embodiment of this application.

[0042] Figure 2 This is a block diagram of a bridge crack detection system provided in an embodiment of this application. Detailed Implementation

[0043] The method embodiments provided in this application can be executed in a bridge crack detection system, a bridge crack detection system, or a similar computing device. Taking a bridge crack detection system as an example, the bridge crack detection system may include one or more processors and a memory for storing data. Optionally, the bridge crack detection system may also include a transmission device for communication functions. Those skilled in the art will understand that the above structure is merely illustrative and does not limit the structure of the bridge crack detection system. For example, the bridge crack detection system may include more or fewer components than shown above, or have a different configuration than shown above. The memory can be used to store computer programs, such as application software programs and modules, such as the computer program corresponding to one of the methods described in this application embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby implementing the above method. The memory may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the bridge crack detection system via a network. Examples of such networks include, but are not limited to, enterprise intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for a bridge crack detection system.

[0044] Based on the above introduction to bridge crack detection systems, please refer to [the relevant literature / reference]. Figure 1 , Figure 1 This is an exemplary implementation of a cloud-edge collaborative bridge crack detection method provided in this application embodiment, which may further include steps 10-30.

[0045] Step 10: Obtain the first infrared thermal distribution and the first load-related variable from the first bridge crack detection report, and obtain the second infrared thermal distribution and the second load-related variable from the second bridge crack detection report.

[0046] Step 20: Determine whether the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match by using the first infrared thermal distribution and the second infrared thermal distribution; and determine whether the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match by using the first load-related variable and the second load-related variable.

[0047] Step 30: In response to the matching of the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report, and the matching of the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report, the first bridge crack detection report and the second bridge crack detection report are determined to be associated bridge crack detection reports.

[0048] Preferably, determining whether the detection areas of the first bridge crack detection report and the second bridge crack detection report match based on the first infrared thermal distribution and the second infrared thermal distribution includes: determining a first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution; and determining that the detection areas of the first bridge crack detection report and the second bridge crack detection report match if the first Pearson correlation coefficient is greater than a first preset coefficient value. Determining whether the crack categories of the first bridge crack detection report and the second bridge crack detection report match based on the first load-related variable and the second load-related variable includes: determining a second Pearson correlation coefficient between the first load-related variable and the second load-related variable; and determining that the crack categories of the first bridge crack detection report and the second bridge crack detection report match if the second Pearson correlation coefficient is greater than a second preset coefficient value.

[0049] Preferably, the step of determining the first bridge crack detection report and the second bridge crack detection report as associated bridge crack detection reports in response to a match between the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report, and a match between the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report, includes: determining a third Pearson correlation coefficient between the first bridge crack detection report and the second bridge crack detection report using the first Pearson correlation coefficient and the second Pearson correlation coefficient; and determining the first bridge crack detection report and the second bridge crack detection report as associated bridge crack detection reports in response to a third preset coefficient value.

[0050] Preferably, the first infrared thermal distribution includes the third infrared thermal distribution of each first bridge crack detection item in the first bridge crack detection report, and the second infrared thermal distribution includes the fourth infrared thermal distribution of each second bridge crack detection item in the second bridge crack detection report, wherein each first bridge crack detection item corresponds to one second bridge crack detection item; obtaining the first infrared thermal distribution of the first bridge crack detection report and obtaining the second infrared thermal distribution of the second bridge crack detection report includes: adjusting the first bridge crack detection report and the second bridge crack detection report respectively to obtain a first adjusted bridge crack detection report and a second adjusted bridge crack detection report; dividing the first adjusted bridge crack detection report and the second adjusted bridge crack detection report into multiple first bridge crack detection items and multiple second bridge crack detection items respectively; obtaining the third infrared thermal distribution of each first bridge crack detection item and the fourth infrared thermal distribution of the second bridge crack detection item corresponding to each first bridge crack detection item respectively.

[0051] Preferably, determining the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution includes: determining the Pearson correlation coefficient between the third infrared thermal distribution of each first bridge crack detection item and the fourth infrared thermal distribution of the second bridge crack detection item corresponding to each first bridge crack detection item, thereby obtaining a plurality of fourth Pearson correlation coefficients; and determining the average of the plurality of fourth Pearson correlation coefficients as the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution.

[0052] Preferably, the first infrared thermal distribution includes first infrared thermal data and first stress detection feedback data from the first bridge crack detection report, and the second infrared thermal distribution includes second infrared thermal data and second stress detection feedback data from the second bridge crack detection report. Determining whether the detection areas of the first and second bridge crack detection reports match using the first and second infrared thermal distributions includes: determining a first correlation confidence level between the first and second bridge crack detection reports using the first and second infrared thermal data; determining a second correlation confidence level between the first and second bridge crack detection reports using the first and second stress detection feedback data; determining a first Pearson correlation coefficient between the first and second infrared thermal distributions using the first and second correlation confidence levels; and determining a first Pearson correlation coefficient between the first and second infrared thermal distributions using the first and second correlation confidence levels. If the first Pearson correlation coefficient is greater than a first preset coefficient value, then the detection areas of the first and second bridge crack detection reports are determined to match.

[0053] Preferably, the first load-related variable in the first bridge crack detection report includes the third load-related variable of each first bridge crack detection report cluster in the first bridge crack detection report, and the second load-related variable in the second bridge crack detection report includes the fourth load-related variable of each second bridge crack detection report cluster in the second bridge crack detection report, wherein each first bridge crack detection report cluster corresponds to one second bridge crack detection report cluster. Based on this, determining the second Pearson correlation coefficient between the first load-related variable and the second load-related variable includes: determining the Pearson correlation coefficient between the third load-related variable of each first bridge crack detection report cluster and the fourth load-related variable of the second bridge crack detection report cluster corresponding to each first bridge crack detection report cluster, thereby obtaining a plurality of fifth Pearson correlation coefficients; and determining the average of the Pearson correlation coefficients of the plurality of fifth Pearson correlation coefficients as the second Pearson correlation coefficient between the first load-related variable and the second load-related variable.

[0054] In some optional embodiments, the method further includes: determining, using a text discrimination model, whether the first bridge crack detection report and the second bridge crack detection report are related bridge crack detection reports based on the first load-related variable, the first infrared thermal distribution, the second load-related variable, and the second infrared thermal distribution.

[0055] Based on the same inventive concept, a computer-readable storage medium is also provided, on which a program is stored, which, when executed by a processor, implements the above-described method.

[0056] Based on the same inventive concept, please refer to [the relevant documentation / reference]. Figure 2 A bridge crack detection system 20 is also provided, including a processor 210 and a memory 220; the processor 210 and the memory 200 are communicatively connected, and the processor 210 is used to read a computer program from the memory 220 and execute it to implement the above-described method.

[0057] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0058] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this application.

[0059] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the gateway, proxy server, or system according to the embodiments of this application. This application can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0060] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A cloud-edge collaborative method for detecting bridge cracks, characterized in that, The method, applied to a bridge crack detection system, includes: Obtain the first infrared thermal distribution and the first load-related variable from the first bridge crack detection report, and obtain the second infrared thermal distribution and the second load-related variable from the second bridge crack detection report; Based on the first infrared thermal distribution and the second infrared thermal distribution, it is determined whether the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match. Based on the first load-related variable and the second load-related variable, it is determined whether the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match. If the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match, and the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match, then the first bridge crack detection report and the second bridge crack detection report are determined to be associated bridge crack detection reports.

2. The method as described in claim 1, characterized in that, The step of determining whether the detection areas of the first bridge crack detection report and the second bridge crack detection report match based on the first infrared thermal distribution and the second infrared thermal distribution includes: Determine the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution; If the first Pearson correlation coefficient is greater than the first preset coefficient value, then it is determined that the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match. The step of determining whether the crack categories in the first bridge crack detection report and the second bridge crack detection report match using the first load-related variable and the second load-related variable includes: Determine the second Pearson correlation coefficient between the first load-related variable and the second load-related variable; If the second Pearson correlation coefficient is greater than the second preset coefficient value, then the crack category in the first bridge crack detection report and the crack category in the second bridge crack detection report are determined to match.

3. The method as described in claim 2, characterized in that, The condition that the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report match, and the crack category of the first bridge crack detection report and the crack category of the second bridge crack detection report match, then the first bridge crack detection report and the second bridge crack detection report are determined to be associated bridge crack detection reports, including: A third Pearson correlation coefficient between the first bridge crack detection report and the second bridge crack detection report is determined using the first Pearson correlation coefficient and the second Pearson correlation coefficient. If the third Pearson correlation coefficient is greater than the third preset coefficient value, then the first bridge crack detection report and the second bridge crack detection report are determined to be related bridge crack detection reports.

4. The method as described in claim 2, characterized in that, The first infrared thermal distribution includes the third infrared thermal distribution of each first bridge crack detection entry in the first bridge crack detection report, and the second infrared thermal distribution includes the fourth infrared thermal distribution of each second bridge crack detection entry in the second bridge crack detection report, wherein each first bridge crack detection entry corresponds to one second bridge crack detection entry. The acquisition of the first infrared thermal distribution of the first bridge crack detection report and the acquisition of the second infrared thermal distribution of the second bridge crack detection report include: The first bridge crack detection report is adjusted to obtain the first adjusted bridge crack detection report, and the second bridge crack detection report is adjusted to obtain the second adjusted bridge crack detection report. The first adjusted bridge crack detection report is divided into multiple first bridge crack detection items, and the second adjusted bridge crack detection report is divided into multiple second bridge crack detection items. The third infrared thermal distribution of each first bridge crack detection item and the fourth infrared thermal distribution of the second bridge crack detection item corresponding to each first bridge crack detection item are obtained respectively.

5. The method as described in claim 4, characterized in that, Determining the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution includes: The Pearson correlation coefficients between the third infrared thermal distribution of each first bridge crack detection item and the fourth infrared thermal distribution of the second bridge crack detection item corresponding to each first bridge crack detection item are determined respectively, resulting in multiple fourth Pearson correlation coefficients. The average Pearson correlation coefficient of the plurality of fourth Pearson correlation coefficients is determined as the first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution.

6. The method as described in claim 1, characterized in that, The first infrared thermal distribution includes the first infrared thermal data and the first stress detection feedback data in the first bridge crack detection report; the second infrared thermal distribution includes the second infrared thermal data and the second stress detection feedback data in the second bridge crack detection report. The step of determining whether the detection areas of the first bridge crack detection report and the second bridge crack detection report match based on the first infrared thermal distribution and the second infrared thermal distribution includes: Based on the first infrared thermal data and the second infrared thermal data, a first correlation confidence level between the first bridge crack detection report and the second bridge crack detection report is determined; Based on the first stress detection feedback data and the second stress detection feedback data, a second correlation confidence level between the first bridge crack detection report and the second bridge crack detection report is determined. The first Pearson correlation coefficient between the first infrared thermal distribution and the second infrared thermal distribution is determined using the first correlation confidence level and the second correlation confidence level. If the first Pearson correlation coefficient is greater than the first preset coefficient value, then the detection area of ​​the first bridge crack detection report and the detection area of ​​the second bridge crack detection report are determined to match.

7. The method as described in claim 2, characterized in that, The first load-related variable in the first bridge crack detection report includes the third load-related variable of each first bridge crack detection report cluster in the first bridge crack detection report; the second load-related variable in the second bridge crack detection report includes the fourth load-related variable of each second bridge crack detection report cluster in the second bridge crack detection report; and each first bridge crack detection report cluster corresponds to one second bridge crack detection report cluster. Determining the second Pearson correlation coefficient between the first load-related variable and the second load-related variable includes: The Pearson correlation coefficients between the third load-related variable of each first bridge crack detection report cluster and the fourth load-related variable of the second bridge crack detection report cluster corresponding to each first bridge crack detection report cluster are determined respectively, resulting in multiple fifth Pearson correlation coefficients. The mean of the plurality of fifth Pearson correlation coefficients is determined as the second Pearson correlation coefficient between the first load-related variable and the second load-related variable.

8. The method as described in claim 1, characterized in that, The method further includes: Using the first load-related variable, the first infrared thermal distribution, the second load-related variable, and the second infrared thermal distribution, a text discrimination model is used to determine whether the first bridge crack detection report and the second bridge crack detection report are related bridge crack detection reports.

9. A bridge crack detection system, characterized in that, It includes a processor and a memory; the processor and the memory are communicatively connected, and the processor is configured to read a computer program from the memory and execute it to implement the method of any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, It stores a program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images