Bridge damage detection method, device and equipment and readable storage medium
By acquiring and analyzing bridge damage image data, combining historical data and sensor data to predict the development trend of bridge damage, the problem of inaccurate prediction of damage development in the existing technology is solved, and accurate detection and maintenance prompts of bridge damage are achieved.
Patent Information
- Application Number
- CN202411170763.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing bridge damage detection scheme cannot accurately predict the development of the damage, and only targets the detection of the damage without judging the damage trend.
By obtaining damage image data at the bridge damage location, judging the damage type, and predicting the development trend of damage based on the relationship between historical image data and damage type. Use displacement sensor groups and flatness meter to obtain data, combine drone scanning and feature data comparison, divide damage levels, and output defect or maintenance prompt information.
Accurate prediction of bridge damage is achieved, and the overall defect inspection and maintenance tips for bridges are provided, ensuring the safety and effective maintenance of the bridge.
Smart Images

Figure CN119027403A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of building quality inspection, and in particular to a method, device, equipment and readable storage medium for detecting bridge damage. Background Art
[0002] As an important building used to cross rivers, valleys or other transportation lines, bridges play a vital role in the transportation process; the inspection of bridge projects is an important basis for ensuring the normal use of bridges and carrying out maintenance and reinforcement.
[0003] During the process of being put into use, bridges will inevitably suffer certain damage over time. Existing bridge damage detection schemes mostly only detect bridge damage and rarely involve the judgment of damage trends. However, bridge damage always shows a trend of accelerating as the damage expands. Therefore, existing bridge detection schemes cannot accurately predict the development of damage. Summary of the invention
[0004] Based on this, it is necessary to provide a bridge damage detection method, device, equipment and readable storage medium to address the above technical problems.
[0005] In a first aspect, the present application provides a method for detecting bridge damage, the method comprising:
[0006] In response to acquiring damage image data of a damage position of the bridge within a preset survey period, determining a damage type of the damage position based on the damage image data;
[0007] Obtaining and based on the historical image data of multiple continuous time nodes corresponding to the damage type, obtaining the damage correspondence relationship between different historical image data under each damage type and the damage degree of the bridge;
[0008] Based on the damage image data and damage correspondence, the damage development trend of the damaged position of the bridge is predicted.
[0009] In one embodiment, the method further comprises:
[0010] Receive in real time the bridge deflection data measured by the displacement sensor group segmentedly set on the bridge, and the road surface smoothness data measured by the smoothness meter;
[0011] In response to the change rate of the bridge deflection data exceeding a first preset percentage, or the change rate of the road surface flatness data exceeding a second preset percentage, a drone equipped with a high-definition camera is dispatched to scan the bridge to find the damaged location of the bridge and obtain damage image data of the damaged location of the bridge.
[0012] In one embodiment, the damage types include erosion damage, crack damage, and uneven foundation settlement damage; based on the historical image data of multiple continuous time nodes corresponding to the damage types, the step of obtaining the damage correspondence relationship between different historical image data under each damage type and the damage degree of the bridge includes:
[0013] According to the influence on the strength of the bridge structure from small to large, the damage degree is divided into multiple levels in sequence according to the first preset rule;
[0014] The feature data corresponding to the damage type in the historical images of each continuous time node are extracted, and each feature value in the feature data is corresponded to each level of damage degree according to multiple preset threshold values from small to large, so as to obtain the damage correspondence relationship; wherein: when the damage type is erosion damage, the feature values in the feature data include erosion area, erosion depth and exposed steel bar area; when the damage type is crack damage, the feature values include crack length, crack width and crack depth; when the damage type is uneven foundation settlement damage, the feature values include the number of settlement points exceeding the preset settlement value, and the settlement depth of each settlement point.
[0015] In one embodiment, the step of predicting the development trend of damage at a bridge damage location includes:
[0016] Extracting damage images corresponding to each continuous time node in a preset survey period from the damage image data;
[0017] Selecting historical image data according to the damage type of the damage image, and performing feature comparison between the historical image data and the damage image;
[0018] According to the comparison results of feature comparison and the damage correspondence, the damaged image is divided into corresponding damage degree levels;
[0019] When the damage image is divided into more than a preset number of levels, bridge defect prompt information is output, otherwise bridge maintenance prompt information is output; wherein: the bridge defect prompt information is used to instruct the overall defect inspection of the bridge; the bridge maintenance prompt information is used to instruct the maintenance of the current bridge damage location.
[0020] In one embodiment, the method further comprises:
[0021] In response to the output of the bridge defect prompt information, the structural strength analysis of the concrete at the damaged position of the bridge is performed based on the pre-extracted concrete specimen of the bridge, and the formula is as follows:
[0022]
[0023] In the formula, Strength is the structural strength parameter of concrete; x iis the circularity coefficient of each pore in concrete; w i is the weight corresponding to each pore in concrete; S, F is the porosity of concrete; Z 2 is the discreteness of the pores in concrete;
[0024] If the concrete structure strength parameter is less than the first preset value, an evaluation result indicating that the concrete structure strength is poor is output; otherwise, an evaluation result indicating that the concrete structure strength is moderate is output.
[0025] In one embodiment, the method further comprises:
[0026] In response to outputting bridge maintenance prompt information and the damage being erosion damage or crack damage, obtaining a characteristic value of the erosion damage or crack damage;
[0027] When the characteristic value of the erosion damage is below the second preset value or the crack damage is below the third preset value, outputting prompt information for repairing by concrete;
[0028] When the characteristic value of the erosion damage exceeds the second preset value or the crack damage exceeds the third preset value, a prompt message is outputted to chisel off the damage and re-use concrete construction.
[0029] In a second aspect, the present application further provides a bridge damage detection device, the device comprising:
[0030] A judgment module, configured to respond to the acquisition of damage image data of a bridge damage position within a preset survey period and to judge the damage type of the damage position based on the damage image data;
[0031] An acquisition module is used to acquire and obtain the damage correspondence between different historical image data and the damage degree of the bridge under each damage type based on the historical image data of multiple continuous time nodes corresponding to the damage type;
[0032] The prediction module is used to predict the development trend of damage at the damage location of the bridge based on the damage image data and the damage correspondence relationship.
[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first aspect of the present application are implemented.
[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present application.
[0035] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present application.
[0036] The above-mentioned bridge damage detection method, device, equipment and readable storage medium can obtain damage image data of the damaged position of the bridge within a certain survey period, determine which type of damage the damaged position belongs to based on the damage image data, and then obtain historical image data about this type of damage in a targeted manner based on the damage type, and obtain the correspondence between the historical image data and the degree of bridge damage under each damage type based on the historical image data. Finally, the damage image data found in the survey period are matched with the historical image data and the degree of bridge damage at each continuous time node, and then the existing damage image data are deduced according to the historical image data, so as to predict the development trend of the damage at the damaged position of the bridge, which effectively solves the problem that the existing bridge detection scheme cannot accurately predict the development of damage. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0038] Figure 1 It is a schematic diagram of the overall steps of a method for detecting bridge damage in one embodiment;
[0039] Figure 2 A schematic diagram of a process flow for obtaining a damage image of a bridge damage location in one embodiment;
[0040] Figure 3 is a schematic flow chart of a structural strength assessment step in one embodiment;
[0041] Figure 4 A schematic flow chart of a step of selecting a repair method for bridge damage in one embodiment;
[0042] Figure 5 Schematic diagram of the structure of a bridge damage detection device in one embodiment. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0044] In one embodiment, Figure 1 As shown, a bridge damage detection method is provided. This embodiment uses the method applied to a terminal as an example for illustration, and includes the following steps 102 to 106. Among them:
[0045] Step 102: in response to obtaining damage image data of a damaged position of a bridge within a preset survey period, determining a damage type of the damaged position based on the damage image data.
[0046] Specifically, the preset survey period may be a survey period set according to nodes where damage is commonly found on the bridge.
[0047] Furthermore, the survey cycle may be to continuously survey the bridge at fixed time intervals after a preset time node.
[0048] Specifically, the damage type in the image data can be identified based on existing algorithms by acquiring data features in the damaged image data; wherein the damage type can be the most representative damage type that occurs in the bridge.
[0049] Step 104 , obtaining and based on the historical image data of a plurality of continuous time nodes corresponding to the damage types, obtaining a damage correspondence relationship between different historical image data under each damage type and the damage degree of the bridge.
[0050] Specifically, the historical image data at consecutive time nodes can be used to indicate the development and change of existing bridge damage, and then the development and change of existing bridge damage can be corresponded to the historical image data at each time node.
[0051] Step 106: predicting the development trend of damage at the damaged position of the bridge based on the damage image data and the damage correspondence relationship.
[0052] Specifically, the damage image data may include multiple damage images within a preset survey period. In the specific implementation process, feature recognition can be performed on each damage image to find the closest historical image data, and the degree of bridge damage corresponding to each current damage image can be determined based on the correspondence between the historical image data and the degree of bridge damage. The development trend of damage in the damage image data can be judged based on the degree of bridge damage corresponding to each damage image. It is an existing technology to perform feature recognition on the damage image to find another group of similar images, which will not be repeated here.
[0053] Furthermore, the development trend of the injury may include changes in the condition of the injury under different injury types and the corresponding relationship between the development of the injury and time.
[0054] The bridge damage detection method provided in the present application can obtain damage image data of the damaged position of the bridge within a certain survey period, determine which type of damage the damaged position belongs to based on the damage image data, and then obtain historical image data about this type of damage in a targeted manner based on the damage type, and obtain the correspondence between the historical image data and the degree of bridge damage under each damage type based on the historical image data. Finally, the damage image data found in the survey period are matched with the historical image data and the degree of bridge damage at each continuous time node, and then the existing damage image data are deduced according to the historical image data, so as to predict the development trend of the damage at the damaged position of the bridge, which effectively solves the problem that the existing bridge detection scheme cannot accurately predict the development of damage.
[0055] In an exemplary embodiment, Figure 2 As shown, the bridge damage detection method further includes the following steps 202 to 204. Among them:
[0056] Step 202, receiving in real time the bridge deflection data measured by the displacement sensor group segmentedly arranged on the bridge, and the road surface smoothness data measured by the smoothness meter.
[0057] Specifically, in the case of a long bridge, multiple groups of displacement sensors may be installed in sections on the bridge to obtain and specifically determine the settlement change position of the bridge based on the deflection data of the bridge.
[0058] For example, when the bridge is short, only one set of displacement sensors may be provided.
[0059] Specifically, the smoothness measuring instrument may be a road surface smoothness measuring instrument, which is used to detect the unevenness of the road surface and preliminarily determine whether the road surface is damaged based on the unevenness.
[0060] Step 204, in response to the change rate of the bridge deflection data exceeding a first preset percentage, or the change rate of the road surface flatness data exceeding a second preset percentage, a drone equipped with a high-definition camera is dispatched to scan the bridge to find the damaged position of the bridge, and obtain damage image data of the damaged position of the bridge.
[0061] Specifically, when the change rate of the deflection data of the bridge exceeds the first preset percentage, it means that the bridge is bent and there is uneven settlement; when the change rate of the roadside flatness data exceeds the second preset percentage, it means that the bridge deck may have some damage.
[0062] Furthermore, the first preset percentage can be set according to the allowable settlement range of the bridge; the second preset percentage can be set according to the flatness of the road surface that can cause the car to experience obvious road bumps. The setting process can be combined with the needs of the specific implementation situation, and no specific restrictions are made here.
[0063] In an exemplary embodiment, the damage types include erosion damage, crack damage, and uneven foundation settlement damage; based on the historical image data of multiple continuous time nodes corresponding to the damage types, the step of obtaining the damage correspondence between different historical image data under each damage type and the damage degree of the bridge includes the following steps 1042 to 1044. Among them:
[0064] Step 1042, according to the influence on the strength of the bridge structure from small to large, the damage degree is divided into multiple levels in sequence according to the first preset rule.
[0065] Specifically, bridge damage can affect the local or overall structural strength of the bridge within a certain range. In the specific implementation process, the first preset rule may be to set the damage level that makes the bridge have a certain probability of collapse to the highest level, and to set the damage level that only affects the local structural strength of the bridge in the local range around the damage location to the lowest level; then use the highest and lowest damage levels as references, quantify the damage level according to the existing technology, and set multiple intermediate levels that ascend step by step according to the severity, and the specific setting of the levels is not specified here.
[0066] Step 1044, extracting feature data corresponding to the damage type in the historical images of each continuous time node, and corresponding each feature value in the feature data to each level of damage degree according to multiple preset threshold values from small to large, to obtain a damage correspondence relationship; wherein: when the damage type is erosion damage, the feature values in the feature data include erosion area, erosion depth and steel bar exposed area; when the damage type is crack damage, the feature values include crack length, crack width and crack depth; when the damage type is uneven foundation settlement damage, the feature values include the number of settlement points exceeding the preset settlement value, and the settlement depth of each settlement point.
[0067] Specifically, the feature data may be damage characteristics corresponding to the damage type obtained after a neural network has learned historical images of multiple consecutive time nodes, including damage characteristics corresponding to erosion damage, crack damage, and uneven foundation settlement damage.
[0068] Furthermore, the characteristic value can be based on the size of the damage corresponding to each damage type in the characteristic data. For example, when the damage type is crack damage, the characteristic value includes crack length, crack width and crack depth; when the damage type is uneven foundation settlement damage, the characteristic value includes the number of settlement points exceeding the preset settlement value, and the settlement depth of each settlement point.
[0069] In an exemplary embodiment, the step of predicting the development trend of damage at the damaged position of the bridge includes the following steps 1062 to 1068. Among them:
[0070] Step 1062: extract the damage image corresponding to each continuous time node in the preset survey period from the damage image data.
[0071] Specifically, each damaged image in the damaged image data may be correspondingly extracted according to the order of time nodes.
[0072] Step 1064, selecting historical image data according to the damage type of the damaged image, and performing feature comparison between the historical image data and the damaged image.
[0073] Specifically, after learning the characteristic data of image damage through existing technologies such as neural networks, a model is established. Each damaged image can be simultaneously identified through the learned neural network model, and the identified damaged images are then compared with the image features in the historical image data to find the damaged images corresponding to the historical images at each continuous time node in the historical image data, so as to facilitate the classification of the damaged images.
[0074] Step 1066, classifying the damaged image into corresponding damage degree levels according to the comparison result of the feature comparison and the damage correspondence.
[0075] Specifically, after finding out the damaged image corresponding to the historical image at each continuous time node in the historical image data, the damaged image is graded into corresponding damage degree levels.
[0076] Step 1068, when the damage image is classified to a level exceeding a preset number, output bridge defect prompt information, otherwise output bridge maintenance prompt information; wherein: the bridge defect prompt information is used to instruct the overall defect inspection of the bridge; the bridge maintenance prompt information is used to instruct the maintenance of the current bridge damage location.
[0077] It can be understood that each damage image has been assigned a corresponding level of damage. After the damage levels have been divided according to the preset rules, if each damage image corresponds to a different level within the preset period, it indicates that the development of the image damage has accelerated significantly. On the contrary, if each damage image corresponds to the same level, or the levels corresponding to each damage image only account for a preset number, it indicates that the damage has developed more slowly, that is, the development trend is slower.
[0078] Furthermore, the staff may determine whether the bridge needs to be repaired urgently or maintained according to the preset maintenance cycle based on the predicted damage trend.
[0079] Furthermore, if there is a rapid development trend, it also means that there may be problems with the materials used in the bridge. In this case, the entire bridge should be checked.
[0080] In an exemplary embodiment, Figure 3 As shown, the bridge damage detection method further includes the following steps 302 and 304. Among them:
[0081] Step 302, in response to outputting the bridge defect prompt information, a structural strength analysis of the concrete at the damaged position of the bridge is performed based on the pre-extracted concrete specimen of the bridge, and the formula is as follows:
[0082]
[0083] In the formula, Strength is the structural strength parameter of concrete; x i is the circularity coefficient of each pore in concrete; w i is the weight corresponding to each pore in concrete; S, F is the porosity of concrete; Z 2 The discreteness of the pores in concrete.
[0084] Specifically, a cross-sectional image of a concrete specimen may be obtained by performing CT scanning on the concrete specimen, and then the image may be analyzed to identify the number of pores in the image and calculate the size of each pore.
[0085] Furthermore, a weight can be assigned to each pore according to the size of the pore.
[0086] It is understandable that pores are related to the strength of concrete. During the process of water immersion or chemical infiltration, water injection and corrosion channels are easily formed. Once the channels are formed, the concrete is easily broken when subjected to stamping, thereby reducing the strength of the concrete. Therefore, this application uses pores as a separate reference quantity for the change in concrete strength, which is used to establish an evaluation mechanism for concrete related only to pores, forming a reference for the structural strength of concrete.
[0087] Furthermore, the formula for calculating the circularity coefficient of each pore is as follows:
[0088]
[0089] Where x is the circularity coefficient of the pore, A is the cross-sectional area of the pore, and C is the circumference of the cross section.
[0090] Based on the cross-sectional area data of concrete and the cross-sectional area data of each pore in concrete, the porosity of concrete is obtained. The formula is as follows:
[0091]
[0092] Where V is the porosity of concrete; A z is the sum of the areas of all pores, and H is the cross-sectional area of the concrete.
[0093] For example, the sum of the areas of the pores can be determined by the number of pixels of the pores in the CT image, and the area of the concrete can be determined by the total number of pixels in the CT image.
[0094] Furthermore, the degree of pore dispersion can be determined according to the following formula:
[0095]
[0096] Where n is the number of pores; a i is the distance from the center point of the i-th pore to the center point of the concrete section; It is the average distance from the center of each pore to the center point of the concrete interface.
[0097] Furthermore, the position of the center point of the concrete section can be determined based on the image edge data, and the position of the center point of the pore can be determined based on the pore boundary data, and then the discrete degree of the pore distribution in each concrete section can be determined according to the variance formula.
[0098] Furthermore, the closer the structural strength parameter is to 1, the smaller the influence of the pores on the structural strength is, and the closer it is to 0, the greater the influence of the pores on the structural strength is and the more unstable the concrete structure is.
[0099] Step 304: if the concrete structure strength parameter is less than the first preset value, output an evaluation result indicating that the concrete structure strength is poor; otherwise, output an evaluation result indicating that the concrete structure strength is moderate.
[0100] Specifically, the first preset value can be actually set based on different materials and mix ratios of concrete, or can be set by determining the relationship between the strength of concrete that can be put into practical application and the structural strength parameters through a limited number of experiments, and no specific restrictions are made here.
[0101] In an exemplary embodiment, Figure 4 As shown, the bridge damage detection method further includes the following steps 402 and 406. Among them:
[0102] Step 402: in response to outputting bridge maintenance prompt information and the damage being erosion damage or crack damage, obtaining a characteristic value of the erosion damage or crack damage.
[0103] Specifically, for bridge erosion damage or crack damage, the maintenance method of the bridge can also be determined based on the degree of damage, that is, the size of the characteristic value.
[0104] Step 404: when the characteristic value of the erosion damage is below the second preset value or the crack damage is below the third preset value, output a prompt message for repairing with concrete.
[0105] Specifically, the second preset value and the third preset value can be set according to actual experience or through the experimental results of a limited number of experiments. The specific setting idea is that when the crack damage or erosion damage reaches a certain extent, ordinary filling maintenance cannot ensure that the structure has sufficient bonding cross-sectional area, and it is easy for the filler to fall off.
[0106] Step 406: When the characteristic value of the erosion damage exceeds the second preset value or the crack damage exceeds the third preset value, output a prompt message to chisel off the damage and re-repair with concrete.
[0107] Specifically, ordinary filling maintenance cannot ensure that the structure has sufficient bonding cross-sectional area, which may easily cause the filler to fall off. If the characteristic value of the erosion damage exceeds the second preset value or the crack damage exceeds the third preset value, a prompt message is output to chisel out the damage and re-use concrete construction. The concrete strength is ensured by chiseling out the damage as a whole and then constructing it uniformly.
[0108] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0109] Based on the same inventive concept, the embodiment of the present application also provides a bridge damage detection device for implementing the bridge damage detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more bridge damage detection devices provided below can refer to the limitations of the bridge damage detection method above, and will not be repeated here.
[0110] In an exemplary embodiment, Figure 5 As shown, a bridge damage detection device 500 is provided, the device comprising:
[0111] A judgment module 501 is used to determine the damage type of the damage location based on the damage image data in response to obtaining the damage image data of the damage location of the bridge within a preset survey period;
[0112] An acquisition module 502 is used to acquire and obtain a damage correspondence relationship between different historical image data under each damage type and the damage degree of the bridge based on historical image data of multiple continuous time nodes corresponding to the damage type;
[0113] The prediction module 503 is used to predict the development trend of damage at the damaged position of the bridge according to the damage image data and the damage correspondence relationship.
[0114] Each module in the above-mentioned bridge damage detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0115] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
[0116] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0117] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.
[0118] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0119] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0120] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for detecting bridge damage, characterized in that: The method comprises: In response to acquiring damage image data of a damage position of the bridge within a preset survey period, determining a damage type of the damage position based on the damage image data; Acquire and obtain, based on historical image data of a plurality of continuous time nodes corresponding to the damage type, a damage correspondence relationship between different historical image data under each damage type and the damage degree of the bridge; The development trend of the damage at the damaged position of the bridge is predicted based on the damage image data and the damage correspondence relationship.
2. The bridge damage detection method according to claim 1, characterized in that: The method further comprises: Receive in real time the bridge deflection data measured by the displacement sensor group segmentedly set on the bridge, and the road surface smoothness data measured by the smoothness meter; In response to the change rate of the bridge deflection data exceeding a first preset percentage, or the change rate of the road surface flatness data exceeding a second preset percentage, a drone equipped with a high-definition camera is dispatched to scan the bridge to find the damaged location of the bridge and obtain the damage image data of the damaged location of the bridge.
3. The bridge damage detection method according to claim 2, characterized in that: The damage types include erosion damage, crack damage and uneven foundation settlement damage; the step of obtaining the damage correspondence between different historical image data under each damage type and the damage degree of the bridge based on the historical image data of multiple continuous time nodes corresponding to the damage type includes: According to the influence on the strength of the bridge structure from small to large, the damage degree is divided into multiple levels in sequence according to the first preset rule; Extract feature data corresponding to the damage type in the historical image of each continuous time node, correspond each feature value in the feature data to each level of the damage degree according to multiple preset threshold values from small to large, and obtain the damage correspondence relationship; wherein: when the damage type is erosion damage, the feature values in the feature data include erosion area, erosion depth and steel bar exposed area; when the damage type is crack damage, the feature values include crack length, crack width and crack depth; when the damage type is uneven foundation settlement damage, the feature values include the number of settlement points exceeding the preset settlement value, and the settlement depth of each settlement point.
4. The bridge damage detection method according to claim 3, characterized in that: The step of predicting the development trend of damage at the bridge damage location comprises: Extracting the damage image corresponding to each continuous time node in the preset survey period from the damage image data; Selecting the historical image data according to the damage type of the damage image, and performing feature comparison between the historical image data and the damage image; Classifying the damaged image into corresponding levels of damage degree according to the comparison result of the feature comparison and the damage correspondence; When the damage image is divided into more than a preset number of levels, bridge defect prompt information is output, otherwise bridge maintenance prompt information is output; wherein: the bridge defect prompt information is used to instruct defect inspection of the entire bridge; the bridge maintenance prompt information is used to instruct maintenance of the current bridge damage location.
5. The bridge damage detection method according to claim 4, characterized in that: The method further comprises: In response to outputting the bridge defect prompt information, a structural strength analysis of the concrete at the damaged position of the bridge is performed based on a pre-extracted concrete specimen of the bridge, and the formula is as follows: Wherein, Strength is the structural strength parameter of the concrete; x i is the circularity coefficient of each pore in the concrete; w i is the weight corresponding to each pore in the concrete; S, F is the porosity of the concrete; Z 2 is the degree of discreteness of the pores of the concrete; If the concrete structure strength parameter is less than a first preset value, an evaluation result indicating that the concrete structure strength is poor is output; otherwise, an evaluation result indicating that the concrete structure strength is moderate is output.
6. The bridge damage detection method according to claim 5, characterized in that: The method further comprises: In response to outputting the bridge maintenance prompt information and the damage being erosion damage or crack damage, acquiring a characteristic value of the erosion damage or crack damage; When the characteristic value of the erosion damage is below the second preset value or the crack damage is below the third preset value, outputting prompt information for repairing by concrete; When the characteristic value of the erosion damage exceeds the second preset value or the crack damage exceeds the third preset value, a prompt message is outputted to chisel off the damage and re-construct with concrete.
7. A bridge damage detection device, characterized in that: The device comprises: A judgment module, configured to, in response to obtaining damage image data of a bridge damage position within a preset survey period, judge the damage type of the damage position based on the damage image data; An acquisition module, used to acquire and obtain, based on historical image data of multiple continuous time nodes corresponding to the damage type, a damage correspondence relationship between different historical image data under each damage type and the damage degree of the bridge; The prediction module is used to predict the development trend of the damage at the damaged position of the bridge according to the damage image data and the damage correspondence relationship.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
Citation Information
Patent Citations
Bridge image detection method and device, electronic equipment and readable storage medium
CN115272257A
Damage prediction method, system and equipment for aircraft windshield and storage medium
CN117874905A
Bridge damage assessment method, device and equipment and storage medium
CN118378879A
Method for quick detection of damage to bridge, and related device
WO2021119947A1
Cited By
Evaluation device and method for simply identifying defects of recycled aggregate
CN119715538A
Bridge veneer transverse connection damage monitoring method and system and storage medium
CN121431823A
