Bridge health monitoring method and device, electronic equipment and storage medium

Abstract

The invention discloses a bridge health monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a bridge image, recognizing a crack in the bridge image, and obtaining the crack information of the crack; obtaining prediction data, wherein the prediction data comprises prediction temperature difference data and prediction load data; inputting the predicted temperature difference data, the predicted load data and the crack information into a preset bridge evaluation model to obtain a predicted bridge evaluation result, the predicted bridge evaluation result including a predicted health result, a predicted sub-health result and a predicted abnormal result; judging whether the predicted bridge evaluation result is one of a sub-health result and an abnormal result or not; and if yes, starting an alarm device to give an alarm. By implementing the technical scheme provided by the invention, the effect of early warning possible adverse conditions of the bridge in the future can be achieved.

Description

Technical Field

[0001] The present application relates to the technical field of bridge monitoring, and in particular to a bridge health monitoring method, device, electronic device and storage medium. Background Art

[0002] Bridges have always been an extremely important part of transportation. After the construction of a bridge, it is necessary to monitor the health of the bridge and maintain its structure to prevent disasters such as bridge collapse.

[0003] At present, video monitoring and sensor acquisition are usually used to monitor bridges in real time, where the monitoring targets include cracks in the bridge, and the cracks are analyzed. If there are fewer cracks, the monitored bridge is in a healthy state, and if there are more cracks, the monitored bridge is not in a healthy state.

[0004] If there are foreseeable adverse conditions in the future that may pose a threat to the bridge, such as heavy rain predicted in two days, it may affect the health of the bridge, but the existing technology cannot provide early warning. That is, the above-mentioned bridge monitoring method only monitors the current health of the bridge, and obviously cannot provide early warning of adverse conditions that may occur in the future. Summary of the invention

[0005] The present application provides a bridge health monitoring method, device, electronic device and storage medium, which have the effect of providing early warning of adverse situations that may occur in the future.

[0006] In a first aspect, the present application provides a bridge health monitoring method, the method comprising the following steps: Acquire a bridge image, wherein the bridge image is an image of each part of the bridge; Identifying cracks in the bridge image and obtaining crack information of the cracks; Acquiring prediction data, wherein the prediction data includes predicted temperature difference data and predicted load data; Inputting the predicted temperature difference data, the predicted load data and the crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, wherein the predicted bridge assessment result includes a predicted healthy result, a predicted sub-healthy result and a predicted abnormal result; Determining whether the predicted bridge assessment result is a sub-health result or an abnormal result; If so, the alarm device is activated to sound an alarm.

[0007] By adopting the above technical solution, images of different parts of the entire bridge are obtained, cracks in the bridge images are identified, and crack information of the cracks is obtained, and prediction data is obtained. The prediction data and crack information are input into a preset bridge assessment model to obtain a predicted bridge assessment result. If the predicted bridge assessment result is one of a sub-healthy result and an abnormal result, the alarm device is activated to sound an alarm, thereby giving advance warning of adverse situations that may occur in the future.

[0008] Optionally, the crack information includes the importance of the crack, and the identifying the crack in the bridge image and obtaining the crack information of the crack specifically includes the following steps: Performing crack segmentation on the bridge image to obtain a crack segmentation result; Querying the crack position corresponding to the crack segmentation result; According to the crack positions and a preset crack importance correspondence table, the importance levels corresponding to cracks at different positions are obtained.

[0009] By adopting the above technical solution, crack segmentation is performed on the acquired bridge image to obtain the crack segmentation result. According to the crack position and the preset crack importance correspondence table, the importance of cracks in different positions is obtained. The importance of the crack reflects the impact of the crack on the health of the bridge, which has the effect of improving the accuracy of the predicted bridge assessment results.

[0010] Optionally, the crack information also includes structural information of the cracks and information on the number of cracks. After obtaining the severity corresponding to the type information of the cracks, the following steps are further included: According to the crack segmentation result, three-dimensional modeling is performed on the crack to obtain a three-dimensional crack model; The structural information of the cracks and the quantity information of the cracks are obtained according to the three-dimensional crack model. The structural information of the cracks includes the length information of the cracks, the width information of the cracks and the depth information of the cracks.

[0011] By adopting the above technical scheme, a three-dimensional crack model is established according to the crack segmentation results, and the structural information of the cracks and the number of cracks are obtained. This scheme comprehensively evaluates the cracks from the perspective of the number of cracks, the length of the cracks, the width of the cracks, and the depth of the cracks, which has the effect of improving the accuracy of the predicted bridge evaluation results.

[0012] Optionally, the crack information further includes crack association information, and the crack association information includes load-associated cracks and load-independent cracks. After the structural information of the cracks is obtained according to the three-dimensional crack model, the following steps are also included: Obtain historical crack information and historical load data of the crack; Judging whether the crack is affected by the load data according to the historical crack information of the crack, the historical load data and a preset crack association judgment rule; If the crack is affected by the load data, the crack is determined to be a load-associated crack, and if the crack is not affected by the load data, the crack is determined to be a load-independent crack.

[0013] By adopting the above technical scheme, it is determined whether the cracks are affected by the load data based on the historical crack information, historical load data and preset crack association judgment rules, and cracks affected by the load data are determined as load-associated cracks, and cracks not affected by the load data are determined as load-independent cracks. When predicting the health status of the bridge, the influence of the predicted load data on the cracks can be determined, thereby further improving the accuracy of the predicted bridge assessment results.

[0014] Optionally, the obtaining of prediction data specifically includes the following steps: Obtain forecast weather information and forecast temperature difference data within a preset time period; The predicted load data is obtained according to the predicted weather information and a preset load prediction table.

[0015] By adopting the above technical solution, the predicted weather information and predicted temperature difference data within a preset time period are obtained, and the predicted load data is obtained based on the predicted weather information and the preset load prediction table. The predicted load data is associated with the predicted weather information to improve the accuracy of the predicted load data.

[0016] Optionally, after determining whether the predicted bridge assessment result is a sub-health result or an abnormal result, the following steps are further included: Determine whether the predicted bridge assessment result is a predicted sub-health result, and if the predicted bridge assessment result is a predicted sub-health result, send inspection information to the inspector terminal, wherein the inspection information includes the inspection time and the inspection location; If the predicted bridge assessment result is not a predicted sub-health result, it is determined whether the predicted bridge assessment result is a predicted abnormal result. If the predicted bridge assessment result is a predicted abnormal result, vehicle restriction information is sent to the vehicle restriction device to restrict the vehicle from traveling on the bridge, and the restriction information includes a restriction time.

[0017] By adopting the above technical solution, when the predicted bridge assessment result is a predicted sub-health result, the inspection information is sent to the inspector's terminal so that the inspector can conduct the inspection at the inspection location when the inspection time arrives. When the predicted bridge assessment result is a predicted abnormal result, the vehicle restriction information is sent to the vehicle restriction device to restrict the vehicle from driving on the bridge to temporarily relieve the pressure on the bridge.

[0018] Optionally, the preset bridge assessment model is a neural network model.

[0019] By adopting the above technical solution, the health status of the bridge is predicted and analyzed through a neural network model with high accuracy.

[0020] In a second aspect of the present application, a bridge health monitoring system is provided, the system comprising: A bridge image acquisition module is used to acquire a bridge image, wherein the bridge image is an image of each part of the bridge; A crack information acquisition module, used for identifying cracks in the bridge image and acquiring crack information of the cracks; A prediction data acquisition module, used to acquire prediction data, wherein the prediction data includes predicted temperature difference data and predicted load data; A bridge health assessment module, used for inputting the predicted temperature difference data, the predicted load data and the crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, wherein the predicted bridge assessment result includes a predicted health result, a predicted sub-health result and a predicted abnormal result; A judgment module, used to judge whether the predicted bridge assessment result is a sub-health result or an abnormal result; The alarm module is used to activate the alarm device to sound an alarm if the alarm occurs.

[0021] In a third aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the steps of a bridge health monitoring method.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a plurality of instructions, and when the instructions are executed, steps of a bridge health monitoring method are executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application is used to obtain predicted bridge assessment results. If the predicted bridge assessment result is a sub-health result or an abnormal result, the alarm device is activated to sound an alarm, thereby giving advance warning of adverse situations that may occur in the future.

[0024] 2. The present application can comprehensively evaluate cracks in terms of the number of cracks, length of cracks, width of cracks and depth of cracks, which has the effect of improving the accuracy of predicted bridge evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1It is a flow chart of a bridge health monitoring method disclosed in an embodiment of the present application.

[0026] Figure 2 It is a flowchart of the steps of obtaining crack information disclosed in the embodiment of the present application.

[0027] Figure 3 It is a flow chart of another bridge health monitoring method disclosed in an embodiment of the present application.

[0028] Figure 4 It is a module schematic diagram of a bridge health monitoring system disclosed in an embodiment of the present application.

[0029] Figure 5 It is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application.

[0030] Explanation of the accompanying drawings: 1. Bridge image acquisition module; 2. Crack information acquisition module; 3. Prediction data acquisition module; 4. Bridge health assessment module; 5. Judgment module; 6. Alarm module; 1000. Electronic device; 1001. Processor; 1002. Communication bus; 1003. User interface; 1004. Network interface; 1005. Memory. DETAILED DESCRIPTION

[0031] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0032] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0033] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0034] The technical solution provided by this application can be applied to the scenario of bridge health status prediction. At present, video monitoring and sensor acquisition are usually used to monitor bridges in real time, wherein the monitoring targets include cracks in the bridge, and the cracks are analyzed. If there are fewer cracks, the monitored bridge is in a healthy state, and if there are more cracks, the monitored bridge is not in a healthy state. If there are foreseeable adverse conditions in the future that may pose a threat to the bridge, for example, heavy rain is predicted in two days, but the above-mentioned bridge monitoring method only monitors the current health status of the bridge, it is obviously impossible to give early warning of adverse conditions that may occur in the future.

[0035] This application provides a bridge health monitoring method, referring to Figure 1 , Figure 1 1 is a flow chart of a bridge health monitoring method disclosed in an embodiment of the present application. The bridge health monitoring method is applied to a server and includes steps S10 to S50, which are as follows: S10: Acquire a bridge image, where the bridge image is an image of each part of the bridge; The bridge image is an image of each part of the bridge taken by a drone. In the embodiment of the present application, the drone can be controlled to take pictures of the bridge at a preset position at a fixed time every day. The preset position must meet the safety shooting standards of the drone and can capture all structural parts of the bridge. The structure of the bridge includes the bridge deck, bearings, piers, main beams, arch soffits and abutments.

[0036] S20: identifying cracks in the bridge image and obtaining crack information of the cracks; Specifically, after obtaining the bridge image, the cracks in the bridge image are identified, and the crack information of the cracks is obtained, the crack information includes the number of cracks, the importance of cracks, the structural information of cracks, and the crack correlation information. Among them, the importance of cracks is divided into important cracks and ordinary cracks; the structural information of cracks includes crack length information, crack width information, and crack depth information; the crack correlation information includes load-related cracks and load-independent cracks.

[0037] Reference Figure 2 , Figure 2 : is a flow chart of the steps of obtaining crack information disclosed in the embodiment of the present application, step S20 includes steps S21 to S218, and the above steps are as follows: S21: performing crack segmentation on the bridge image to obtain a crack segmentation result; In an embodiment of the present application, a clustering-based image segmentation algorithm can be used to segment cracks in a bridge image, thereby identifying cracks in the bridge image. Clustering methods include K-means clustering, fuzzy C-means algorithm, maximum expectation algorithm, etc.

[0038] Specifically, after obtaining the bridge image, the bridge image is preprocessed, that is, the bridge image is converted into the data format required by the segmentation algorithm. The data format can specifically be the feature vector corresponding to each pixel in the bridge image. After completing the preprocessing of the bridge image, the bridge image is segmented for cracks using the existing K-means clustering method to obtain the crack segmentation result. The crack segmentation result is a volume data set composed of a series of two-dimensional slices.

[0039] In other embodiments, the bridge image may also be segmented using a segmentation algorithm based on edge detection.

[0040] S22: querying the crack position corresponding to the crack segmentation result; It can be understood that the bridge image is an image of each structural part of the bridge taken by the drone, so the bridge image has a corresponding relationship with each structural part of the bridge, and the crack segmentation result is obtained by segmenting the bridge image, so the crack segmentation result has a corresponding relationship with the bridge image. After obtaining the crack segmentation result, the bridge image corresponding to the crack segmentation result is searched, and the structural part of the actual bridge corresponding to the bridge image is queried to obtain the crack position, which includes the bridge deck, bearing, pier, main beam, arch soffit and abutment.

[0041] S23: Obtaining the importance levels corresponding to cracks at different locations according to the crack locations and a preset crack importance level correspondence table; The crack importance correspondence table includes the structural parts of the bridge and the importance of the cracks in the structural parts of the bridge. The importance of cracks is divided into ordinary cracks and important cracks. Since the piers and abutments are important supporting structures of the bridge, they bear large loads and pressures. The main beam is the main horizontal bearing structure of the bridge, responsible for transferring the load to the piers. The arch is a key part that bears the load. If cracks appear in the above parts, the stability and strength of the arch bridge may decrease, posing a serious threat to the safety of the bridge. Therefore, in the embodiment of the present application, cracks in the piers, abutments, main beams and arches are confirmed as important cracks, and cracks in the bridge deck and bearings are confirmed as ordinary cracks.

[0042] S24: performing three-dimensional modeling on the crack according to the crack segmentation result to obtain a three-dimensional crack model; The three-dimensional modeling of bridge cracks in the embodiment of the present invention can adopt the existing moving cube algorithm. After obtaining the crack segmentation result, since the crack segmentation result is a volume data set composed of a series of two-dimensional slices, if the resolution of each two-dimensional slice is M×N, and the number of slices (including virtual slices) is L, then these two-dimensional slices can form a spatial discrete data field with a resolution of M×N×L. The spatial discrete data field can be regarded as the result of sampling the continuous function f(x, y, z) in the x, y, and z directions at a certain interval. If the volume data is regarded as a sampling set of a certain object attribute in a spatial region, and the value at the non-sampling point is estimated by the interpolation of its neighboring sampling points, then the set of points with a certain same value in the spatial region will constitute an isosurface. Since the grayscale values ​​of different cracks are different in the image, when appropriate values ​​are selected to define the isosurface, three-dimensional reconstruction of different cracks can be achieved.

[0043] S25: obtaining structural information of the cracks and information on the number of cracks according to the three-dimensional crack model, wherein the structural information of the cracks includes information on crack length, crack width, and crack depth; After obtaining the three-dimensional model of the crack, a measuring tool is used to measure the width, length and depth of the crack to obtain structural information of the crack, and the number of cracks is counted to obtain the number information of the cracks.

[0044] S26: Obtain historical crack information and historical load data of the crack; The database stores the historical crack information of each crack on the bridge, including the historical record time, historical crack code, historical crack location and historical crack structure information. When the cracks in the bridge image are identified, the identified cracks are numbered to obtain the crack code, and the structural information, crack location and recording time of the crack corresponding to the crack code are stored in the database to form the historical crack information. Among them, the recording time refers to the time when the drone takes the bridge picture corresponding to the crack.

[0045] The database also stores the historical load data corresponding to each recording time. The historical load data is the total weight data of vehicles and pedestrians on the bridge at the recording time. Two weighing devices are installed at the front and rear of the lane on one side of the bridge, and two weighing devices are installed at the front and rear of the lane on the other side of the bridge. When a vehicle or pedestrian enters the right road, the total weight = the original total weight + the weight of the vehicle or pedestrian. When the vehicle drives out or the pedestrian walks out of the right road, the total weight = the original total weight - the weight of the vehicle or pedestrian.

[0046] Since the recording time is a specific time, the vehicles and pedestrians passing on the bridge at this time are accidental. In other embodiments, the first half hour of the recording time and the second half hour of the recording time can be used as the new recording time, and the average load data of the bridge during the new recording time can be calculated and stored in the database as historical load data.

[0047] S27: judging whether the crack is affected by the load data according to the historical crack structure information, the historical load data and the preset crack association judgment rule; The preset crack association judgment rule is to judge whether the correlation coefficient between the historical crack structure information and the historical load data is greater than the preset correlation coefficient. If it is greater than the preset correlation coefficient, the crack is affected by the load data; if it is not greater than the preset correlation coefficient, the crack is not affected by the load data.

[0048] Specifically, the correlation coefficient between the historical length information and the historical load data in the historical crack structure information of each crack, the correlation coefficient between the historical length information and the historical load data in the historical crack structure information, and the correlation coefficient between the historical depth information and the historical load data in the historical crack structure information are calculated respectively. When at least one of the three correlation coefficients of a certain crack is greater than the preset correlation coefficient, the crack is affected by the load data. If all three correlation coefficients of a certain crack are less than the preset correlation coefficient, the crack is not affected by the load data. Among them, the correlation coefficient can be calculated using the existing calculation method Pearson correlation coefficient, and the preset correlation coefficient can be specifically 0.7.

[0049] S28: If the crack is affected by the load data, the crack is determined to be a load-associated crack; if the crack is not affected by the load data, the crack is determined to be a load-independent crack.

[0050] Specifically, after determining whether the crack is affected by the load data, if the crack is affected by the load data, the crack is determined to be a load-associated crack; if the crack is not affected by the load data, the crack is determined to be a load-independent crack, thereby obtaining crack-associated information, which includes load-associated cracks and load-independent cracks.

[0051] S30: Acquire prediction data, where the prediction data includes predicted temperature difference data and predicted load data; Specifically, the forecast weather information and the forecast temperature difference data within a preset time period are obtained, and the forecast load data is obtained according to the forecast weather information and a preset load forecast table.

[0052] The preset time period may be the third day in the future or the second day in the future, and no limitation is made as long as it is reasonable.

[0053] The predicted weather data includes sunny, cloudy, light rain, moderate rain, heavy rain and snowy days. The predicted temperature difference data is the difference between the highest temperature and the lowest temperature in a preset time period. The predicted weather data and the predicted temperature difference data can be obtained through weather forecasts. In order to further improve the prediction accuracy, a weather radar can also be installed around the bridge to obtain the predicted weather data and the predicted temperature difference data.

[0054] The preset load prediction table is the load data corresponding to the weather in different months. The load prediction table includes predicted weather information and corresponding predicted load data. The load prediction table can be made based on the historical load data of the bridge and the historical weather data.

[0055] Specifically, the predicted weather information and predicted temperature difference data within a preset time period are obtained, and the month information of the current time is obtained. According to the month information of the current time, the load prediction table of the corresponding month in the preset load prediction table is selected, and according to the predicted weather information, the predicted load data corresponding to the predicted weather information is searched in the load prediction table of the corresponding month.

[0056] S40: inputting the predicted temperature difference data, the predicted load data and the crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, wherein the predicted bridge assessment result includes a predicted healthy result, a predicted sub-healthy result and a predicted abnormal result; Among them, the bridge evaluation model is a neural network model, and the bridge evaluation model can be obtained by training the initial neural network model, wherein the training samples of the initial neural network model are: historical temperature difference data, historical load data, historical crack information, and the training samples have been manually marked with the real health status; the training standard of the initial neural network model is: the health status of the bridge; the training samples and the training standards are input into the initial neural network model, so that the initial neural network model converges to obtain the bridge evaluation model.

[0057] It can be understood that when the predicted temperature difference is large, due to the principle of thermal expansion and contraction, the degree of cracking will expand, thereby affecting the health of the bridge; when the predicted load data is large, the pressure on the bridge increases, thereby affecting the health of the bridge; when the predicted load data is large and the crack is a load-related crack, the degree of cracking will further expand, thereby affecting the health of the bridge; the higher the importance of the crack in the crack information, the higher its weight in the neural network model, and the deeper the impact of the crack on the health of the bridge; the more cracks in the crack information, the longer the crack length, the wider the crack width, and the deeper the crack depth, the more they will affect the health of the bridge.

[0058] Specifically, after obtaining the predicted temperature difference data, predicted load data and crack information, the predicted temperature difference data, predicted load data and crack information are input into the preset bridge assessment model to obtain the predicted bridge assessment results. Among them, the predicted bridge assessment results include predicted health results, predicted sub-health results and predicted abnormal results. The predicted health results refer to the predicted bridge will not be affected, the predicted sub-health results refer to the data have affected the health of the bridge, but are still within the limit bearing range of the bridge, and the predicted abnormal results refer to the bridge exceeding the limit bearing range, and there is a possibility of collapse.

[0059] In other embodiments, before the step of inputting the predicted temperature difference data, predicted load data and crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, the following steps can be performed: inputting the current load data and crack information into a preset bridge assessment model to obtain a bridge assessment result, thereby monitoring the health status of the bridge in real time.

[0060] In other embodiments, in order to further improve the accuracy of the predicted health results of the bridge, the bottom of the bridge can be photographed by a drone to obtain the bridge settlement data, and the settlement data, predicted temperature difference data, predicted load data and crack information are input into a preset bridge assessment model to obtain the predicted bridge assessment results. Settlement data refers to the data of foundation settlement. When the bridge settles unevenly, it will affect the health status of the bridge, and the load data will further affect the settlement data.

[0061] S50: Determine whether the predicted bridge assessment result is a sub-health result or an abnormal result. If so, activate the alarm device to sound an alarm.

[0062] Specifically, after obtaining the predicted bridge assessment result, it is determined whether the predicted bridge assessment result is a sub-health result or an abnormal result. If the predicted bridge assessment result is a sub-health result or an abnormal result, the alarm device is activated to sound an alarm to remind relevant staff.

[0063] In another embodiment, to further ensure bridge safety, Figure 3 It is a flowchart of another bridge health monitoring method disclosed in an embodiment of the present application. After executing step S50, steps S60 to S70 may also be executed.

[0064] S60: Determine whether the predicted bridge assessment result is a predicted sub-health result. If the predicted bridge assessment result is a predicted sub-health result, send inspection information to the inspector terminal, where the inspection information includes the inspection time and the inspection location; S70: If the predicted bridge assessment result is not a predicted sub-health result, determine whether the predicted bridge assessment result is a predicted abnormal result. If the predicted bridge assessment result is a predicted abnormal result, send vehicle restriction information to the vehicle restriction device to restrict the vehicle from traveling on the bridge. The restriction information includes a restriction time.

[0065] Specifically, if the predicted bridge assessment result is one of a sub-health result and an abnormal result, it is determined whether the predicted bridge assessment result is a predicted sub-health result. If the predicted bridge assessment result is a predicted sub-health result, inspection information is sent to the inspector terminal, and the inspection information includes the inspection time and the inspection location, so that the inspector goes to the inspection location for inspection at the inspection time. The inspection time is a preset time, and the inspection location is the location of the crack. If the predicted bridge assessment result is not a predicted sub-health result, it is determined whether the predicted bridge assessment result is a predicted abnormal result. If the predicted bridge assessment result is a predicted abnormal result, vehicle restriction information is sent to the vehicle restriction device, and the restriction information includes the restriction time, so as to restrict the vehicle from driving on the bridge during the restriction time, and the restriction time is a preset time.

[0066] In other embodiments, in order to further ensure the safety of the bridge, after predicting that the bridge assessment result is an abnormal result, repair information can be sent to the repair personnel terminal so that the repair personnel can perform repairs in time.

[0067] The implementation principle of a bridge health monitoring method provided by the present application is as follows: obtaining a bridge image, identifying cracks in the bridge image, and obtaining crack information of the cracks; obtaining prediction data, including predicted temperature difference data and predicted load data; inputting the predicted temperature difference data, predicted load data and crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, including a predicted healthy result, a predicted sub-healthy result and a predicted abnormal result; judging whether the predicted bridge assessment result is one of a sub-healthy result and an abnormal result; if so, activating an alarm device to give an alarm. Implementing the technical solution provided by the present application can achieve the effect of giving early warning of adverse conditions that may occur in the future of the bridge.

[0068] The present application also discloses a bridge health monitoring system, referring to Figure 4 , Figure 4 It is a module schematic diagram of a bridge health monitoring system disclosed in an embodiment of the present application, the system comprising: a bridge image acquisition module 1, a crack information acquisition module 2, a prediction data acquisition module 3, a bridge health assessment module 4, a judgment module 5, and an alarm module 6.

[0069] The bridge image acquisition module 1 is used to acquire a bridge image, which is an image of each part of the bridge; A crack information acquisition module 2 is used to identify cracks in the bridge image and obtain crack information of the cracks; Prediction data acquisition module 3, used to acquire prediction data, the prediction data includes prediction temperature difference data and prediction load data; The bridge health assessment module 4 is used to input the predicted temperature difference data, the predicted load data and the crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, which includes a predicted health result, a predicted sub-health result and a predicted abnormal result; A judgment module 5 is used to judge whether the predicted bridge assessment result is a sub-health result or an abnormal result; The alarm module 6 is used to activate the alarm device to sound an alarm if the alarm occurs.

[0070] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0071] Reference Figure 5 , Figure 5 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0072] The communication bus 1002 is used to realize the connection and communication between these components.

[0073] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0074] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0075] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0076] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Figure 5 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a bridge health monitoring method.

[0077] exist Figure 5In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application program storing a bridge health monitoring method in the memory 1005. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0078] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0079] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0080] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0085] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A bridge health monitoring method, characterized in that: The following steps are involved: Acquire a bridge image, wherein the bridge image is an image of each part of the bridge; Identifying cracks in the bridge image and obtaining crack information of the cracks; Acquiring prediction data, wherein the prediction data includes predicted temperature difference data and predicted load data; Inputting the predicted temperature difference data, the predicted load data and the crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, wherein the predicted bridge assessment result includes a predicted healthy result, a predicted sub-healthy result and a predicted abnormal result; Determining whether the predicted bridge assessment result is a sub-health result or an abnormal result; If so, the alarm device is activated to sound an alarm.

2. A bridge health monitoring method according to claim 1, characterized in that: The crack information includes the importance of the crack, and the identifying of the crack in the bridge image and obtaining the crack information of the crack specifically includes the following steps: Performing crack segmentation on the bridge image to obtain a crack segmentation result; Querying the crack position corresponding to the crack segmentation result; According to the crack positions and a preset crack importance correspondence table, the importance levels corresponding to cracks at different positions are obtained.

3. A bridge health monitoring method according to claim 2, characterized in that: The crack information also includes structural information of the cracks and information on the number of cracks. After obtaining the severity corresponding to the type information of the cracks, the following steps are also included: According to the crack segmentation result, three-dimensional modeling is performed on the crack to obtain a three-dimensional crack model; The structural information of the cracks and the quantity information of the cracks are obtained according to the three-dimensional crack model. The structural information of the cracks includes the length information of the cracks, the width information of the cracks and the depth information of the cracks.

4. A bridge health monitoring method according to claim 3, characterized in that: The crack information also includes crack association information, and the crack association information includes load-related cracks and load-independent cracks. After obtaining the structural information of the cracks according to the three-dimensional crack model, the following steps are also included: Obtain historical crack information and historical load data of the crack; Judging whether the crack is affected by the load data according to the historical crack information of the crack, the historical load data and a preset crack association judgment rule; If the crack is affected by the load data, the crack is determined to be a load-associated crack, and if the crack is not affected by the load data, the crack is determined to be a load-independent crack.

5. A bridge health monitoring method according to claim 1, characterized in that: The obtaining of prediction data specifically comprises the following steps: Obtain forecast weather information and forecast temperature difference data within a preset time period; The predicted load data is obtained according to the predicted weather information and a preset load prediction table.

6. A bridge health monitoring method according to claim 1, characterized in that: After determining whether the predicted bridge assessment result is a sub-health result or an abnormal result, the following steps are also included: Determine whether the predicted bridge assessment result is a predicted sub-health result, and if the predicted bridge assessment result is a predicted sub-health result, send inspection information to the inspector terminal, wherein the inspection information includes the inspection time and the inspection location; If the predicted bridge assessment result is not a predicted sub-health result, it is determined whether the predicted bridge assessment result is a predicted abnormal result. If the predicted bridge assessment result is a predicted abnormal result, vehicle restriction information is sent to the vehicle restriction device to restrict the vehicle from traveling on the bridge, and the restriction information includes a restriction time.

7. A bridge health monitoring method according to claim 1, characterized in that: The preset bridge assessment model is a neural network model.

8. A bridge health monitoring device, characterized in that: The device comprises: A bridge image acquisition module (1) is used to acquire a bridge image, wherein the bridge image is an image of each part of the bridge; A crack information acquisition module (2), used to identify cracks in the bridge image and acquire crack information of the cracks; A prediction data acquisition module (3), used to acquire prediction data, the prediction data including prediction temperature difference data and prediction load data; A bridge health assessment module (4) is used to input the predicted temperature difference data, the predicted load data and the crack information into a preset bridge assessment model to obtain a predicted bridge assessment result, wherein the predicted bridge assessment result includes a predicted health result, a predicted sub-health result and a predicted abnormal result; A judgment module (5) is used to judge whether the predicted bridge assessment result is a sub-health result or an abnormal result; The alarm module (6) is used to activate the alarm device to sound an alarm if the alarm occurs.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 7.

Images