Millimeter wave radar-based bridge health monitoring method and related device

Abstract

The invention discloses a bridge health monitoring method based on a millimeter wave radar and a related device. The method comprises the following steps: acquiring load dynamic change data fed back by a dynamic weighing system in real time; obtaining expansion joint displacement dynamic change data fed back by the millimeter wave radar sensor in real time, and performing baseline correction on the expansion joint displacement dynamic change data; predicting the health condition of the bridge based on the load dynamic change data and the expansion joint displacement dynamic change data; and when the health condition of the bridge has a problem, sending early warning information. According to the invention, real-time monitoring of bridge health can be realized, early warning can be carried out in time when the health condition of the bridge goes wrong, the safety of the bridge structure can be ensured, the service life of the bridge structure can be prolonged, and the maintenance efficiency can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of bridge health monitoring, and specifically relates to a method and related device for bridge health monitoring based on millimeter wave radar. Background Art

[0002] Bridges are an important part of transportation infrastructure. During the construction and use of bridges, due to the erosion of the environment, harmful substances, vehicles, wind, earthquakes, fatigue, human factors, and the continuous degradation of the material's own performance, the various parts of the structure suffer varying degrees of damage and deterioration long before reaching the design life. Therefore, health monitoring of bridges is an important measure to ensure the safety of bridge structures, extend their service life, and improve maintenance efficiency.

[0003] At present, conventional bridge monitoring systems can only monitor bridge loads through weighing systems, but cannot monitor the health of bridges. Existing technologies can only monitor the health of bridges through regular structural inspections, but cannot provide timely warnings when the bridge structure is unstable, which is not conducive to improving the service life of bridges and ensuring the structural safety of bridges. Summary of the invention

[0004] The purpose of the present application is to provide a method and related devices for bridge health monitoring based on millimeter wave radar, so as to solve the problem that the existing bridge monitoring system cannot realize bridge health status monitoring, and can only realize bridge health status monitoring through regular structural inspections. It is impossible to issue a timely warning when the bridge structure becomes unstable, which is not conducive to improving the service life of the bridge and ensuring the structural safety of the bridge.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a method for bridge health monitoring based on millimeter wave radar, wherein a dynamic weighing system is arranged at a target position of the bridge, and millimeter wave radar sensors and targets corresponding to the positions are arranged at both ends of the target position respectively; the method comprises:

[0006] Obtaining the dynamic load change data fed back in real time by the dynamic weighing system;

[0007] Acquire the dynamic change data of the expansion joint displacement fed back by the millimeter wave radar sensor in real time, and perform baseline correction on the dynamic change data of the expansion joint displacement;

[0008] Predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement;

[0009] Send early warning information when there is a problem with the health of the bridge.

[0010] In one or more embodiments, the step of predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement includes:

[0011] Traversing the instantaneous load at each moment in the load dynamic change data, extracting instantaneous loads of similar magnitude and their corresponding moments, and collecting them into a first queue;

[0012] Based on the first queue and the dynamic change data of the expansion joint displacement, the health status of the bridge is predicted.

[0013] In one or more embodiments, the step of predicting the health status of the bridge based on the first queue and the dynamic change data of the expansion joint displacement includes:

[0014] Extracting the instantaneous displacement fluctuation corresponding to the instantaneous load in the first queue from the dynamic change data of the expansion joint displacement, and collecting it into the second queue;

[0015] Determine whether the difference of the instantaneous displacement fluctuation amount in the second queue is greater than a first threshold;

[0016] If yes, then there is a problem with the health of the bridge.

[0017] In one or more embodiments, the step of predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement includes:

[0018] Traversing the instantaneous displacement fluctuation at each moment in the dynamic change data of the expansion joint displacement, extracting the instantaneous displacement fluctuation greater than the second threshold and its corresponding moment, and collecting them into a third queue;

[0019] Based on the third queue, load prediction change data of the bridge is obtained, wherein the load prediction change data includes predicted loads at each moment;

[0020] The health status of the bridge is predicted based on the load prediction change data and the load dynamic change data.

[0021] In one or more embodiments, the step of predicting the health status of the bridge based on the load prediction change data and the load dynamic change data includes:

[0022] Calculating the difference between the load prediction change data and the load data at corresponding moments in the load dynamic change data, and determining whether there is a difference greater than a third threshold;

[0023] If yes, then there is a problem with the health of the bridge.

[0024] In one or more embodiments, it further includes:

[0025] Acquiring temperature change data and / or humidity change data;

[0026] Inputting the temperature at the target time in the temperature change data and / or the humidity at the target time in the humidity change data into a pre-trained deep learning neural network model to obtain a predicted reference value of the expansion joint at the target time;

[0027] The health status of the bridge is predicted based on the predicted reference value and the dynamic change data of the expansion joint displacement.

[0028] In one or more embodiments, the step of predicting the health status of the bridge based on the predicted reference value and the dynamic change data of the expansion joint displacement includes:

[0029] Extracting the actual reference value of the expansion joint at the target time from the dynamic change data of the expansion joint displacement, calculating the difference between the predicted reference value and the actual reference value, and judging whether the difference is greater than a fourth threshold;

[0030] If so, there is a problem with the health of the bridge.

[0031] In order to achieve the above-mentioned purpose, the second aspect of the present application provides a bridge health monitoring device based on millimeter wave radar, wherein a dynamic weighing system is arranged at the target position of the bridge, and millimeter wave radar sensors and targets corresponding to the positions are arranged at both ends of the target position respectively; the device comprises:

[0032] A load acquisition module, used to acquire the dynamic load change data fed back in real time by the dynamic weighing system;

[0033] An expansion joint displacement acquisition module is used to acquire the dynamic change data of the expansion joint displacement fed back by the millimeter wave radar sensor in real time, and perform baseline correction on the dynamic change data of the expansion joint displacement;

[0034] A prediction module, used to predict the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement;

[0035] The early warning module is used to send early warning information when there are problems with the health status of the bridge.

[0036] In order to achieve the above-mentioned object, the third aspect of the present application provides an electronic device, including:

[0037] at least one processor; and

[0038] A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the method for bridge health monitoring based on millimeter-wave radar as described in any of the above embodiments.

[0039] In order to achieve the above-mentioned purpose, the fourth aspect of the present application is a machine-readable storage medium, which stores executable instructions, and when the instructions are executed, the machine executes the method for bridge health monitoring based on millimeter wave radar as described in any of the above-mentioned embodiments.

[0040] Different from the prior art, the beneficial effects of this application are:

[0041] This application can achieve real-time monitoring of bridge health and provide timely warnings when problems occur in the health of the bridge, helping to ensure the safety of the bridge structure, extend its service life and improve maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a schematic diagram of the application scenarios of various embodiments of the present application;

[0044] Figure 2 It is a flowchart of an implementation method of a bridge health monitoring method based on millimeter wave radar of the present application;

[0045] Figure 3 It is a schematic diagram of an implementation method of the dynamic change data of the expansion joint displacement in the present application;

[0046] Figure 4 It is a schematic diagram of an implementation method of the present application after baseline correction of the dynamic change data of the expansion joint displacement;

[0047] Figure 5 yes Figure 2 A schematic flow chart of an implementation method corresponding to S300;

[0048] Figure 6 yes Figure 5 A schematic diagram of a flow chart of an implementation method corresponding to S302a;

[0049] Figure 7 yes Figure 2 A schematic flow chart of another implementation method corresponding to S300;

[0050] Figure 8 It is a schematic diagram of an implementation method of the linear relationship between displacement fluctuation magnitude and load magnitude of the present application;

[0051] Fig. 9 This is a schematic diagram of the relationship between the expansion joint reference value and temperature and humidity in this application;

[0052] Fig.10 It is a structural schematic diagram of an implementation method of a device for bridge health monitoring based on millimeter wave radar in the present application;

[0053] Fig.11 It is a schematic structural diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0055] This application is mainly used in bridge health monitoring scenarios. For details, please refer to Figure 1 , Figure 1 It is a schematic diagram of the application scenarios of various embodiments of the present application. Figure 1 As shown, the bridge deck 10 is installed on the column 20, and an elastic support 30 is provided between the bridge deck 10 and the column 20. When the bridge deck 10 is subjected to a load, the elastic support 30 will undergo elastic or inelastic instantaneous deformation, which will cause the width of the expansion joint 100 between the elastic support 30 and the column 20 to change. Therefore, the instantaneous change in the displacement of the expansion joint 100 can indirectly reflect the change in the bridge load.

[0056] The present application enables bridge maintenance personnel to obtain the load data of the bridge by setting the corresponding millimeter wave radar sensor 200 and target 300 on the elastic support 30 and the column 20, and analyzing the change data of the expansion joint 100 fed back in real time by the millimeter wave radar sensor 200. The arrangement position of the millimeter wave radar sensor 200 and the target 300 can be the position of the elastic support 30 on the bridge that has the largest response to the displacement change of the expansion joint 100 caused by the vehicle load, and the position can be selected based on experiments or bridge maintenance history to improve the monitoring accuracy and precision of the present application.

[0057] When the structure of the bridge remains stable, the displacement fluctuations of the expansion joint 100 caused by vehicles with similar dead weight at different times should be basically the same. On the contrary, when there are problems with the health of the bridge, the displacement fluctuations of the expansion joint 100 caused by vehicles with similar dead weight at different times will be greatly different. Therefore, the health monitoring of the bridge can be achieved based on the displacement of the expansion joint 100 and the weight of the passing vehicles.

[0058] The present application sets corresponding millimeter-wave radar sensors 200 and targets 300 at both ends of the target position of the bridge, and arranges a dynamic weighing system 400 at the target position. By analyzing the change data of the expansion joint 100 fed back by the millimeter-wave radar sensor 200 and the load data fed back by the dynamic weighing system 400, the health monitoring of the bridge can be achieved.

[0059] Specifically, see Figure 2 , Figure 2 It is a flow chart of an implementation method of a bridge health monitoring method based on millimeter wave radar of the present application.

[0060] like Figure 2 As shown, the methods for bridge health monitoring include:

[0061] S100, obtaining the dynamic load change data fed back in real time by the dynamic weighing system.

[0062] Among them, the dynamic weighing system can weigh the weight of vehicles passing through the target location in real time and form load dynamic change data, which includes the weight of vehicles passing through the target location at each moment.

[0063] S200, obtaining dynamic change data of expansion joint displacement fed back by the millimeter wave radar sensor in real time, and performing baseline correction on the dynamic change data of expansion joint displacement.

[0064] The millimeter wave radar sensor has a high sampling rate and can output the dynamic displacement of the expansion joint at a high sampling rate. At the same time, the millimeter wave radar sensor is an electronic wireless connection. Compared with the traditional weight sensor method, it has lower requirements for installation, high reliability, and is not easy to damage.

[0065] In addition, compared with the traditional pull-rope displacement meter for monitoring the displacement of expansion joints, the millimeter-wave radar sensor of the present application is completely different. The sampling rate of the traditional pull-rope displacement meter is very low. It is used to monitor the change trend of the expansion joint caused by factors such as temperature and humidity, so as to provide reference for bridge maintenance personnel, but it cannot observe the instantaneous change of the expansion joint displacement.

[0066] The millimeter wave radar sensor of the present application is used to monitor the instantaneous change of the expansion joint displacement, and the purposes and working methods of the two are completely different.

[0067] The millimeter wave radar sensor provides real-time feedback of the distance between it and the target during operation, that is, the dynamic change data of the expansion joint displacement. This data includes the correlation between the expansion joint displacement of the bridge and time. Figure 3 , Figure 3 It is a schematic diagram of an implementation method of the dynamic change data of expansion joint displacement in the present application.

[0068] like Figure 3 As shown in Figure 3, the displacement of the expansion joint changes with time, which is caused by the passage of heavy vehicles and can represent the flow rate and weight of heavy vehicles passing on the bridge.

[0069] There are fluctuations and data drift in the change of expansion joint displacement, and there are errors in the baseline of expansion joint displacement at each moment, such as Figure 3 As shown, in order to reduce deviation and improve the accuracy and reliability of data analysis, it is also necessary to perform baseline correction on the dynamic change data of expansion joint displacement.

[0070] Among them, the baseline correction can adopt polynomial fitting, other fitting methods, Mann-Kendall test and other methods commonly used in the art, all of which can achieve the effect of this embodiment and will not be repeated again.

[0071] After baseline correction, the displacement of the expansion joint at each moment in a short period of time is on the same basis, which can be applied to the next analysis operation. Figure 3 For example, the dynamic change data of expansion joint displacement after baseline correction is as follows Figure 4 As shown, Figure 4 It is a schematic diagram of an implementation method of the dynamic change data of expansion joint displacement after baseline correction of the present application.

[0072] However, it should be noted that the above Figure 3 and Figure 4 The baseline correction diagram shown is only a diagram of baseline correction within a shorter period of time. Over a longer period of time (e.g. 12 hours, one day, one month, etc.), due to changes in temperature and humidity, the baseline value of the bridge at each moment after baseline correction does not remain unchanged, but is associated with changes in temperature and humidity.

[0073] S300: predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement.

[0074] S400. When there is a problem with the health status of the bridge, send an early warning message.

[0075] This application realizes the health status monitoring of the bridge by combining the change data of the load and the change data of the expansion joint.

[0076] In one embodiment, multiple vehicles with similar loads can be selected based on the dynamic change data of load, and the displacement fluctuations of the expansion joint caused by the multiple vehicles can be extracted from the dynamic change data of the expansion joint displacement. The health status of the bridge can be reflected by judging the difference between the displacement fluctuations of the multiple vehicles.

[0077] Specifically, see Figure 5 , Figure 5 yes Figure 2 A flow chart of an implementation method corresponding to S300 in FIG.

[0078] like Figure 5 As shown, methods for predicting the health of a bridge include:

[0079] S301a, traverse the instantaneous load at each moment in the load dynamic change data, extract instantaneous loads with similar magnitudes and their corresponding moments, and collect them into the first queue.

[0080] First, instantaneous loads of similar magnitude may be extracted from the load dynamic change data, and the instantaneous loads and their corresponding times may be collected into a first queue, wherein the number of extracted loads may be two or more.

[0081] In actual application, a threshold of the load difference may be set. When the difference between two instantaneous loads is less than the threshold, the two instantaneous loads may be considered to be similar in size. It should be understood that in order to optimize the prediction result, the two closest instantaneous loads may be selected and collected into the first queue.

[0082] S302a, predicting the health status of the bridge based on the first queue and the dynamic change data of the expansion joint displacement.

[0083] Since the first queue includes several target moments with similar load sizes, the expansion joint displacement fluctuation at that moment can be extracted from the dynamic change data of the expansion joint displacement based on the target moment, and then the health status of the bridge can be predicted based on the expansion joint displacement fluctuation at different target times.

[0084] Specifically, see Figure 6 , Figure 6 yes Figure 5 A flow chart of an implementation method corresponding to S302a.

[0085] like Figure 6 As shown, the prediction methods include:

[0086] S3021a, extracting the instantaneous displacement fluctuation corresponding to the instantaneous load in the first queue from the dynamic change data of the expansion joint displacement, and collecting them into the second queue.

[0087] Firstly, based on the corresponding moments of each instantaneous load in the first queue, the instantaneous displacement fluctuation corresponding to the instantaneous load can be extracted from the dynamic change data of the expansion joint displacement.

[0088] S3022a. Determine whether the difference in the instantaneous displacement fluctuation in the second queue is greater than a first threshold.

[0089] If so, then

[0090] S3023a. There are issues with the health of the bridge.

[0091] It should be understood that in the short term, the displacement fluctuation of the expansion joint is caused by the load. Therefore, when the structure of the bridge is stable, the displacement fluctuation of the expansion joint is similar for loads of similar magnitude. If there are problems with the health of the bridge, the difference in the displacement fluctuation of the expansion joint will become larger for loads of similar magnitude.

[0092] Therefore, a first threshold may be set, and when the difference in the instantaneous displacement fluctuation in the second queue is greater than the first threshold, it is determined that there is a problem with the health of the bridge.

[0093] The first threshold value may be preset based on actual working conditions, for example, based on the accuracy of a dynamic weighing system, a maximum displacement of an expansion joint, and the like.

[0094] In the above embodiment, the health status of the bridge is monitored by extracting the displacement fluctuation of expansion joints with similar loads. In another embodiment, the dynamic change data of the expansion joint displacement can be analyzed to obtain predicted load data, and the health status of the bridge can be monitored based on the predicted load data and the dynamic change data of the load measured by the dynamic weighing system.

[0095] Specifically, see Figure 7 , Figure 7 yes Figure 2 A flowchart of another implementation method corresponding to S300 in FIG.

[0096] like Figure 7 As shown, the prediction methods include:

[0097] S301b, traverse the instantaneous displacement fluctuation at each moment in the dynamic change data of the expansion joint displacement, extract the instantaneous displacement fluctuation greater than the second threshold and its corresponding time, and collect them into the third queue.

[0098] Since the instantaneous expansion joint fluctuation amount is proportional to the weight of the passing vehicle, a second threshold value of the instantaneous expansion joint fluctuation amount can be set to shield the fluctuation caused by interference from radar measurement errors and bridge environment and other factors.

[0099] When the fluctuation amount is greater than the second threshold, it is determined that the fluctuation amount at this time is caused by vehicle passage, and when the fluctuation amount is less than the second threshold, it is determined that the expansion joint fluctuation at this time is caused by detection error, thereby simplifying the data and improving the effectiveness and accuracy of monitoring.

[0100] Among them, the second threshold value can be set based on actual needs according to the construction specifications and historical traffic data of the bridge, and the effect of this implementation can be achieved.

[0101] The extracted instantaneous displacement fluctuations and their corresponding moments are collected into the third queue, and the originally complex change data are converted into point value data, which helps to simplify subsequent analysis operations.

[0102] S302b. Based on the third queue, obtain the load prediction change data of the bridge.

[0103] Since the displacement fluctuation of the expansion joint is positively correlated with the weight of the passing vehicles, the load change data of the bridge, that is, the predicted load at each moment, can be predicted based on the third queue.

[0104] The following is a detailed introduction to the method of obtaining load prediction change data.

[0105] In one embodiment, a linear relationship between the displacement fluctuation of the expansion joint and the weight of the passing vehicle, i.e., a mapping relationship, can be constructed for the target position of the target bridge. The mapping relationship can be obtained through preliminary experiments or through simulation methods.

[0106] By traversing the instantaneous displacement fluctuation in the queue and inputting the traversed instantaneous displacement fluctuation at the target time into the mapping relationship, the weight of the heavy vehicle passing the target position at the target time can be obtained.

[0107] Specifically, see Figure 8 , Figure 8 Schematic diagram of an implementation method of the linear relationship between displacement fluctuation magnitude and load size in this application. Figure 8 As shown in the figure, the displacement fluctuation and passing vehicle weight data obtained through previous experiments show that the displacement fluctuation and passing vehicle weight are linearly correlated as a whole. Based on the above data, the linear relationship between the two can be fitted. By bringing the instantaneous displacement fluctuation into the linear relationship, the weight of the passing vehicle can be obtained.

[0108] In another embodiment, a deep learning neural network model may be constructed for the target position of the target bridge, and the model is used to describe the functional relationship between the displacement fluctuation of the expansion joint at the target position and the weight of the passing vehicle.

[0109] By using the instantaneous displacement fluctuation in the queue and inputting the instantaneous displacement fluctuation at the target moment into a pre-trained deep learning neural network model, the weight of the heavy vehicle passing through the target position at the target moment can be obtained.

[0110] Specifically, the training method of the deep learning neural network model may include:

[0111] A sample target set is obtained and divided into a sample training set and a sample verification set, wherein the sample target set includes displacement fluctuations of expansion joints at several target positions marked with weight labels;

[0112] The displacement fluctuation of the expansion joint at the target position in the sample training set is used as the input of the deep learning neural network model, and based on the loss function and weight label, the weight of the deep learning neural network model is updated along the direction of gradient descent until the loss function converges;

[0113] The effectiveness of the deep learning neural network model is tested with a sample validation set to obtain the optimal model parameters.

[0114] Among them, the sample target set can be obtained through preliminary experimental methods or simulation methods.

[0115] S303b. Predict the health status of the bridge based on the load prediction change data and the load dynamic change data.

[0116] After obtaining the load prediction change data, the health status of the bridge can be monitored by combining it with the load dynamic change data fed back by the dynamic weighing system.

[0117] It is understandable that when the structure of the bridge is stable, the load prediction change data obtained based on the expansion joint displacement prediction should be close to the load dynamic change data. If the difference between the two is large, there may be problems with the health of the bridge.

[0118] Therefore, the difference between the load prediction change data and the load dynamic change data at the corresponding time can be calculated to determine whether there is a difference greater than the third threshold;

[0119] If yes, then there is a problem with the health of the bridge.

[0120] The above embodiments introduce a method for predicting the health status of a bridge by combining the dynamic change data of load and the dynamic change data of expansion joint displacement. In another embodiment, the health status of the bridge can also be monitored by combining the humidity change data and the temperature change data.

[0121] Specifically, it also includes:

[0122] S500: Acquire temperature change data and / or humidity change data.

[0123] S600: Input the temperature at a target time in the temperature change data and / or the humidity at a target time in the humidity change data into a pre-trained deep learning neural network model to obtain a predicted reference value of the expansion joint at the target time.

[0124] S700: Predict the health status of the bridge based on the predicted reference value and the dynamic change data of the expansion joint displacement.

[0125] As you can understand, the base value of expansion joints is related to temperature and humidity, please refer to Fig. 9 , Fig. 9 This is a schematic diagram of the relationship between the expansion joint benchmark value and temperature and humidity in this application. The benchmark value is negatively correlated with temperature as a whole, and positively correlated with humidity as a whole.

[0126] When the structure of the bridge is stable, the base value of the expansion joint should not change much at similar temperatures and / or humidity. If the base value of the expansion joint varies greatly at similar temperatures and / or humidity, there may be a problem with the health of the bridge. Therefore, the health of the bridge can be predicted by combining humidity change data and / or temperature change data, as well as dynamic change data of expansion joint displacement.

[0127] Among them, the deep learning neural network model can be trained based on the historical data of the expansion joint benchmark value and the historical temperature and humidity data. Its training method can be the same as the model in S302b, which will not be repeated here.

[0128] By inputting the temperature and / or humidity at the target time into the model, the predicted reference value of the expansion joint at the target time can be obtained. By comparing the actual reference value at the target time in the dynamic change data of the expansion joint displacement with the predicted reference value, the health status of the bridge can be predicted.

[0129] For example, if the difference between the predicted reference value and the actual reference value is greater than the fourth threshold, it can be determined that there is a problem with the health status of the bridge, thereby enabling the health status of the bridge to be monitored based on temperature, humidity and expansion joint displacement over a longer period.

[0130] The monitoring methods based on the above-mentioned implementation modes can realize real-time monitoring of bridge health and issue early warnings in time when problems occur in the health status of the bridge, which helps to ensure the safety of the bridge structure, extend its service life and improve maintenance efficiency.

[0131] This application also provides a bridge health monitoring device based on millimeter wave radar, please refer to Fig.10 , Fig.10 It is a structural schematic diagram of an implementation scheme of a bridge health monitoring device based on millimeter wave radar in the present application.

[0132] like Fig.10As shown, the device includes a load acquisition module 21, an expansion joint displacement acquisition module 22, a prediction module 23 and an early warning module 24.

[0133] The load acquisition module 21 is used to obtain the dynamic load change data fed back by the dynamic weighing system in real time;

[0134] The expansion joint displacement acquisition module 22 is used to obtain the dynamic change data of the expansion joint displacement fed back by the millimeter wave radar sensor in real time, and perform baseline correction on the dynamic change data of the expansion joint displacement;

[0135] The prediction module 23 is used to predict the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement;

[0136] The early warning module 24 is used to send early warning information when there is a problem with the health status of the bridge.

[0137] As above Figures 1 to 9 , a method for bridge health monitoring based on millimeter wave radar according to an embodiment of this specification is described. The details mentioned in the above description of the method embodiment are also applicable to the device for bridge health monitoring based on millimeter wave radar in the embodiment of this specification. The above device for bridge health monitoring based on millimeter wave radar can be implemented by hardware, or by software, or by a combination of hardware and software.

[0138] This application also provides an electronic device, see Fig.11 , Fig.11 Schematic diagram of the structure of an electronic device of the present application. Fig.11 As shown, the electronic device 40 may include at least one processor 41, a memory 42 (e.g., a non-volatile memory), a memory 43, and a communication interface 44, and the at least one processor 41, the memory 42, the memory 43, and the communication interface 44 are connected together via a bus 45. At least one processor 41 executes at least one computer-readable instruction stored or encoded in the memory 42.

[0139] It should be understood that the computer executable instructions stored in the memory 42, when executed, cause at least one processor 41 to perform the above combined operations in various embodiments of the present specification. Figure 1-Figure 9 Describes the various operations and functions.

[0140] In the embodiments of the present specification, the electronic device 40 may include, but is not limited to: a personal computer, a server computer, a workstation, a desktop computer, a laptop computer, a notebook computer, a mobile electronic device, a smart phone, a tablet computer, a cellular phone, a personal digital assistant (PDA), a handheld device, a messaging device, a wearable electronic device, a consumer electronic device, and the like.

[0141] According to one embodiment, a program product such as a machine-readable medium is provided. The machine-readable medium may have instructions (i.e., the above-mentioned elements implemented in the form of software), which, when executed by a machine, causes the machine to perform the above-mentioned combination of various embodiments of this specification. Figure 1-Figure 5 Specifically, a system or device equipped with a readable storage medium may be provided, on which a software program code implementing the functions of any of the above-mentioned embodiments is stored, and a computer or processor of the system or device reads and executes the instructions stored in the readable storage medium.

[0142] In this case, the program code itself read from the machine-readable medium can realize the function of any one of the above embodiments, and thus the machine-readable code and the machine-readable storage medium storing the machine-readable code constitute part of this specification.

[0143] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network.

[0144] Those skilled in the art should understand that the various embodiments disclosed above can be modified and altered in various ways without departing from the essence of the invention. Therefore, the protection scope of this specification should be defined by the appended claims.

[0145] It should be noted that not all steps and units in the above-mentioned processes and system structure diagrams are necessary, and some steps or units can be ignored according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients, or some components in multiple independent devices may be implemented together.

[0146] In the above embodiments, the hardware unit or module can be realized by mechanical or electrical means. For example, a hardware unit, module or processor can include permanent dedicated circuit or logic (such as special processor, FPGA or ASIC) to complete the corresponding operation. The hardware unit or processor can also include programmable logic or circuit (such as general-purpose processor or other programmable processor), which can be temporarily set by software to complete the corresponding operation. Specific implementation (mechanical method or dedicated permanent circuit or temporary circuit) can be determined based on cost and time consideration.

[0147] The specific embodiments described above in conjunction with the accompanying drawings describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of protection of the claims. The term "exemplary" used throughout this specification means "used as an example, instance or illustration" and does not mean "preferred" or "having advantages" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, these technologies can be implemented without these specific details. In some instances, in order to avoid making the concepts of the described embodiments difficult to understand, well-known structures and devices are shown in block diagram form.

[0148] The above description of the present disclosure is provided to enable any person of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to those of ordinary skill in the art, and the general principles corresponding to the present disclosure may be applied to other variations without departing from the scope of protection of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is consistent with the widest range of principles and novel features disclosed herein.

Claims

1. A method for bridge health monitoring based on millimeter wave radar, characterized in that: A dynamic weighing system is arranged at the target position of the bridge, and millimeter-wave radar sensors and targets corresponding to the positions are arranged at both ends of the target position respectively; the method comprises: Obtaining the dynamic load change data fed back in real time by the dynamic weighing system; Acquire the dynamic change data of the expansion joint displacement fed back by the millimeter wave radar sensor in real time, and perform baseline correction on the dynamic change data of the expansion joint displacement; Predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement; Send early warning information when there is a problem with the health of the bridge.

2. The method according to claim 1, characterized in that The step of predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement comprises: Traversing the instantaneous load at each moment in the load dynamic change data, extracting instantaneous loads of similar magnitude and their corresponding moments, and collecting them into a first queue; Based on the first queue and the dynamic change data of the expansion joint displacement, the health status of the bridge is predicted.

3. The method according to claim 2, characterized in that The step of predicting the health status of the bridge based on the first queue and the dynamic change data of the expansion joint displacement includes: Extracting the instantaneous displacement fluctuation corresponding to the instantaneous load in the first queue from the dynamic change data of the expansion joint displacement, and collecting it into the second queue; Determine whether the difference of the instantaneous displacement fluctuation amount in the second queue is greater than a first threshold; If yes, then there is a problem with the health of the bridge.

4. The method according to claim 1, characterized in that: The step of predicting the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement comprises: Traversing the instantaneous displacement fluctuation at each moment in the dynamic change data of the expansion joint displacement, extracting the instantaneous displacement fluctuation greater than the second threshold and its corresponding moment, and collecting them into a third queue; Based on the third queue, load prediction change data of the bridge is obtained, wherein the load prediction change data includes predicted loads at each moment; The health status of the bridge is predicted based on the load prediction change data and the load dynamic change data.

5. The method according to claim 4, characterized in that The step of predicting the health status of the bridge based on the load prediction change data and the load dynamic change data comprises: Calculating the difference between the load prediction change data and the load data at corresponding moments in the load dynamic change data, and determining whether there is a difference greater than a third threshold; If yes, then there is a problem with the health of the bridge.

6. The method according to claim 1, characterized in that Also includes: Acquiring temperature change data and / or humidity change data; Inputting the temperature at the target time in the temperature change data and / or the humidity at the target time in the humidity change data into a pre-trained deep learning neural network model to obtain a predicted reference value of the expansion joint at the target time; The health status of the bridge is predicted based on the predicted reference value and the dynamic change data of the expansion joint displacement.

7. The method according to claim 6, characterized in that The step of predicting the health status of the bridge based on the predicted reference value and the dynamic change data of the expansion joint displacement comprises: Extracting the actual reference value of the expansion joint at the target time from the dynamic change data of the expansion joint displacement, calculating the difference between the predicted reference value and the actual reference value, and judging whether the difference is greater than a fourth threshold; If so, there is a problem with the health of the bridge.

8. A bridge health monitoring device based on millimeter wave radar, characterized in that: The target position of the bridge is provided with a dynamic weighing system, and both ends of the target position are provided with millimeter-wave radar sensors and targets corresponding to the positions; the device comprises: A load acquisition module, used to acquire the dynamic load change data fed back in real time by the dynamic weighing system; An expansion joint displacement acquisition module is used to acquire the dynamic change data of the expansion joint displacement fed back by the millimeter wave radar sensor in real time, and perform baseline correction on the dynamic change data of the expansion joint displacement; A prediction module, used to predict the health status of the bridge based on the dynamic change data of the load and the dynamic change data of the expansion joint displacement; The early warning module is used to send early warning information when there are problems with the health status of the bridge.

9. An electronic device, comprising: at least one processor; as well as A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the method for bridge health monitoring based on millimeter wave radar as described in any one of claims 1 to 7.

10. A machine-readable storage medium storing executable instructions, which, when executed, enable the machine to perform the method for bridge health monitoring based on millimeter-wave radar according to any one of claims 1 to 7.

Images