Bridge dynamic weighing method, system, equipment and medium based on combination of radar and vision

Abstract

A bridge dynamic weighing method, system, equipment and medium based on the combination of radar and vision, the bridge dynamic weighing method includes: constructing a bridge structure strain observation function based on the strain data obtained by the bridge dynamic strain sensor module; obtaining the bridge deck vehicle traffic parameters by fusion analysis of radar and camera sensor modules; solving the target vehicle weight based on the strain response lateral distribution algorithm, and combining the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge. The present application can integrate radar and vision information to accurately perceive the bridge deck vehicle traffic parameters, and is not affected by the external natural environment. It can realize the multi-vehicle weight recognition under complex traffic conditions in all weather and all time periods, and solves the technical problems existing in the related technologies that visual perception is seriously affected by external lighting conditions and bad weather, and that the radar perception method has shortcomings such as weak azimuth measurement and target omission.

Description

Technical Field

[0001] The present application relates to the field of vehicle weighing technology, and in particular to a method, system, equipment and medium for dynamic weighing of bridges based on the combination of radar and vision. Background Art

[0002] At present, there are a large number of bridges in service in my country. As the service age increases, the structural bearing capacity declines due to the aging of bridge components themselves. In addition, the demand for transportation continues to expand, and the actual daily load of bridges has far exceeded the estimated traffic volume during design. While developing transportation, how to effectively prevent and control the problem of overload is a common problem faced by the operation and maintenance of bridges in service in my country. Accurately identifying the traffic parameters and weight information of vehicles passing on the bridge is of great guiding significance for controlling overloaded vehicles, statistically analyzing bridge traffic patterns, and constructing bridge traffic load spectra, thereby evaluating bridge safety performance.

[0003] The bridge dynamic weighing technology uses the bridge structure response when the vehicle passes the bridge to invert the weight of the vehicle passing the bridge. Due to its advantages such as high stability, good durability and low implementation cost, this technology has been widely used in recent years. However, in the traditional bridge dynamic weighing system, the FAD sensor identification of the axle is affected by the coupling of multiple factors such as bridge type, bridge span, bridge deck thickness, road surface flatness, etc., which restricts the further promotion and application of this technology.

[0004] In related technologies, with the development of computer vision technology, a large number of scholars have introduced this technology into the bridge dynamic weighing system to identify vehicle traffic parameters. This method has high recognition accuracy and is not affected by the characteristics of the bridge structure itself. However, visual perception is seriously affected by external lighting conditions and bad weather. Compared with visual perception, radar perception has strong weather adaptability and can accurately identify vehicle traffic parameters in bad weather environments. However, this method has shortcomings such as weak azimuth measurement and target omission, and when the distance between the measured targets is close, it is easy to identify a single target as multiple targets.

[0005] Therefore, it is necessary to design a new bridge dynamic weighing method based on the combination of radar and vision to overcome the above problems. Summary of the invention

[0006] The present application provides a method, system, equipment and medium for dynamic weighing of bridges based on the combination of radar and vision, which can solve the technical problems existing in the related art that visual perception is seriously affected by external lighting conditions and bad weather, and that radar perception methods have shortcomings such as weak azimuth measurement and target omission.

[0007] In a first aspect, an embodiment of the present application provides a bridge dynamic weighing method based on the combination of radar and vision, and the bridge dynamic weighing method includes:

[0008] The bridge structure strain observation function is constructed based on the strain data obtained by the bridge dynamic strain sensing module;

[0009] Use radar and camera sensor modules to fuse and analyze to obtain bridge vehicle traffic parameters;

[0010] Based on the strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain benchmark function for vehicles crossing the bridge, the target vehicle weight is calculated.

[0011] In combination with the first aspect, in one embodiment, before calculating the target vehicle weight based on the strain response lateral distribution algorithm and combining the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge, the method further includes:

[0012] The bridge deck vehicle traffic parameters are aligned with the bridge structure strain observation function based on the time alignment method.

[0013] In combination with the first aspect, in one implementation, the step of constructing a bridge structure strain observation function based on strain data acquired by a bridge dynamic strain sensing module includes:

[0014] Calculate effective strain data based on the original strain data obtained by the bridge dynamic strain sensing module;

[0015] Comparing the effective strain data with the vehicle identification strain threshold;

[0016] When multiple consecutive valid strain data are greater than the vehicle identification strain threshold, a weighing warning is triggered;

[0017] The mean value of the original strain data before or after the vehicle crosses the bridge is taken as the baseline of the vehicle crossing the bridge strain, and the bridge structure strain observation function is constructed by combining the original strain data of the entire vehicle crossing the bridge.

[0018] In combination with the first aspect, in one implementation, the calculating effective strain data based on the original strain data acquired by the bridge dynamic strain sensing module includes:

[0019] The original strain data measured by the bridge dynamic strain sensing module is acquired in real time and continuously pushed to the baseline autonomous update sliding window queue. When the number of input original strain data is greater than the queue window length, the earliest input original strain data in the queue is discarded and updated to the latest queue.

[0020] The strain baseline is calculated based on the long sliding window queue with baseline autonomous update, and the effective strain data is calculated in combination with the original strain data.

[0021] In combination with the first aspect, in one embodiment, before calculating the target vehicle weight based on the strain response lateral distribution algorithm and combining the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge, the method further includes:

[0022] The strain influence surface of the bridge structure is calibrated through controlled experiments, and a strain benchmark function of the bridge structure for vehicles crossing the bridge is constructed.

[0023] In combination with the first aspect, in one implementation, the bridge dynamic strain sensing module includes a plurality of dynamic strain sensors installed along the bottom of the same section of the bridge beam; the bridge structure strain influence surface calibration is achieved through controlled testing, and a bridge structure strain reference function for vehicles crossing the bridge is constructed, including:

[0024] Construct the calibration vehicle parallel lane line along the bridge lateral position The strain time history function of each dynamic strain sensor that passes the bridge once at a uniform speed is:

[0025] ,in, is the strain time history function of the dynamic strain sensor, Indicates that the lateral position of the parallel lane line of the calibrated vehicle along the bridge is When passing the bridge Dynamic strain sensor Strain data;

[0026] Based on the strain time history function of each dynamic strain sensor And the weight of the vehicle , calculate the bridge structure strain benchmark function for vehicles passing through the bridge .

[0027] In combination with the first aspect, in one implementation, after obtaining the bridge deck vehicle traffic parameters by fusion analysis using the radar and camera sensor modules, the method further includes:

[0028] The information fusion of radar and camera is realized based on the registration of radar coordinate system to image coordinate system.

[0029] In a second aspect, an embodiment of the present application provides a bridge dynamic weighing system, the bridge dynamic weighing system comprising:

[0030] Bridge dynamic strain sensing module and radar and camera sensing module;

[0031] A structural response acquisition module, which is used to construct a bridge structure strain observation function based on the strain data acquired by the bridge dynamic strain sensing module;

[0032] A vehicle parameter acquisition module is used to obtain the vehicle parameters on the bridge deck by fusion analysis of radar and camera sensor modules;

[0033] The solution module is used to solve the target vehicle weight based on the strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge.

[0034] In a third aspect, an embodiment of the present application provides a bridge dynamic weighing device, which includes a processor, a memory, and a bridge dynamic weighing program stored in the memory and executable by the processor, wherein when the bridge dynamic weighing program is executed by the processor, the steps of the above-mentioned bridge dynamic weighing method are implemented.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a bridge dynamic weighing program is stored, wherein when the bridge dynamic weighing program is executed by a processor, the steps of the above-mentioned bridge dynamic weighing method are implemented.

[0036] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0037] Through the strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters obtained by the fusion analysis of the radar and camera sensor modules, the bridge structure strain observation function and the constructed bridge structure strain reference function of the vehicle crossing the bridge, the target vehicle weight can be solved, and the bridge deck vehicle traffic parameters can be accurately perceived by integrating the radar vision information, without being disturbed by the external natural environment. It can realize the weight recognition of multiple vehicles under complex traffic conditions in all weather and all time periods, and solves the technical problems existing in related technologies that visual perception is seriously affected by external lighting conditions and bad weather, and that radar perception methods have shortcomings such as weak azimuth measurement and target omission. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flow chart of an embodiment of a bridge dynamic weighing method of the present application;

[0039] Figure 2 A schematic diagram of an embodiment of a bridge dynamic weighing system of the present application;

[0040] Figure 3 This is a flow chart of the dynamic weighing algorithm for bridges in this application;

[0041] Figure 4 This is a schematic diagram of the structure of the bridge dynamic weighing system installed on the bridge in this application;

[0042] Figure 5This is a schematic diagram of the hardware structure of the dynamic weighing equipment for bridges involved in the embodiment of the present application.

[0043] In the figure:

[0044] 1. Radar and camera sensor module; 2. Dynamic strain sensor; 3. Strain acquisition equipment. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution 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 this field without creative work are within the scope of protection of this application.

[0046] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0047] In a first aspect, an embodiment of the present application provides a dynamic weighing method for a bridge based on a combination of radar and vision.

[0048] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the bridge dynamic weighing method of this application. Figure 1 As shown, the dynamic weighing method of bridge includes:

[0049] S1: Construct the bridge structure strain observation function based on the strain data obtained by the bridge dynamic strain sensing module.

[0050] S2: Obtain the traffic parameters of the bridge deck vehicles by fusion analysis of the radar and camera sensor module 1.

[0051] S3: Based on the strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain benchmark function for vehicles crossing the bridge, the target vehicle weight is calculated.

[0052] In this embodiment, before constructing the bridge structure strain observation function, a bridge dynamic strain sensing module can be installed at a set position. The bridge dynamic strain sensing module is a plurality of dynamic strain sensors 2 ( Figure 4As shown), the dynamic strain sensor 2 can obtain the bridge strain data in real time, and a weighing warning can be triggered when a vehicle passes on the bridge deck, and a bridge structure strain observation function can be constructed based on the strain data obtained by multiple dynamic strain sensors 2. In step S2, the radar and camera sensor module 1 is first installed at the set position. The radar and camera sensor module 1 integrates the radar and the camera, and the coordinate systems of the radar and the camera can be unified and jointly calibrated. The bridge deck vehicle traffic parameters are obtained through redundant perception fusion analysis of the data obtained by the radar and the camera. The bridge deck vehicle traffic parameters can specifically include vehicle speed and vehicle trajectory. The radar and the camera have a perception overlap area to meet the radar and camera information fusion requirements.

[0053] This embodiment uses a strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters obtained by the fusion analysis of the radar and camera sensor module 1, the bridge structure strain observation function and the constructed bridge structure strain reference function of the vehicle crossing the bridge, to calculate the target vehicle weight, and can accurately perceive the bridge deck vehicle traffic parameters by integrating the information captured by the radar and the camera, and is not affected by the external natural environment. It can realize the weight recognition of multiple vehicles in complex traffic conditions under all weather and all time periods, and solves the technical problems existing in the related technologies that visual perception is seriously affected by external lighting conditions and bad weather, and that the radar perception method has deficiencies such as weak azimuth measurement and target omission.

[0054] Furthermore, in one embodiment, before solving the target vehicle weight based on the strain response lateral distribution algorithm, and combining the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge, that is, between steps S2 and S3, it can also include: aligning the bridge deck vehicle traffic parameters with the bridge structure strain observation function based on the time alignment method. In this embodiment, the two sets of data, the bridge deck vehicle traffic parameters and the bridge structure strain observation function, can be associated together through timestamps, so that the data of the two systems at the same time are associated. Through the registration, the spatiotemporal position of the bridge deck vehicle and the structural response can be achieved in a one-to-one correspondence.

[0055] Furthermore, in some embodiments, constructing a bridge structure strain observation function based on the strain data acquired by the bridge dynamic strain sensing module may include:

[0056] S11: Calculate effective strain data based on the original strain data obtained by the bridge dynamic strain sensing module.

[0057] S12: Compare the effective strain data with the vehicle identification strain threshold.

[0058] S13: When the valid strain data is greater than the vehicle identification strain threshold for multiple consecutive times, a weighing warning is triggered.

[0059] S14: Take the average of the original strain data before or after the vehicle crosses the bridge as the baseline of the vehicle crosses the bridge strain, and construct the bridge structure strain observation function in combination with the original strain data of the entire process of the vehicle crossing the bridge.

[0060] In this embodiment, multiple dynamic strain sensors 2 are installed at the bottom of the same cross-section beam of the transverse bridge, and the original strain data of each dynamic strain sensor 2 is obtained in real time, and the effective strain data is calculated based on the original strain data of each dynamic strain sensor 2. ; Comparison of effective strain data The effective strain data of each dynamic strain sensor 2 and the vehicle identification strain threshold. When there is a dynamic strain sensor 2 with effective strain data greater than the vehicle identification strain threshold for multiple consecutive times, it is judged as a vehicle crossing the bridge event, triggering a weighing warning, where the vehicle identification strain threshold is determined based on a controlled test. Extract the original strain data of the entire process of the vehicle crossing the bridge event, take the average of the appropriate original strain data before or after the event as the baseline of the vehicle crossing the bridge strain, and construct the strain observation function:

[0061] ,in Indicates the vehicle crossing the bridge event Dynamic strain sensor 2 The vehicle strain is determined by: , The first vehicle crossing the bridge Dynamic strain sensor 2 The original strain data; For the corresponding Dynamic strain sensor 2 The strain baseline of the original strain data.

[0062] Since the original strain data includes the influence of multiple effects such as environmental effects and temperature drift, this embodiment uses effective strain data to compare and judge with the vehicle identification strain threshold. The effective strain data eliminates the effects of non-vehicle effects contained in the original strain data, ensuring that the alarm event is a real alarm.

[0063] Furthermore, in step S11, the calculation of effective strain data based on the original strain data acquired by the bridge dynamic strain sensing module includes:

[0064] S111: acquiring the original strain data measured by the bridge dynamic strain sensing module in real time, and continuously pushing it to the baseline autonomous update sliding window length queue. When the number of input original strain data is greater than the queue window length, the earliest input original strain data in the queue is discarded and updated to the latest queue;

[0065] S112: Calculate the strain baseline based on the baseline autonomous update sliding window long queue, and calculate the effective strain data in combination with the original strain data.

[0066] In this embodiment, the original strain data of each dynamic strain sensor 2 is obtained in real time and continuously pushed to the baseline autonomous update sliding window length queue. When the number of input data is greater than the queue window length, the earliest input data in the queue is discarded and updated to the latest input data. The queue can be expressed as:

[0067] ,

[0068] in, Indicates The output of the dynamic strain sensor 2 is The original strain data are selected, and the queue window length is selected based on the principle of stabilizing the baseline recognition.

[0069] Take the baseline to autonomously update the sliding window long queue Before the sensor The median value of the original strain data is taken as the The baseline of the strain bar is used to calculate the effective strain data :

[0070]

[0071] in, Express The front of the dynamic strain sensor 2 The median value of the original strain data was taken.

[0072] In the above embodiment, the strain baseline is calculated to exclude strain changes caused by non-vehicle loads; the use of a finite window length can, on the one hand, reduce the amount of calculation and ensure the real-time performance of the baseline calculation; on the other hand, a suitable window length can ensure that the baseline deviates from the true baseline due to strain response interference caused by the passage of the preceding vehicle.

[0073] On the basis of the above technical solution, in the radar and camera sensor module 1, the radar perception and identification of vehicle traffic parameters is to emit high-frequency electromagnetic waves to surrounding objects and receive echoes, and the distance of the measured target can be obtained by calculating the time of electromagnetic wave reflection. When there is relative motion between the radar and the target, the radar echo will produce a Doppler frequency shift effect, so by comparing the frequency shift before and after the electromagnetic wave reflection, the speed of the measured target can be obtained; the camera's visual perception and identification of vehicle traffic parameters is based on deep learning methods to identify target trajectories and types, and convert them into world coordinates based on affine transformation.

[0074] On the basis of the above technical solution, after the radar and camera sensor module 1 are used to fuse and analyze the acquired bridge vehicle traffic parameters, it also includes: realizing the information fusion of the radar and camera images based on the alignment of the radar coordinate system to the image coordinate system.

[0075] Furthermore, before solving the target vehicle weight based on the strain response lateral distribution algorithm, and combining the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge, it can also include: calibrating the bridge structure strain influence surface through controlled experiments, and constructing a bridge structure strain reference function for vehicles crossing the bridge.

[0076] Preferably, the bridge dynamic strain sensing module includes a plurality of dynamic strain sensors 2 installed along the bottom of the same section of the bridge beam; the bridge structure strain influence surface calibration through controlled experiments and the construction of the bridge structure strain reference function for vehicles crossing the bridge may include:

[0077] Step a: Construct the lateral position of the parallel lane line of the vehicle along the bridge as The strain time history function of each dynamic strain sensor 2 that passes the bridge once at a uniform speed is:

[0078] ,in, is the strain time history function of dynamic strain sensor 2, t indicates that the matrix is ​​the time domain matrix for calibrating vehicle traffic, Indicates that the lateral position of the parallel lane line of the calibrated vehicle along the bridge is When passing the bridge Dynamic strain sensor 2 Here, The strain data are the original strain data.

[0079] Step b: Based on the strain time history function of each dynamic strain sensor 2 And the weight of the vehicle , calculate the bridge structure strain benchmark function for vehicles passing through the bridge .

[0080] In this embodiment, the specific steps of constructing the bridge structure strain reference function for vehicles crossing the bridge include:

[0081] Based on a single calibration with known vehicle weight, the vehicle passes the bridge multiple times at a uniform speed along different transverse positions along parallel lane lines. The number of passes at each transverse position is determined based on the principle that the vehicle strain tends to be stable, and the transverse position is selected based on the principle that the structural influence surface calibration is accurate.

[0082] Construct the calibration vehicle parallel lane line along the bridge lateral position The strain time history function of each dynamic strain sensor 2 in a single bridge crossing event with a uniform speed , calculated as follows:

[0083] ,in, Indicates that the lateral position of the parallel lane line of the calibrated vehicle along the bridge is When passing the bridge Dynamic strain sensor 2 Strain data.

[0084] It is known that the sampling frequency of dynamic strain sensor 2 is , the vehicle's current speed is calibrated as , then the original strain time history function Can be converted into bridge space domain function :

[0085] . Among them, s indicates that the matrix is ​​a calibration vehicle traffic space domain matrix, which corresponds to the time domain matrix above. Because the influence surface of the bridge structure is obtained for different spatial positions of the bridge, and the dynamic strain response data is time series data, the time domain data must be converted into space domain data.

[0086] The original spatial domain function is reconstructed through the spline interpolation function:

[0087] .

[0088] in, Indicates that the lateral position of the parallel lane line of the calibrated vehicle along the bridge is When passing the bridge The dynamic strain sensors 2 are located at the bridge span Vehicle response.

[0089] The lateral position of the parallel lane line of the vehicle along the bridge is calibrated as Repeat the passage n times, and the spatial domain function corresponding to the bridge can be calculated as follows:

[0090] .

[0091] The weight of the calibrated vehicle is known to be , the bridge structure strain benchmark function for vehicles passing through the bridge The calculation formula can be expressed as follows:

[0092] .

[0093] See also Figure 3 As shown, based on the above technical solution, the specific steps of calculating the target vehicle weight may include:

[0094] Based on the radar and camera sensor module 1, the number, speed and trajectory parameters of passing vehicles can be obtained to construct the residual equation:

[0095] .

[0096] In the formula, The weights are of n A vehicle queue formed by vehicles; is the strain observation function; Indicates the vehicle crossing the bridge event Dynamic strain sensor Vehicle strain; theoretical strain response = ; Indicates the corresponding i Vehicles passing in the horizontal position of the bridge m The corresponding spatial domain function at time is, Indicates i A car in k The vehicle should pass through the bridge in the forward direction at the corresponding moment.

[0097] It is not difficult to find that the minimum value of the residual function is obtained when its gradient is 0. Vehicle load Partial derivative of:

[0098] .

[0099] By setting the above formula equal to 0, we can obtain the best estimate of the vehicle load in the sense of minimum Euclidean distance:

[0100] .

[0101] Among them, the best estimate is the smallest residual between the theoretical weight and the calculated weight. can be regarded as the target vehicle weight, where is the vehicle queue vector, which contains the weight of each vehicle.

[0102] In a second aspect, an embodiment of the present application also provides a bridge dynamic weighing system.

[0103] like Figure 2 and Figure 4As shown, the dynamic weighing system of the bridge includes: a bridge dynamic strain sensing module and a radar and camera sensing module 1; and a structural response acquisition module, which is used to construct a bridge structure strain observation function based on the strain data obtained by the bridge dynamic strain sensing module; a passing vehicle parameter acquisition module, which is used to obtain the bridge deck vehicle passing parameters by fusion analysis of the radar and camera sensing module 1; a solution module, which is used to solve the target vehicle weight based on the strain response lateral distribution algorithm, combined with the bridge deck vehicle passing parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function of the vehicle crossing the bridge.

[0104] In this embodiment, the bridge dynamic strain sensing module includes a plurality of dynamic strain sensors 2, and the plurality of dynamic strain sensors 2 are installed at the bottom of the beam with the same cross section in the transverse direction of the bridge. The radar and camera sensing module 1 integrates a radar and a camera, and is installed at a set position.

[0105] Furthermore, in one embodiment, the bridge dynamic weighing system also includes a calibration module, which is used to realize the bridge structure strain influence surface calibration through controlled experiments and construct the bridge structure strain reference function of vehicles passing the bridge. And the bridge dynamic weighing system also includes a transmission module, which is used to transmit the vehicle information of the target vehicle to the background server in real time based on the calculated target vehicle weight when the target vehicle weight is greater than the preset weight.

[0106] Among them, the functional implementation of each module in the above-mentioned bridge dynamic weighing system corresponds to the various steps in the above-mentioned bridge dynamic weighing method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0107] This application is based on multi-source information such as vehicle traffic information, multi-lane response matrix, real-time dynamic strain response, etc., and uses non-negative matrix decomposition to calculate the actual single vehicle weight of each lane, and combines the calibrated bridge influence surface to determine whether the lane combination weight exceeds the design specification load. The present invention does not require excavation of the road surface to lay sensor elements, has little impact on traffic on the bridge, and has low cost. At the same time, it improves the dynamic weighing coverage range, realizes vehicle traffic condition identification and vehicle weight solution under complex vehicle traffic conditions on the entire bridge deck of a multi-lane bridge, and realizes all-weather identification of vehicle traffic conditions; at the same time, it adopts the data processing method of "edge-end-cloud" collaborative computing, which saves edge computing terminal computing power and reduces hardware costs; this application is suitable for common small and medium-sized bridges such as hollow slab beam bridges, T-beam bridges, and prefabricated beam bridges.

[0108] In a third aspect, the present application provides a bridge dynamic weighing device. Figure 5 As shown, in the embodiment of the present application, the dynamic weighing equipment for a bridge may include a processor, a memory, a communication interface and a communication bus.

[0109] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0110] The communication interface includes input / output (I / O) interface, physical interface and logical interface, which are used to realize the interconnection of devices inside the bridge dynamic weighing equipment, and the interface used to realize the interconnection of the bridge dynamic weighing equipment with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display (Display), a keyboard (Keyboard), etc.

[0111] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0112] The processor may be a general-purpose processor, which may call the bridge dynamic weighing program stored in the memory and execute the bridge dynamic weighing method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the bridge dynamic weighing program is called may refer to the various embodiments of the bridge dynamic weighing method of the present application, which will not be described in detail here.

[0113] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0114] The readable storage medium of the present application stores a bridge dynamic weighing program, wherein when the bridge dynamic weighing program is executed by a processor, the steps of the bridge dynamic weighing method as described above are implemented.

[0115] Among them, the method implemented when the dynamic weighing program of the bridge is executed can refer to the various embodiments of the dynamic weighing method of the bridge in this application, and will not be repeated here.

[0116] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0117] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0118] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "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 "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0119] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0120] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0122] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A bridge dynamic weighing method based on the combination of radar and vision, characterized in that: The bridge dynamic weighing method comprises: The bridge structure strain observation function is constructed based on the strain data obtained by the bridge dynamic strain sensing module; The radar and camera sensor modules (1) are used to perform fusion analysis to obtain the traffic parameters of the bridge deck vehicles; The bridge structure strain influence surface is calibrated through controlled tests, and the bridge structure strain benchmark function for vehicles crossing the bridge is constructed; Based on the strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain benchmark function for vehicles crossing the bridge, the target vehicle weight is calculated.

2. The bridge dynamic weighing method according to claim 1, characterized in that: Before calculating the target vehicle weight based on the strain response lateral distribution algorithm, and combining the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge, the following is also included: The bridge deck vehicle traffic parameters are aligned with the bridge structure strain observation function based on the time alignment method.

3. The bridge dynamic weighing method according to claim 1, characterized in that: The method of constructing a bridge structure strain observation function based on the strain data obtained by the bridge dynamic strain sensing module includes: Calculate effective strain data based on the original strain data obtained by the bridge dynamic strain sensing module; comparing the effective strain data with the vehicle identification strain threshold; When multiple consecutive valid strain data are greater than the vehicle identification strain threshold, a weighing warning is triggered; The mean value of the original strain data before or after the vehicle crosses the bridge is taken as the baseline of the vehicle crossing the bridge strain, and the bridge structure strain observation function is constructed by combining the original strain data of the entire vehicle crossing the bridge.

4. The bridge dynamic weighing method according to claim 3, characterized in that: The calculating of effective strain data based on the original strain data acquired by the bridge dynamic strain sensing module includes: The original strain data measured by the bridge dynamic strain sensing module is acquired in real time and continuously pushed to the baseline autonomous update sliding window queue. When the number of input original strain data is greater than the queue window length, the earliest input original strain data in the queue is discarded and updated to the latest queue. The strain baseline is calculated based on the long sliding window queue with baseline autonomous update, and the effective strain data is calculated in combination with the original strain data.

5. The bridge dynamic weighing method according to claim 1, characterized in that: The bridge dynamic strain sensing module comprises a plurality of dynamic strain sensors (2) installed along the bottom of the same section of the bridge beam; the bridge structure strain influence surface calibration is achieved through controlled testing, and a bridge structure strain reference function for vehicles crossing the bridge is constructed, comprising: Construct the calibration vehicle parallel lane line along the bridge lateral position The strain time history function of each dynamic strain sensor (2) that passes the bridge once at a constant speed is: ,in, is the strain time history function of the dynamic strain sensor (2), Indicates that the lateral position of the parallel lane line of the calibrated vehicle along the bridge is When passing the bridge Dynamic strain sensor (2) Strain data; Based on each dynamic strain sensor (2) strain time function And the weight of the vehicle , calculate the bridge structure strain benchmark function for vehicles passing through the bridge .

6. The bridge dynamic weighing method according to claim 1, characterized in that: After obtaining the bridge deck vehicle traffic parameters by fusion analysis using the radar and camera sensor modules (1), the method further includes: The information fusion of radar and camera is realized based on the registration of radar coordinate system to image coordinate system.

7. A bridge dynamic weighing system, characterized in that: The bridge dynamic weighing system comprises: Bridge dynamic strain sensing module and radar and camera sensing module (1); A structural response acquisition module, which is used to construct a bridge structure strain observation function based on the strain data acquired by the bridge dynamic strain sensing module; A vehicle passing parameter acquisition module, which is used to obtain the vehicle passing parameters on the bridge deck by fusion analysis using the radar and camera sensor modules (1); A construction module is used to calibrate the strain influence surface of the bridge structure through controlled tests and to construct a strain reference function of the bridge structure for vehicles crossing the bridge; The solution module is used to solve the target vehicle weight based on the strain response lateral distribution algorithm, combined with the bridge deck vehicle traffic parameters, the bridge structure strain observation function and the constructed bridge structure strain reference function for vehicles crossing the bridge.

8. A bridge dynamic weighing device, characterized in that: The bridge dynamic weighing device includes a processor, a memory, and a bridge dynamic weighing program stored in the memory and executable by the processor, wherein when the bridge dynamic weighing program is executed by the processor, the steps of the bridge dynamic weighing method as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a bridge dynamic weighing program, wherein when the bridge dynamic weighing program is executed by a processor, the steps of the bridge dynamic weighing method according to any one of claims 1 to 6 are implemented.

Images