A vehicle weight detection method and device

Abstract

The application is suitable for the field of weighing technology, and provides a vehicle weight detection method and device.The method comprises the following steps: obtaining weighing information of a vehicle, wherein the weighing information comprises weighing data collected by a strip weighing sensor and collection time; obtaining a time-weight curve of a vehicle axle passing through a weighing area based on the weighing information; converting the time-weight curve into a displacement-weight curve; determining weighing characteristic information according to the displacement-weight curve; inputting the weighing characteristic information into a preset weighing model to obtain a prediction result of the vehicle weight, which can obtain an accurate vehicle weight through a small amount of weighing characteristic information, does not need to determine the vehicle weight based on all weighing data, can reduce the cost of hardware equipment, improve the robustness of the weighing model, and can also obtain an accurate vehicle weight when part of the weighing data is missing, and meanwhile, the extraction of the weighing characteristic information can highlight the detailed features of the weighing data, thereby improving the weighing accuracy.

Description

Technical Field

[0001] This application belongs to the field of weighing technology, and in particular relates to a method and device for detecting vehicle weight. Background Technology

[0002] Currently, there are two main types of bar weighing sensors: narrow bar weighing sensors and quartz bar weighing sensors. The narrow bar dynamic truck scales and quartz dynamic truck scales composed of these sensors have the characteristics of small deformation and fast response. Compared with vehicle-type dynamic truck scales, axle-type dynamic truck scales, and axle-load-type dynamic truck scales, they are better able to adapt to the dynamic weighing of vehicles at higher speeds (above 20km / h).

[0003] The weighing method of dynamic truck scales composed of bar sensors mainly relies on the product of speed and the integral of the weighing curve. However, this technique requires all the weighing data collected. If data is missing due to interference during data collection, the weighing results will be inaccurate. Moreover, the method of using all weighing data ignores the detailed features collected by the bar weighing sensor, thus failing to achieve high weighing accuracy. Summary of the Invention

[0004] This application provides a vehicle weight detection method and apparatus that can solve the problems of missing weighing data and improve weighing accuracy.

[0005] In a first aspect, embodiments of this application provide a vehicle weight detection method, including:

[0006] Acquire vehicle weighing information, wherein the weighing information includes the acquisition time of the bar weighing sensor and the weighing data acquired corresponding to the acquisition time;

[0007] Based on the weighing information, the time-weight curve of the vehicle wheel axle passing through the weighing area is obtained, and the time-weight curve is converted into a displacement-weight curve.

[0008] Weighing characteristic information is determined based on the displacement-weight curve;

[0009] Based on the weighing feature information, the vehicle weight is predicted by inputting it into a preset weighing model.

[0010] In one embodiment, converting the time-weight curve into a displacement-weight curve includes:

[0011] Based on the time-weight curves of different bar weighing sensors, the time-displacement curves of the vehicle wheel axle passing through the weighing area are obtained;

[0012] The displacement-weight curve is determined based on the time-weight curve and time-displacement curve of the vehicle wheel axle passing through the weighing area.

[0013] In one embodiment, determining weighing characteristic information based on the displacement-weight curve includes:

[0014] Based on the displacement-weight curve, n displacement points and their corresponding weighing data are selected as weighing feature information, where n≥5.

[0015] In one embodiment, the n displacement points are selected by random sampling, stratified sampling, systematic sampling, or cluster sampling.

[0016] In one embodiment, the average distance between any two adjacent displacement points among the n displacement points is greater than a preset threshold.

[0017] In one embodiment, the step of inputting the weighing feature information into a preset weighing model to obtain a predicted vehicle weight includes:

[0018] Substituting the displacement X and the weighing information Z from the weighing characteristic information into the deflection equation, we obtain the information about the spring constant k. z The overdetermined set of equations for the moment of inertia I, tension T, and elastic coefficient E, wherein the deflection equation is: ;

[0019] In the spring constant k z The optimal combination of the rotational inertia I, the tension T, and the elastic coefficient E within a preset range is selected to obtain the optimal solution of the overdetermined equation system.

[0020] The spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted weight of the vehicle. The preset formula is as follows:

[0021] ;

[0022] Among them, F z Z is the predicted weight of the vehicle. o This represents the maximum value of radial deformation. It is a constant. .

[0023] In one embodiment, the method further includes:

[0024] Obtain at least two of the prediction results, and derive the vehicle weight based on the prediction results.

[0025] In one embodiment, the method further includes:

[0026] Obtain preset weighing models and corresponding prediction results for different n values, and obtain the vehicle weight based on the prediction results.

[0027] In one embodiment, obtaining the optimal solution to the overdetermined system of equations includes:

[0028] The optimal solution to the overdetermined system of equations is obtained using a machine learning model.

[0029] In one embodiment, the weighing feature information is used as a model feature and the low-speed station data is used as a model label to establish a weighing model between the model feature and the model label, thereby obtaining the preset weighing model.

[0030] Secondly, embodiments of this application provide a vehicle weight detection device, comprising:

[0031] The acquisition module is used to acquire the vehicle's weighing information, wherein the weighing information includes the weighing data acquired by the bar weighing sensor and the acquisition time;

[0032] The data processing module is used to obtain the time-weight curve of the vehicle wheel axle when it passes through the weighing area from the weighing information, and to convert the time-weight curve into a displacement-weight curve.

[0033] Used to determine weighing characteristic information based on the displacement-weight curve;

[0034] Furthermore, based on the weighing feature information, the predicted vehicle weight is obtained by inputting it into a preset weighing model.

[0035] In one embodiment, the data processing module is specifically used for:

[0036] Substituting the displacement X and the weighing information Z from the weighing characteristic information into the deflection equation, we obtain the information about the spring constant k. z The overdetermined set of equations for the moment of inertia I, tension T, and elastic coefficient E, wherein the deflection equation is: ;

[0037] In the spring constant k z The optimal combination of the rotational inertia I, the tension T, and the elastic coefficient E within a preset range is selected to obtain the optimal solution of the overdetermined equation system.

[0038] The spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted weight of the vehicle. The preset formula is as follows:

[0039] ;

[0040] Among them, Fz Z is the predicted weight of the vehicle. o This represents the maximum value of radial deformation. It is a constant. .

[0041] In one embodiment, the length of the strip-shaped load cell along the vehicle's direction of travel is less than 100 mm, and it may be one or more of a narrow strip load cell, a quartz load cell, and a piezoelectric load cell.

[0042] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any one of the first aspects above.

[0043] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any one of the first aspects above.

[0044] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the method described in any one of the first aspects above.

[0045] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0046] The beneficial effects of the embodiments in this application compared with the prior art are:

[0047] This application embodiment acquires vehicle weighing information, including weighing data and acquisition time collected by a bar weighing sensor; based on the weighing information, it obtains the time-weight curve of the vehicle's wheel axle passing through the weighing area, and converts the time-weight curve into a displacement-weight curve; it determines weighing feature information based on the displacement-weight curve; based on the weighing feature information, it inputs it into a preset weighing model to obtain a predicted vehicle weight. This allows for accurate vehicle weight determination using only a small amount of weighing feature information, eliminating the need to determine the vehicle weight based on all weighing data. This reduces data processing volume, lowers hardware costs, and improves the robustness of the weighing model. Even when some weighing data is missing, accurate vehicle weight can still be obtained. Furthermore, by extracting weighing feature information, it highlights the detailed features of the weighing data, thereby improving weighing accuracy. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic flowchart of a vehicle weight detection method provided in an embodiment of this application;

[0050] Figure 2 This is a schematic diagram of the arrangement of a bar weighing sensor provided in an embodiment of this application;

[0051] Figure 3 This is a schematic diagram of a time-weight curve provided in an embodiment of this application;

[0052] Figure 4 This is a schematic diagram of a time-displacement curve provided in an embodiment of this application;

[0053] Figure 5 This is a schematic diagram of a displacement-weight curve provided in an embodiment of this application;

[0054] Figure 6 This is a schematic diagram of the vehicle weight detection device provided in the embodiments of this application;

[0055] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0056] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0057] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0058] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0059] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0060] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0061] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0062] Figure 1 This is a schematic flowchart of a vehicle weight detection method provided in one embodiment of this application. It is intended as an example and not a limitation. Figure 1 As shown, the method includes:

[0063] S101: Obtain the weight information of the vehicle tires relative to the ground by using a bar-shaped weighing sensor installed on the road surface.

[0064] The tire's weight information on the ground includes the acquisition time of the bar weighing sensor and the corresponding weight data acquired at that time.

[0065] S102: Based on the weighing information, obtain the time-weight curve of the vehicle wheel axle passing through the weighing area, and convert the time-weight curve into a displacement-weight curve.

[0066] The weighing area is the data acquisition area of ​​the bar weighing sensor.

[0067] Specifically, under the combined action of the vehicle's own weight and the road surface's supporting force, the tire undergoes elastic deformation.

[0068] When a vehicle passes over a bar-shaped load cell, the load cell deforms. Since the length of the load cell along the vehicle's travel direction is much smaller than the tire's contact length with the ground, its envelope characteristics are related to the ground's support force on the vehicle and the tire's radial deformation. Using the deformation characteristics under load as an evaluation index, a spring constant k is constructed. z The relationship between the moment of inertia I, tension T, and elastic coefficient E and the deformation in the longitudinal direction at any displacement point is given by the following deflection equation for the tire envelope characteristics:

[0069] ;

[0070] Where X represents the position information of any point on the contact surface of the tire, and Z represents the deformation of the sensor in the longitudinal direction.

[0071] The general solution to the longitudinal flexure equation:

[0072] ;

[0073] in,

[0074] ,

[0075] ,

[0076] ,

[0077] ,

[0078] .

[0079] Then, the spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted vehicle weight. The preset formula is as follows:

[0080] ;

[0081] Among them, F z Z is the predicted result for vehicle weight. o This represents the maximum value of radial deformation. It is a constant. .

[0082] The weighing information collected by the bar load cell is positively correlated with the deformation of the sensor, so all points on the displacement-weight curve conform to the flexure equation.

[0083] Based on the above analysis results, the time-weight curve can be linked with the time-displacement curve, thereby converting the time-weight curve of vehicle weighing information into a displacement-weight curve.

[0084] S103: Determine the weighing characteristic information based on the displacement-weight curve.

[0085] S104: Based on the weighing feature information, input into the preset weighing model to obtain the predicted result of the vehicle weight.

[0086] This embodiment acquires vehicle weighing information, including weighing data and acquisition time collected by a bar weighing sensor; based on the weighing information, it obtains the time-weight curve of the vehicle's wheel axle passing through the weighing area, and converts the time-weight curve into a displacement-weight curve; it determines weighing characteristic information based on the displacement-weight curve; and based on the weighing characteristic information, it inputs it into a preset weighing model to obtain a predicted vehicle weight. This method can obtain an accurate vehicle weight using only a small amount of weighing characteristic information, eliminating the need to determine the vehicle weight based on all weighing data. This reduces hardware costs, improves the robustness of the weighing model, and ensures accurate vehicle weight even when some weighing data is missing, thereby improving weighing accuracy.

[0087] In another embodiment, converting the time-weight curve into a displacement-weight curve includes:

[0088] First, based on the time-weight curves of different bar weighing sensors, the time-displacement curves of the vehicle wheel axle passing through the weighing area are obtained.

[0089] Figure 2 This is a schematic diagram of the arrangement of a bar weighing sensor according to an embodiment of this application. Figure 2 As shown, the bar-shaped load cell 101 is arranged in the road with its upper surface flush with the road surface. When a vehicle passes through the road where the bar-shaped load cell 101 is installed, the bar-shaped load cell 101 can collect the pressure of the vehicle's wheel axles on it. It should be noted that... Figure 2 The arrangement of the bar sensors shown is only one embodiment of the present invention. Those skilled in the art can obtain different combinations of bar sensors by increasing or decreasing the number of bar sensors and adjusting the positional relationship of the bar sensors.

[0090] Figure 3 yes Figure 2 A schematic diagram of the time-weight curve provided by the bar sensor in the illustrated embodiment. (See diagram below.) Figure 3The diagram shows the time-weight curves obtained after the front and rear axles of a vehicle pass through two bar weighing sensors. The solid line represents the weight data collected by the two bar weighing sensors after the front axle passes through; the dashed line represents the weight data collected by the two bar weighing sensors after the rear axle passes through. Characteristic information such as the time when the vehicle enters or leaves the bar weighing sensors, and the peak value can be obtained from the time-weight curves.

[0091] For example, after the vehicle axle passes through two bar weighing sensors, the time-displacement curve of the vehicle axle passing through the weighing area is obtained based on the distance between the two bar weighing sensors, the speed of the vehicle axle passing through the two bar weighing sensors, and the time-weight curve of the two bar weighing sensors.

[0092] The time difference between the two bar load cells corresponding to one of the axles is obtained from their time-weight curves. Specifically, the time difference between the two bar load cells can be obtained from the two peak values. The speed of the vehicle axle passing through the two bar load cells is calculated based on the time difference and the distance between them. Thus, the time-displacement curve of the vehicle axle passing through the weighing area is obtained based on the distance between the two bar load cells, the speed of the vehicle axle passing through the two bar load cells, and the time difference.

[0093] Figure 4 This is a schematic diagram of a time-displacement curve provided in an embodiment of this application. For example... Figure 4 As shown, this illustrates the change in vehicle displacement from the moment the vehicle enters the bar weighing sensor until it leaves the bar weighing sensor.

[0094] Next, based on the time-weight curve and time-displacement curve of the vehicle wheel axle passing through the weighing area, the displacement-weight curve is determined.

[0095] Specifically, based on the relationship between time and displacement, the vehicle displacement from entering the bar weighing sensor to leaving the bar weighing sensor is correlated with the time-weight curve of the vehicle passing through the bar weighing sensor and the position-weight curve of the vehicle passing through the bar weighing sensor, so as to convert the time-weight curve into a displacement-weight curve.

[0096] By extracting data from the displacement-weight curves whose weight exceeds a certain preset value and extending them forward and backward by a certain displacement, multiple effective displacement-weight curves can be obtained.

[0097] Figure 5 This is a schematic diagram of a displacement-weight curve provided in one embodiment of this application. For example... Figure 5As shown, this illustrates the change in vehicle weight as the vehicle's displacement changes after passing the bar weighing sensor. The displacement points and corresponding weighing data on this displacement-weight curve satisfy the longitudinal flexure equation, and characteristic information such as the displacement points when the vehicle enters and leaves the bar weighing sensor can be obtained from the displacement-weight curve.

[0098] In another embodiment, determining weighing characteristic information based on the displacement-weight curve includes:

[0099] Based on the displacement-weight curve, n displacement points and their corresponding weighing data are selected as weighing characteristic information, where n≥5.

[0100] Among them, the spring constant k is based on the longitudinal flexural equation. z The equations relating the moment of inertia I, tension T, and elastic coefficient E to the deformation include the spring constant k. z To obtain accurate prediction results, at least five weighing characteristic information points need to be selected from the four variables: moment of inertia I, tension T, and elastic coefficient E.

[0101] The difficulty and computational complexity of solving for the variables can be considered. Before selecting n weighing feature information, the maximum value of n can be set based on the specific usage scenario and hardware equipment. At the same time, the value of n is not set to be equal to the total amount of weighing data collected, so as to avoid the uniformity of data affecting the accuracy of solving for the optimal variables.

[0102] For example, based on the entire vehicle's passage through the bar weighing sensor, the weighing data at corresponding characteristic moments can be determined. This allows for the selection of corresponding weighing characteristic information from the displacement-weight curve, including the characteristic moment corresponding to the peak waveform, the characteristic moment of entering the bar weighing sensor, the characteristic moment of leaving the bar weighing sensor, and the characteristic moment of nonlinear stress-displacement change. Depending on the specific application scenario, the characteristic moment of nonlinear stress-displacement change can be selected as either the moment of entering, leaving, or both simultaneously.

[0103] For example, n displacement points can be selected through random sampling, stratified sampling, systematic sampling, or cluster sampling to determine the weighing characteristic information. For instance, by selecting displacement points through stratified sampling, the weighing data collected by the bar weighing sensor is divided into n equal parts, and one displacement point is selected from each part of the data.

[0104] In another embodiment, the average distance between two adjacent displacement points among the n displacement points is greater than a preset threshold to avoid reducing the accuracy of the prediction results due to two adjacent displacement points being too close.

[0105] The preset threshold can be set according to the needs of the actual use case.

[0106] In another embodiment, based on weighing feature information, a predicted vehicle weight is obtained by inputting it into a preset weighing model, including:

[0107] First, substituting the displacement X and the weight Z from the weighing characteristic information into the deflection equation, we obtain the information about the spring constant k. z An overdetermined set of equations relating moment of inertia I, tension T, and elastic coefficient E.

[0108] The deflection equation is: .

[0109] Because the bar load cell collects a large amount of weighing data, it will result in an overdetermined set of equations. To obtain an accurate spring constant k... z The rotational inertia I, tension T, and elastic coefficient provide the basis.

[0110] Next, at the spring constant k z The optimal combination of rotational inertia I, tension T, and elastic coefficient E is selected within the preset range to obtain the optimal solution of the overdetermined equation system.

[0111] Wherein, the spring constant k z The preset ranges for the rotational inertia I, tension T, and elastic coefficient E can be determined based on the existing tire parameters, which also facilitates the selection of the optimal combination.

[0112] Then, the spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted vehicle weight. The preset formula is as follows:

[0113] ;

[0114] Among them, F z Z is the predicted result for vehicle weight. o This represents the maximum value of radial deformation. It is a constant. .

[0115] Among them, Z o It can be determined from the peak value in the displacement-weight curve.

[0116] In another embodiment, the method further includes:

[0117] Obtain at least two prediction results and derive the vehicle weight based on the prediction results.

[0118] Specifically, based on the set value of n, at least two sets of weighing feature information are obtained. Each set of n weighing feature information is selected by random sampling, stratified sampling, systematic sampling or cluster sampling. The n weighing feature information of each set is input into the preset weighing model to obtain the predicted result of the vehicle weight. The vehicle weight is obtained based on all the predicted results.

[0119] For example, let n be six, and obtain three sets of weighing feature information. For each set, six weighing feature information are selected using random sampling, stratified sampling, systematic sampling, or cluster sampling. For each set of weighing feature information, the six weighing feature information in the set are input into a preset weighing model to obtain the predicted vehicle weight. The vehicle weight is then obtained based on the three predicted results.

[0120] This embodiment obtains at least two prediction results and calculates the vehicle weight based on these prediction results to obtain a more accurate vehicle weight.

[0121] In another embodiment, the method further includes:

[0122] Obtain preset weighing models and corresponding prediction results for different n values, and obtain the vehicle weight based on the prediction results.

[0123] For example, the corresponding prediction result is data from a vehicle in free-flow condition, which can be collected by bar weighing sensors at non-stop overload detection stations, highway overload detection stations, etc. In addition, the weighing information can also include vehicle type, number of axles, speed, etc. For example, five weighing feature information points are obtained and input into the corresponding preset weighing model to obtain the predicted vehicle weight; six weighing feature information points are obtained and input into the corresponding preset weighing model to obtain the predicted vehicle weight; nine weighing feature information points are obtained and input into the corresponding preset weighing model to obtain the predicted vehicle weight; and the vehicle weight is obtained based on all the prediction results.

[0124] This embodiment obtains preset weighing models with different n values ​​and corresponding prediction results, and obtains the vehicle weight based on the prediction results, so as to obtain a more accurate vehicle weight.

[0125] In another embodiment, obtaining the optimal solution to the overdetermined system of equations includes:

[0126] Solve the optimal solution to an overdetermined system of equations using a machine learning model.

[0127] In another embodiment, weighing characteristic information from a bar weighing sensor installed on the road is acquired, along with vehicle weight information from nearby low-speed stations. The vehicle weight information may also include vehicle type, number of axles, speed, etc.

[0128] Matching weighing feature information and vehicle weight information using vehicle license plate numbers is a clear method that allows technical personnel in this industry to assess the matching effectiveness based on factors such as vehicle license plate number, the time difference between the vehicle passing through roadside stations and low-speed stations, and the similarity between weighing feature information and vehicle weight data.

[0129] In another embodiment, the weighing feature information is used as the model feature and the low-speed station data is used as the model label to establish a weighing model between the model feature and the model label, thereby obtaining a preset weighing model.

[0130] The weighing model is a deep learning model, which includes an input layer, a batch normalization (BN) layer, an intermediate layer, and a fully connected layer. The intermediate layer contains a combination of multiple convolutional layers and pooling layers.

[0131] The BN layer normalizes the data to obtain the mean and variance. The convolutional layers in the middle multiply and then add the feature values ​​and feature factors of the location. The pooling layers in the middle find the maximum value of the adjacent data to maximize the data features of the redundant parts of the multi-sensor system. The fully connected layers integrate the local information with class discrimination from the convolutional or pooling layers.

[0132] The loss function of the weighing model is the mean squared error, and the weights of each layer of the neural network are updated by backpropagation of the error.

[0133] In another embodiment, the weighing feature information is fitted using the least squares method to establish a weighing model, thus obtaining a preset weighing model.

[0134] For example, five weighing features were selected and represented in matrix form as {Z1, Z2, Z3, Z4, Z5}. Assuming a sample size of 100 (i.e., 100 displacement-weight curves for different vehicles), 100 equations were established to find the optimal solution for (θ1, θ2, θ3, θ4, θ5). The optimal solution was then substituted into the original weighing model to obtain the preset weighing model. (Constructing the original weighing model) ,Right now The loss function is the second-order matrix between the accurately measured vehicle weight information from low-speed station data and the prediction results obtained from the original weighing model. ,in For the prediction results, w represents the low-speed site data, T is the transpose, and (θ1, θ2, θ3, θ4, θ5) is obtained when the loss function is minimized. J（θ）min This is the optimal solution.

[0135] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0136] For ease of explanation, only the parts related to the embodiments of this application are shown in the methods described in the above embodiments.

[0137] Figure 6 This is a schematic diagram of the vehicle weight detection device provided in an embodiment of this application. It is intended as an example and not a limitation. Figure 6 As shown, the device includes:

[0138] The acquisition module 10 is used to acquire the vehicle's weighing information, which includes the weighing data acquired by the bar weighing sensor and the acquisition time.

[0139] Data processing module 11 is used to obtain the time-weight curve of the vehicle wheel axle when it passes through the weighing area based on the weighing information, and to convert the time-weight curve into a displacement-weight curve.

[0140] Used to determine weighing characteristic information based on the displacement-weight curve;

[0141] Furthermore, based on the weighing feature information, the vehicle weight prediction result is obtained by inputting it into a preset weighing model.

[0142] In another embodiment, the data processing module is specifically used for:

[0143] Substituting the displacement X and the weighing information Z from the weighing characteristic information into the deflection equation, we obtain the information about the spring constant k. z The overdetermined equations for the moment of inertia I, tension T, and elastic coefficient E, and the deflection equation are as follows: ;

[0144] At the spring constant k z The optimal combination of rotational inertia I, tension T, and elastic coefficient E is selected within the preset range to obtain the optimal solution of the overdetermined equation system.

[0145] The spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted vehicle weight. The preset formula is as follows:

[0146] ;

[0147] Among them, F z Z is the predicted result for vehicle weight. o This represents the maximum value of radial deformation. It is a constant. .

[0148] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 2 of this embodiment includes: at least one processor 20 ( Figure 7 (Only one is shown in the diagram), memory 21, and computer program 22 stored in said memory 21 and executable on said at least one processor 20, wherein said processor 20 executes said computer program 22 to implement the steps in any of the above method embodiments.

[0149] The electronic device 2 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The electronic device 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 7 This is merely an example of electronic device 2 and does not constitute a limitation on electronic device 2. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0150] The processor 20 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0151] In some embodiments, the memory 21 may be an internal storage unit of the electronic device 2, such as a hard disk or memory of the electronic device 2. In other embodiments, the memory 21 may be an external storage device of the electronic device 2, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 2. Furthermore, the memory 21 may include both internal and external storage units of the electronic device 2. The memory 21 is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0152] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0153] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0154] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the above-described method embodiments.

[0155] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the various method embodiments.

[0156] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0157] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0158] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0159] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0160] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0161] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting vehicle weight, characterized in that, include: Acquire vehicle weighing information, wherein the weighing information includes the acquisition time of the bar weighing sensor and the weighing data acquired corresponding to the acquisition time; Based on the weighing information, the time-weight curve of the vehicle wheel axle passing through the weighing area is obtained, and the time-weight curve is converted into a displacement-weight curve. Weighing characteristic information is determined based on the displacement-weight curve; Substituting the displacement X and the weighing information Z from the weighing characteristic information into the deflection equation, we obtain the information about the spring constant k. z The overdetermined set of equations for the moment of inertia I, tension T, and elastic coefficient E, wherein the deflection equation is: ; In the spring constant k z The optimal combination of the rotational inertia I, the tension T, and the elastic coefficient E within a preset range is selected to obtain the optimal solution of the overdetermined equation system. The spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted weight of the vehicle. The preset formula is as follows: ； Among them, F z Z is the predicted weight of the vehicle. o This represents the maximum value of radial deformation. It is a constant. .

2. The method as described in claim 1, characterized in that, The step of converting the time-weight curve into a displacement-weight curve includes: Based on the time-weight curves of different bar weighing sensors, the time-displacement curves of the vehicle wheel axle passing through the weighing area are obtained; The displacement-weight curve is determined based on the time-weight curve and time-displacement curve of the vehicle wheel axle passing through the weighing area.

3. The method as described in claim 1, characterized in that, Weighing characteristic information is determined based on the displacement-weight curve, including: Based on the displacement-weight curve, n displacement points and their corresponding weighing data are selected as weighing feature information, where n≥5.

4. The method as described in claim 3, characterized in that, n displacement points are selected by random sampling, stratified sampling, systematic sampling, or cluster sampling.

5. The method as described in claim 4, characterized in that, The average distance between any two adjacent displacement points among the n displacement points is greater than a preset threshold.

6. The method according to any one of claims 1 to 5, characterized in that, Also includes: Obtain at least two of the prediction results, and derive the vehicle weight based on the prediction results.

7. The method as described in claim 1, characterized in that, Using the weighing feature information as model features and low-speed station data as model labels, a weighing model is established between the model features and the model labels to obtain the preset weighing model.

8. A vehicle weight detection device, characterized in that, include: The acquisition module is used to acquire the vehicle's weighing information, wherein the weighing information includes the weighing data acquired by the bar weighing sensor and the acquisition time; The data processing module is used to obtain the time-weight curve of the vehicle wheel axle when it passes through the weighing area based on the weighing information, and to convert the time-weight curve into a displacement-weight curve. Used to determine weighing characteristic information based on the displacement-weight curve; Furthermore, by substituting the displacement X and the weighing information Z from the weighing characteristic information into the flexure equation, the relationship with the spring constant k is obtained. z The overdetermined set of equations for the moment of inertia I, tension T, and elastic coefficient E, wherein the deflection equation is: ; In the spring constant k z The optimal combination of the rotational inertia I, the tension T, and the elastic coefficient E within a preset range is selected to obtain the optimal solution of the overdetermined equation system. The spring constant k in the optimal solution z The moment of inertia I, tension T, and elastic coefficient E are substituted into a preset formula to obtain the predicted weight of the vehicle. The preset formula is as follows: ； Among them, F z Z is the predicted weight of the vehicle. o This represents the maximum value of radial deformation. It is a constant. .

9. The vehicle weight detection device as described in claim 8, characterized in that, The length of the bar-shaped weighing sensor along the vehicle's travel direction is less than 100 mm.

Images