Vehicle weighing method and device, equipment and storage medium
By acquiring and processing a variety of data of the vehicle, combining tire pressure and vehicle speed, and using preset models, the accuracy of dynamic weighing of the vehicle is improved, and the problems of low accuracy and large error in the prior art are solved.
Patent Information
- Application Number
- CN202410997996.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-24
AI Technical Summary
The existing dynamic weighing methods of vehicles have low accuracy and are easily disturbed by factors such as vehicle vibration, resulting in unstable weighing data and large errors.
By obtaining the first measurement data of the vehicle, including the weighing signal, vehicle speed, vehicle model and tire temperature, filtering and identification processing are performed, combining tire pressure and vehicle speed to calculate the second total weight, and using the preset total weight prediction The model considers the influence of tire temperature on weighing, and gradually improves the weighing accuracy.
It improves the accuracy of dynamic weighing of vehicles, reduces weighing errors, enhances data stability, and reduces dependence on vehicle speed range.
Smart Images

Figure CN118936609A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle weighing, and in particular to a vehicle weighing method and device, equipment and storage medium. Background Art
[0002] Overloading of vehicles will endanger road safety, so it is necessary to weigh the vehicle to determine whether it is overloaded. In the prior art, static weighing or dynamic weighing is usually used to weigh vehicles. Since the static weighing method requires the vehicle to be driven into the measuring and weighing area and stationary before weighing the vehicle, it may cause delays in the corresponding journey of the vehicle, thereby causing unnecessary losses; the dynamic weighing method does not require the vehicle to slow down or stop, and will not delay the vehicle's journey, but the current dynamic weighing method usually uses the method of analyzing the data of the weighing sensor for weighing, and has a high tolerance for the vehicle speed range, but the corresponding weighing accuracy is low, the weighing data is unstable, and it is easily affected by factors such as vehicle vibration. Therefore, how to improve the accuracy of dynamic weighing of vehicles is still a technical problem that needs to be solved urgently. Summary of the invention
[0003] The present application provides a vehicle weighing method and device, equipment and storage medium to solve the technical problems of low precision and large error in dynamic weighing of vehicles.
[0004] According to a first aspect of the embodiments of the present application, a vehicle weighing method is provided, comprising:
[0005] Acquire first measurement data of the current vehicle to be weighed; wherein the first measurement data includes a first weighing signal, a vehicle speed, a vehicle model, and a tire temperature;
[0006] Filtering the first weighing signal to obtain a first total weight;
[0007] Obtaining a tire pressure of the current vehicle based on the vehicle model, and obtaining a second total weight by combining the tire pressure and the vehicle speed;
[0008] Inputting the first total weight, the second total weight and the tire temperature into a preset first total weight prediction model to obtain a third total weight;
[0009] The current total weight of the current vehicle is obtained according to the first total weight, the second total weight and the third total weight.
[0010] The present application obtains first measurement data of the current vehicle to be weighed, and filters the first weighing signal therein to obtain the first total weight, thereby filtering out interference signals in the weighing signal, improving the accuracy of the weighing signal, and preliminarily determining the total weight of the vehicle. Then, the tire pressure is obtained based on the vehicle model, and the second total weight is obtained by combining the tire pressure and the vehicle speed. The total weight of the vehicle calculated by the tire pressure can be corrected according to the vehicle speed to reduce the weighing error. The first total weight, the second total weight and the tire temperature are then input into the first total weight prediction model to obtain the third total weight. The influence of the tire temperature on the measurement of the vehicle total weight is fitted by the prediction model, thereby improving the accuracy of vehicle weighing. When the current total weight of the current vehicle is obtained according to the first total weight, the second total weight and the third total weight, the error of the current total weight relative to the actual total weight of the vehicle is reduced, thereby improving the accuracy of dynamic vehicle weighing.
[0011] In certain embodiments of the present application, the obtaining of the first measurement data of the current vehicle to be weighed specifically includes:
[0012] Acquire a first weighing signal of the current vehicle collected by a sensor; and acquire multiple frames of monitoring images of the current vehicle collected by multiple cameras;
[0013] Performing recognition processing on the multiple monitoring image frames to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle;
[0014] The first weighing signal, the vehicle speed, the vehicle model and the tire temperature are combined to obtain first measurement data.
[0015] The present application first obtains a first weighing signal and multiple frames of monitoring images, and performs recognition processing on the multiple frames of monitoring images to obtain vehicle speed, vehicle model and tire temperature, thereby obtaining first measurement data, which can provide a data basis for subsequent calculation of the first total weight.
[0016] In certain embodiments of the present application, the recognition processing of the multiple monitoring images to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle specifically includes:
[0017] The multiple monitoring images include multiple first monitoring images in front of the vehicle taken by a high-speed camera and multiple second monitoring images on the left and right sides of the vehicle taken by an infrared camera;
[0018] According to the preset first recognition model, each frame of the first monitoring image is recognized to obtain multiple groups of recognition results; and the vehicle model corresponding to the maximum recognition probability in the multiple groups of recognition results is used as the vehicle model of the current vehicle; wherein the recognition result includes the vehicle model and the corresponding recognition probability;
[0019] According to a preset first segmentation model, each frame of the second monitoring image is segmented to obtain a plurality of first regions; and the temperatures of the plurality of first regions are acquired, and the average temperature of the plurality of first regions is used as the tire temperature of the current vehicle; wherein the first region is a region in the second monitoring image that only contains tires;
[0020] According to a preset second recognition model, each frame of the second monitoring image is recognized to obtain multiple second areas; and the displacement of the second areas between each frame of the second monitoring image is calculated, and the vehicle speed of the current vehicle is calculated based on the displacement of the multiple second areas; wherein the second area is an area in the second monitoring image that only contains the vehicle body.
[0021] The present application first identifies each frame of the first monitoring image according to the first recognition model, and obtains the vehicle model according to the recognition result corresponding to the maximum recognition probability, which can accurately identify the vehicle model of the current vehicle, and then segments each frame of the second monitoring image according to the first segmentation model to obtain multiple first areas, and calculates the tire temperature according to the temperature of the first area, which can accurately identify the area where the tires of the current vehicle are located, and then calculate the tire temperature of the current vehicle, and then identifies each frame of the second monitoring image according to the second recognition model to obtain multiple second areas, and calculates the vehicle speed according to the displacement of the second area between each frame of the second monitoring image, which can accurately calculate the displacement of the current vehicle between frames, and then calculate the vehicle speed of the current vehicle, thereby improving the accuracy of the acquired vehicle speed, vehicle model, and tire temperature.
[0022] In certain embodiments of the present application, filtering the first weighing signal to obtain the first total weight specifically includes:
[0023] According to a preset frequency threshold, high-pass filtering is performed on the first weighing signal to obtain a second weighing signal;
[0024] performing Kalman filtering on the second weighing signal to obtain a third weighing signal;
[0025] The third weighing signal is sampled by sliding average to obtain a first total weight.
[0026] The present application first performs high-pass filtering to filter out high-frequency mechanical vibrations in the signal, then performs Kalman filtering, and then performs sliding average sampling, which can improve the accuracy of signal sampling and reduce the error of the first total weight when the first total weight is obtained.
[0027] In certain embodiments of the present application, obtaining the tire pressure of the current vehicle based on the vehicle model, and combining the tire pressure and the vehicle speed to obtain the second total weight specifically includes:
[0028] According to the vehicle model, the calibrated tire pressure of the current vehicle is obtained by matching from a preset vehicle database;
[0029] According to the vehicle model and in combination with the calibrated tire pressure, obtaining the tire pressure of the current vehicle;
[0030] A second total weight of the current vehicle is calculated according to the tire pressure and the vehicle speed.
[0031] The present application first calibrates the tire pressure according to the vehicle model and then obtains the tire pressure of the current vehicle, taking into account the design parameters of the current vehicle, and calculates the second total weight in combination with the tire pressure and the vehicle speed, while taking into account the effects of the tire pressure and the vehicle speed on the vehicle total weight, thereby reducing the error of the second total weight when calculating the second total weight.
[0032] In certain embodiments of the present application, calculating the second total weight of the current vehicle according to the tire pressure and the vehicle speed specifically includes:
[0033] Calculating the second weight of each tire of the current vehicle according to the tire pressure, the vehicle speed and the vehicle model;
[0034] The second weight of each tire is specifically:
[0035]
[0036] in, is the second weight of the i-th tire from front to back on side d, where side d includes the left side and the right side; is the first stiffness coefficient, β is the second stiffness coefficient; is the vertical deflection of the ith tire from front to back on side d; P is the tire pressure; v c is the rated maximum speed of the current vehicle; v is the vehicle speed;
[0037] A second total weight of the current vehicle is obtained according to the second partial weights of all tires of the current vehicle.
[0038] The present application first calculates the second partial weight of each tire of the current vehicle, and then obtains the second total weight based on the second partial weight of each tire, taking into account the contribution of each tire to the total weight of the vehicle, and then reducing the error of the second total weight when calculating the second total weight through the second partial weight of each tire.
[0039] In certain embodiments of the present application, inputting the first total weight, the second total weight, and the tire temperature into a preset first total weight prediction model to obtain a third total weight specifically includes:
[0040] Acquire a historical weighing data set; wherein the historical weighing data set includes a plurality of groups of weighing data; the weighing data includes first historical weighing data of a historical vehicle, second historical weighing data and tire temperature of the historical vehicle during weighing;
[0041] Iteratively training an initial total weight prediction model with preset initial parameters using the historical weighing data set, updating the model parameters during iteration, and stopping the training until the model parameters meet a preset threshold, thereby obtaining a first total weight prediction model;
[0042] The first gross weight, the second gross weight and the tire temperature are input into the first gross weight prediction model to obtain a third gross weight of the current vehicle.
[0043] This application first obtains a first gross weight prediction model through training of a historical weighing data set, and then obtains a third gross weight by combining the first gross weight, the second gross weight and the tire temperature, taking into account the impact of tire temperature on the vehicle's gross weight. When the third gross weight is obtained from the first gross weight prediction model, it is more in line with the actual situation.
[0044] According to a second aspect of the implementation of the present application, there is provided a vehicle weighing device, including a vehicle data acquisition module, a first total weight acquisition module, a second total weight acquisition module, a third total weight acquisition module and a current total weight acquisition module;
[0045] The vehicle data acquisition module is used to acquire first measurement data of the current vehicle to be weighed; wherein the first measurement data includes a first weighing signal, a vehicle speed, a vehicle model and a tire temperature;
[0046] The first total weight acquisition module is used to filter the first weighing signal to obtain a first total weight;
[0047] The second total weight acquisition module is used to obtain the tire pressure of the current vehicle based on the vehicle model, and obtain the second total weight by combining the tire pressure and the vehicle speed;
[0048] The third total weight acquisition module is used to input the first total weight, the second total weight and the tire temperature into a preset first total weight prediction model to obtain a third total weight;
[0049] The current total weight acquisition module is used to obtain the current total weight of the current vehicle according to the first total weight, the second total weight and the third total weight.
[0050] The present application obtains first measurement data of the current vehicle to be weighed, and filters the first weighing signal therein to obtain the first total weight, thereby filtering out interference signals in the weighing signal, improving the accuracy of the weighing signal, and preliminarily determining the total weight of the vehicle. Then, the tire pressure is obtained based on the vehicle model, and the second total weight is obtained by combining the tire pressure and the vehicle speed. The total weight of the vehicle calculated by the tire pressure can be corrected according to the vehicle speed to reduce the weighing error. The first total weight, the second total weight and the tire temperature are then input into the first total weight prediction model to obtain the third total weight. The influence of the tire temperature on the measurement of the vehicle total weight is fitted by the prediction model, thereby improving the accuracy of vehicle weighing. When the current total weight of the current vehicle is obtained according to the first total weight, the second total weight and the third total weight, the error of the current total weight relative to the actual total weight of the vehicle is reduced, thereby improving the accuracy of dynamic vehicle weighing.
[0051] According to a third aspect of the embodiments of the present application, there is provided a computer device, comprising: a processor; a memory; a computer program stored in the memory and configured to be executed by the processor;
[0052] When the processor executes the computer program, a vehicle weighing method described in the present application is implemented.
[0053] According to a fourth aspect of the implementation of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for loading by a processor to execute a vehicle weighing method described in the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 : A schematic flow chart of a vehicle weighing method shown in certain embodiments of the present application;
[0055] Figure 2 : A module structure diagram of a vehicle weighing device shown in certain embodiments of the present application. DETAILED DESCRIPTION
[0056] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below in conjunction with the accompanying drawings are exemplary and are only used to explain some embodiments of the present application, and should not be construed as limitations on the embodiments of the present application. Based on the embodiments shown in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0057] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, unless otherwise clearly and specifically defined, "multiple" and "several" mean two or more.
[0058] Existing vehicle dynamic weighing methods usually use the method of analyzing the data of the weighing sensor to weigh, which has low requirements on the vehicle speed range, but the weighing accuracy is also low accordingly, and the weighing data is unstable and easily disturbed by factors such as vehicle vibration. Therefore, a vehicle weighing method that can improve the accuracy of vehicle dynamic weighing and reduce the error of vehicle dynamic weighing is needed.
[0059] Based on the above technical background, please refer to Figure 1 The embodiment of the present application provides a vehicle weighing method, including steps S101 to S105, each of which is as follows:
[0060] Step S101: Acquire first measurement data of the current vehicle to be weighed; wherein the first measurement data includes a first weighing signal, vehicle speed, vehicle model and tire temperature.
[0061] In certain embodiments of the present application, the obtaining of the first measurement data of the current vehicle to be weighed specifically includes:
[0062] Acquire a first weighing signal of the current vehicle collected by a sensor; and acquire multiple frames of monitoring images of the current vehicle collected by multiple cameras;
[0063] Performing recognition processing on the multiple monitoring image frames to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle;
[0064] The first weighing signal, the vehicle speed, the vehicle model and the tire temperature are combined to obtain first measurement data.
[0065] The present application first obtains a first weighing signal and multiple frames of monitoring images, and performs recognition processing on the multiple frames of monitoring images to obtain vehicle speed, vehicle model and tire temperature, thereby obtaining first measurement data, which can provide a data basis for subsequent calculation of the first total weight.
[0066] In certain optional embodiments of the present application, the preferred installation location of the sensor is the bottom of the road weighing area, and the preferred type is a gravity sensor; the preferred installation location of the multiple cameras is the two sides and the sky above the road weighing area, and the preferred types include but are not limited to high-speed cameras and infrared cameras. Specifically, the gravity sensor can obtain the weighing signal of the current vehicle, and then obtain the total weight of the current vehicle; the high-speed camera can capture the image of the current vehicle, and then obtain the model information of the current vehicle; the infrared camera can capture the image of the current vehicle, and then obtain the temperature information of the current image, and then identify the tires and body in the current image, and then obtain the tire temperature and body displacement, and then calculate the vehicle speed.
[0067] In certain embodiments of the present application, the recognition processing of the multiple monitoring images to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle specifically includes:
[0068] The multiple monitoring images include multiple first monitoring images in front of the vehicle taken by a high-speed camera and multiple second monitoring images on the left and right sides of the vehicle taken by an infrared camera;
[0069] According to the preset first recognition model, each frame of the first monitoring image is recognized to obtain multiple groups of recognition results; and the vehicle model corresponding to the maximum recognition probability in the multiple groups of recognition results is used as the vehicle model of the current vehicle; wherein the recognition result includes the vehicle model and the corresponding recognition probability;
[0070] According to a preset first segmentation model, each frame of the second monitoring image is segmented to obtain a plurality of first regions; and the temperatures of the plurality of first regions are acquired, and the average temperature of the plurality of first regions is used as the tire temperature of the current vehicle; wherein the first region is a region in the second monitoring image that only contains tires;
[0071] According to a preset second recognition model, each frame of the second monitoring image is recognized to obtain multiple second areas; and the displacement of the second areas between each frame of the second monitoring image is calculated, and the vehicle speed of the current vehicle is calculated based on the displacement of the multiple second areas; wherein the second area is an area in the second monitoring image that only contains the vehicle body.
[0072] In certain optional embodiments of the present application, a preferred scheme of the first recognition model is a tree model based on machine learning, including but not limited to a decision tree model, a random forest model, a gradient boosting tree model, an XGBoost model and an AdaBoost model; a preferred scheme of the first segmentation model includes but is not limited to a YOLO v3 model or an R-CNN model; a preferred scheme of the second recognition model includes but is not limited to a YOLO v3 model or an R-CNN model.
[0073] The present application first identifies each frame of the first monitoring image according to the first recognition model, and obtains the vehicle model according to the recognition result corresponding to the maximum recognition probability, which can accurately identify the vehicle model of the current vehicle, and then segments each frame of the second monitoring image according to the first segmentation model to obtain multiple first areas, and calculates the tire temperature according to the temperature of the first area, which can accurately identify the area where the tires of the current vehicle are located, and then calculate the tire temperature of the current vehicle, and then identifies each frame of the second monitoring image according to the second recognition model to obtain multiple second areas, and calculates the vehicle speed according to the displacement of the second area between each frame of the second monitoring image, which can accurately calculate the displacement of the current vehicle between frames, and then calculate the vehicle speed of the current vehicle, thereby improving the accuracy of the acquired vehicle speed, vehicle model, and tire temperature.
[0074] Step S102: filtering the first weighing signal to obtain a first total weight.
[0075] In certain embodiments of the present application, filtering the first weighing signal to obtain the first total weight specifically includes:
[0076] According to a preset frequency threshold, high-pass filtering is performed on the first weighing signal to obtain a second weighing signal;
[0077] performing Kalman filtering on the second weighing signal to obtain a third weighing signal;
[0078] The third weighing signal is sampled by sliding average to obtain a first total weight.
[0079] In certain optional implementations of the present application, the preferred solution for the frequency threshold is 60 Hz.
[0080] The reason for considering high-pass filtering of the first weighing signal is that when the vehicle passes the sensor in the road weighing area, the vehicle's wheel rotation and the sensor system will generate high-frequency vibrations. If the sensor responds to these high-frequency vibrations during detection, high-frequency vibration signal interference will be generated, thereby affecting the actual weighing signal; the reason for considering performing Kalman filtering is that random high- and low-frequency noise interference will inevitably be mixed in during the sensor acquisition process. Kalman filtering can effectively eliminate noise interference, and sliding average sampling can improve the accuracy of signal sampling, thereby reducing the error of the weighing signal.
[0081] The present application first performs high-pass filtering to filter out high-frequency mechanical vibrations in the signal, then performs Kalman filtering, and then performs sliding average sampling, which can improve the accuracy of signal sampling and reduce the error of the first total weight when the first total weight is obtained.
[0082] Step S103: obtaining the tire pressure of the current vehicle based on the vehicle model, and obtaining a second total weight by combining the tire pressure and the vehicle speed.
[0083] In certain embodiments of the present application, obtaining the tire pressure of the current vehicle based on the vehicle model, and combining the tire pressure and the vehicle speed to obtain the second total weight specifically includes:
[0084] According to the vehicle model, the calibrated tire pressure of the current vehicle is obtained by matching from a preset vehicle database;
[0085] According to the vehicle model and in combination with the calibrated tire pressure, obtaining the tire pressure of the current vehicle;
[0086] A second total weight of the current vehicle is calculated according to the tire pressure and the vehicle speed.
[0087] In some optional implementations of the present application, obtaining the tire pressure of the current vehicle according to the vehicle model in combination with the calibrated tire pressure specifically includes:
[0088] According to the vehicle model, matching and obtaining the tire pressure multiplier coefficient of the current vehicle from the vehicle database;
[0089] The tire pressure of the current vehicle is obtained according to the tire pressure multiplier coefficient and the calibrated tire pressure.
[0090] For example, if the vehicle type corresponding to the vehicle model of the current vehicle is a truck, the tire pressure ratio coefficient is 1.2; if the vehicle type corresponding to the vehicle model of the current vehicle is a sedan, the tire pressure ratio coefficient is 1.05.
[0091] In some optional implementations of the present application, the tire pressure of the current vehicle is obtained according to the tire pressure multiplier coefficient and the calibrated tire pressure, specifically:
[0092] The product of the tire pressure multiplier coefficient and the calibrated tire pressure is used as the current tire pressure of the vehicle.
[0093] The present application first calibrates the tire pressure according to the vehicle model and then obtains the tire pressure of the current vehicle, taking into account the design parameters of the current vehicle, and calculates the second total weight in combination with the tire pressure and the vehicle speed, while taking into account the effects of the tire pressure and the vehicle speed on the vehicle total weight, thereby reducing the error of the second total weight when calculating the second total weight.
[0094] In certain embodiments of the present application, calculating the second total weight of the current vehicle according to the tire pressure and the vehicle speed specifically includes:
[0095] Calculating the second weight of each tire of the current vehicle according to the tire pressure, the vehicle speed and the vehicle model;
[0096] The second weight of each tire is specifically:
[0097]
[0098] in, is the second weight of the i-th tire from front to back on side d, where side d includes the left side and the right side; is the first stiffness coefficient, β is the second stiffness coefficient; is the vertical deflection of the ith tire from front to back on side d; P is the tire pressure; v c is the rated maximum speed of the current vehicle; v is the vehicle speed;
[0099] A second total weight of the current vehicle is obtained according to the second partial weights of all tires of the current vehicle.
[0100] In some optional implementations of the present application, obtaining the second total weight of the current vehicle according to the second partial weights of all tires of the current vehicle specifically includes:
[0101] The sum of the second partial weights of all tires of the current vehicle is taken as the second total weight of the current vehicle.
[0102] The present application first calculates the second partial weight of each tire of the current vehicle, and then obtains the second total weight based on the second partial weight of each tire, taking into account the contribution of each tire to the total weight of the vehicle, and then reducing the error of the second total weight when calculating the second total weight through the second partial weight of each tire.
[0103] Step S104: inputting the first total weight, the second total weight and the tire temperature into a preset first total weight prediction model to obtain a third total weight.
[0104] In certain embodiments of the present application, inputting the first total weight, the second total weight, and the tire temperature into a preset first total weight prediction model to obtain a third total weight specifically includes:
[0105] Acquire a historical weighing data set; wherein the historical weighing data set includes a plurality of groups of weighing data; the weighing data includes first historical weighing data of a historical vehicle, second historical weighing data and tire temperature of the historical vehicle during weighing;
[0106] Iteratively training an initial total weight prediction model with preset initial parameters using the historical weighing data set, updating the model parameters during iteration, and stopping the training until the model parameters meet a preset threshold, thereby obtaining a first total weight prediction model;
[0107] The first gross weight, the second gross weight and the tire temperature are input into the first gross weight prediction model to obtain a third gross weight of the current vehicle.
[0108] In certain optional embodiments of the present application, the preferred scheme of the initial total weight prediction model is an LSTM (Long Short-Term Memory) model and its variants.
[0109] Preferably, the first historical weighing data and the second historical weighing data are weighing data of the same time.
[0110] This application first obtains a first gross weight prediction model through training of a historical weighing data set, and then obtains a third gross weight by combining the first gross weight, the second gross weight and the tire temperature, taking into account the impact of tire temperature on the vehicle's gross weight. When the third gross weight is obtained from the first gross weight prediction model, it is more in line with the actual situation.
[0111] Step S105: Obtaining the current total weight of the current vehicle according to the first total weight, the second total weight and the third total weight.
[0112] In some optional implementations of the present application, obtaining the current gross weight of the current vehicle according to the first gross weight, the second gross weight and the third gross weight specifically includes:
[0113] An average of the first total weight, the second total weight and the third total weight is used as the current total weight of the current vehicle.
[0114] In some optional implementations of the present application, obtaining the current gross weight of the current vehicle according to the first gross weight, the second gross weight and the third gross weight specifically includes:
[0115] A weighted average of the first total weight, the second total weight and the third total weight is used as the current total weight of the current vehicle.
[0116] Preferably, considering the high accuracy of the sensor, the weight of the first total weight is 0.4, the weight of the second total weight is 0.3, and the weight of the third total weight is 0.3; considering the influence of speed correction of the total weight, the weight of the first total weight is 0.35, the weight of the second total weight is 0.45, and the weight of the third total weight is 0.2; considering the influence of temperature correction of the total weight, the weight of the first total weight is 0.3, the weight of the second total weight is 0.3, and the weight of the third total weight is 0.4.
[0117] The present application obtains first measurement data of the current vehicle to be weighed, and filters the first weighing signal therein to obtain the first total weight, thereby filtering out interference signals in the weighing signal, improving the accuracy of the weighing signal, and preliminarily determining the total weight of the vehicle. Then, the tire pressure is obtained based on the vehicle model, and the second total weight is obtained by combining the tire pressure and the vehicle speed. The total weight of the vehicle calculated by the tire pressure can be corrected according to the vehicle speed to reduce the weighing error. The first total weight, the second total weight and the tire temperature are then input into the first total weight prediction model to obtain the third total weight. The influence of the tire temperature on the measurement of the vehicle total weight is fitted by the prediction model, thereby improving the accuracy of vehicle weighing. When the current total weight of the current vehicle is obtained according to the first total weight, the second total weight and the third total weight, the error of the current total weight relative to the actual total weight of the vehicle is reduced, thereby improving the accuracy of dynamic vehicle weighing.
[0118] Corresponding to the previous method, see Figure 2 , the embodiment of the present application provides a vehicle weighing device, including a vehicle data acquisition module 210, a first total weight acquisition module 220, a second total weight acquisition module 230, a third total weight acquisition module 240 and a current total weight acquisition module 250;
[0119] The vehicle data acquisition module 210 is used to acquire first measurement data of the current vehicle to be weighed; wherein the first measurement data includes a first weighing signal, vehicle speed, vehicle model and tire temperature;
[0120] The first total weight acquisition module 220 is used to filter the first weighing signal to obtain a first total weight;
[0121] The second total weight acquisition module 230 is used to obtain the tire pressure of the current vehicle based on the vehicle model, and obtain the second total weight by combining the tire pressure and the vehicle speed;
[0122] The third total weight acquisition module 240 is used to input the first total weight, the second total weight and the tire temperature into a preset first total weight prediction model to obtain a third total weight;
[0123] The current total weight acquisition module 250 is used to obtain the current total weight of the current vehicle according to the first total weight, the second total weight and the third total weight.
[0124] In certain embodiments of the present application, the vehicle data acquisition module 210 includes a data acquisition submodule 211 , an image recognition submodule 212 , and a data combination submodule 213 ;
[0125] The data acquisition submodule 211 is used to acquire a first weighing signal of the current vehicle collected by a sensor; and to acquire multiple frames of monitoring images of the current vehicle collected by multiple cameras;
[0126] The image recognition submodule 212 is used to perform recognition processing on the multiple monitoring images to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle;
[0127] The data combination submodule 213 is used to combine the first weighing signal, the vehicle speed, the vehicle model and the tire temperature to obtain first measurement data.
[0128] In certain embodiments of the present application, the multiple monitoring images include multiple first monitoring images in front of the vehicle taken by a high-speed camera and multiple second monitoring images on the left and right sides of the vehicle taken by an infrared camera, and the image recognition submodule 212 includes a model recognition unit 2121, a temperature calculation unit 2122, and a speed calculation unit 2123;
[0129] The model recognition unit 2121 is used to recognize each frame of the first monitoring image according to a preset first recognition model to obtain multiple groups of recognition results; and use the vehicle model corresponding to the maximum recognition probability in the multiple groups of recognition results as the vehicle model of the current vehicle; wherein the recognition result includes the vehicle model and the corresponding recognition probability;
[0130] The temperature calculation unit 2122 is used to segment each frame of the second monitoring image according to a preset first segmentation model to obtain a plurality of first regions; and obtain the temperatures of the plurality of first regions, and use the average temperature of the plurality of first regions as the tire temperature of the current vehicle; wherein the first region is a region in the second monitoring image that only contains tires;
[0131] The speed calculation unit 2123 is used to identify each frame of the second monitoring image according to a preset second recognition model to obtain multiple second areas; and calculate the displacement of the second area between each frame of the second monitoring image, and calculate the vehicle speed of the current vehicle based on the displacement of the multiple second areas; wherein the second area is the area in the second monitoring image that only contains the vehicle body.
[0132] In some embodiments of the present application, the first total weight acquisition module 220 includes a first filtering submodule 221, a second filtering submodule 222 and a signal sampling submodule 223;
[0133] The first filtering submodule 221 is used to perform high-pass filtering on the first weighing signal according to a preset frequency threshold to obtain a second weighing signal;
[0134] The second filtering submodule 222 is used to perform Kalman filtering on the second weighing signal to obtain a third weighing signal;
[0135] The signal sampling submodule 223 is used to perform sliding average sampling on the third weighing signal to obtain the first total weight.
[0136] In certain embodiments of the present application, the second total weight acquisition module 230 includes a tire pressure matching submodule 231, a tire pressure acquisition submodule 232, and a total weight calculation submodule 233;
[0137] The tire pressure matching submodule 231 is used to match and obtain the calibrated tire pressure of the current vehicle from a preset vehicle database according to the vehicle model;
[0138] The tire pressure acquisition submodule 232 is used to obtain the tire pressure of the current vehicle according to the vehicle model and the calibrated tire pressure;
[0139] The total weight calculation submodule 233 is used to calculate a second total weight of the current vehicle according to the tire pressure and the vehicle speed.
[0140] In certain embodiments of the present application, the total weight calculation submodule 233 includes a sub-weight calculation unit 2331 and a total weight calculation unit 2332;
[0141] The weight calculation unit 2331 is used to calculate the second weight of each tire of the current vehicle according to the tire pressure, the vehicle speed and the vehicle model;
[0142] The second weight of each tire is specifically:
[0143]
[0144] in, is the second weight of the i-th tire from front to back on side d, where side d includes the left side and the right side; is the first stiffness coefficient, β is the second stiffness coefficient; is the vertical deflection of the ith tire from front to back on side d; P is the tire pressure; v c is the rated maximum speed of the current vehicle; v is the vehicle speed;
[0145] The total weight calculation unit 2332 is used to obtain the second total weight of the current vehicle according to the second divided weights of all tires of the current vehicle.
[0146] In certain embodiments of the present application, the third total weight acquisition module 240 includes a historical data acquisition submodule 241, a model training submodule 242, and a total weight prediction submodule 243;
[0147] The historical data acquisition submodule 241 is used to acquire a historical weighing data set; wherein the historical weighing data set includes a plurality of weighing data sets; the weighing data includes the first historical weighing data of the historical vehicle, the second historical weighing data and the tire temperature of the historical vehicle during weighing;
[0148] The model training submodule 242 is used to iteratively train the initial total weight prediction model with preset initial parameters using the historical weighing data set, update the model parameters during iteration, and stop training when the model parameters meet the preset threshold value to obtain the first total weight prediction model;
[0149] The gross weight prediction submodule 243 is used to input the first gross weight, the second gross weight and the tire temperature into the first gross weight prediction model to obtain a third gross weight of the current vehicle.
[0150] The present application obtains first measurement data of the current vehicle to be weighed, and filters the first weighing signal therein to obtain the first total weight, thereby filtering out interference signals in the weighing signal, improving the accuracy of the weighing signal, and preliminarily determining the total weight of the vehicle. Then, the tire pressure is obtained based on the vehicle model, and the second total weight is obtained by combining the tire pressure and the vehicle speed. The total weight of the vehicle calculated by the tire pressure can be corrected according to the vehicle speed to reduce the weighing error. The first total weight, the second total weight and the tire temperature are then input into the first total weight prediction model to obtain the third total weight. The influence of the tire temperature on the measurement of the vehicle total weight is fitted by the prediction model, thereby improving the accuracy of vehicle weighing. When the current total weight of the current vehicle is obtained according to the first total weight, the second total weight and the third total weight, the error of the current total weight relative to the actual total weight of the vehicle is reduced, thereby improving the accuracy of dynamic vehicle weighing.
[0151] Adaptively, the embodiments of the present application also provide a computer device and a computer-readable storage medium.
[0152] The computer device comprises: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor;
[0153] Wherein, when the processor executes the computer program, a vehicle weighing method described in the present application is implemented.
[0154] The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute a vehicle weighing method described in the present application.
[0155] The above are some implementation methods of the present application, and the purpose, technical scheme and beneficial effects of the present application are further described in detail. It should be clear that the above-mentioned partial implementation methods of the present application cannot be understood as limiting the present application. It is particularly pointed out that for those skilled in the art, any changes, modifications, equivalent substitutions and variations made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims
1. A vehicle weighing method, characterized in that: include: Acquire first measurement data of the current vehicle to be weighed; wherein the first measurement data includes a first weighing signal, a vehicle speed, a vehicle model, and a tire temperature; Filtering the first weighing signal to obtain a first total weight; Obtaining a tire pressure of the current vehicle based on the vehicle model, and obtaining a second total weight by combining the tire pressure and the vehicle speed; Inputting the first total weight, the second total weight and the tire temperature into a preset first total weight prediction model to obtain a third total weight; The current total weight of the current vehicle is obtained according to the first total weight, the second total weight and the third total weight.
2. A vehicle weighing method according to claim 1, characterized in that: The obtaining of the first measurement data of the current vehicle to be weighed specifically includes: Acquire a first weighing signal of the current vehicle collected by a sensor; and acquire multiple frames of monitoring images of the current vehicle collected by multiple cameras; Performing recognition processing on the multiple monitoring image frames to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle; The first weighing signal, the vehicle speed, the vehicle model and the tire temperature are combined to obtain first measurement data.
3. A vehicle weighing method according to claim 2, characterized in that: The identifying and processing the multiple monitoring images to obtain the vehicle speed, vehicle model and tire temperature of the current vehicle specifically includes: The multiple monitoring images include multiple first monitoring images in front of the vehicle taken by a high-speed camera and multiple second monitoring images on the left and right sides of the vehicle taken by an infrared camera; According to the preset first recognition model, each frame of the first monitoring image is recognized to obtain multiple groups of recognition results; and the vehicle model corresponding to the maximum recognition probability in the multiple groups of recognition results is used as the vehicle model of the current vehicle; wherein the recognition result includes the vehicle model and the corresponding recognition probability; According to a preset first segmentation model, each frame of the second monitoring image is segmented to obtain a plurality of first regions; and the temperatures of the plurality of first regions are acquired, and the average temperature of the plurality of first regions is used as the tire temperature of the current vehicle; wherein the first region is a region in the second monitoring image that only contains tires; According to a preset second recognition model, each frame of the second monitoring image is recognized to obtain multiple second areas; and the displacement of the second areas between each frame of the second monitoring image is calculated, and the vehicle speed of the current vehicle is calculated based on the displacement of the multiple second areas; wherein the second area is an area in the second monitoring image that only contains the vehicle body.
4. A vehicle weighing method according to claim 1, characterized in that: The filtering the first weighing signal to obtain the first total weight specifically includes: According to a preset frequency threshold, high-pass filtering is performed on the first weighing signal to obtain a second weighing signal; performing Kalman filtering on the second weighing signal to obtain a third weighing signal; The third weighing signal is sampled by sliding average to obtain a first total weight.
5. A vehicle weighing method according to claim 1, characterized in that: The obtaining of the tire pressure of the current vehicle based on the vehicle model and obtaining the second total weight by combining the tire pressure and the vehicle speed specifically includes: According to the vehicle model, the calibrated tire pressure of the current vehicle is obtained by matching from a preset vehicle database; According to the vehicle model and in combination with the calibrated tire pressure, obtaining the tire pressure of the current vehicle; A second total weight of the current vehicle is calculated according to the tire pressure and the vehicle speed.
6. A vehicle weighing method according to claim 5, characterized in that: The calculating the second total weight of the current vehicle according to the tire pressure and the vehicle speed specifically includes: Calculating the second weight of each tire of the current vehicle according to the tire pressure, the vehicle speed and the vehicle model; The second weight of each tire is specifically: in, is the second weight of the i-th tire from front to back on side d, where side d includes the left side and the right side; is the first stiffness coefficient, β is the second stiffness coefficient; is the vertical deflection of the ith tire from front to back on side d; P is the tire pressure; υ c is the rated maximum speed of the current vehicle; υ is the vehicle speed; A second total weight of the current vehicle is obtained according to the second partial weights of all tires of the current vehicle.
7. A vehicle weighing method according to claim 1, characterized in that: The step of inputting the first total weight, the second total weight, and the tire temperature into a preset first total weight prediction model to obtain a third total weight specifically includes: Acquire a historical weighing data set; wherein the historical weighing data set includes a plurality of groups of weighing data; the weighing data includes first historical weighing data of a historical vehicle, second historical weighing data and tire temperature of the historical vehicle during weighing; Iteratively training an initial total weight prediction model with preset initial parameters using the historical weighing data set, updating the model parameters during iteration, and stopping the training until the model parameters meet a preset threshold, thereby obtaining a first total weight prediction model; The first gross weight, the second gross weight and the tire temperature are input into the first gross weight prediction model to obtain a third gross weight of the current vehicle.
8. A vehicle weighing device, characterized in that: It includes a vehicle data acquisition module, a first total weight acquisition module, a second total weight acquisition module, a third total weight acquisition module and a current total weight acquisition module; The vehicle data acquisition module is used to acquire first measurement data of the current vehicle to be weighed; wherein the first measurement data includes a first weighing signal, a vehicle speed, a vehicle model and a tire temperature; The first total weight acquisition module is used to filter the first weighing signal to obtain a first total weight; The second total weight acquisition module is used to obtain the tire pressure of the current vehicle based on the vehicle model, and obtain the second total weight by combining the tire pressure and the vehicle speed; The third total weight acquisition module is used to input the first total weight, the second total weight and the tire temperature into a preset first total weight prediction model to obtain a third total weight; The current total weight acquisition module is used to obtain the current total weight of the current vehicle according to the first total weight, the second total weight and the third total weight.
9. A computer device, characterized in that: include: processor; Memory; a computer program stored in the memory and configured to be executed by the processor; When the processor executes the computer program, a vehicle weighing method as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute a vehicle weighing method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Intelligent dynamic weighing and vehicle type, axle type, tire number and axle number integrated detection and analysis system
CN108387300A
Detection system and detection method for detecting vehicle load capacity by utilizing tire pressure
CN112498019A
Vehicle weight self-detection method based on high-precision vehicle-mounted TPMS (Tire Pressure Monitor System) and laser range finder
CN116674570A
Loading state determining method for vehicle, involves detecting temporal change of measured tire pressure
DE10029282A1
METHOD AND DEVICE FOR CALIBRATING A WEIGHT ESTIMATE
DE102022116115A1
