Vehicle mass estimation method and apparatus

Abstract

The application relates to a vehicle mass estimation method and device. The method comprises the following steps: dividing a pre-acquired driving state data set into multiple driving state intervals; the driving state data set comprises driving state data corresponding to each sampling time; for any driving state interval, driving state data in the driving state interval is screened based on a preset screening condition to obtain a target mass estimation interval; and a vehicle mass estimation value of the driving state interval is determined according to the driving state data of the target mass estimation interval and a pre-acquired vehicle dynamics model. The method can reduce the influence of distorted data on the accuracy of the vehicle mass estimation value and improve the accuracy of the vehicle mass estimation value.

Description

Technical Field

[0001] This application relates to the field of vehicle weight estimation technology, and in particular to a vehicle weight estimation method and apparatus. Background Technology

[0002] Accurate gross vehicle weight estimation for trucks is crucial for lightweight design of load-bearing assemblies and components such as suspension and chassis, and also provides important data for designers in various disciplines. Currently, the methods for estimating truck weight are primarily based on modeling and estimating driving data using vehicle dynamics models.

[0003] In traditional technologies, driving status data is obtained based on vehicle networking platforms. However, the sampling frequency of driving status data obtained by vehicle networking platforms is relatively low, which leads to coarse driving status data and easy distortion of some information processing, resulting in low accuracy of vehicle quality estimation. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle mass estimation method and apparatus that can process low-frequency or distorted driving status data and improve the accuracy of vehicle mass estimation without adding sensors, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for estimating vehicle weight. The method includes:

[0006] The pre-acquired driving status dataset is divided into multiple driving status intervals; the driving status dataset includes driving status data corresponding to each sampling time.

[0007] For any driving state interval, the driving state data in the driving state interval is filtered based on preset filtering conditions to obtain the target quality estimation interval;

[0008] Based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model, the estimated vehicle mass value of the driving state range is determined.

[0009] In one embodiment, the driving status data includes an elevation signal, the target quality estimation interval includes a straight road section interval and / or an uphill road section interval, and the preset filtering conditions include a first preset filtering condition and a second preset filtering condition; based on the preset filtering conditions, the driving status data in the driving status interval is filtered to obtain the target quality estimation interval, including:

[0010] The sampling interval containing the elevation signal that meets the first preset screening condition is determined as the straight road section interval;

[0011] The sampling interval containing the elevation signal that meets the second preset screening condition is determined as the climbing section interval.

[0012] In one embodiment, the driving state data further includes a vehicle speed signal, the target quality estimation interval further includes a flat acceleration interval, and the preset filtering conditions further include a third preset filtering condition. Based on the preset filtering conditions, the driving state data in the driving state interval is filtered to obtain the target quality estimation interval, which also includes:

[0013] The sampling intervals containing multiple vehicle speed signals that meet the third preset screening criteria in the straight road section are determined as multiple pre-selected intervals;

[0014] The pre-selected interval containing the most sampling times is determined as the flat acceleration interval.

[0015] In one embodiment, the pre-selected interval containing the most sampling times is used as the flat acceleration interval, including:

[0016] Multiple pre-selected intervals are preprocessed to obtain multiple initial intervals;

[0017] The initial interval containing the most sampling times will be used as the flat acceleration interval.

[0018] In one embodiment, the vehicle mass estimate for the driving state range is determined based on driving state data within the target mass estimation range and a pre-acquired vehicle dynamics model, including:

[0019] Determine the slope data corresponding to the target quality estimation interval;

[0020] Based on the driving state data, slope data, and pre-acquired vehicle dynamics model of the target mass estimation range, the estimated vehicle mass value of the driving state range is determined.

[0021] In one embodiment, the driving state data further includes a transmission gear position signal. Based on the driving state data, slope data, and a pre-acquired vehicle dynamics model for the target mass estimation range, a vehicle mass estimate for the driving state range is determined, including:

[0022] Remove driving status data in the target quality estimation range where the transmission gear signal is either the lowest or highest gear;

[0023] The driving state data and slope data of the target mass estimation interval after elimination are input into the pre-acquired vehicle dynamics model to determine the vehicle mass estimation value of the driving state interval.

[0024] In one embodiment, determining the slope data corresponding to the target quality estimation interval includes:

[0025] If the target quality estimation interval is a straight road section, then the slope data corresponding to the target quality estimation interval is 0;

[0026] If the target quality estimation interval is an uphill section, then the slope data corresponding to the target quality estimation interval is determined based on the vehicle speed signal and the elevation signal.

[0027] In one embodiment, determining the slope data corresponding to the target quality estimation interval based on the vehicle speed signal and the elevation signal includes:

[0028] Integrate the vehicle speed signal within the target quality estimation interval to obtain the mileage value corresponding to the target quality estimation interval;

[0029] By fitting the mileage values ​​to the elevation signal, a fitting function is obtained. The derivative of the fitting function is then calculated to obtain the slope data corresponding to the target quality estimation interval.

[0030] In one embodiment, the estimated vehicle mass for the target mass estimation range is determined based on driving state data, slope data, and a pre-acquired vehicle dynamics model, including:

[0031] Input the slope data and driving state data corresponding to the target mass estimation interval into the pre-acquired vehicle dynamics model, and obtain the initial mass estimation value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model;

[0032] Probability density statistics are performed on the initial mass estimation values ​​corresponding to the target mass estimation interval, and the initial mass estimation value corresponding to the maximum probability density is used as the vehicle mass estimation value of the driving state interval.

[0033] Secondly, this application also provides a vehicle weight estimation device, the device comprising:

[0034] The first interval division module is used to divide the pre-acquired driving state dataset into multiple driving state intervals; the driving state dataset includes driving state data corresponding to each sampling time.

[0035] The second interval division module is used to filter the driving status data in any driving status interval based on preset filtering conditions to obtain the target quality estimation interval.

[0036] The vehicle mass estimation module is used to determine the estimated vehicle mass value for the driving state range based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model.

[0037] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0038] The pre-acquired driving status dataset is divided into multiple driving status intervals; the driving status dataset includes driving status data corresponding to each sampling time.

[0039] For any driving state interval, the driving state data in the driving state interval is filtered based on preset filtering conditions to obtain the target quality estimation interval;

[0040] Based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model, the estimated vehicle mass value of the driving state range is determined.

[0041] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0042] The pre-acquired driving status dataset is divided into multiple driving status intervals; the driving status dataset includes driving status data corresponding to each sampling time.

[0043] For any driving state interval, the driving state data in the driving state interval is filtered based on preset filtering conditions to obtain the target quality estimation interval;

[0044] Based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model, the estimated vehicle mass value of the driving state range is determined.

[0045] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0046] The pre-acquired driving status dataset is divided into multiple driving status intervals; the driving status dataset includes driving status data corresponding to each sampling time.

[0047] For any driving state interval, the driving state data in the driving state interval is filtered based on preset filtering conditions to obtain the target quality estimation interval;

[0048] Based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model, the estimated vehicle mass value of the driving state range is determined.

[0049] The aforementioned vehicle mass estimation method and apparatus divide the driving state dataset into multiple driving state intervals, then filters the driving state data within each interval to obtain a target mass estimation interval. A vehicle dynamics model is used to determine the vehicle mass estimate corresponding to the target mass estimation interval, and this vehicle mass estimate is used as the vehicle mass estimate for the driving state interval to which the target mass estimation interval belongs. Compared to the traditional method of using a single vehicle mass estimate to approximate the total mass of the vehicle throughout its entire driving process, this method first divides the pre-acquired driving state dataset into multiple driving state intervals and obtains vehicle mass estimates for different driving states. This avoids the impact of changes in the total vehicle mass under different driving states on the accuracy of the overall vehicle mass estimation. Secondly, by filtering the driving state data within each interval to obtain a high-quality target mass estimation interval suitable for assessing vehicle mass, and using the vehicle mass estimate corresponding to the target mass estimation interval as the vehicle mass estimate for the driving state interval to which the target mass estimation interval belongs, the method reduces the impact of distorted data on the accuracy of the vehicle mass estimation, thereby improving the accuracy of the vehicle mass estimation. Attached Figure Description

[0050] Figure 1 This is a diagram illustrating the application environment of a vehicle mass estimation method in one embodiment.

[0051] Figure 2 This is a flowchart illustrating a vehicle weight estimation method in one embodiment;

[0052] Figure 3 This is a schematic diagram illustrating the division of driving state intervals in one embodiment;

[0053] Figure 4 This is a schematic diagram of the probability density function in another embodiment;

[0054] Figure 5 This is a detailed flowchart of a vehicle weight estimation method in one embodiment;

[0055] Figure 6 This is a structural block diagram of a vehicle mass estimation device in one embodiment;

[0056] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] The vehicle weight estimation method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Terminal 102 divides a pre-acquired driving state dataset into multiple driving state intervals; the driving state dataset includes driving state data corresponding to each sampling time; for any driving state interval, based on preset filtering conditions, the driving state data in the driving state interval is filtered to obtain a target quality estimation interval; based on the driving state data of the target quality estimation interval and the pre-acquired vehicle dynamics model, the estimated vehicle quality value of the driving state interval is determined. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0059] Currently, methods for estimating truck weight primarily rely on modeling and estimation based on driving status data acquired through vehicle-to-everything (V2X) platforms and vehicle dynamics models to obtain a vehicle weight estimate. However, the low sampling frequency of driving status data acquired by V2X platforms leads to coarse-grained data, making some information processing prone to distortion and resulting in low accuracy in vehicle weight estimation. Therefore, to address the above issues, in one embodiment, such as... Figure 2 As shown, a vehicle weight estimation method is provided, which is applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps:

[0060] Step 202: Divide the pre-acquired driving state dataset into multiple driving state intervals; the driving state dataset includes driving state data corresponding to each sampling time.

[0061] The driving status dataset can be the status data generated by the vehicle during driving, obtained from the vehicle-to-everything (V2X) platform. The driving status data in the dataset is arranged in the order of sampling time. The driving status data includes status data and vehicle configuration information. The status data includes vehicle speed signal, engine output torque, engine speed signal, clutch switch signal, brake switch signal, elevation signal, current time, and transmission gear signal, etc.; the vehicle configuration information includes transmission model, tire model, rear axle model, cab and cargo box model, etc.

[0062] It's important to note that the elevation signal refers to the distance from a point on the vehicle along a vertical line to the ground, which can be obtained via the vehicle's GPS. The gear position signal can be detected by a position sensor located on the gearshift.

[0063] The driving state interval represents the sampling interval of the change in the total weight of the vehicle under different driving states within the sampling time corresponding to the driving state dataset.

[0064] For example, such as Figure 3 As shown, considering the characteristics of vehicle transportation, the driving state interval is divided based on vehicle speed, power output shaft speed, and idling time to represent changes in mass. If the vehicle speed is greater than 0 and the engine speed is greater than 0, the driving state interval represents the sampling interval corresponding to the vehicle's total weight remaining constant during driving. If the vehicle speed is equal to 0, the engine speed is greater than 0, and the idling time is less than 2 minutes, the driving state interval represents the sampling interval corresponding to the vehicle's total mass remaining constant during idling. If the idling time is greater than 2 minutes, the driving state interval represents the sampling interval corresponding to the vehicle's total mass changing when cargo is added or removed during idling. If the parking time is greater than 2 minutes, the driving state interval represents the sampling interval corresponding to the vehicle's total mass changing when cargo is added or removed during parking.

[0065] It's important to note that idling generally refers to the engine operating at its lowest possible RPM when the accelerator is fully released and the vehicle speed is zero. This differs from a stationary state, where the engine speed is zero, while in idling, the engine speed is greater than zero. The initial moment when the vehicle speed equals zero and the engine speed is greater than zero is the start of idling. The moment when the vehicle speed remains above zero after this point is the end of idling. The idling duration is determined based on the start and end times. If the idling duration is less than 2 minutes, it indicates the vehicle is in a temporary parking state, and the idling duration does not meet the needs of adding or removing cargo. Therefore, when the idling duration is less than 2 minutes, the total mass of the vehicle remains unchanged during idling. If the idling duration is greater than 2 minutes, the idling duration meets the needs of adding or removing cargo, and the total mass of the vehicle may change accordingly.

[0066] Optionally, the terminal obtains the driving status dataset collected within a preset time period from the vehicle network platform, arranges the driving status data corresponding to each sampling time in the driving status dataset according to the order of sampling time, and divides the driving status dataset into multiple driving status intervals based on preset division conditions.

[0067] Step 204: For any driving state interval, based on preset filtering conditions, filter the driving state data in the driving state interval to obtain the target quality estimation interval.

[0068] The preset filtering conditions can be set based on driving status data, and can be adjusted according to specific needs. The specific rules for defining the preset filtering conditions are not limited here. The purpose of filtering driving status data within the driving status range is to obtain a high-quality sampling range and avoid distorted or interfering data from affecting the accuracy of vehicle mass estimation.

[0069] Optionally, for any driving state interval, the terminal filters the driving state data in the driving state interval based on preset filtering conditions, and removes data that does not conform to the sampling, distorted data, etc., and obtains a high-quality target mass estimation interval that can be used to estimate the vehicle mass from the driving state interval.

[0070] Step 206: Determine the estimated vehicle mass value for the driving state range based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model.

[0071] Optionally, the terminal inputs the driving state data of the target mass estimation interval into the vehicle dynamics model, outputs the vehicle mass estimation value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model, and performs averaging, probability density statistics or other processing on the vehicle mass estimation value corresponding to each sampling time in the target mass estimation interval to obtain the vehicle mass estimation value corresponding to the target mass estimation interval. The vehicle mass estimation value corresponding to the target mass estimation interval is used as the vehicle mass estimation value of the driving state interval to which the target mass estimation interval belongs.

[0072] In the aforementioned vehicle weight estimation method, the driving state dataset is divided into multiple driving state intervals, and the driving state data in each interval is filtered to obtain a target weight estimation interval. The vehicle weight estimation value corresponding to the target weight estimation interval is determined using a vehicle dynamics model, and the vehicle weight estimation value corresponding to the target weight estimation interval is used as the vehicle weight estimation value of the driving state interval to which the target weight estimation interval belongs. Compared to the traditional method of using a single vehicle weight estimation value to approximate the total weight of the vehicle throughout its entire driving process, this embodiment first divides the pre-acquired driving state dataset into multiple driving state intervals and obtains vehicle weight estimation values ​​under different driving states. This avoids the impact of changes in the total vehicle weight under different driving states on the accuracy of the overall vehicle weight estimation. Secondly, the driving state data in each driving state interval is filtered to obtain a high-quality target weight estimation interval that can be used to assess vehicle weight. Using the vehicle weight estimation value corresponding to the target weight estimation interval as the vehicle weight estimation value of the driving state interval to which the target weight estimation interval belongs reduces the impact of distorted data on the accuracy of the vehicle weight estimation value and improves the accuracy of the vehicle weight estimation value.

[0073] In one embodiment, since the driving conditions of vehicles on straight road sections and sloping road sections are different, the driving status data obtained by the vehicle networking platform on straight road sections and sloping road sections are significantly different. In order to obtain a high-quality target quality estimation interval, this application embodiment sets the target quality estimation interval to include a straight road section interval and / or an uphill road section interval, and the preset screening conditions include a first preset screening condition and a second preset screening condition.

[0074] Based on preset filtering criteria, the driving state data in the driving state interval is filtered to obtain the target quality estimation interval. The specific steps include:

[0075] Step 1: The sampling interval containing the elevation signal that meets the first preset screening condition is determined as the straight road section interval.

[0076] The first preset screening condition is that the difference between continuous elevation signal changes is less than a threshold, which is used to obtain driving conditions on relatively flat roads. Further, the first preset screening condition includes that the difference between continuous elevation signal changes at consecutive sampling times is less than a first preset value, and the sampling duration at each consecutive sampling time is greater than a first duration threshold. For example, setting the threshold for the difference between continuous elevation signal changes to 2m, and the sampling duration at each consecutive sampling time to at least 40s, using these as the main conditions to screen the obtained driving sections, assumes that the vehicle is driving on a straight road, and the slope data can be considered as 0. This embodiment filters the driving state data corresponding to elevation signals that do not meet the first preset screening condition, extracting only the sampling interval containing the elevation signals that meet the first preset screening condition.

[0077] The sampling interval belongs to the target quality estimation interval, meaning the sampling interval is a part of the target quality estimation interval. For example, if the target quality estimation interval includes 100 sampling times, each sampling time being 1 second, and the difference in the continuous change of the elevation signal within the sampling time corresponding to the 20th sampling time to the 80th sampling time is less than 2m, then the sampling interval corresponding to the 20th sampling time to the 80th sampling time is considered to be a straight road section interval.

[0078] Step 2: The sampling interval containing the elevation signal that meets the second preset screening condition is determined as the climbing section interval.

[0079] The second preset screening condition can be used to obtain the driving conditions for climbing, where the difference in continuous changes of elevation signals is greater than a second preset value and the elevation signal does not decrease in adjacent sampling times. Further, the second preset screening condition includes that the difference in continuous changes of elevation signals corresponding to consecutive sampling times is greater than a second preset value, the sampling duration corresponding to consecutive sampling times is greater than a second duration threshold, and the distance between adjacent elevation signals does not decrease within the sampling duration. For example, the threshold for the difference in continuous changes of elevation signals is set to 3m, the sampling duration for continuous changes of elevation signals is at least 20s, and the continuous climbing is defined as the elevation signal not decreasing in adjacent times. Using this as the main condition, the obtained driving segments are considered to be on climbing sections. In this embodiment, driving state data corresponding to elevation signals that do not meet the second preset screening condition are filtered, and only the sampling interval containing the elevation signals that meet the second preset screening condition is extracted.

[0080] It should be noted that in this embodiment, the uphill section is selected from the target mass estimation range, rather than the downhill section. This is mainly because when a vehicle is going downhill, it needs to apply the brakes, generating a brake switch signal, which reduces the vehicle's acceleration. According to Newton's second law of motion, F = m × a, the smaller the acceleration a, the larger the mass m, and the less accurate the estimated vehicle mass. Furthermore, when going downhill, the measured slope data is negative. Inputting negative slope data into the vehicle dynamics model seriously affects the estimation accuracy of the vehicle dynamics model. Therefore, in this embodiment, only the uphill section is selected from the target mass estimation range.

[0081] In this embodiment, based on the characteristics of vehicle transportation, the target mass estimation interval is set to include a straight road section interval and / or an uphill road section interval. Based on the first preset screening conditions and the second preset screening conditions, the straight road section interval and the uphill road section interval are selected from the driving state interval, so as to provide high-quality input data for subsequent vehicle mass estimation through vehicle dynamics model and improve the accuracy of vehicle mass estimation value.

[0082] In one embodiment, a vehicle may be traveling at a constant speed or accelerating within a straight road section. Since the acceleration during constant speed travel is almost zero, according to Newton's second law of motion F = m × a, when the acceleration a remains constant, the estimated vehicle mass is inaccurate due to wind influence. Therefore, to address this issue, this embodiment further filters out a straight acceleration section within the straight road section. The vehicle mass estimate for the driving state section is then based on the driving state data from the straight acceleration section, further improving the accuracy of the vehicle mass estimate. The driving state data also includes vehicle speed signals, the target mass estimation section includes the straight acceleration section, and the preset filtering conditions include a third preset filtering condition.

[0083] Based on preset filtering criteria, the driving state data in the driving state range is filtered to obtain the target quality estimation range, which also includes the following steps:

[0084] Step 1: Select multiple sampling intervals containing vehicle speed signals that meet the third preset screening criteria within the straight road section as multiple pre-selected intervals.

[0085] The third preset filtering condition is that the acceleration is positive and the vehicle speed signal gradually increases. In this embodiment, the specific value of the acceleration is not limited. The sampling duration corresponding to the sampling interval is not limited. This embodiment filters the driving state data corresponding to vehicle speed signals that do not meet the third preset filtering condition, and only extracts the sampling interval containing the vehicle speed signals that meet the third preset filtering condition.

[0086] Optionally, the terminal may select multiple pre-selected intervals from the sampling intervals in the straight road section where the acceleration is positive and the vehicle speed signal gradually increases.

[0087] Step 2: The pre-selected interval containing the most sampling times is determined as the flat acceleration interval.

[0088] In order to improve the data quality of the flat acceleration interval, this embodiment of the application selects the pre-selected interval with the most sampling times and determines it as the flat acceleration interval.

[0089] In some embodiments, determining the preselected interval containing the most sampling times as the flat acceleration interval includes the following steps:

[0090] Multiple pre-selected intervals are preprocessed to obtain multiple initial intervals; the initial interval containing the most sampling times is taken as the flat acceleration interval.

[0091] Preprocessing refers to removing driving status data containing brake switch signals or clutch switch signals in the pre-selected range, or removing driving status data in the pre-selected range where the vehicle speed signal exceeds the threshold, or removing abnormal points in the pre-selected range that obviously do not meet the requirements, or other distorted data.

[0092] For example, the terminal selects the top 5 pre-selected intervals with the most sampling times, then removes driving status data containing brake switch signals or clutch switch signals from the 5 pre-selected intervals, and finally uses the initial interval with the most sampling times from the removed pre-selected intervals as the straight acceleration interval.

[0093] In this embodiment of the application, a straight acceleration interval is further selected in the straight road section. The vehicle mass estimation value of the driving state interval is estimated based on the driving state data of the straight acceleration interval. This can avoid the problem of inaccurate vehicle mass estimation value caused by wind force when driving at a constant speed, and can further improve the accuracy of vehicle mass estimation value.

[0094] In one embodiment, the methods for estimating truck mass are basically based on vehicle dynamics models, with differences in the acquisition and calculation methods of various parameters in the dynamics model. For example, the acquisition of the vehicle's driving gradient varies. Some methods involve adding gradient sensors, increasing costs; others ignore the impact of gradient on modeling, leading to reduced estimation accuracy; still others use intelligent filtering algorithms to calculate gradient, but these require specific sampling frequency and accuracy. Currently, gradient parameter processing mainly relies on altitude data provided by GPS. However, the single-point error of onboard GPS altitude data is relatively large, resulting in low reliability and significant errors in the measured gradient data, further reducing the accuracy of the estimated vehicle mass. Therefore, in this embodiment, the estimated vehicle mass value for the driving state interval is determined based on the driving state data of the target mass estimation interval and the pre-acquired vehicle dynamics model, specifically including the following steps:

[0095] Step 1: Determine the slope data corresponding to the target quality estimation interval.

[0096] Specifically, if the target quality estimation interval is a straight road section (or a straight acceleration section), the slope data corresponding to the target quality estimation interval is 0; if the target quality estimation interval is an uphill road section, the slope data corresponding to the target quality estimation interval is determined based on the vehicle speed signal and the elevation signal.

[0097] In some embodiments, if the target quality estimation interval is an uphill section, the slope data corresponding to the target quality estimation interval is determined based on the vehicle speed signal and the elevation signal, including the following steps:

[0098] Integrate the vehicle speed signal within the target quality estimation interval to obtain the mileage value corresponding to the target quality estimation interval; fit the mileage value with the elevation signal to obtain the fitting function, and differentiate the fitting function to obtain the slope data corresponding to the target quality estimation interval.

[0099] The fitting function is h = a + bx + cx 2 +dx 3 .

[0100] Step 2: Determine the estimated vehicle mass value for the driving state range based on the driving state data, slope data, and pre-acquired vehicle dynamics model for the target mass estimation range.

[0101] As can be seen from the above embodiments, the target quality estimation interval includes at least 5 combinations: Combination 1: straight road section interval; Combination 2: straight acceleration interval; Combination 3: uphill road section interval; Combination 4: straight road section interval and uphill road section interval; Combination 5: straight acceleration interval and uphill road section interval.

[0102] Optionally, the terminal determines the combination type of the target mass estimation interval, determines the slope data corresponding to the combination type, uses the determined slope data to replace the slope data obtained by the vehicle network platform, and inputs the driving state data and slope data of the target mass estimation interval into the pre-acquired vehicle dynamics model to obtain the vehicle mass estimation value of the driving state interval.

[0103] In this embodiment, by selecting straight road sections and uphill road sections from the target quality estimation interval, and calculating the slope data corresponding to the straight road sections and uphill road sections respectively, the slope data obtained by the calculation can be used to replace the slope data collected by the vehicle network platform, thus avoiding the problem of large errors in slope data obtained by processing GPS single-point altitude data.

[0104] In some embodiments, considering that when a manual transmission vehicle starts in the lowest gear, factors such as large inertial resistance and clutch slippage lead to inaccurate vehicle driving force, and that the engine's reserve power is insufficient when the vehicle is running in the highest gear, this application embodiment further filters the target mass estimation range based on gear selection criteria. Specifically, based on the driving state data, slope data, and pre-acquired vehicle dynamics model of the target mass estimation range, the estimated vehicle mass value of the driving state range is determined, including the following steps:

[0105] Remove driving state data in the target mass estimation range where the transmission gear signal is the lowest or highest gear signal; input the driving state data and slope data of the removed target mass estimation range into the pre-acquired vehicle dynamics model to determine the vehicle mass estimate value of the driving state range.

[0106] In this embodiment of the application, driving state data in the target mass estimation interval where the transmission gear signal is the lowest gear signal or the highest gear signal are excluded. This can avoid the problem that the vehicle driving force is inaccurate due to factors such as large inertial resistance and clutch slippage when the vehicle is running in the lowest gear, and insufficient engine reserve power when the vehicle is running in the highest gear, which in turn leads to inaccurate vehicle mass estimation values ​​estimated by the vehicle dynamics model.

[0107] In one embodiment, the estimated vehicle mass for the target mass estimation range is determined based on driving state data, slope data, and a pre-acquired vehicle dynamics model, including:

[0108] Step 1: Input the slope data and driving state data corresponding to the target mass estimation interval into the pre-acquired vehicle dynamics model, and obtain the initial mass estimation value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model.

[0109] The target quality estimation range can be either the target quality estimation range after gear selection or the target quality estimation range without gear selection.

[0110] The vehicle dynamics model is mainly based on the vehicle's driving equations. Since it takes the estimation of the mass of a traditional two-axle cargo vehicle as an example, the driving force generated by the engine is equal to the sum of other resistances. The specific model is as follows:

[0111]

[0112] Right now:

[0113] Among them, T tq For engine output torque, i g For the gear ratio of the transmission, i o The transmission ratio of the main reducer, η T Where r is the mechanical efficiency of the transmission system, m is the tire radius, g is the vehicle mass, f is the rolling resistance coefficient, and C is the total mass of the vehicle. D denoted as the air resistance coefficient, A as the vehicle's frontal area, u as the vehicle's speed, i as the gradient, and δ as the vehicle's rotational mass conversion factor.

[0114] In this embodiment of the application, T tq 、u refers to the data information provided by the vehicle networking platform, i g ,r,i o A depends on the vehicle configuration, η T f, C D δ represents the experience accumulated by the vehicle design manufacturer and can be considered a constant, while i is obtained through the calculation process described in the above embodiments.

[0115] In this embodiment of the application, the slope data and driving state data corresponding to the target mass estimation interval are input into the pre-acquired vehicle dynamics model, and the vehicle mass m at each time within the target mass estimation interval can be obtained.

[0116] Step 2: Perform probability density statistics on the initial mass estimation values ​​corresponding to the target mass estimation interval, and take the initial mass estimation value corresponding to the maximum probability density as the vehicle mass estimation value of the driving state interval.

[0117] Specifically, the probability density function is obtained by performing probability density statistics on the initial quality estimates within the target quality estimation interval. This probability density function is a kernel density function. A schematic diagram of the probability density function is shown below. Figure 4 As shown.

[0118] In this embodiment of the application, by performing probability density statistics on the initial mass estimation values ​​corresponding to the target mass estimation interval, and using the initial mass estimation value corresponding to the maximum probability density value as the vehicle mass estimation value in the driving state interval, the problem of signal distortion caused by low data frequency of the vehicle network platform can be further eliminated, and the estimation accuracy can be improved.

[0119] In one embodiment, this application provides detailed steps of a vehicle weight estimation method, such as... Figure 5 As shown, the specific steps include:

[0120] Step 502: Divide the pre-acquired driving state dataset into multiple driving state intervals; the driving state dataset includes driving state data corresponding to each sampling time.

[0121] Step 504: For any driving state interval, the sampling interval containing the elevation signal that meets the first preset screening condition is determined as a straight road section interval; the sampling interval containing the elevation signal that meets the second preset screening condition is determined as an uphill road section interval.

[0122] Step 506: The sampling intervals containing multiple vehicle speed signals that meet the third preset screening conditions in the straight road section are determined as multiple pre-selected intervals; the multiple pre-selected intervals are pre-processed to obtain multiple initial intervals; the initial interval containing the most sampling times is taken as the straight acceleration interval.

[0123] Step 508: If the target quality estimation interval is a straight road section interval or a straight acceleration interval, then the slope data corresponding to the target quality estimation interval is 0, and proceed to step 512.

[0124] Step 510: If the target quality estimation interval is an uphill section, integrate the vehicle speed signal in the target quality estimation interval to obtain the mileage value corresponding to the target quality estimation interval; fit the mileage value with the elevation signal to obtain the fitting function, and differentiate the fitting function to obtain the slope data corresponding to the target quality estimation interval, and then execute step 512.

[0125] Step 512: Remove driving status data in the target quality estimation range where the transmission gear signal is the lowest or highest gear signal;

[0126] Step 514: Input the slope data and driving state data corresponding to the target mass estimation interval after elimination into the pre-acquired vehicle dynamics model, and obtain the initial mass estimation value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model.

[0127] Step 516: Perform probability density statistics on the initial mass estimation values ​​corresponding to the target mass estimation interval, and take the initial mass estimation value corresponding to the maximum probability density as the vehicle mass estimation value of the driving state interval.

[0128] In this embodiment, driving state data in each driving state interval is filtered to obtain a high-quality target quality estimation interval that can be used to evaluate vehicle quality. The vehicle quality estimation value corresponding to the target quality estimation interval is used as the vehicle quality estimation value of the driving state interval to which the target quality estimation interval belongs. This can reduce the impact of distorted data on the accuracy of vehicle quality estimation value and improve the accuracy of vehicle quality estimation value. By performing probability density statistics on the initial quality estimation value corresponding to the target quality estimation interval, and using the initial quality estimation value corresponding to the maximum probability density value as the vehicle quality estimation value of the driving state interval, the problem of signal distortion caused by low data frequency of the vehicle network platform can be eliminated.

[0129] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0130] Based on the same inventive concept, this application also provides a vehicle weight estimation device for implementing the vehicle weight estimation method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more vehicle weight estimation device embodiments provided below can be found in the limitations of the vehicle weight estimation method described above, and will not be repeated here.

[0131] In one embodiment, such as Figure 6 As shown, a vehicle weight estimation device is provided, including: a first interval division module 100, a second interval division module 200, and a vehicle weight estimation module 300, wherein:

[0132] The first interval division module 100 is used to divide the pre-acquired driving state dataset into multiple driving state intervals; the driving state dataset includes driving state data corresponding to each sampling time.

[0133] The second interval division module 200 is used to filter the driving state data in any driving state interval based on preset filtering conditions to obtain the target quality estimation interval.

[0134] The vehicle mass estimation module 300 is used to determine the estimated vehicle mass value for the driving state range based on the driving state data of the target mass estimation range and the pre-acquired vehicle dynamics model.

[0135] In one embodiment, the driving status data includes elevation signals, the target quality estimation interval includes straight road section intervals and / or uphill road section intervals, and the preset screening conditions include a first preset screening condition and a second preset screening condition; the second interval division module 200 is further configured to: determine the sampling interval where the elevation signal that meets the first preset screening condition is located as a straight road section interval;

[0136] The sampling interval containing the elevation signal that meets the second preset screening condition is determined as the climbing section interval.

[0137] In one embodiment, the driving status data also includes vehicle speed signals, the target quality estimation interval also includes a straight acceleration interval, the preset filtering conditions also include a third preset filtering condition, and the second interval division module 200 is further used to: determine the sampling intervals of multiple vehicle speed signals that meet the third preset filtering condition in the straight road section interval as multiple pre-selected intervals;

[0138] The pre-selected interval containing the most sampling times is determined as the flat acceleration interval.

[0139] In one embodiment, the second interval division module 200 is further configured to: preprocess multiple pre-selected intervals to obtain multiple initial intervals;

[0140] The initial interval containing the most sampling times will be used as the flat acceleration interval.

[0141] In one embodiment, the vehicle mass estimation module 300 is further configured to: determine the slope data corresponding to the target mass estimation range;

[0142] Based on the driving state data, slope data, and pre-acquired vehicle dynamics model of the target mass estimation range, the estimated vehicle mass value of the driving state range is determined.

[0143] In one embodiment, the driving status data also includes a transmission gear signal, and the vehicle mass estimation module 300 is further used for:

[0144] Remove driving status data in the target quality estimation range where the transmission gear signal is either the lowest or highest gear;

[0145] The driving state data and slope data of the target mass estimation interval after elimination are input into the pre-acquired vehicle dynamics model to determine the vehicle mass estimation value of the driving state interval.

[0146] In one embodiment, the vehicle mass estimation module 300 is further configured to: if the target mass estimation interval is a straight road section interval, then the slope data corresponding to the target mass estimation interval is 0;

[0147] If the target quality estimation interval is an uphill section, then the slope data corresponding to the target quality estimation interval is determined based on the vehicle speed signal and the elevation signal.

[0148] In one embodiment, the vehicle mass estimation module 300 is further configured to: integrate the vehicle speed signal in the target mass estimation interval to obtain the mileage value corresponding to the target mass estimation interval;

[0149] By fitting the mileage values ​​to the elevation signal, a fitting function is obtained. The derivative of the fitting function is then calculated to obtain the slope data corresponding to the target quality estimation interval.

[0150] In one embodiment, the vehicle mass estimation module 300 is further configured to: input the slope data and driving state data corresponding to the target mass estimation interval into a pre-acquired vehicle dynamics model, and obtain the initial mass estimation value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model;

[0151] Probability density statistics are performed on the initial mass estimation values ​​corresponding to the target mass estimation interval, and the initial mass estimation value corresponding to the maximum probability density is used as the vehicle mass estimation value of the driving state interval.

[0152] Each module in the aforementioned vehicle weight estimation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0153] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a vehicle mass estimation method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0154] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0155] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0156] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0157] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0159] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0160] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for estimating vehicle weight, characterized in that, The method includes: The pre-acquired driving status dataset is divided into multiple driving status intervals; the driving status dataset includes driving status data corresponding to each sampling time, and the driving status data includes elevation signals and vehicle speed signals; For any driving state interval, the driving state data in the driving state interval is filtered based on preset filtering conditions to obtain the target quality estimation interval; The combination type of the target quality estimation interval is determined, and the slope data corresponding to the combination type is determined. The combination types of the target quality estimation interval include at least: Combination 1: straight road section interval, Combination 2: straight acceleration interval, Combination 3: climbing road section interval, Combination 4: straight road section interval and climbing road section interval, Combination 5: straight acceleration interval and climbing road section interval; wherein, if the target quality estimation interval is a straight road section interval, the slope data corresponding to the target quality estimation interval is 0; if the target quality estimation interval is a climbing road section interval, the slope data corresponding to the target quality estimation interval is determined based on the vehicle speed signal and the elevation signal. Using predetermined slope data instead of the slope data obtained by the vehicle-to-everything (V2X) platform, and inputting the driving state data and slope data of the target mass estimation interval into a pre-acquired vehicle dynamics model, the vehicle mass estimation value of the driving state interval is obtained. This includes: inputting the slope data and driving state data corresponding to the target mass estimation interval into the pre-acquired vehicle dynamics model; obtaining the initial mass estimation value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model; performing probability density statistics on the initial mass estimation values ​​corresponding to the target mass estimation interval; and using the initial mass estimation value corresponding to the maximum probability density value as the vehicle mass estimation value of the driving state interval. The vehicle dynamics model is as follows: Right now: in, For engine output torque, This refers to the gear ratio of the transmission. The transmission ratio of the main reducer. For the mechanical efficiency of the transmission system, For the tire radius, For the overall vehicle quality, It is the acceleration due to gravity. The rolling resistance coefficient, The air drag coefficient, The vehicle's frontal area. For vehicle speed, For slope, t represents the vehicle rotational mass conversion factor, and t represents each sampling time.

2. The method according to claim 1, characterized in that, The target quality estimation interval includes straight road section intervals and / or uphill road section intervals, and the preset screening conditions include a first preset screening condition and a second preset screening condition; The step of filtering driving state data within the driving state range based on preset filtering conditions to obtain the target quality estimation range includes: The sampling interval containing the elevation signal that meets the first preset screening condition is determined as the straight road section interval; The sampling interval containing the elevation signal that meets the second preset screening condition is determined as the climbing section interval.

3. The method according to claim 2, characterized in that, The target quality estimation interval also includes a flat acceleration interval, and the preset filtering conditions also include a third preset filtering condition. The step of filtering the driving state data in the driving state interval based on the preset filtering conditions to obtain the target quality estimation interval further includes: The sampling intervals containing multiple vehicle speed signals that meet the third preset screening conditions in the straight road section are determined as multiple pre-selected intervals; The pre-selected interval containing the most sampling times is determined as the flat acceleration interval.

4. The method according to claim 3, characterized in that, The pre-selected interval containing the most sampling times will be used as the flat acceleration interval, including: Multiple pre-selected intervals are preprocessed to obtain multiple initial intervals; The initial interval containing the most sampling times will be used as the flat acceleration interval.

5. The method according to claim 1, characterized in that, The driving status data also includes a transmission gear position signal, and the method further includes: Remove driving status data in the target quality estimation range where the transmission gear signal is the lowest or highest gear signal; The driving state data and slope data of the target mass estimation interval after elimination are input into the pre-acquired vehicle dynamics model to determine the vehicle mass estimation value of the driving state interval.

6. The method according to claim 1, characterized in that, The step of determining the slope data corresponding to the target mass estimation interval based on the vehicle speed signal and elevation signal includes: Integrate the vehicle speed signal within the target quality estimation interval to obtain the mileage value corresponding to the target quality estimation interval; The mileage value is fitted to the elevation signal to obtain a fitting function, and the derivative of the fitting function is calculated to obtain the slope data corresponding to the target quality estimation interval.

7. A vehicle mass estimation device, characterized in that, The device includes: The first interval division module is used to divide the pre-acquired driving state dataset into multiple driving state intervals; the driving state dataset includes driving state data corresponding to each sampling time, and the driving state data includes elevation signals and vehicle speed signals; The second interval division module is used to filter the driving state data in any driving state interval based on preset filtering conditions to obtain the target quality estimation interval. The vehicle mass estimation module is used to determine the combination type of the target mass estimation interval and the corresponding slope data. The combination types of the target mass estimation interval include at least: Combination 1: straight road section interval; Combination 2: straight acceleration section interval; Combination 3: uphill road section interval; Combination 4: straight road section interval and uphill road section interval; Combination 5: straight acceleration section and uphill road section interval. Wherein, if the target mass estimation interval is a straight road section interval, the corresponding slope data is 0; if the target mass estimation interval is an uphill road section interval, the slope data corresponding to the target mass estimation interval is determined based on the vehicle speed signal and elevation signal; the determined slope data is then used. Instead of using slope data obtained from the vehicle networking platform, the driving state data and slope data of the target mass estimation interval are input into a pre-acquired vehicle dynamics model to obtain the vehicle mass estimate value of the driving state interval. This includes: inputting the slope data and driving state data corresponding to the target mass estimation interval into the pre-acquired vehicle dynamics model; obtaining the initial mass estimate value corresponding to each sampling time in the target mass estimation interval through the vehicle dynamics model; performing probability density statistics on the initial mass estimate values ​​corresponding to the target mass estimation interval; and using the initial mass estimate value corresponding to the maximum probability density value as the vehicle mass estimate value of the driving state interval. The vehicle dynamics model is as follows: Right now: in, For engine output torque, This refers to the gear ratio of the transmission. The transmission ratio of the main reducer. For the mechanical efficiency of the transmission system, For the tire radius, For the overall vehicle quality, It is the acceleration due to gravity. The rolling resistance coefficient, The air drag coefficient, The vehicle's frontal area. For vehicle speed, For slope, t represents the vehicle rotational mass conversion factor, and t represents each sampling time.

8. The apparatus according to claim 7, characterized in that, The target quality estimation interval includes a straight road section interval and / or an uphill road section interval, and the preset screening conditions include a first preset screening condition and a second preset screening condition; the second interval division module is further used to determine the sampling interval where the elevation signal that meets the first preset screening condition is located as the straight road section interval; and to determine the sampling interval where the elevation signal that meets the second preset screening condition is located as the uphill road section interval.

Images