Vehicle mass determination method, device and equipment, vehicle and medium

Abstract

The embodiment of the invention provides a vehicle mass determination method and device, equipment, a vehicle and a medium. The method comprises the steps of selecting a plurality of real-time quality estimation fragments from full-real-time quality estimation results, then obtaining a vehicle quality estimation result corresponding to each real-time quality estimation fragment, and finally, obtaining a real-time quality estimation result corresponding to each real-time quality estimation fragment on the basis of a road adhesion coefficient and the vehicle quality estimation result when a vehicle runs corresponding to each real-time quality estimation fragment. And determining a single operation process quality estimation result. The method is used for achieving the effect of improving the accuracy and reliability of the quality estimation result in the single operation process.

Description

Technical Field

[0001] The present application relates to the field of automotive engineering, and in particular to a vehicle mass determination method, device, equipment, vehicle and medium. Background Art

[0002] Vehicle mass is an important parameter in vehicle dynamics control and can remain basically stable during a single vehicle operation. Accurate vehicle mass information plays a key role in vehicle performance optimization, fuel economy strategy formulation, fault diagnosis, and maintenance.

[0003] In the prior art, the real-time mass estimation result is a set of data that fluctuates dramatically due to road conditions, and there is a problem that different road conditions lead to significant deviations in the vehicle mass estimation result. In the existing solution, the unloaded weight or common mass of the vehicle is selected as the mass estimation result of a single operation process.

[0004] However, the quality estimation results of a single run process determined in this way have low accuracy and poor reliability. Summary of the invention

[0005] Embodiments of the present application provide a vehicle mass determination method, apparatus, device, vehicle, and medium to achieve the effect of improving the accuracy and reliability of vehicle mass estimation results obtained during a single operation process.

[0006] In a first aspect, an embodiment of the present application provides a method for determining vehicle mass, comprising:

[0007] Selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result;

[0008] Obtaining a vehicle mass estimation result corresponding to each real-time mass estimation segment;

[0009] The mass estimation result of a single running process is determined based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment.

[0010] In a possible implementation manner, determining the mass estimation result of a single operation process based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment includes:

[0011] For each real-time quality estimation segment, determining a weighting factor corresponding to the real-time quality estimation segment according to a road adhesion coefficient corresponding to the real-time quality estimation segment when the vehicle is traveling;

[0012] The single operation process mass estimation result is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor.

[0013] In a possible implementation manner, determining the single operation process mass estimation result according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor includes:

[0014] According to the weighting factor corresponding to each real-time mass estimation segment, the vehicle mass estimation results corresponding to multiple real-time mass estimation segments are weighted averaged to obtain the mass estimation result of the single operation process.

[0015] In a possible implementation manner, determining a weighting factor corresponding to the real-time quality estimation segment according to a road adhesion coefficient corresponding to the real-time quality estimation segment when the vehicle is traveling includes:

[0016] Based on the mapping relationship between the preset adhesion coefficient range and the weighting factor, and the road adhesion coefficient of the vehicle corresponding to the real-time quality estimation segment, the weighting factor corresponding to the range of the road adhesion coefficient is determined as the weighting factor corresponding to the real-time quality estimation segment.

[0017] In a possible implementation manner, the selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result includes:

[0018] According to the road type during a single operation of the vehicle, multiple real-time quality estimation segments are selected from the full real-time quality estimation result; wherein the number of real-time quality estimation segments selected for different road types is different.

[0019] In a possible implementation manner, the selecting of multiple real-time quality estimation segments from the full real-time quality estimation result according to the road surface type during a single operation of the vehicle includes:

[0020] Selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result according to the road surface type during a single operation of the vehicle and a preset real-time quality estimation segment selection rule;

[0021] The real-time quality estimation segment selection rule includes at least one restriction condition on vehicle driving data.

[0022] In a possible implementation manner, the real-time quality estimation segment selection rule includes at least one of the following conditions:

[0023] The vehicle speed is greater than the preset speed;

[0024] The vehicle's acceleration is greater than the preset acceleration;

[0025] The driving torque of the vehicle is greater than the preset torque;

[0026] The vehicle's traction control system TC, anti-lock braking system ABS and yaw stability control system YSC functions are not activated.

[0027] In a possible implementation, the method further includes:

[0028] During the operation of the vehicle, the collected road surface images are classified using a pre-trained road surface classification algorithm to obtain the road surface type.

[0029] In a possible implementation manner, the road surface type includes any one of the following:

[0030] Snowy roads;

[0031] Unpaved roads;

[0032] flooded roads;

[0033] Dry paved road surface.

[0034] In a possible implementation manner, obtaining the vehicle mass estimation result corresponding to each real-time mass estimation segment includes:

[0035] For each real-time mass estimation segment, a mean value of mass estimation results of a plurality of sampling points in the real-time mass estimation segment is calculated to obtain a vehicle mass estimation result corresponding to the real-time mass estimation segment.

[0036] In a possible implementation manner, before calculating the average of the quality estimation results of multiple sampling points in the real-time quality estimation segment, the method further includes:

[0037] Eliminating abnormal data in the quality estimation results of the multiple sampling points in the real-time quality estimation segment to obtain processed quality estimation results of the multiple sampling points;

[0038] Accordingly, the calculating the mean value of the quality estimation results of the multiple sampling points in the real-time quality estimation segment includes:

[0039] The average of the quality estimation results of the plurality of sampling points after the processing is calculated.

[0040] In a possible implementation, the method further includes:

[0041] During the operation of the vehicle, a Kalman filter state estimation model is used to perform real-time estimation of mass according to basic information, driving data and environmental data of the vehicle to obtain the full real-time mass estimation result;

[0042] The Kalman filter state estimation model is obtained based on a four-dimensional state space equation established based on the vehicle longitudinal dynamics equation after optimizing the front wheel steering angle parameters.

[0043] In a possible implementation manner, before determining the mass estimation result of the single operation process according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor, the method includes:

[0044] For each real-time mass estimation segment, obtaining the acceleration of the vehicle within a preset time period before the real-time mass estimation segment;

[0045] Correcting the weighting factor corresponding to the real-time quality estimation segment according to the acceleration to obtain a corrected weighting factor;

[0046] Accordingly, determining the single operation process mass estimation result according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor includes:

[0047] The mass estimation result of the single operation process is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the corrected weighting factor.

[0048] In a possible implementation, the method further includes:

[0049] If it is detected that the vehicle is parked and the door is open, re-collecting the full real-time quality estimation result, and determining the quality estimation result of a single operation process of the vehicle according to the newly collected full real-time quality estimation result;

[0050] or,

[0051] If it is detected that the vehicle is parked and the parking time is greater than the preset time, the full real-time quality estimation result is re-collected, and the quality estimation result of a single operation process of the vehicle is determined based on the newly collected full real-time quality estimation result.

[0052] In a possible implementation, the method further includes:

[0053] During the operation of the vehicle, the road adhesion coefficient is determined in real time based on data detected by sensors of the vehicle.

[0054] In a second aspect, an embodiment of the present application provides a vehicle mass determination device, comprising:

[0055] A selection module, used for selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result;

[0056] An acquisition module, used to acquire a vehicle mass estimation result corresponding to each real-time mass estimation segment;

[0057] The determination module is used to determine the mass estimation result of a single running process based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment.

[0058] In a third aspect, an embodiment of the present application provides a vehicle quality determination device, including: a memory, a processor;

[0059] The memory stores computer-executable instructions;

[0060] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0061] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0062] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0063] The vehicle mass determination method, device, equipment, vehicle and medium provided in the embodiments of the present application first select multiple real-time mass estimation fragments from the full real-time mass estimation result in a single operation process, and obtain the vehicle mass estimation result corresponding to the fragment, and finally determine the mass estimation result of this operation process based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to the fragment. This solution takes into account the influence of the road adhesion coefficient on the mass estimation result, and achieves the effect of improving the accuracy and reliability of the obtained vehicle mass estimation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0065] Figure 1 A flow chart of a first embodiment of a method for determining vehicle mass provided in the present application;

[0066] Figure 2 A flowchart of a specific vehicle mass determination method embodiment 3 provided in this application;

[0067] Figure 3 A schematic diagram of the structure of a first embodiment of a device for determining vehicle mass provided by the present application;

[0068] Figure 4 A schematic diagram of the structure of the second embodiment of the vehicle mass determination device provided by the present application;

[0069] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0070] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0072] First, the terms involved in this application are explained:

[0073] Road adhesion coefficient: The road adhesion coefficient is a key parameter to measure the slipperiness of the road surface, and its magnitude depends on the characteristics of the road surface and tires. Generally, the adhesion coefficient of dry, good asphalt or concrete roads is high, while on wet, muddy or icy roads, the adhesion coefficient may be significantly reduced. During vehicle driving, the size of the road adhesion coefficient will have a certain impact on the accuracy of the estimated results of the vehicle mass.

[0074] Electronic Control Unit: The Electronic Control Unit (ECU) is the core control component in a car. It is responsible for receiving, processing and storing information from various sensors and other components of the car, and controlling various systems and components of the car according to preset programs and algorithms.

[0075] In order to clearly understand the technical solution of the present application, the solution of the prior art is introduced in detail below.

[0076] Real-time estimation of vehicle mass is to input basic vehicle information and driving status data into an established evaluation model for evaluating vehicle mass. After the estimation model processes the input data, the real-time estimation result of vehicle mass can be obtained. The accuracy of the estimation result is affected by the road environment.

[0077] Full real-time vehicle mass estimation is to estimate the vehicle mass at all times. The obtained full real-time mass estimation results are a set of data that fluctuates dramatically with environmental changes. This method has the problem that different road conditions lead to significant deviations in vehicle mass estimation results. When performing vehicle performance optimization, fault diagnosis, and maintenance operations, the real-time mass estimation results obtained by the full real-time mass estimation method have poor reference value.

[0078] In addition, some existing technical solutions directly use the vehicle's unloaded weight or common mass as the mass estimation result of a single operation, and use it for vehicle performance optimization, fault diagnosis and maintenance, etc. The mass estimation results determined by this method have the problems of low accuracy and poor reliability.

[0079] In response to the above technical problems, the technical concept of this application is: fully consider the impact of the road adhesion coefficient on the vehicle mass estimation result, and adjust the final single-run process mass estimation result according to the road adhesion coefficient corresponding to each real-time mass estimation segment. By flexibly responding to the impact of different road conditions on the accuracy of the mass estimation result, the vehicle mass determination method provided by this application improves the accuracy of vehicle mass estimation while ensuring timely estimation, and can meet the requirements of various working conditions such as vehicle performance optimization, fault diagnosis and maintenance.

[0080] The method for determining the vehicle mass provided in the present application can estimate the mass of the vehicle during a single operation based on the road adhesion coefficient. It can be executed in the ECU in the vehicle, or the relevant data required in the estimation process can be imported into other electronic devices such as computer devices for execution. This scheme does not limit the specific form of the equipment.

[0081] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0082] Figure 1 The flowchart of the first embodiment of the method for determining the vehicle mass provided in this application is as follows: Figure 1 As shown, the method includes:

[0083] S101. Select multiple real-time quality estimation segments from the full real-time quality estimation result.

[0084] In this solution, while the vehicle is driving, the vehicle's sensors can obtain the vehicle's own driving data and the environmental data of the road section on which the vehicle is driving in real time. By inputting the vehicle's own basic information and the data obtained in real time into the model for quality estimation, a full real-time quality estimation result can be obtained. Based on the obtained full real-time quality estimation result of a single operation process, the quality estimation result of a single operation process can be determined.

[0085] The full real-time mass estimation result includes the mass estimation result of the vehicle at every moment. Specifically, during the operation of the vehicle, the mass is estimated in real time using an estimation model based on the basic information of the vehicle, driving data, and environmental data, to obtain the full real-time mass estimation result. The basic information of the vehicle is the inherent parameters of the vehicle, such as: the unloaded mass of the vehicle, the windward area, the air resistance coefficient, etc. The driving data and environmental data are acquired in real time during the driving process of the vehicle, wherein the driving data includes the acceleration, speed, front wheel angle, etc. of the vehicle; the environmental data includes air density, slope, etc.

[0086] In a specific implementation, before real-time estimation of the mass is performed, the unloaded mass of the vehicle is used as an initial value of the mass estimation result.

[0087] In a specific implementation, the estimation model may be a Kalman filter state estimation model. The Kalman filter state estimation model is obtained based on a four-dimensional state space equation established based on the vehicle longitudinal dynamics equation. Specifically, a four-dimensional state space equation is first established based on the vehicle longitudinal dynamics equation, and a corresponding output equation is obtained. The Kalman filter state estimation model can be established based on the state space equation and the output equation.

[0088] In a specific implementation, the vehicle longitudinal dynamics equation may be the vehicle longitudinal dynamics equation after optimizing the front wheel turning angle parameters. Specifically, the vehicle longitudinal dynamics equation after optimizing the front wheel turning angle parameters is:

[0089]

[0090] Among them, F rdrive is the total driving torque of the rear axle of the vehicle, F fdrive is the total driving torque of the front axle of the vehicle, F rbrake is the total braking torque of the vehicle rear axle, F fbrake is the total braking torque of the front axle of the vehicle, β is the front wheel turning angle, f is the rolling resistance coefficient, m is the vehicle mass, g is the acceleration of gravity, i is the slope, C D is the air resistance coefficient, A is the frontal area of ​​the vehicle, ρ is the air density, v is the vehicle speed, and a is the longitudinal acceleration of the vehicle.

[0091] The four-dimensional state space equation established based on the vehicle longitudinal dynamics equation is as follows:

[0092]

[0093] Where k and k-1 represent time k and time k-1 respectively, Δt is the time interval, and W is the process noise.

[0094] The output equation of the obtained system is:

[0095]

[0096] where V is the measurement noise of the system.

[0097] Based on the above state equation and output equation, a Kalman filter state estimation model can be established for real-time vehicle mass estimation.

[0098] In this method, the Kalman filter state estimation model is obtained based on the vehicle longitudinal dynamics equation after optimizing the front wheel steering parameters. The traditional vehicle longitudinal dynamics equation is not suitable for turning conditions. Therefore, when estimating the vehicle mass when the vehicle turns according to the mass estimation model established therein, the estimation result will also have a large deviation. Considering that when the vehicle turns, the change of the front wheel steering angle of the vehicle will cause the longitudinal force of the vehicle to change. Therefore, the introduction of the front wheel steering parameters into the traditional vehicle longitudinal dynamics equation can optimize the vehicle longitudinal dynamics equation. The estimation model established based on the vehicle longitudinal dynamics equation after optimizing the front wheel steering parameters can have a higher estimation accuracy when the vehicle turns, thereby ensuring the stability and accuracy of the real-time mass estimation results obtained.

[0099] In this step, this scheme fully considers the characteristic that the vehicle mass remains basically stable during the operation of the vehicle. By selecting multiple real-time mass estimation fragments from the full real-time mass estimation results, and realizing the quality estimation results of a single operation process based on the selected multiple real-time mass estimation fragments, the overall estimation efficiency is improved.

[0100] The number of the selected real-time quality estimation segments is not limited in this embodiment.

[0101] S102: Obtain a vehicle mass estimation result corresponding to each real-time mass estimation segment.

[0102] In this step, after selecting multiple real-time quality estimation segments from the full real-time quality estimation result, each real-time quality estimation segment contains multiple sampling points, and each sampling point corresponds to a quality estimation result. For example, each real-time quality estimation segment takes 100 sampling points, and each sampling point corresponds to a quality estimation result. Therefore, in this step, it is necessary to obtain and process the quality estimation results corresponding to the multiple sampling points contained in each real-time quality estimation segment to obtain the vehicle quality estimation result corresponding to each real-time quality estimation segment.

[0103] In a specific implementation, the following method may be used to obtain the vehicle mass estimation result corresponding to each real-time mass estimation segment:

[0104] For each real-time mass estimation segment, the mean value of the mass estimation results of multiple sampling points in the real-time mass estimation segment is calculated to obtain the vehicle mass estimation result corresponding to the real-time mass estimation segment.

[0105] In this method, by taking the average of multiple sampling points in the real-time mass estimation segment as the vehicle mass estimation result corresponding to the segment, the influence of uncertain factors on the mass estimation result is reduced, the accuracy, reliability and stability of the mass estimation result corresponding to the segment are improved, and the accuracy of the vehicle mass estimation result finally obtained is also improved.

[0106] In a specific implementation, before calculating the average of the quality estimation results of multiple sampling points in the real-time quality estimation segment, the following method may be used to process the quality estimation results of the multiple sampling points:

[0107] Abnormal data in the quality estimation results of multiple sampling points in the real-time quality estimation segment are eliminated to obtain the quality estimation results of the multiple sampling points after processing; accordingly, the calculating the mean of the quality estimation results of the multiple sampling points in the real-time quality estimation segment includes: calculating the mean of the quality estimation results of the multiple sampling points after processing.

[0108] The abnormal data is a real-time mass estimation result that deviates too much from the true value. Specifically, when the mass estimation result is higher than the full-load mass plus a preset threshold, or the mass estimation result is lower than the no-load mass minus the preset threshold, the mass estimation result is determined to be abnormal data that deviates from the true value. The size of the preset threshold is set according to the actual situation and is not limited in this solution.

[0109] In this method, by eliminating abnormal data in the quality estimation results of multiple sampling points in the real-time quality estimation segment, the influence of uncertain factors on the quality estimation results is effectively reduced, and the accuracy and reliability of the vehicle quality estimation results corresponding to each real-time quality estimation segment obtained are further improved.

[0110] S103: Determine a single running process mass estimation result based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment.

[0111] In this step, the influence of the road adhesion coefficient on the accuracy of the vehicle mass estimation result is fully considered. Among them, the magnitude of the road adhesion coefficient can characterize the road conditions during driving, reflects the magnitude of the friction between the tires and the road surface of the driving section, and further reflects the accuracy of the mass estimation result obtained by estimating the mass of the driving section. During a single vehicle operation process, by adjusting the final single operation process mass estimation result according to the road adhesion coefficient corresponding to each real-time mass estimation segment, it is possible to reduce the influence of different road conditions on the accuracy of the mass estimation result and improve the accuracy of the vehicle mass estimation of the final single operation process.

[0112] In a specific implementation, determining a single running process mass estimation result based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment includes:

[0113] In the first step, for each real-time quality estimation segment, a weighting factor corresponding to the real-time quality estimation segment is determined according to a road adhesion coefficient corresponding to the real-time quality estimation segment when the vehicle is traveling.

[0114] In this step, during the operation of the vehicle, the road adhesion coefficient can be determined in real time based on data detected by the vehicle's sensors, wherein the vehicle's sensors include but are not limited to an inertial measurement unit (IMU), a wheel speed sensor, and the like.

[0115] The size of the road adhesion coefficient corresponding to the real-time quality estimation segment reflects the accuracy of the quality estimation result corresponding to the real-time quality estimation segment. Therefore, in this scheme, different weighting factors are assigned to each real-time quality estimation segment according to the size of the road adhesion coefficient corresponding to the segment, which can improve the accuracy of the quality estimation result of a single operation process finally obtained, and can cope with various working conditions. Among them, the size of the weighting factor can reflect the size of the deviation of the quality estimation result corresponding to the real-time quality estimation segment from the true value. When the quality estimation result corresponding to the real-time quality estimation segment deviates from the true value by a small amount, a weighting factor with a larger value is assigned to the real-time quality estimation segment; otherwise, a smaller weighting factor is assigned.

[0116] In a specific implementation, determining a weighting factor corresponding to the real-time quality estimation segment according to a road adhesion coefficient of the vehicle when the vehicle is traveling corresponding to the real-time quality estimation segment includes:

[0117] Based on the mapping relationship between the preset adhesion coefficient range and the weighting factor, and the road adhesion coefficient of the vehicle corresponding to the real-time quality estimation segment, the weighting factor corresponding to the range of the road adhesion coefficient is determined as the weighting factor corresponding to the real-time quality estimation segment.

[0118] Exemplarily, the mapping relationship between the road adhesion coefficient range and the weighting factor can be determined in the following two ways:

[0119] Method 1: directly set different weighting factors corresponding to different adhesion coefficient ranges.

[0120] Method 2: First determine an adhesion level according to the range of adhesion coefficient, and then determine the weighting factor according to the relationship between different levels and weighting factors. For example, adhesion coefficient 0-0.3 is set as level 1; adhesion coefficient 0.3-0.6 is set as level 2; adhesion coefficient 0.6-1 is set as level 3. The selection of adhesion coefficient range and how to divide the levels are not limited in this scheme.

[0121] Based on the mapping relationship between the above two attachment coefficient ranges and weighting factors, and the attachment coefficient corresponding to the real-time quality estimation segment, the weighting factor corresponding to the segment can be determined. For example, when the attachment coefficient corresponding to a real-time quality estimation segment is level 1, a weighting factor of 0.2 is assigned to the segment; when the attachment coefficient corresponding to a real-time quality estimation segment is level 2, a weighting factor of 0.5 is assigned to the segment; when the attachment coefficient corresponding to a real-time quality estimation segment is level 3, a weighting factor of 1 is assigned to the segment. Specifically, how to set the weighting factor corresponding to the level is not limited in this solution.

[0122] In the second step, the mass estimation result of the single operation process is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor.

[0123] In this step, by processing the vehicle mass estimation results corresponding to multiple real-time mass estimation segments and the corresponding weighting factors, the final single-run process mass estimation result can be obtained. The mass estimation result has higher reliability, accuracy and environmental adaptability.

[0124] In a specific implementation, the vehicle mass estimation results corresponding to multiple real-time mass estimation segments may be weighted averaged according to a weighting factor corresponding to each real-time mass estimation segment to obtain the mass estimation result of the single operation process.

[0125] For example, in a certain operation process, 3 real-time mass estimation segments are selected, where segment 1 corresponds to a vehicle mass estimation result of M1, with a weighting factor of A1; segment 2 corresponds to a vehicle mass estimation result of M2, with a weighting factor of A2; and segment 3 corresponds to a vehicle mass estimation result of M3, with a weighting factor of A2. The final single operation process mass estimation result M is:

[0126] M=(A1*M1+A2*M2+A2*M3) / (A1+A2+A2)

[0127] In a specific implementation, before determining the mass estimation result of the single operation process according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor, the method may further include:

[0128] For each real-time mass estimation segment, obtaining the acceleration of the vehicle within a preset time period before the real-time mass estimation segment;

[0129] Correcting the weighting factor corresponding to the real-time quality estimation segment according to the acceleration to obtain a corrected weighting factor;

[0130] Correspondingly, determining the quality estimation result of the single operation process according to the vehicle mass estimation result and the weighting factor corresponding to each real-time mass estimation segment includes: determining the quality estimation result of the single operation process according to the vehicle mass estimation result and the corrected weighting factor corresponding to each real-time mass estimation segment.

[0131] In this method, the weighting factor corresponding to the segment is corrected according to the acceleration of the vehicle in the preset time period before the extracted real-time mass estimation segment. In the preset time period before the real-time mass estimation segment, if the acceleration of the vehicle is greater than a certain threshold, it means that the vehicle mass estimation result corresponding to the segment is too large, and the weighting factor corresponding to the segment is reduced; if the acceleration is less than a certain threshold, it means that the vehicle mass estimation result corresponding to the segment is too small, and the weighting factor corresponding to the segment is increased. The preset time period is determined according to the situation and is not limited in this scheme.

[0132] For example, a real-time quality estimation segment is selected from the 15th to 20th second after the car starts to drive, and the weighting factor corresponding to the segment is determined to be 1 according to the adhesion coefficient of the segment. The acceleration within 30ms before the segment is judged: if the acceleration of the vehicle is -5m / s within 30ms before the segment 2 , then the weighting factor corresponding to the segment is modified to 1.05. The data in this example is given based on personal experience, and this solution does not limit the setting of the numerical value.

[0133] In a specific implementation, the method for determining the vehicle mass provided in this embodiment further includes:

[0134] If it is detected that the vehicle is stopped and the door is open, the full real-time quality estimation result is re-collected, and the quality estimation result of a single operation process of the vehicle is determined based on the newly collected full real-time quality estimation result; or, if it is detected that the vehicle is stopped and the parking time is greater than the preset time, the full real-time quality estimation result is re-collected, and the quality estimation result of a single operation process of the vehicle is determined based on the newly collected full real-time quality estimation result.

[0135] In this method, after the quality estimation result of a single operation process is determined by the above steps, it is necessary to determine whether the vehicle quality estimation result is reset. If it is determined that it needs to be reset, steps S101-S103 are repeated to determine the quality estimation result of the next operation process. In addition, before the result is reset, the quality estimation result of the current operation process remains unchanged. There are two ways to determine whether the vehicle quality estimation result is reset:

[0136] Method 1: The vehicle is parked and the door is open;

[0137] Method 2: The vehicle is parked and the parking time is longer than the preset time. The preset time is determined according to the specific application situation and is not limited by this solution.

[0138] In the method for determining vehicle mass provided in this embodiment, a plurality of real-time mass estimation segments are first selected from the full real-time mass estimation result, and then the vehicle mass estimation result corresponding to each real-time mass estimation segment is obtained, and finally, the mass estimation result of a single operation process is determined based on the road adhesion coefficient and the vehicle mass estimation result corresponding to each real-time mass estimation segment when the vehicle is traveling. This embodiment fully considers the characteristic that the vehicle can basically remain stable during a single operation process, and uses a plurality of selected real-time mass estimation segments to estimate a single operation process, so that the mass estimation result can be obtained more efficiently. In addition, this embodiment considers the influence of the road adhesion coefficient on the accuracy of the mass estimation result, and adjusts the mass estimation result of a single operation process finally obtained by using the road adhesion coefficient corresponding to each real-time mass estimation segment, thereby reducing the influence of different road conditions on the accuracy of the mass estimation result, and improving the accuracy of the vehicle mass estimation of the single operation process finally obtained.

[0139] On the basis of the above embodiments, regarding how to select multiple real-time mass estimation segments from the full real-time mass estimation result, the present application further provides a second embodiment of a method for determining vehicle mass, which is as follows:

[0140] Selecting multiple real-time quality estimation fragments from the full real-time quality estimation result may also include:

[0141] According to the road type during a single operation of the vehicle, multiple real-time quality estimation segments are selected from the full real-time quality estimation result; wherein the number of real-time quality estimation segments selected for different road types is different.

[0142] In this embodiment, the number of selected real-time quality estimation segments is determined according to the road surface type during a single operation of the vehicle. For a single operation, after the vehicle is started, the road surface type during the single operation can be determined by vehicle sensors such as a vehicle-mounted camera. When the road surface type is determined to be a poor road condition, more real-time quality estimation segments are selected; otherwise, fewer real-time quality estimation segments are selected. Specifically, the corresponding relationship between the road surface type and the number of real-time quality estimation segments to be selected is not limited in this solution.

[0143] In a specific implementation, the following method may be used to determine the road surface type during a single run:

[0144] During the operation of the vehicle, the collected road surface images are classified using the pre-trained road surface classification algorithm to obtain the road surface type of this operation process.

[0145] Specifically, an advanced driver assistance system (ADAS) or an advanced driving controller uses an on-board camera to obtain road images, and uses a pre-trained road classification algorithm to classify the road images. The classification processing results are sent to the ECU used to realize vehicle mass estimation via the on-board communication network. Among them, the on-board communication network includes but is not limited to the Flexray communication protocol, the controller area network (CAN), the controller area network with flexible data rate (CAN with Flexible Data-Rate, CANFD), etc. In addition, the training data used in the pre-training is a large number of road images collected previously. And the classification processing results can be sent to the ECU used to realize vehicle mass estimation in the form of digital signals.

[0146] In a specific implementation, it should be understood that the road surface type can be updated in real time during the driving process of the vehicle. Specifically, after each time period, the ADAS or advanced driving controller will send the new classification processing results to the ECU used to implement vehicle mass estimation via the vehicle communication network. Among them, the setting of the time period is determined according to the actual situation and is not limited in this application. Exemplarily, the road surface type in the ECU used to implement vehicle mass estimation is updated every 5 minutes.

[0147] In a specific implementation, the road surface type includes any of the following:

[0148] Snow-covered road; unpaved road; flooded road; dry paved road.

[0149] For example, when the road surface of this operation is classified as a snowy road surface, 7 real-time quality estimation segments are selected from the full real-time quality estimation result; when the road surface of this operation is classified as a dry paved road surface, 3 real-time quality estimation segments are selected from the full real-time quality estimation result. The data in this example is given based on experience. In actual applications, the number of real-time quality estimation segments to be selected corresponding to the road surface type is not limited by this solution.

[0150] In a specific implementation, selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result according to the road surface type during a single operation of the vehicle may also include:

[0151] According to the road surface type during a single operation of the vehicle and a preset real-time quality estimation segment selection rule, multiple real-time quality estimation segments are selected from the full real-time quality estimation result; wherein the real-time quality estimation segment selection rule includes at least one restriction condition on the vehicle driving data.

[0152] In a specific implementation, the selection rules include but are not limited to limiting the selected fragments in the following aspects:

[0153] The vehicle's speed, acceleration and driving torque, whether the traction control system TC, the anti-lock braking system ABS and the yaw stability control system YSC are activated,

[0154] In practical applications, this solution does not limit how to set the selection rules.

[0155] Specifically, the real-time quality estimation segment selection rule includes at least one of the following conditions:

[0156] The vehicle speed is greater than the preset speed;

[0157] The vehicle's acceleration is greater than the preset acceleration;

[0158] The driving torque of the vehicle is greater than the preset torque;

[0159] The vehicle's traction control system (TC), anti-lock braking system (ABS) and yaw stability control system (YSC) functions are not activated.

[0160] For example, the real-time quality estimation segment selection rule is: vehicle speed is greater than 15km / h; vehicle acceleration is greater than 1m / s 2 ; Driving torque greater than 1000Nm; No TC, ABS, YSC activation, etc.

[0161] In this method, in the process of selecting multiple real-time quality estimation fragments from the full real-time quality estimation results, the selected real-time quality estimation fragments can be further screened according to preset real-time quality estimation fragment selection rules, which can effectively reduce the impact of uncertain factors on the quality estimation results and further improve the accuracy and reliability of the obtained quality estimation results.

[0162] The method for determining vehicle mass provided in this embodiment, based on the above-mentioned embodiment, refines how to select multiple real-time mass estimation segments from the full real-time mass estimation result. First, determine the road type during a single operation of the vehicle, then determine the number of real-time mass estimation segments to be selected based on the determined road type, and then select the corresponding number of real-time mass estimation segments from the full real-time mass estimation result. This embodiment fully considers the impact of the road type on the quality estimation result. For poor road types, by selecting a larger number of real-time mass estimation segments, more data references are obtained, thereby improving the accuracy and reliability of the quality estimation result of the single operation process finally obtained; for better road types, by selecting a smaller number of real-time mass estimation segments, the calculation efficiency can be significantly improved, and more efficient acquisition of the quality estimation result of a single operation process can be achieved. Therefore, this solution can efficiently obtain the vehicle mass estimation result while ensuring the accuracy, reliability, and environmental adaptability of the obtained estimation result.

[0163] Figure 2 The flowchart of the third embodiment of the method for determining the vehicle mass provided in this application is as follows: Figure 2 As shown, the method includes:

[0164] S201. Give an initial value of vehicle mass.

[0165] After the vehicle is powered on, the ECU used for vehicle mass estimation is activated, and the vehicle's unloaded mass is used as the initial value of the mass estimation result.

[0166] S202: Determine the type of road surface on which the vehicle is running.

[0167] After the vehicle is started, the ADAS or advanced driving controller collects vehicle operation image information through the vehicle camera, and uses the pre-trained road type classification function module to classify the road image;

[0168] The training of the road type classification function module is carried out during the quality estimation function development stage, by collecting a large number of road signals to classify a relatively standard classification basis;

[0169] Among them, this function module will classify the road surface information into three road surface types. The specific road surface types are as follows: road surface 1 is a snowy road surface or an unpaved road surface, road surface 2 is a large-scale flooded road surface caused by rain, etc., and road surface 3 is a dry paved road surface;

[0170] After the road type classification function module determines the road type of this operation process, the road type is sent to the ECU for quality estimation via the vehicle network in the form of sending digital signals 1, 2, 3;

[0171] Among them, digital signals 1, 2, and 3 correspond to road surface 1, road surface 2, and road surface 3 respectively; the vehicle network can be Flexray communication protocol, CAN, CANFD, etc.;

[0172] In addition, the road surface type is updated every 5 minutes, that is, every 5 minutes, the ADAS or advanced driving controller will send an updated road surface type to the ECU used for quality estimation via the vehicle network.

[0173] S203: Obtain the road surface adhesion level in real time.

[0174] Based on the signals collected by vehicle sensors such as IMU and wheel speed sensors, the road adhesion coefficient can be acquired in real time;

[0175] The road adhesion coefficient obtained in real time is divided into three levels; specifically, the adhesion coefficient with a value of 0 to 0.3 is determined as level 1, corresponding to a low-adhesion road surface; the adhesion coefficient with a value of 0.3 to 0.6 is determined as level 2, corresponding to a medium-adhesion road surface; the adhesion coefficient with a value of 0.6 to 1 is determined as level 3, corresponding to a high-adhesion road surface.

[0176] S204: Estimate the vehicle mass in real time.

[0177] Based on the longitudinal dynamics equation after optimizing the front wheel turning angle, a four-dimensional state space equation is established, and a Kalman filter state estimation model is established according to the state equation and the corresponding output equation;

[0178] By inputting the basic information of the vehicle, driving data and environmental data acquired in real time into the Kalman filter state estimation model, a full real-time quality estimation result can be obtained.

[0179] S205: Extract real-time quality estimation segments.

[0180] Extracting real-time quality estimation segments that meet the segment selection rules, wherein each segment is set to 100 sampling points;

[0181] Determine the number of segments to be extracted according to the road surface type during the current operation determined in S202; where road surface 1 corresponds to extracting 7 segments, road surface 2 corresponds to extracting 5 segments, and road surface 3 corresponds to extracting 3 segments;

[0182] Eliminate abnormal data in the mass estimation results of multiple sampling points in each real-time mass estimation segment; wherein the abnormal data is defined as a mass estimation result that is not within a preset range, and the preset range is: [vehicle unloaded mass - preset threshold, vehicle fully loaded mass + preset threshold];

[0183] The mean of the residual mass estimation results within the segment is taken as the vehicle mass estimation result of the segment.

[0184] S206: Obtain a vehicle mass estimation result during a single operation of the vehicle.

[0185] For the quality estimation results of the multiple real-time quality estimation segments, based on the road adhesion level results obtained in S203, weighting factors corresponding to the real-time quality estimation segments are given; wherein level 1 corresponds to 0.3, level 2 corresponds to a weighting factor of 0.5, and level 3 corresponds to a weighting factor of 1;

[0186] Correcting a weighting factor corresponding to the real-time mass estimation segment according to the acceleration of the vehicle in a preset time period before the real-time mass estimation segment;

[0187] Based on the corrected weighting factor, the vehicle mass estimation results corresponding to each real-time mass estimation segment are weighted averaged to obtain the mass estimation result of the vehicle during this operation.

[0188] S207: Determine whether the quality estimation result is reset.

[0189] For passenger cars, the vehicle parking signal and the door switch signal are used as the basis for determining the quality estimation reset. The above two signals are set to 1, and the above quality estimation cycle is reset, jumping to step S201 to start the quality estimation of the next running process;

[0190] For commercial vehicles, the vehicle parking signal and the parking time>5min signal are used as the basis for determining the quality estimation reset. The above two signals are set to 1, the above quality estimation cycle is reset, and the process jumps to step S201 to start the quality estimation for the next operation process.

[0191] The vehicle mass estimation method provided in this embodiment takes into account the influence of the road adhesion coefficient and the road type on the mass estimation result. The number of selected segments is first determined according to the road type, and then the weighting factors corresponding to the segments are determined according to the road adhesion coefficient. Finally, the mass estimation results of multiple segments are weighted averaged according to the weighting factors. While ensuring timely estimation, the accuracy of vehicle mass estimation in different environments is improved.

[0192] Figure 3 This is a schematic diagram of the structure of the first embodiment of the vehicle mass determination device provided in this application, as shown in FIG. Figure 3 As shown, the vehicle mass determination device 30 provided in this embodiment includes:

[0193] A selection module 301 is used to select a plurality of real-time quality estimation segments from the full real-time quality estimation result;

[0194] An acquisition module 302 is used to acquire a vehicle mass estimation result corresponding to each real-time mass estimation segment;

[0195] The determination module 303 is used to determine the mass estimation result of a single operation process based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment.

[0196] In a possible implementation, the selection module 301 is specifically used for:

[0197] According to the road type during a single operation of the vehicle, multiple real-time quality estimation segments are selected from the full real-time quality estimation result; wherein the number of real-time quality estimation segments selected for different road types is different.

[0198] In a possible implementation, the selection module 301 can also be used to select multiple real-time quality estimation segments from the full real-time quality estimation results based on the road surface type during a single operation of the vehicle and a preset real-time quality estimation segment selection rule; wherein the real-time quality estimation segment selection rule includes at least one restriction condition on the vehicle driving data.

[0199] In one possible implementation, the real-time mass estimation segment selection rule includes at least one of the following conditions: the vehicle speed is greater than a preset speed; the vehicle acceleration is greater than a preset acceleration; the vehicle driving torque is greater than a preset torque; the vehicle's traction control system TC, anti-lock braking system ABS and yaw stability control system YSC functions are not activated.

[0200] In a possible implementation, the acquisition module 302 is specifically configured to:

[0201] For each real-time mass estimation segment, a mean value of mass estimation results of a plurality of sampling points in the real-time mass estimation segment is calculated to obtain a vehicle mass estimation result corresponding to the real-time mass estimation segment.

[0202] In a possible implementation, the acquisition module 302 may also be used to:

[0203] Eliminating abnormal data in the quality estimation results of the multiple sampling points in the real-time quality estimation segment to obtain processed quality estimation results of the multiple sampling points;

[0204] Accordingly, the calculating the mean value of the quality estimation results of the multiple sampling points in the real-time quality estimation segment includes:

[0205] The average of the quality estimation results of the plurality of sampling points after the processing is calculated.

[0206] In a possible implementation, the determination module 303 is specifically configured to:

[0207] For each real-time quality estimation segment, determining a weighting factor corresponding to the real-time quality estimation segment according to a road adhesion coefficient corresponding to the real-time quality estimation segment when the vehicle is traveling;

[0208] The single operation process mass estimation result is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor.

[0209] In a possible implementation, the determination module 303 may also be used to:

[0210] According to the weighting factor corresponding to each real-time mass estimation segment, the vehicle mass estimation results corresponding to multiple real-time mass estimation segments are weighted averaged to obtain the mass estimation result of the single operation process.

[0211] In a possible implementation, the determination module 303 may also be used to:

[0212] Based on the mapping relationship between the preset adhesion coefficient range and the weighting factor, and the road adhesion coefficient of the vehicle corresponding to the real-time quality estimation segment, the weighting factor corresponding to the range of the road adhesion coefficient is determined as the weighting factor corresponding to the real-time quality estimation segment.

[0213] In a possible implementation, the determination module 303 may also be used to:

[0214] For each real-time mass estimation segment, obtaining the acceleration of the vehicle within a preset time period before the real-time mass estimation segment;

[0215] Correcting the weighting factor corresponding to the real-time quality estimation segment according to the acceleration to obtain a corrected weighting factor;

[0216] Accordingly, determining the single operation process mass estimation result according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor includes:

[0217] The mass estimation result of the single operation process is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the corrected weighting factor.

[0218] The vehicle mass determination device provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0219] Figure 4 This is a schematic diagram of the structure of the second embodiment of the vehicle mass determination device provided in the present application. Based on the above-mentioned vehicle mass determination device 30, the vehicle mass determination device 30 further includes:

[0220] Processing module 304 is used to classify the collected road surface images using a pre-trained road surface classification algorithm during vehicle operation to obtain the road surface type.

[0221] In a possible implementation, the road surface type includes any one of the following: snow-covered road surface; unpaved road surface; flooded road surface; dry paved road surface.

[0222] Estimation module 305: used for performing real-time estimation of mass using a Kalman filter state estimation model according to basic information, driving data and environmental data of the vehicle during the operation of the vehicle, so as to obtain the full real-time mass estimation result;

[0223] The Kalman filter state estimation model is obtained based on a four-dimensional state space equation established based on the vehicle longitudinal dynamics equation after optimizing the front wheel steering angle parameters.

[0224] The reset module 306 is used to determine whether the quality estimation result is reset:

[0225] If it is detected that the vehicle is parked and the door is open, re-collecting the full real-time quality estimation result, and determining the quality estimation result of a single operation process of the vehicle according to the newly collected full real-time quality estimation result;

[0226] Alternatively, if it is detected that the vehicle is parked and the parking time is greater than a preset time, the full real-time quality estimation result is re-collected, and the quality estimation result of a single operation process of the vehicle is determined based on the newly collected full real-time quality estimation result.

[0227] The detection device 307 is used to determine the road adhesion coefficient in real time based on the data detected by the sensor of the vehicle during the operation of the vehicle.

[0228] The vehicle quality determination device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0229] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 40 provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the device 40 also includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected via a bus 404.

[0230] In a specific implementation process, at least one processor 401 executes the computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0231] The specific implementation process of the processor 401 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0232] The present application also provides a vehicle, which includes an electronic device 40, and the electronic device 40 may be an electronic control unit of the vehicle. In a specific implementation process, the electronic device 40 in the vehicle is used to implement the method for determining the vehicle mass described in the above method embodiment.

[0233] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method for determining the vehicle mass described in the above method embodiment can be implemented.

[0234] The present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for determining the vehicle mass described in the above method embodiment can be implemented.

[0235] Finally, it should be noted that those skilled in the art will easily think of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the technical field that are not disclosed in the present application. The description and examples are considered to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims. The present application is not limited to the precise structure described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is limited only by the attached claims.

Claims

1. A method for determining vehicle mass, characterized in that: include: Selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result; Obtaining a vehicle mass estimation result corresponding to each real-time mass estimation segment; The mass estimation result of a single running process is determined based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment.

2. The method according to claim 1, characterized in that The determining of the mass estimation result of a single operation process based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment includes: For each real-time quality estimation segment, determining a weighting factor corresponding to the real-time quality estimation segment according to a road adhesion coefficient corresponding to the real-time quality estimation segment when the vehicle is traveling; The single operation process mass estimation result is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor.

3. The method according to claim 2, characterized in that The determining of the single operation process mass estimation result according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor includes: According to the weighting factor corresponding to each real-time mass estimation segment, the vehicle mass estimation results corresponding to multiple real-time mass estimation segments are weighted averaged to obtain the mass estimation result of the single operation process.

4. The method according to claim 2, characterized in that: The step of determining a weighting factor corresponding to the real-time quality estimation segment according to a road adhesion coefficient corresponding to the real-time quality estimation segment when the vehicle is traveling comprises: Based on the mapping relationship between the preset adhesion coefficient range and the weighting factor, and the road adhesion coefficient of the vehicle corresponding to the real-time quality estimation segment, the weighting factor corresponding to the range of the road adhesion coefficient is determined as the weighting factor corresponding to the real-time quality estimation segment.

5. The method according to any one of claims 1 to 4, characterized in that: The selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result comprises: According to the road type during a single operation of the vehicle, multiple real-time quality estimation segments are selected from the full real-time quality estimation result; wherein the number of real-time quality estimation segments selected for different road types is different.

6. The method according to claim 5, characterized in that The method of selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result according to the road surface type during a single operation of the vehicle includes: Selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result according to the road surface type during a single operation of the vehicle and a preset real-time quality estimation segment selection rule; The real-time quality estimation segment selection rule includes at least one restriction condition on vehicle driving data.

7. The method according to claim 6, characterized in that The real-time quality estimation segment selection rule includes at least one of the following conditions: The vehicle speed is greater than the preset speed; The vehicle's acceleration is greater than the preset acceleration; The driving torque of the vehicle is greater than the preset torque; The vehicle's traction control system TC, anti-lock braking system ABS and yaw stability control system YSC functions are not activated.

8. The method according to claim 5, characterized in that The method further comprises: During the operation of the vehicle, the collected road surface images are classified using a pre-trained road surface classification algorithm to obtain the road surface type.

9. The method according to claim 5, characterized in that The road surface type includes any of the following: Snowy roads; Unpaved roads; flooded roads; Dry paved road surface.

10. The method according to any one of claims 1 to 4, characterized in that: The obtaining of the vehicle mass estimation result corresponding to each real-time mass estimation segment includes: For each real-time mass estimation segment, a mean value of mass estimation results of a plurality of sampling points in the real-time mass estimation segment is calculated to obtain a vehicle mass estimation result corresponding to the real-time mass estimation segment.

11. The method according to claim 10, characterized in that Before calculating the mean value of the quality estimation results of the plurality of sampling points in the real-time quality estimation segment, the method further comprises: Eliminating abnormal data in the quality estimation results of the multiple sampling points in the real-time quality estimation segment to obtain processed quality estimation results of the multiple sampling points; Accordingly, the calculating the mean value of the quality estimation results of the multiple sampling points in the real-time quality estimation segment includes: The average of the quality estimation results of the plurality of sampling points after the processing is calculated.

12. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: During the operation of the vehicle, a Kalman filter state estimation model is used to perform real-time estimation of mass according to basic information, driving data and environmental data of the vehicle to obtain the full real-time mass estimation result; The Kalman filter state estimation model is obtained based on a four-dimensional state space equation established based on the vehicle longitudinal dynamics equation after optimizing the front wheel steering angle parameters.

13. The method according to any one of claims 2 to 4, characterized in that: Before determining the mass estimation result of the single operation process according to the vehicle mass estimation result and the weighting factor corresponding to each real-time mass estimation segment, the method includes: For each real-time mass estimation segment, obtaining the acceleration of the vehicle within a preset time period before the real-time mass estimation segment; Correcting the weighting factor corresponding to the real-time quality estimation segment according to the acceleration to obtain a corrected weighting factor; Accordingly, determining the single operation process mass estimation result according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the weighting factor includes: The mass estimation result of the single operation process is determined according to the vehicle mass estimation result corresponding to each real-time mass estimation segment and the corrected weighting factor.

14. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: If it is detected that the vehicle is parked and the door is open, re-collecting the full real-time quality estimation result, and determining the quality estimation result of a single operation process of the vehicle according to the newly collected full real-time quality estimation result; or, If it is detected that the vehicle is parked and the parking time is greater than the preset time, the full real-time quality estimation result is re-collected, and the quality estimation result of a single operation process of the vehicle is determined based on the newly collected full real-time quality estimation result.

15. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: During the operation of the vehicle, the road adhesion coefficient is determined in real time based on data detected by sensors of the vehicle.

16. A vehicle mass determination device, characterized in that: include: A selection module, used for selecting a plurality of real-time quality estimation segments from the full real-time quality estimation result; An acquisition module, used to acquire a vehicle mass estimation result corresponding to each real-time mass estimation segment; The determination module is used to determine the mass estimation result of a single running process based on the road adhesion coefficient and the vehicle mass estimation result when the vehicle is traveling corresponding to each real-time mass estimation segment.

17. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 14.

18. A vehicle, characterized in that: include: The electronic device of claim 17.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 14 when executed by a processor.

Images