A method, apparatus, vehicle, and storage medium for determining vehicle mass.

Abstract

This application relates to the field of artificial intelligence technology and provides a method, apparatus, vehicle, and storage medium for determining vehicle mass. The method includes: initiating a vehicle mass identification operation when a preset trigger condition is met. The vehicle mass identification operation includes: acquiring vehicle operation data of the target vehicle during its operation; generating mass identification data based on the vehicle operation data and a pre-built mass identification model; stopping the vehicle mass identification operation when the obtained mass identification data sequence meets a preset cutoff condition; and determining the mass identification data sequence meeting the preset cutoff condition as the target data sequence; and generating the vehicle mass of the target vehicle based on the target data sequence. This application can achieve timely and accurate determination of vehicle mass, which helps to enable precise vehicle control based on the obtained accurate vehicle mass, thereby improving vehicle driving safety.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, vehicle, and storage medium for determining vehicle quality. Background Technology

[0002] During the use of a vehicle, the overall weight of the vehicle often changes. Taking a park logistics vehicle equipped with an unmanned driving system as an example, the vehicle often needs to load and unload goods, resulting in a large range of changes in the overall weight of the vehicle.

[0003] In related technologies, vehicle mass plays a crucial role in intelligent vehicle control. The accuracy of vehicle mass identification directly affects the control precision of the vehicle's control system, thus impacting driving safety. Taking autonomous vehicles as an example, the accuracy of vehicle mass determination significantly affects the vehicle's lateral and longitudinal control precision, thereby influencing the vehicle's control performance. In other words, inaccurate vehicle mass determination can easily lead to reduced vehicle control precision and driving safety. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, vehicle, and storage medium for determining vehicle mass, in order to solve the problem in the related art that inaccurate determination of vehicle mass can easily lead to reduced vehicle control accuracy and vehicle driving safety.

[0005] In a first aspect, embodiments of this application provide a method for determining vehicle mass, including:

[0006] When the preset triggering conditions are triggered, the vehicle quality identification operation is started. The vehicle quality identification operation includes: acquiring the vehicle operation data of the target vehicle during the driving process, and generating quality identification data based on the vehicle operation data and the pre-built quality identification model.

[0007] When the obtained quality identification data sequence meets the preset cutoff condition, the vehicle quality identification operation is stopped, and the quality identification data sequence that meets the preset cutoff condition is determined as the target data sequence. The quality identification data sequence includes quality identification data from multiple consecutive time points.

[0008] The vehicle mass of the target vehicle is generated based on the target data sequence.

[0009] In some embodiments, the preset triggering conditions include:

[0010] The system detected that the target vehicle was in the starting phase and that a change in the target vehicle's quality had occurred.

[0011] In some embodiments, after generating quality identification data, the method further includes:

[0012] If the quality identification data is greater than the preset quality threshold, the quality identification data will be stored in the quality identification data sequence.

[0013] In some embodiments, the preset cutoff condition includes any one of the following:

[0014] The target quality identification curve corresponding to the quality identification data sequence has a maximum value. The target quality identification curve is the curve obtained by smoothing and filtering the quality identification data sequence.

[0015] The quality identification data sequence contains target quality identification data, and the quality identification data corresponding to a preset number of consecutive time points after the time corresponding to the target quality identification data are smaller than the target quality identification data.

[0016] In some embodiments, generating the vehicle mass of a target vehicle based on a target data sequence includes:

[0017] The vehicle mass is generated based on the maximum value of the target mass identification curve corresponding to the target data sequence and the pre-determined target correction data.

[0018] In some embodiments, the target correction data is determined as follows:

[0019] Obtain the test quality identification curve corresponding to the driving process of the target vehicle during the test phase. The test quality identification curve includes the maximum value and the stationary value.

[0020] The target correction data are determined based on the maximum and stationary values ​​of the test quality identification curve.

[0021] In some embodiments, the vehicle mass is generated based on the maximum value of the target mass identification curve corresponding to the target data sequence and predetermined target correction data, including:

[0022] Based on the pre-stored mapping relationship between correction-related data and correction data, determine the reference correction data corresponding to the current correction-related data, wherein the current correction-related data includes at least one of the following: the maximum value of the target quality identification curve and the current throttle depth;

[0023] The target correction data is adjusted based on the reference correction data, and the vehicle mass is generated based on the adjusted target correction data and the maximum value of the target mass identification curve.

[0024] Secondly, embodiments of this application provide a vehicle mass determination device, comprising:

[0025] The data generation unit is used to initiate and execute vehicle quality identification operations when a preset trigger condition is triggered. The vehicle quality identification operations include: acquiring vehicle operation data of the target vehicle during driving, and generating quality identification data based on the vehicle operation data and a pre-built quality identification model.

[0026] The sequence determination unit is used to stop executing the vehicle quality identification operation when the obtained quality identification data sequence meets the preset cutoff condition, and to determine the quality identification data sequence that meets the preset cutoff condition as the target data sequence, wherein the quality identification data sequence includes quality identification data at multiple consecutive times.

[0027] The quality generation unit is used to generate the vehicle quality of the target vehicle based on the target data sequence.

[0028] In some embodiments, the preset triggering conditions include: detecting that the target vehicle is in the vehicle start-up phase, and detecting that the target vehicle has undergone a quality change.

[0029] In some embodiments, after generating quality identification data, the data generation unit further includes: storing the quality identification data into a quality identification data sequence if the quality identification data is greater than a preset quality threshold.

[0030] In some embodiments, the preset cutoff condition includes any one of the following:

[0031] The target quality identification curve corresponding to the quality identification data sequence has a maximum value. The target quality identification curve is the curve obtained by smoothing and filtering the quality identification data sequence.

[0032] The quality identification data sequence contains target quality identification data, and the quality identification data corresponding to a preset number of consecutive time points after the time corresponding to the target quality identification data are smaller than the target quality identification data.

[0033] In some embodiments, the quality generation unit is specifically used to generate vehicle quality based on the maximum value of the target quality identification curve corresponding to the target data sequence and predetermined target correction data.

[0034] In some embodiments, in the quality generation unit, the target correction data is determined in the following manner:

[0035] Obtain the test quality identification curve corresponding to the driving process of the target vehicle during the test phase. The test quality identification curve includes the maximum value and the stationary value.

[0036] The target correction data are determined based on the maximum and stationary values ​​of the test quality identification curve.

[0037] In some embodiments, the quality generation unit generates vehicle quality based on the maximum value of the target quality identification curve corresponding to the target data sequence and predetermined target correction data, including:

[0038] Based on the pre-stored mapping relationship between correction-related data and correction data, determine the reference correction data corresponding to the current correction-related data, wherein the current correction-related data includes at least one of the following: the maximum value of the target quality identification curve and the current throttle depth;

[0039] The target correction data is adjusted based on the reference correction data, and the vehicle mass is generated based on the adjusted target correction data and the maximum value of the target mass identification curve.

[0040] Thirdly, embodiments of this application provide a vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the vehicle. When the processor executes the computer program, it implements the steps of the vehicle quality determination method provided in the first aspect.

[0041] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the vehicle mass determination method provided in the first aspect.

[0042] Fifthly, embodiments of this application provide a computer program product that, when run on a vehicle, causes the vehicle to execute any of the aforementioned vehicle quality determination methods.

[0043] The beneficial effects of this application embodiment compared with related technologies are as follows: During the driving process of the target vehicle, multiple quality identification data are identified by acquiring real-time vehicle operation data and a pre-built quality identification model. When the quality identification data sequence composed of several quality identification data meets the preset cutoff condition, the vehicle quality is automatically generated based on the quality identification data sequence. This can realize timely and accurate determination of vehicle quality, which helps to realize precise control of the vehicle based on the obtained accurate vehicle quality, thereby improving vehicle driving safety.

[0044] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the implementation of a vehicle weight determination method according to an embodiment of this application;

[0047] Figure 2 This is a schematic diagram illustrating the effect of a target quality identification curve provided in an embodiment of this application;

[0048] Figure 3 This is a schematic diagram illustrating the effect of a test quality identification curve provided in one embodiment of this application;

[0049] Figure 4 This is a flowchart illustrating the implementation of a vehicle mass determination method according to another embodiment of this application;

[0050] Figure 5 This is a structural block diagram of a vehicle weight determination device provided in an embodiment of this application;

[0051] Figure 6 This is a structural block diagram of a vehicle provided in one embodiment of this application. Detailed Implementation

[0052] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0053] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0054] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0055] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0056] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0057] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0058] To illustrate the technical solution of this application, the following embodiments will be used for explanation.

[0059] Please see Figure 1 This application provides a method for determining vehicle mass, including:

[0060] Step 101: When the preset triggering condition is triggered, start the vehicle quality identification operation.

[0061] The vehicle quality identification operation includes: acquiring vehicle operation data of the target vehicle during driving, and generating quality identification data based on the vehicle operation data and a pre-built quality identification model.

[0062] The aforementioned preset trigger conditions are typically pre-defined conditions used to initiate the vehicle quality identification operation. For example, the preset trigger condition could be receiving a user-input start command. This start command is used to initiate the vehicle quality identification operation.

[0063] The target vehicles mentioned above are usually pre-defined vehicles, such as driverless logistics vehicles.

[0064] The vehicle operation data mentioned above is typically real-time data during vehicle operation. In practice, this data may include vehicle longitudinal speed, vehicle longitudinal acceleration, road longitudinal slope angle, and the output torque of the vehicle's powertrain. "Longitudinal" usually refers to the vehicle's direction of travel; for example, vehicle longitudinal speed refers to the vehicle's speed in that direction.

[0065] The aforementioned quality identification model is typically a model that identifies vehicle quality based on recursive least squares with a forgetting factor.

[0066] In practice, the process of determining the aforementioned quality identification model may include: deriving the vehicle mass equation based on the longitudinal driving mechanics model of the target vehicle; then discretizing the vehicle mass equation to obtain a discrete vehicle mass equation; finally, using a recursive least squares method with a forgetting factor, identifying the vehicle mass in the discrete vehicle mass equation, thereby constructing the aforementioned quality identification model. The process of determining the aforementioned quality identification model is as follows.

[0067] The longitudinal driving mechanics model of the target vehicle can be:

[0068] F t =F j +F i +F f +F w (1)

[0069] Among them, F t For the driving force of the whole vehicle, F j To increase resistance, F i For slope resistance, F f For rolling resistance, F w For air resistance. The specific calculation formulas for each element in the longitudinal driving mechanics model can be:

[0070]

[0071] F j =ma (3)

[0072] F i =mgsinα (4)

[0073] F f =mgfcosα (5)

[0074]

[0075]

[0076] Among them, T m For the output torque of the power system, i gFor the transmission ratio, i0 is the gear ratio of the main reducer, and η is the gear ratio of the gearbox. t Let r be the overall vehicle power transmission efficiency, m be the effective wheel radius, g be the overall vehicle mass, f be the rolling resistance coefficient, and C be the total vehicle mass. d denoted as the air resistance coefficient, A as the frontal area, v as the longitudinal vehicle speed, a as the longitudinal acceleration of the vehicle, and α as the longitudinal slope angle of the road surface.

[0077] Combining equations (1) to (7) above, we can obtain the following vehicle mass equation:

[0078]

[0079]

[0080]

[0081] Discretizing the above vehicle mass equation yields the discrete vehicle mass equation:

[0082]

[0083] When identifying vehicle mass using the recursive least squares method with a forgetting factor, the resulting mass identification model is as follows:

[0084]

[0085]

[0086]

[0087]

[0088] Here, λ is the forgetting factor. The value of λ is usually greater than 0.9 and less than 1. It should be noted that the recursive least squares method based on the forgetting factor can usually accurately identify the object, that is, after a number of identification times, the identification result can approximate the true value of the object relatively accurately.

[0089] In this embodiment, the executing entity of the above-described vehicle mass determination method is typically a vehicle, and specifically, a vehicle controller within the vehicle. This executing entity can acquire vehicle operating data through sensors. For example, the longitudinal velocity of the vehicle can be collected using a speed sensor, and the longitudinal acceleration of the vehicle can be collected using an acceleration sensor.

[0090] In practice, for each moment, the aforementioned executing entity can use the vehicle's inherent design parameters, real-time sensor-collected parameters, and powertrain output torque as inputs to the aforementioned quality identification model, thereby identifying the quality identification data for that moment. The inherent vehicle design parameters include the transmission ratio i. g , Main reducer transmission ratio i0, Overall vehicle power transmission efficiency η t Effective wheel radius r, gravitational acceleration g, rolling resistance coefficient f, and air resistance coefficient C d The windward area A. The real-time parameters collected by the sensors involved include the vehicle's longitudinal speed v, longitudinal acceleration a, and the longitudinal slope angle α of the road surface.

[0091] It should be noted that for each moment, one quality identification data can be obtained, and after multiple consecutive moments, multiple corresponding quality identification data can be obtained.

[0092] Step 102: When the obtained quality identification data sequence meets the preset cutoff condition, stop executing the vehicle quality identification operation and determine the quality identification data sequence that meets the preset cutoff condition as the target data sequence.

[0093] The quality identification data sequence includes quality identification data from multiple consecutive time points. In this embodiment, for ease of description, the quality identification data sequence that meets the preset cutoff condition is typically referred to as the target data sequence.

[0094] Here, the aforementioned quality identification data sequence can be a sequence composed of all obtained quality identification data, or it can be a sequence composed of quality identification data that is greater than a preset quality threshold.

[0095] In practice, each quality identification data point in the quality identification data sequence is typically greater than a preset quality threshold. This preset quality threshold is usually a pre-defined value. In practice, this preset quality threshold is typically less than and close to the vehicle's unloaded weight. For example, if the vehicle's unloaded weight is X, then the preset quality threshold could be 0.8X.

[0096] It should be noted that, since the initial quality identification data obtained at the beginning of the quality identification process often fluctuates significantly, it is usually helpful to analyze the quality identification data that is higher than the preset quality threshold to improve the accuracy of vehicle quality analysis.

[0097] The aforementioned preset cutoff conditions are typically pre-set conditions used to trigger the cessation of vehicle quality identification operations.

[0098] In practice, the aforementioned pre-set cutoff conditions may include, but are not limited to, any one of the first and second items below.

[0099] The first condition is that the target quality identification curve corresponding to the quality identification data sequence has a maximum value. The target quality identification curve is the curve obtained by smoothing and filtering the quality identification data sequence.

[0100] Figure 2 This is a schematic diagram illustrating the effect of the target quality identification curve provided in the embodiments of this application. Figure 2 As shown, the curve ECD is the target quality identification curve corresponding to the quality identification data sequence, with the horizontal axis representing time and the vertical axis representing quality. The quality identification data corresponding to point E corresponds to the aforementioned preset quality threshold.

[0101] The second condition is that the quality identification data sequence contains target quality identification data, and the quality identification data corresponding to a predetermined number of consecutive time points after the time point corresponding to the target quality identification data are less than the target quality identification data. This predetermined number is usually a pre-set value. For example, if the predetermined number is 5, and the quality identification data corresponding to the 5 consecutive time points after time T10 are all less than the quality identification data corresponding to time T10, then it can be considered that the quality identification data sequence contains target quality data, and the target quality data is the quality identification data corresponding to time T10.

[0102] It should be noted that by setting a cutoff condition, it is possible to determine in a timely and accurate manner whether it is necessary to continue generating quality identification data for subsequent time moments, thereby stopping the generation of quality identification data in a timely manner without waiting for the entire curve to converge to a stable value before ending the generation of quality identification data. This can speed up the determination of vehicle quality and help improve data processing efficiency.

[0103] Step 103: Generate the vehicle mass of the target vehicle based on the target data sequence.

[0104] Here, the aforementioned executing entity can use the target data sequence to obtain the vehicle mass. For example, the mass identification data with the largest value in the target data sequence can be used as the vehicle mass. Alternatively, the product of the mass identification data with the largest value and a preset adjustment coefficient can be used as the vehicle mass. The preset adjustment coefficient is typically a pre-defined value, and its value is usually greater than 0 and less than 1. As an example, the preset adjustment coefficient could be 0.95.

[0105] The method provided in this embodiment identifies multiple quality identification data during the driving process of the target vehicle by acquiring real-time vehicle operation data and a pre-built quality identification model. When the quality identification data sequence composed of several quality identification data meets a preset cutoff condition, the vehicle quality is automatically generated based on the quality identification data sequence. This can realize timely and accurate determination of vehicle quality, which helps to achieve precise control of the vehicle based on the obtained accurate vehicle quality, thereby improving vehicle driving safety.

[0106] In some optional implementations of this embodiment, the preset triggering conditions may include: detecting that the target vehicle is in the vehicle start-up phase, or detecting that the target vehicle has undergone a change in mass.

[0107] Here, the aforementioned executing entity can determine whether the target vehicle is in the vehicle starting phase in multiple ways. As an example, when vehicle starting is detected and the time difference between the current moment and the vehicle starting moment is less than a preset duration threshold, the executing entity can consider the target vehicle to be in the vehicle starting phase. As another example, when vehicle starting is detected and the current vehicle speed is less than a preset speed threshold, and the current vehicle acceleration is greater than a preset acceleration threshold, the executing entity can consider the target vehicle to be in the vehicle starting phase.

[0108] The aforementioned executing entity can determine whether a change in the target vehicle's mass has occurred in several ways. As an example, a change in the target vehicle's mass can be determined when a pressure sensor on the target vehicle detects a change in the load on the vehicle. As another example, a change in the target vehicle's mass can be determined when a loading or unloading command is received during the target vehicle's previous journey. The loading command is typically used to control the loading of cargo onto the target vehicle. The unloading command is typically used to control the unloading of cargo from the target vehicle.

[0109] Furthermore, a single driving cycle typically refers to the period from when the vehicle starts to when it stops. During a single driving cycle, if the vehicle receives a loading or unloading instruction, it usually needs to stop to load or unload the cargo. Thus, during the starting phase of the next driving cycle, the vehicle can trigger a vehicle mass determination operation.

[0110] This embodiment can redetermine vehicle mass only when there is a change in vehicle mass, which helps to improve data processing efficiency.

[0111] In some optional implementations of this embodiment, after generating quality identification data, step 101 may further include: if the quality identification data is greater than a preset quality threshold, storing the quality identification data into a quality identification data sequence.

[0112] The aforementioned preset mass threshold is typically a pre-set value. In practice, this preset mass threshold is usually less than and close to the vehicle's unloaded mass. For example, if the vehicle's unloaded mass is X, then the preset mass threshold could be 0.8X.

[0113] Here, when quality identification is first performed, the initial quality identification data values ​​are not very large and usually fluctuate significantly. Only quality identification data values ​​greater than a preset quality threshold are stored in the quality identification data sequence. This yields multiple consecutive quality identification data sets with relatively stable values. Analyzing these stable sets of data allows for a more accurate determination of vehicle quality, thus improving the overall accuracy of vehicle quality analysis.

[0114] In some optional implementations of this embodiment, generating the vehicle mass of the target vehicle based on the target data sequence may include: generating the vehicle mass based on the maximum value of the target mass identification curve corresponding to the target data sequence and predetermined target correction data.

[0115] The aforementioned target correction data is typically used to correct the maximum value of the target quality identification curve to obtain the vehicle quality. In practice, the value of the target correction data is usually greater than 0 and less than 1. As an example, the target correction data could be 0.9. Since the difference between the maximum value and the stationary value of the target quality identification curve is usually not too large, the value of the target correction data is usually close to 1.

[0116] Here, the aforementioned implementing entity typically uses the product of the maximum value of the target quality identification curve and the target correction data as the vehicle quality. Since there is usually a gap between the maximum value of the target quality identification curve and the stationary value of the entire curve, using the target correction data to correct the maximum value of the target quality identification curve can achieve a fast and accurate determination of the vehicle quality.

[0117] It should be noted that, due to the fluctuations that usually exist between the various quality identification data obtained during the process of identifying vehicle quality, generating vehicle quality based on the target quality identification curve corresponding to the quality identification data sequence is generally more accurate than generating vehicle quality based on the largest value in the quality identification data sequence.

[0118] In some alternative implementations, the aforementioned target correction data can be determined in the following ways:

[0119] First, obtain the test quality identification curve corresponding to the driving process of the target vehicle during the testing phase.

[0120] The test quality identification curve includes a maximum value and a stationary value. The stationary value is usually a value that approximates the actual vehicle quality when the quality identification model converges.

[0121] The aforementioned testing phase typically occurs within a short period after the target vehicle is put into use. For example, it could be the first day the target vehicle is put into use.

[0122] The aforementioned test quality identification curve is typically a smooth curve formed by all the quality identification data obtained from the start of identification to convergence of the quality identification model. Figure 3 This is a schematic diagram illustrating the effect of the test quality identification curve provided in the embodiments of this application. Figure 3 As shown, the curve OCF is the test quality identification curve, with the horizontal axis representing time and the vertical axis representing quality. Point O is the identification starting point. Point C is the extreme point, and point F is the stationary point.

[0123] Here, during the testing phase, while the target vehicle is in motion, the aforementioned execution entity can acquire the vehicle's operating data and generate quality identification data based on the vehicle operating data and a pre-built quality identification model. When the quality identification data sequence, composed of all generated quality identification data, converges, the aforementioned execution entity can perform smoothing filtering on the quality identification data sequence to obtain the aforementioned test quality identification curve, as well as the extreme points and stationary points of the test quality identification curve. It should be noted that the convergence of the quality identification data sequence can be defined as the deviation between several newly added quality identification data points and the quality identification data at adjacent time points being less than a pre-set deviation value.

[0124] Then, based on the maximum and stationary values ​​of the test quality identification curve, the target correction data is determined.

[0125] Here, the aforementioned implementing entity can use the obtained maximum and stationary values ​​to calculate the target correction data.

[0126] For example, the aforementioned executing entity can input the maximum value and the stationary value into a preset calculation formula to calculate the aforementioned target correction data.

[0127] The aforementioned preset calculation formula can be: factor = 1 - (max - stable) ÷ stable. Here, factor is the target correction data, max is the maximum value, and stable is the stationary value.

[0128] In this embodiment, target correction data is obtained by analyzing the test quality identification curves corresponding to the testing phase, resulting in relatively accurate target correction data. Since only the full convergence process analysis of the testing phase is required, the computational load is extremely limited. Because the convergence time required for the identification results of the quality identification model is typically long, this embodiment, compared to related technologies that require full convergence process analysis of the target vehicle for each driving process, can significantly improve the efficiency of vehicle quality determination while ensuring accuracy.

[0129] In some optional implementations, the process of generating vehicle mass based on the maximum value of the target mass identification curve corresponding to the target data sequence and the predetermined target correction data may include the following steps one and two.

[0130] Step 1: Based on the pre-stored mapping relationship between correction-related data and correction data, determine the reference correction data corresponding to the current correction-related data.

[0131] The current correction-related data includes at least one of the following: the maximum value of the target quality identification curve and the current throttle depth. In practice, the aforementioned current throttle depth is usually the throttle depth at the current moment. This current throttle depth can be acquired in real time by a throttle depth sensor.

[0132] The aforementioned reference correction data usually refers to the correction data corresponding to the current correction-related data.

[0133] Here, the aforementioned implementing entity can use the current correction-related data to find the aforementioned reference correction data corresponding to the current correction-related data from the mapping relationship between correction-related data and correction data.

[0134] Step two: Adjust the target correction data based on the reference correction data, and generate the vehicle mass based on the adjusted target correction data and the maximum value of the target mass identification curve.

[0135] Here, the aforementioned implementing entity can adjust the target correction data using reference correction data to obtain the adjusted target correction data. For example, the average of the reference correction data and the target correction data can be used as the adjusted target correction data.

[0136] Subsequently, the aforementioned implementing entity can use the adjusted target correction data and the maximum value of the target quality identification curve to generate the vehicle quality.

[0137] It should be noted that adjusting the target correction data using correction data corresponding to the current correction data can make the adjusted target correction data more compatible with the current real driving conditions, which helps to obtain more accurate vehicle quality.

[0138] In some optional implementations of the various embodiments of this application, the above-described vehicle mass determination method may further include: generating vehicle control parameters of the target vehicle based on the vehicle mass, and controlling the target vehicle to drive based on the vehicle control parameters.

[0139] The vehicle control parameters mentioned above are typically used to control the vehicle's movement. For example, these vehicle control parameters could be the driving force used to counteract resistance.

[0140] Here, after obtaining accurate vehicle information, the aforementioned executing entity generates vehicle control parameters based on the accurate vehicle quality, thereby controlling the vehicle with accurate vehicle control parameters, which can improve vehicle control accuracy and driving safety.

[0141] Figure 4 This is a flowchart illustrating the implementation of the vehicle weight determination method provided in an embodiment of this application. Figure 4 As shown, the vehicle quality determination method described above may include the following steps 401-407. The subject executing steps 401-407 is the target vehicle. The target vehicle can be various types of vehicles, such as an unmanned logistics vehicle.

[0142] Step 401: The quality identification model begins to work.

[0143] Here, when the preset triggering conditions are triggered, the vehicle quality identification operation can be started. At this time, the target vehicle can obtain vehicle operation data, and use the obtained vehicle operation data and quality identification model to generate quality identification data.

[0144] The preset trigger conditions may include: detecting that the target vehicle is in the vehicle start-up phase, or detecting that the target vehicle has undergone a change in quality.

[0145] Step 402: The quality identification model generates the quality identification data M for the current moment.

[0146] Here, the target vehicle can generate quality identification data for the current moment based on vehicle operation data and a pre-built quality identification model.

[0147] In practice, for each moment, the aforementioned executing entity can use the vehicle's inherent design parameters, real-time sensor-collected parameters, and powertrain output torque as inputs to the aforementioned quality identification model, thereby identifying the quality identification data for that moment. The inherent vehicle design parameters include the transmission ratio i. g , Main reducer transmission ratio i0, Overall vehicle power transmission efficiency η t Effective wheel radius r, gravitational acceleration g, rolling resistance coefficient f, and air resistance coefficient C dThe windward area A. The real-time parameters collected by the sensors involved include the vehicle's longitudinal speed v, longitudinal acceleration a, and the longitudinal slope angle α of the road surface.

[0148] Step 403: Determine whether M is greater than m0.

[0149] Wherein, m0 is the aforementioned preset quality threshold.

[0150] Here, if M is greater than m0, then proceed to step 405; otherwise, proceed to step 404.

[0151] Step 404: Output the vehicle mass as M_final = M_init.

[0152] Where M_final represents the output vehicle mass, and M_final = M_init represents the vehicle's unloaded mass. It should be noted that before determining the accurate vehicle mass, the target vehicle needs to be controlled based on its unloaded mass to ensure normal operation.

[0153] Step 405: Determine whether the slope at the current moment is less than 0 and whether the slope at the previous moment is greater than 0.

[0154] In practice, if the quality identification data at the current moment is M5, the quality identification data at the previous moment is M4, and the quality identification data at the moment before that is M3, then the slope at the current moment can be (M5-M4)÷ΔT, and the slope at the previous moment can be (M4-M3)÷ΔT, where ΔT is the time difference between two adjacent moments.

[0155] Here, if the slope at the current moment is less than 0 and the slope at the previous moment is greater than 0, the target vehicle can execute step 406; otherwise, it can continue to execute steps 402-405.

[0156] Step 406, output the vehicle mass M_final = M × factor.

[0157] Where M×factor represents the aforementioned target correction data.

[0158] Step 407: The quality identification model completes its work.

[0159] Here, when the aforementioned preset triggering conditions are triggered again, the target vehicle can repeat steps 401-407.

[0160] Please see Figure 5 , Figure 5 This is a structural block diagram of a vehicle weight determination device 500 provided in an embodiment of this application. See also... Figure 5 The vehicle mass determination device 500 includes:

[0161] The data generation unit 501 is used to initiate and execute vehicle quality identification operations when a preset trigger condition is triggered. The vehicle quality identification operations include: acquiring vehicle operation data of the target vehicle during driving, and generating quality identification data based on the vehicle operation data and a pre-built quality identification model.

[0162] The sequence determination unit 502 is used to stop executing the vehicle quality identification operation when the obtained quality identification data sequence meets the preset cutoff condition, and to determine the quality identification data sequence that meets the preset cutoff condition as the target data sequence, wherein the quality identification data sequence includes quality identification data at multiple consecutive times.

[0163] The quality generation unit 503 is used to generate the vehicle quality of the target vehicle based on the target data sequence.

[0164] In some embodiments, the preset triggering conditions include: detecting that the target vehicle is in the vehicle start-up phase, and detecting that the target vehicle has undergone a quality change.

[0165] In some embodiments, after generating quality identification data, the data generation unit 501 further includes: storing the quality identification data into a quality identification data sequence if the quality identification data is greater than a preset quality threshold.

[0166] In some embodiments, the preset cutoff condition includes any one of the following: the target quality identification curve corresponding to the quality identification data sequence has a maximum value, and the target quality identification curve is a curve obtained by smoothing and filtering the quality identification data sequence. The quality identification data sequence contains target quality identification data, and the quality identification data corresponding to a preset number of consecutive time points after the time point corresponding to the target quality data are less than the target quality data.

[0167] In some embodiments, the quality generation unit 503 is specifically used to generate vehicle quality based on the maximum value of the target quality identification curve corresponding to the target data sequence and predetermined target correction data.

[0168] In some embodiments, in the quality generation unit 503, the target correction data is determined as follows: A test quality identification curve corresponding to the driving process of the target vehicle during the testing phase is obtained, wherein the test quality identification curve includes a maximum value and a stationary value. The target correction data is determined based on the maximum value and stationary value of the test quality identification curve.

[0169] In some embodiments, the quality generation unit 503 generates vehicle quality based on the maximum value of the target quality identification curve corresponding to the target data sequence and predetermined target correction data, including: determining reference correction data corresponding to the current correction correlation data based on a pre-stored mapping relationship between correction correlation data and correction data, wherein the current correction correlation data includes at least one of the following: the maximum value of the target quality identification curve and the current throttle depth; adjusting the target correction data based on the reference correction data; and generating vehicle quality based on the adjusted target correction data and the maximum value of the target quality identification curve.

[0170] The vehicle mass determination device provided in this embodiment identifies multiple mass identification data points during the driving process of the target vehicle by acquiring real-time vehicle operation data and a pre-built mass identification model. When the mass identification data sequence composed of several mass identification data points meets a preset cutoff condition, the device automatically generates the vehicle mass based on the mass identification data sequence. This enables timely and accurate determination of the vehicle mass, which helps to achieve precise control of the vehicle based on the obtained accurate vehicle mass, thereby improving vehicle driving safety.

[0171] It should be understood that, Figure 5 In the structural block diagram of the vehicle mass determination device shown, each unit is used to perform... Figure 1 , Figure 4 The steps in the corresponding embodiments, and for Figure 1 , Figure 4 The steps in the corresponding embodiments have been explained in detail in the above embodiments. Please refer to them for details. Figure 1 , Figure 4 as well as Figure 1 , Figure 4 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0172] Figure 6 This is a structural block diagram of a vehicle provided in another embodiment of this application. For example... Figure 6 As shown, the vehicle 600 in this embodiment includes: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601, such as a program for a vehicle weight determination method. When the processor 601 executes the computer program 603, it implements the steps in the various embodiments of the vehicle weight determination methods described above, for example... Figure 1 Steps 101 to 103 are shown. Alternatively, the processor 601 executes the computer program 603 to implement the above. Figure 5 The functions of each unit in the corresponding embodiments, for example, Figure 5 For details on the functions of the data generation units 501 to the quality generation unit 503 shown, please refer to [link / reference]. Figure 5The relevant descriptions in the corresponding embodiments are not repeated here.

[0173] For example, computer program 603 can be divided into one or more units, one or more of which are stored in memory 602 and executed by processor 601 to complete this application. The one or more units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 603 in vehicle 600. For example, computer program 603 can be divided into a data generation unit, a sequence determination unit, and a quality generation unit, with the specific functions of each unit as described above.

[0174] The vehicle may include, but is not limited to, processor 601 and memory 602. Those skilled in the art will understand that... Figure 6 This is merely an example of vehicle 600 and does not constitute a limitation on vehicle 600. It may include more or fewer components than shown, or combine certain components, or different components. For example, the turntable device may also include input / output devices, network access devices, buses, etc.

[0175] The processor 601 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0176] The memory 602 can be an internal storage unit of the vehicle 600, such as a hard drive or RAM. The memory 602 can also be an external storage device of the vehicle 600, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 602 can include both internal and external storage units of the vehicle 600. The memory 602 is used to store computer programs and other programs and data required by the turntable equipment. The memory 602 can also be used to temporarily store data that has been output or will be output.

[0177] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0178] If an integrated module is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer-readable storage medium can be non-volatile or volatile. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the contents of a computer-readable storage medium may be appropriately added to or subtracted from the contents as required by the legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, a computer-readable storage medium may not include electrical carrier signals and telecommunication signals.

[0179] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining vehicle mass, characterized in that, The method includes: When a preset trigger condition is triggered, a vehicle quality identification operation is initiated. The vehicle quality identification operation includes: acquiring vehicle operation data of the target vehicle during driving, and generating quality identification data based on the vehicle operation data and a pre-built quality identification model. When the obtained quality identification data sequence meets the preset cutoff condition, the vehicle quality identification operation is stopped, and the quality identification data sequence that meets the preset cutoff condition is determined as the target data sequence, wherein the quality identification data sequence includes quality identification data at multiple consecutive times. The vehicle mass of the target vehicle is generated based on the target data sequence. The preset cutoff condition includes any one of the following: The target quality identification curve corresponding to the quality identification data sequence has a maximum value, and the target quality identification curve is a curve obtained by smoothing and filtering the quality identification data sequence. The quality identification data sequence contains target quality identification data, and the quality identification data corresponding to a predetermined number of consecutive time points after the time corresponding to the target quality data are smaller than the target quality data. The step of generating the vehicle mass of the target vehicle based on the target data sequence includes: The vehicle mass is generated based on the maximum value of the target mass identification curve corresponding to the target data sequence and the predetermined target correction data.

2. The vehicle weight determination method according to claim 1, characterized in that, The preset triggering conditions include: The target vehicle was detected to be in the vehicle start-up phase, and a change in the mass of the target vehicle was detected.

3. The vehicle weight determination method according to claim 1, characterized in that, After generating the quality identification data, the following is also included: If the quality identification data is greater than a preset quality threshold, the quality identification data is stored in the quality identification data sequence.

4. The vehicle weight determination method according to claim 1, characterized in that, The target correction data is determined in the following manner: Obtain the test quality identification curve corresponding to the driving process of the target vehicle during the test phase, wherein the test quality identification curve includes a maximum value and a stationary value; The target correction data is determined based on the maximum and stationary values ​​of the test quality identification curve.

5. The vehicle weight determination method according to claim 1, characterized in that, The step of generating the vehicle mass based on the maximum value of the target mass identification curve corresponding to the target data sequence and predetermined target correction data includes: Based on the pre-stored mapping relationship between correction-related data and correction data, reference correction data corresponding to the current correction-related data is determined, wherein the current correction-related data includes at least one of the following: the maximum value of the target quality identification curve and the current throttle depth; The target correction data is adjusted based on the reference correction data, and the vehicle mass is generated based on the adjusted target correction data and the maximum value of the target mass identification curve.

6. A vehicle mass determination device, characterized in that, The device includes: The data generation unit is used to initiate and execute a vehicle quality identification operation when a preset trigger condition is triggered. The vehicle quality identification operation includes: acquiring vehicle operation data of the target vehicle during driving, and generating quality identification data based on the vehicle operation data and a pre-built quality identification model. The sequence determination unit is used to stop executing the vehicle quality identification operation when the obtained quality identification data sequence meets the preset cutoff condition, and to determine the quality identification data sequence that meets the preset cutoff condition as the target data sequence, wherein the quality identification data sequence includes quality identification data at multiple consecutive times. A quality generation unit is used to generate the vehicle quality of the target vehicle based on the target data sequence. The preset cutoff condition includes any one of the following: The target quality identification curve corresponding to the quality identification data sequence has a maximum value, and the target quality identification curve is a curve obtained by smoothing and filtering the quality identification data sequence. The quality identification data sequence contains target quality identification data, and the quality identification data corresponding to a predetermined number of consecutive time points after the time corresponding to the target quality data are smaller than the target quality data. The quality generation unit is specifically used to generate the vehicle quality based on the maximum value of the target quality identification curve corresponding to the target data sequence and the predetermined target correction data.

7. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images