A vehicle mass estimation method, device, equipment, medium and product
By initializing the vehicle mass during the initial stage and fine-tuning it during the stable driving stage, the estimated vehicle mass is updated using the acceleration matrix and inverse covariance matrix. This solves the estimation bias problem caused by rapid acceleration and deceleration of the vehicle, and achieves higher accuracy and more stable vehicle mass estimation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING FENGZHI RUILIAN TECH CO LTD
- Filing Date
- 2025-11-19
- Publication Date
- 2026-05-12
AI Technical Summary
In existing technologies, rapid acceleration and deceleration of a vehicle can lead to deviations in the estimation of the vehicle's mass.
During the vehicle start-up phase, the initial vehicle mass is preset based on prior knowledge, and the estimated vehicle mass value is initialized by updating the initial value in real time. During the stable driving phase, the estimated vehicle mass value is updated based on real-time acceleration, and the estimation is performed using the acceleration matrix and the inverse covariance matrix. The sensitivity of the algorithm is adjusted by combining the forgetting factor.
It effectively avoids the impact of rapid acceleration and deceleration on vehicle mass estimation, improves the accuracy and dynamic response capability of the estimation, reduces the influence of historical data, and enhances the stability and robustness of vehicle mass estimation.
Smart Images
Figure CN121404286B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, equipment, medium and product for estimating the weight of a vehicle. Background Technology
[0002] Researchers have conducted extensive studies on the problem of vehicle mass estimation during vehicle operation. However, based on existing research results, rapid acceleration and deceleration of vehicles can lead to deviations in vehicle mass estimation. Summary of the Invention
[0003] This application provides a method, apparatus, device, medium, and product for estimating vehicle mass, aiming to solve the problem that rapid acceleration and deceleration of vehicles can lead to deviations in vehicle mass estimation based on existing research results.
[0004] Firstly, this application provides a method for estimating the weight of a vehicle, including:
[0005] Before the vehicle starts, the initial vehicle mass is preset based on prior knowledge;
[0006] During the vehicle start-up phase, the initial vehicle mass estimate is updated in real time. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than the threshold.
[0007] During the stable driving phase, the vehicle mass estimate is updated based on the vehicle's real-time acceleration; when the vehicle speed is greater than or equal to a threshold, the vehicle transitions from the starting phase to the stable driving phase.
[0008] In one embodiment, during the vehicle start-up phase, each update of the initial vehicle mass estimate specifically includes:
[0009] Receive acceleration from multiple consecutive time steps to obtain the acceleration matrix for the initial stage, where the last time step among the multiple consecutive time steps is the current moment;
[0010] The initial inverse covariance matrix is obtained based on the acceleration matrix;
[0011] The first vehicle mass estimate is obtained based on the initial inverse covariance matrix and acceleration matrix, and is used as the initial vehicle mass estimate.
[0012] In one embodiment, each update of the initial vehicle mass estimate further includes:
[0013] Based on prior knowledge, extreme value constraints are applied to the first estimated vehicle mass value to obtain an initial estimated vehicle mass value.
[0014] In one embodiment, the vehicle mass estimation method further includes: during the vehicle start-up phase, updating real-time state variables, which are related to the longitudinal motion state of the vehicle.
[0015] In one embodiment, during the stable driving phase of the vehicle, each update of the estimated vehicle mass includes:
[0016] The real-time state quantity residual is determined based on the real-time acceleration and real-time state quantity at the current moment;
[0017] The real-time inverse covariance matrix is updated based on the real-time acceleration at the current moment;
[0018] The estimated vehicle mass at the current moment is determined based on the real-time inverse covariance matrix and the real-time state residual.
[0019] In one embodiment, the real-time inverse covariance matrix is inversely proportional to the forgetting factor, which is used to adjust the algorithm's sensitivity to new data.
[0020] Secondly, this application provides a vehicle weight estimation device, comprising:
[0021] The preset module is used to preset the initial vehicle mass based on prior knowledge before the vehicle starts;
[0022] The initialization module is used to update the initial vehicle mass estimate in real time during the vehicle start-up phase. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than the threshold.
[0023] The update module is used to update the estimated vehicle mass based on the vehicle's real-time acceleration during the stable driving phase; wherein, when the vehicle speed is greater than or equal to a threshold, the vehicle enters the stable driving phase from the starting phase.
[0024] Thirdly, this application also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned vehicle weight estimation methods.
[0025] Fourthly, this application also provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the above-described vehicle weight estimation methods.
[0026] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements any of the above-described vehicle weight estimation methods. Attached Figure Description
[0027] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 This is one of the flowcharts illustrating the vehicle weight estimation method provided in this application;
[0029] Figure 2 This is the second flowchart illustrating the vehicle weight estimation method provided in this application;
[0030] Figure 3 This is one of the structural schematic diagrams of the vehicle weight estimation device provided in this application;
[0031] Figure 4 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation
[0032] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0033] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0034] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.
[0035] The following is combined Figures 1 to 4 This application describes a method, apparatus, equipment, medium, and product for estimating the weight of a vehicle.
[0036] It should be noted that the vehicle weight estimation method provided in this application embodiment is implemented based on a vehicle weight estimation device. The vehicle weight estimation method estimates the vehicle weight during the vehicle start-up phase to avoid deviations caused by rapid acceleration and deceleration of the vehicle.
[0037] This application describes the vehicle weight estimation method using a vehicle weight estimation device as the execution subject as an example.
[0038] Figure 1 This is one of the flowcharts illustrating the vehicle weight estimation method provided in this application. Figure 2 This is the second flowchart of a vehicle weight estimation method provided in this application.
[0039] Please refer to Figure 1 and Figure 2 The vehicle weight estimation method provided in this application specifically includes:
[0040] S110: Before the vehicle starts, the initial vehicle mass is preset based on prior knowledge.
[0041] The vehicle's initial state before starting is when it is not moving forward, i.e., stationary (i.e., speed is 0 km / h). At this time, the initial vehicle mass is preset based on prior knowledge.
[0042] S120: During the vehicle start-up phase, the initial vehicle mass estimate is updated in real time. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than the threshold.
[0043] This application sets a mass estimation initialization flag. When the mass estimation initialization flag is set to 1, it indicates that the task of initializing the vehicle mass estimation has been completed; when the mass estimation initialization flag is not set to 1, it indicates that the task of initializing the vehicle mass estimation has not been completed.
[0044] The method for identifying whether the initial vehicle mass estimate needs to be updated is as follows:
[0045] If the vehicle speed is 0 km / h or the vehicle is not moving forward and the mass estimation initialization flag is not set to 1, the vehicle has not entered the starting phase and the initialization of the vehicle mass estimation task has not been completed. The vehicle is waiting to update the initialization of the vehicle mass estimation value.
[0046] If the vehicle speed is 0 km / h or the vehicle is not moving forward, and the mass estimation initialization flag is set to 1, it means that the vehicle is in a stopped state. The initialization of the vehicle mass estimation task is completed before stopping. However, the vehicle mass may change when the vehicle is stopped. Therefore, the vehicle mass estimation before stopping is inaccurate. At this time, the mass estimation initialization flag is set to zero, the acceleration and longitudinal motion state variables are cleared to zero, and the vehicle mass estimation value is updated and initialized.
[0047] When the vehicle is moving forward, its speed is greater than 0 km / h but less than the threshold, and the mass estimation initialization flag is not set to 1, the vehicle is in the starting phase and the initial vehicle mass estimation value can be updated.
[0048] The driving torque during the initial stage of vehicle start-up is relatively large, and the error in estimating the overall vehicle mass using this data is relatively small.
[0049] In one possible implementation, given the road slope information, the estimated vehicle mass is initialized by updating the state during longitudinal movement.
[0050] S130: During the stable driving phase, update the estimated vehicle mass based on the vehicle's real-time acceleration.
[0051] Specifically, when the vehicle speed is greater than or equal to a threshold, the vehicle transitions from the starting phase to the stable driving phase. Once in the stable driving phase, the mass estimation initialization flag is set to 1. It should be noted that the stable driving phase here is relative to the starting phase. During the stable driving phase, vehicle speed, acceleration, etc., can change until the vehicle speed drops to 0 km / h, at which point the vehicle enters a stationary state. After the vehicle enters a stationary state, the process returns to step S110 to begin the next vehicle mass estimation loop.
[0052] In one possible implementation, the estimated vehicle mass can be obtained using the least squares method or the weighted least squares method.
[0053] In this embodiment, the vehicle mass is initialized during the vehicle start-up phase and fine-tuned based on real-time acceleration during the stable driving phase. This utilizes high-quality data from the start-up phase to establish an initial estimate, obtaining the statistically optimal initial value. This avoids the slow convergence problem caused by starting with an arbitrary initial value, and also avoids the large deviation in vehicle mass estimation during rapid acceleration and deceleration caused by directly estimating the vehicle mass during the vehicle's driving phase.
[0054] In one possible implementation, step S120, during the vehicle start-up phase, involves updating the initial vehicle mass estimate each time, specifically including:
[0055] S1201: Receives acceleration from multiple consecutive time steps to obtain the acceleration matrix during the initial phase. The last time step in a series of consecutive time steps is the current time.
[0056] Therefore, the acceleration matrix It is a collection of batch accelerations over a period of time during the initial stage.
[0057] S1202: Obtaining the initial inverse covariance matrix based on the acceleration matrix .
[0058] Initial inverse covariance matrix The calculation formula is as follows:
[0059] (1).
[0060] S1203: Obtain the first estimated vehicle mass based on the initial inverse covariance matrix and acceleration matrix. This serves as the initial vehicle mass estimate.
[0061] First estimated vehicle weight The calculation formula is as follows:
[0062] (2);
[0063] in, This indicates the initialization of the system state.
[0064] This application embodiment obtains the initial vehicle mass estimate by using a set of acceleration matrices to measure the batch accelerations during the initial stage and by performing matrix operations. Compared with the method of determining the initial vehicle mass estimate based on a single acceleration, this method obtains a more accurate initial vehicle mass.
[0065] In one possible implementation, please see Figure 2 In step S120, each update of the initial vehicle mass estimate also includes:
[0066] Based on prior knowledge, extreme value constraints are applied to the first estimated vehicle mass value to obtain an initial estimated vehicle mass value.
[0067] Specifically, prior knowledge provides an upper and lower limit for the vehicle mass. If the first estimated vehicle mass is higher than the upper limit or lower than the lower limit, the initial estimated vehicle mass will be assigned an extreme value that is close to the first estimated vehicle mass.
[0068] The embodiments of this application can accelerate the convergence speed of the vehicle mass estimate by limiting prior knowledge.
[0069] In one possible implementation, the vehicle weight estimation method also includes:
[0070] During the vehicle start-up phase, update the real-time state variables. The real-time state variables are related to the longitudinal motion state of the vehicle. Therefore, the real-time state variables are used to characterize the real-time longitudinal motion state of the vehicle. The real-time state variables are updated during the start-up phase to provide initial state variables for the stable driving phase, which are used to update the estimated value of the vehicle mass during the stable driving phase.
[0071] Real-time state variables can be represented as:
[0072] (3);
[0073] in, express Wheel-side driving force at all times Indicates the wheel radius. Represents gravitational acceleration. Represents the rolling friction coefficient. This represents the estimated vehicle mass at the previous moment. express The cosine value of the slope at time t. Indicates the air drag coefficient. Indicates the windward area. Indicates air density, express The vehicle speed at any given moment. Among them, , , These are the longitudinal motion state parameters.
[0074] Based on this, please see Figure 2 In step S130, during the stable driving phase of the vehicle, the estimated vehicle mass is updated each time, specifically including:
[0075] S1301: Determine the real-time state variable residual based on the real-time acceleration and real-time state variables at the current moment.
[0076] First, update the real-time state variables based on the real-time longitudinal motion state parameters in the above equation (3). Based on the updated real-time state variables Calculate the residuals of real-time state variables :
[0077] (4)
[0078] in, express Real-time acceleration at any moment express The estimated vehicle mass at any given time.
[0079] In one possible implementation, when updating the real-time state quantity residual for the first time during the stable driving phase, the average value of the initial vehicle mass of the last preset number (e.g., 3) from the initialization phase can be used as... The estimated vehicle mass value at any given time is used to accelerate the convergence speed of the mass estimation.
[0080] S1302: Update the real-time inverse covariance matrix based on the real-time acceleration at the current moment. .
[0081] In one possible implementation, the real-time inverse covariance matrix and the forgetting factor Inversely proportional.
[0082] Specifically, the real-time inverse covariance matrix The calculation formula is as follows:
[0083] (5).
[0084] The forgetting factor is used to adjust the algorithm's sensitivity to new data, and its monotonically decreasing characteristic ensures the algorithm's convergence.
[0085] S1303: Determine the estimated vehicle mass at the current moment based on the real-time inverse covariance matrix and real-time state residuals. :
[0086] (6);
[0087] (7);
[0088] in, This is the gain coefficient.
[0089] In one possible implementation, please see Figure 2 During the stable driving phase of the vehicle, the estimated value of the vehicle mass is obtained. It also estimates the overall vehicle mass based on prior knowledge. Extreme value constraints are applied to obtain the final estimated value of the vehicle mass.
[0090] This application's embodiments determine the vehicle mass estimate by updating the real-time state quantity residuals and the real-time inverse covariance matrix. By continuously introducing new observation data and recursively adjusting the vehicle mass estimate, the estimation results can adapt to changes in vehicle operating conditions, improving the dynamic response capability and accuracy of the vehicle mass estimate. Furthermore, by introducing a forgetting factor, the ability to track time-varying parameter characteristics is enhanced, reducing the influence of historical data and focusing on the latest data, thereby improving the stability and robustness of the estimate and preventing significant deviations from reality due to abnormal data or sudden changes.
[0091] Based on the above vehicle weight estimation method, in real vehicle tests, when the actual vehicle weight is 46,900 kg when fully loaded, the simulation estimate is 47,360 kg, with an estimation error of 0.9%; when unloaded, the actual vehicle weight is 12,100 kg, and the simulation estimate is 12,600 kg, with an estimation error of 4%. The vehicle weight estimation method of this application has achieved good results.
[0092] Based on the above, this application also provides a vehicle weight estimation device. This vehicle weight estimation device and the aforementioned vehicle weight estimation method can be referred to and correspond to each other.
[0093] As an example, such as Figure 3 As shown, the vehicle weight estimation device provided in this application includes:
[0094] The preset module 310 is used to preset the initial vehicle mass based on prior knowledge before the vehicle starts.
[0095] The initialization module 320 is used to update the initial vehicle mass estimate in real time during the vehicle start-up phase. During the vehicle start-up phase, the vehicle moves forward and its speed is greater than 0 km / h and less than a threshold.
[0096] The update module 330 is used to update the estimated vehicle mass based on the vehicle's real-time acceleration during the stable driving phase. Specifically, when the vehicle speed is greater than or equal to a threshold, the vehicle transitions from the initial driving phase to the stable driving phase.
[0097] In this embodiment, the vehicle mass is initialized during the vehicle start-up phase and fine-tuned based on real-time acceleration during the stable driving phase. This utilizes high-quality data from the start-up phase to establish an initial estimate, obtaining the statistically optimal initial value. This avoids the slow convergence problem caused by starting with an arbitrary initial value, and also avoids the large deviation in vehicle mass estimation during rapid acceleration and deceleration caused by directly estimating the vehicle mass during the vehicle's driving phase.
[0098] In one possible implementation, the initialization module 320 is specifically used for:
[0099] Receive acceleration from multiple consecutive time steps to obtain the acceleration matrix for the initial stage, where the last time step among the multiple consecutive time steps is the current moment;
[0100] The initial inverse covariance matrix is obtained based on the acceleration matrix;
[0101] The first vehicle mass estimate is obtained based on the initial inverse covariance matrix and acceleration matrix, and is used as the initial vehicle mass estimate.
[0102] This application embodiment obtains the initial vehicle mass estimate by using a set of acceleration matrices to measure the batch accelerations during the initial stage and by performing matrix operations. Compared with the method of determining the initial vehicle mass estimate based on a single acceleration, this method obtains a more accurate initial vehicle mass.
[0103] In one possible implementation, update module 330 is specifically used for:
[0104] The real-time state quantity residual is determined based on the real-time acceleration and real-time state quantity at the current moment;
[0105] The real-time inverse covariance matrix is updated based on the real-time acceleration at the current moment;
[0106] The estimated vehicle mass at the current moment is determined based on the real-time inverse covariance matrix and the real-time state residual.
[0107] This application's embodiments determine the vehicle mass estimate by updating the real-time state quantity residuals and the real-time inverse covariance matrix. By continuously introducing new observation data and recursively adjusting the vehicle mass estimate, the estimation results can adapt to changes in vehicle operating conditions, improving the dynamic response capability and accuracy of the vehicle mass estimate. Furthermore, by introducing a forgetting factor, the ability to track time-varying parameter characteristics is enhanced, reducing the influence of historical data and focusing on the latest data, thereby improving the stability and robustness of the estimate and preventing significant deviations from reality due to abnormal data or sudden changes.
[0108] Figure 4 This is a schematic diagram of the structure of the electronic device provided in this application, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a vehicle weight estimation method, which includes:
[0109] Before the vehicle starts, the initial vehicle mass is preset based on prior knowledge;
[0110] During the vehicle start-up phase, the initial vehicle mass estimate is updated in real time. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than the threshold.
[0111] During the stable driving phase, the estimated vehicle mass is updated based on the vehicle's real-time acceleration.
[0112] When the vehicle speed is greater than or equal to the threshold, the vehicle enters the stable driving phase from the starting phase.
[0113] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0114] On the other hand, this application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer is able to execute the vehicle weight estimation method provided in the above embodiments. The method includes:
[0115] Before the vehicle starts, the initial vehicle mass is preset based on prior knowledge;
[0116] During the vehicle start-up phase, the initial vehicle mass estimate is updated in real time. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than the threshold.
[0117] During the stable driving phase, the estimated vehicle mass is updated based on the vehicle's real-time acceleration.
[0118] When the vehicle speed is greater than or equal to the threshold, the vehicle enters the stable driving phase from the starting phase.
[0119] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the vehicle weight estimation method provided in the above embodiments, the method comprising:
[0120] Before the vehicle starts, the initial vehicle mass is preset based on prior knowledge;
[0121] During the vehicle start-up phase, the initial vehicle mass estimate is updated in real time. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than the threshold.
[0122] During the stable driving phase, the estimated vehicle mass is updated based on the vehicle's real-time acceleration.
[0123] When the vehicle speed is greater than or equal to the threshold, the vehicle enters the stable driving phase from the starting phase.
[0124] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0125] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.
[0126] Finally, it should be noted that 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.
Claims
1. A method for estimating the weight of a vehicle, characterized in that, include: Before the vehicle starts, the initial vehicle mass is preset based on prior knowledge; During the vehicle start-up phase, the initial vehicle mass estimate is updated in real time. During the vehicle start-up phase, the vehicle moves forward and the speed is greater than 0 km / h and less than a threshold. During the stable driving phase, the estimated vehicle mass is updated based on the vehicle's real-time acceleration; when the vehicle speed is greater than or equal to the threshold, the vehicle transitions from the starting phase to the stable driving phase. Specifically, during the vehicle start-up phase, each update of the initial vehicle mass estimate includes: Receive accelerations at multiple consecutive time steps to obtain the acceleration matrix for the initial stage, wherein the last time step among the multiple consecutive time steps is the current moment; The initial inverse covariance matrix is obtained based on the acceleration matrix; The first vehicle mass estimate is obtained based on the initial inverse covariance matrix and the acceleration matrix, and is used as the initial vehicle mass estimate. Furthermore, during the stable driving phase, the estimated vehicle mass is updated each time, specifically including: The real-time state quantity residual is determined based on the real-time acceleration and real-time state quantity at the current moment, and the real-time state quantity is related to the longitudinal motion state of the vehicle. The real-time inverse covariance matrix is updated based on the real-time acceleration at the current moment; The estimated value of the vehicle mass at the current moment is determined based on the real-time inverse covariance matrix and the real-time state quantity residual.
2. The vehicle weight estimation method according to claim 1, characterized in that, Each update to initialize the vehicle mass estimate also includes: The initial vehicle mass estimate is obtained by applying extreme value restrictions to the first vehicle mass estimate based on prior knowledge.
3. The vehicle weight estimation method according to claim 1, characterized in that, Also includes: During the vehicle start-up phase, update real-time status parameters.
4. The vehicle weight estimation method according to claim 1, characterized in that, The real-time inverse covariance matrix is inversely proportional to the forgetting factor, which is used to adjust the algorithm's sensitivity to new data.
5. A vehicle weight estimation device, characterized in that, include: The preset module is used to preset the initial vehicle mass based on prior knowledge before the vehicle starts; An initialization module is used to update the initial vehicle mass estimate in real time during the vehicle start-up phase, in which the vehicle moves forward and the speed is greater than 0 km / h and less than a threshold. An update module is used to update the estimated vehicle mass based on the vehicle's real-time acceleration during the stable driving phase; wherein, when the vehicle speed is greater than or equal to the threshold, the vehicle enters the stable driving phase from the starting phase. Specifically, the initialization module is used for: Receive acceleration from multiple consecutive time steps to obtain the acceleration matrix for the initial stage, where the last time step among the multiple consecutive time steps is the current moment; The initial inverse covariance matrix is obtained based on the acceleration matrix; The first vehicle mass estimate is obtained based on the initial inverse covariance matrix and acceleration matrix, and is used as the initial vehicle mass estimate. Furthermore, the update module is specifically used for: The real-time state quantity residual is determined based on the real-time acceleration and real-time state quantity at the current moment, wherein the real-time state quantity is related to the longitudinal motion state of the vehicle. The real-time inverse covariance matrix is updated based on the real-time acceleration at the current moment; The estimated vehicle mass at the current moment is determined based on the real-time inverse covariance matrix and the real-time state residual.
6. An electronic device 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 vehicle weight estimation method as described in any one of claims 1 to 4.
7. A non-transitory computer-readable storage medium, wherein a computer program is stored on the non-transitory computer-readable storage medium, characterized in that, When the computer program is executed by the processor, it implements the vehicle weight estimation method as described in any one of claims 1 to 4.
8. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle weight estimation method as described in any one of claims 1 to 4.