CN-121404286-B - Whole vehicle quality estimation method, device, equipment, medium and product

CN121404286BCN 121404286 BCN121404286 BCN 121404286BCN-121404286-B

Abstract

The application provides a method, a device, equipment, a medium and a product for estimating the quality of a whole vehicle, which belong to the technical field of data processing, wherein the method comprises the steps of presetting the initial quality of the whole vehicle according to priori knowledge before starting the vehicle; the method comprises the steps of updating an initial whole vehicle quality estimated value in real time in a vehicle starting stage, wherein the vehicle moves forwards in the vehicle starting stage, the vehicle speed is greater than 0km/h and smaller than a threshold value, updating the whole vehicle quality estimated value based on real-time acceleration of the vehicle in a vehicle stable driving stage, and entering the vehicle stable driving stage from the starting stage when the vehicle speed is greater than or equal to the threshold value. The application establishes initial estimation by using high-quality data in a starting stage, obtains an optimal initial value in a statistical sense, avoids the problem of slow convergence caused by starting from any initial value, and simultaneously avoids the situation that the whole vehicle quality estimation deviation is large under the conditions of rapid acceleration and rapid deceleration caused by directly carrying out whole vehicle quality estimation in a vehicle driving stage.

Inventors

XIE HAIMING
WANG SHIJIA
WANG YAOJUN

Assignees

北京峰智睿联科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251119

Claims (8)

1. The whole vehicle quality estimation method is characterized by comprising the following steps of: Before starting a vehicle, presetting initial whole vehicle mass according to priori knowledge; in a vehicle starting stage, updating and initializing the whole vehicle quality estimated value in real time, wherein in the vehicle starting stage, the vehicle moves forwards, and the vehicle speed is more than 0km/h and less than a threshold value; When the vehicle speed is greater than or equal to the threshold value, the vehicle enters a stable driving stage from a starting stage; In the vehicle starting stage, the method specifically comprises the following steps of: receiving acceleration of a plurality of continuous time steps to obtain an acceleration matrix of a starting stage, wherein the last time step of the plurality of continuous time steps is the current moment; obtaining an initial inverse covariance matrix based on the acceleration matrix; acquiring a first whole vehicle quality estimated value based on the initial inverse covariance matrix and the acceleration matrix, and taking the first whole vehicle quality estimated value as the initial whole vehicle quality estimated value; in addition, in the stable running stage of the vehicle, the whole vehicle quality estimated value is updated each time, and the method specifically comprises the following steps: determining a real-time state quantity residual error based on the real-time acceleration and the real-time state quantity at the current moment, wherein the real-time state quantity is related to the longitudinal movement state of the vehicle; updating a real-time inverse covariance matrix based on the real-time acceleration at the current moment; and determining the whole vehicle quality estimated value at the current moment based on the real-time inverse covariance matrix and the real-time state quantity residual error.
2. The vehicle quality estimation method according to claim 1, characterized in that initializing the vehicle quality estimation value each time is updated, further comprising: And limiting the extreme value of the first whole vehicle quality estimated value based on priori knowledge to obtain the initialized whole vehicle quality estimated value.
3. The vehicle mass estimation method of claim 1, further comprising: in the vehicle start phase, the real-time state quantity is updated.
4. The vehicle quality estimation method of claim 1, wherein the real-time inverse covariance matrix is inversely proportional to a forgetting factor, the forgetting factor being used to adjust the sensitivity of the algorithm to the new data.
5. The whole vehicle quality estimation device is characterized by comprising: the pre-setting module is used for pre-setting the initial whole vehicle quality according to priori knowledge before starting the vehicle; the initialization module is used for updating and initializing the whole vehicle quality estimated value in real time in a vehicle starting stage, and the vehicle moves forwards in the vehicle starting stage, wherein the vehicle speed is greater than 0km/h and less than a threshold value; The updating module is used for updating the whole vehicle quality estimated value based on the real-time acceleration of the vehicle in the stable running stage of the vehicle, wherein when the vehicle speed is greater than or equal to the threshold value, the vehicle enters the stable running stage from the starting stage; the initialization module is specifically configured to: Receiving acceleration of a plurality of continuous time steps to obtain an acceleration matrix of a starting stage, wherein the last time step in the plurality of continuous time steps is the current moment; obtaining an initial inverse covariance matrix based on the acceleration matrix; Acquiring a first whole vehicle quality estimated value based on the initial inverse covariance matrix and the acceleration matrix, and taking the first whole vehicle quality estimated value as an initial whole vehicle quality estimated value; and, the update module is specifically configured to: Determining a real-time state quantity residual error based on the real-time acceleration and the real-time state quantity at the current moment, wherein the real-time state quantity is related to the longitudinal movement state of the vehicle; updating a real-time inverse covariance matrix based on the real-time acceleration at the current moment; and determining the whole vehicle quality estimated value at the current moment based on the real-time inverse covariance matrix and the real-time state quantity residual error.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the whole vehicle mass estimation method according to any one of claims 1 to 4 when executing the computer program.
7. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the whole vehicle mass estimation method according to any one of claims 1 to 4.
8. A computer program product comprising a computer program which, when executed by a processor, implements the vehicle mass estimation method as claimed in any one of claims 1 to 4.

Description

Whole vehicle quality estimation method, device, equipment, medium and product Technical Field The present application relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, a medium, and a product for estimating quality of a whole vehicle. Background The problem of vehicle quality estimation in the vehicle driving process is greatly studied by related researchers, but on the basis of the existing research result, the vehicle rapid acceleration and rapid deceleration can cause deviation of the vehicle quality estimation. Disclosure of Invention The application provides a method, a device, equipment, a medium and a product for estimating the quality of a whole vehicle, and aims to solve the problem that the quality estimation of the whole vehicle is deviated due to rapid acceleration and rapid deceleration of the vehicle based on the existing research result. In a first aspect, the present application provides a method for estimating quality of a whole vehicle, including: Before starting a vehicle, presetting initial whole vehicle mass according to priori knowledge; in a vehicle starting stage, the whole vehicle quality estimated value is updated and initialized in real time, and in the vehicle starting stage, the vehicle moves forwards, and the vehicle speed is more than 0km/h and less than a threshold value; and when the vehicle speed is greater than or equal to a threshold value, the vehicle enters a stable driving stage from a starting stage. In one embodiment, in a vehicle starting stage, each time the whole vehicle quality estimated value is updated and initialized, the method specifically comprises the following steps: Receiving acceleration of a plurality of continuous time steps to obtain an acceleration matrix of a starting stage, wherein the last time step in the plurality of continuous time steps is the current moment; obtaining an initial inverse covariance matrix based on the acceleration matrix; and obtaining a first whole vehicle quality estimated value based on the initial inverse covariance matrix and the acceleration matrix, and taking the first whole vehicle quality estimated value as an initial whole vehicle quality estimated value. In one embodiment, initializing the whole vehicle quality estimate each time an update further comprises: and limiting the extreme value of the first whole vehicle quality estimated value based on the priori knowledge to obtain an initialized whole vehicle quality estimated value. In one embodiment, the vehicle mass estimation method further comprises updating a real-time state quantity in a vehicle starting stage, wherein the real-time state quantity is related to the longitudinal movement state of the vehicle. In one embodiment, in a stable driving stage of the vehicle, updating the whole vehicle quality estimation value each time specifically includes: Determining a real-time state quantity residual error based on the real-time acceleration and the real-time state quantity at the current moment; updating a real-time inverse covariance matrix based on the real-time acceleration at the current moment; and determining the whole vehicle quality estimated value at the current moment based on the real-time inverse covariance matrix and the real-time state quantity residual error. In one embodiment, the real-time inverse covariance matrix is inversely proportional to a forgetting factor, which is used to adjust the sensitivity of the algorithm to the nascent data. In a second aspect, the present application provides a device for estimating quality of a whole vehicle, including: the pre-setting module is used for pre-setting the initial whole vehicle quality according to priori knowledge before starting the vehicle; the initialization module is used for updating and initializing the whole vehicle quality estimated value in real time in a vehicle starting stage, and the vehicle moves forwards in the vehicle starting stage, wherein the vehicle speed is greater than 0km/h and less than a threshold value; And the updating module is used for updating the whole vehicle quality estimated value based on the real-time acceleration of the vehicle in the stable running stage of the vehicle, wherein the vehicle enters the stable running stage from the starting stage when the vehicle speed is greater than or equal to a threshold value. In a third aspect, the present application further provides an electronic device, where the electronic device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and when the processor executes the computer program, any one of the above-mentioned methods for estimating quality of a whole vehicle is implemented. In a fourth aspect, the present application further provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor implements any one of the above-me