Vehicle mass determination method, device, computer equipment, readable storage medium and program product
By periodically obtaining the eigenvalues of the vehicle longitudinal dynamics model and updating the deep neural network model, the resource occupation problem in commercial vehicles is solved, efficient vehicle mass estimation is achieved, and power performance and fuel efficiency are improved.
CN119099634BActive Publication Date: 2025-09-23FAW JIEFANG AUTOMOTIVE CO
Patent Information
- Application Number
- CN202411256408.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2025-09-23
- Estimated Expiration
- 2044-09-09
AI Technical Summary
Technical Problem
Existing commercial vehicle mass estimation algorithms occupy a large amount of on-chip resources, affecting vehicle dynamic performance and fuel efficiency optimization.
Method used
The characteristic values of the vehicle longitudinal dynamics model are periodically obtained, and the deep neural network model parameters are updated multiple times, including initial update, crossover probability and mutation probability adjustment, to optimize the model to determine the vehicle mass.
Benefits of technology
It reduces the usage of on-chip resources and shortens the convergence time of deep neural network model training, thereby improving the accuracy and efficiency of vehicle mass estimation.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119099634B_ABST
Abstract
This application relates to a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining vehicle mass. The method comprises: periodically acquiring multiple sets of target eigenvalues for a vehicle longitudinal dynamics model within a preset time period; updating multiple model parameters of a preset number of initial deep neural network models three times based on the multiple sets of target eigenvalues; and determining the vehicle mass of a target vehicle based on the deep neural network model after the third update. The method provided in this application can reduce on-chip resource usage and effectively shorten the convergence time during deep neural network model training.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Conversion rate prediction method and device, equipment and medium
CN112818291A
Automobile pavement state online estimation system and method based on multi-algorithm fusion prediction
CN113147768A