HEV energy management method and system based on hierarchical return TD3
A technology of energy management and reward function, which is applied in data processing management, transportation and packaging, road transportation emission reduction, etc., can solve the problem of inability to adjust the control strategy, solve the problem of deep deterministic strategy gradient overestimation, and solve the disaster of dimensionality problem, the effect of improving optimality
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] Embodiment 1 provides a HEV energy management method based on tiered reward TD3, comprising the following steps:
[0032] Step 1: Build a parallel hybrid vehicle model.
[0033] Specifically, a parallel hybrid vehicle model can be established through MATLAB / Simulink.
[0034] In the established parallel hybrid vehicle model, the engine and the motor are connected in parallel, and the engine can be coupled or separated from the wheels through the clutch. The vehicle mainly operates in pure electric mode, neutral mode and parallel mode. The above three vehicle working modes depend on the state and gear of the clutch. The structure diagram is shown in the figure below. figure 1 shown.
[0035] The vehicle power system must provide the traction required for the vehicle to run, which can be calculated from the vehicle dynamics equation, which is shown in formula (1):
[0036]
[0037] Among them, F t is the driving force of the car, F f is the rolling resistance of t
Embodiment 2
[0063] Embodiment 2 provides an HEV energy management system based on tiered reward TD3, including: a processor and a memory; the memory stores a control program, and when the control program is executed by the processor, is used to implement the embodiment The HEV energy management method based on tiered reward TD3 described in 1.
[0064] A method and system for HEV energy management based on tiered reward TD3 provided by the embodiments of the present invention include at least the following technical effects:
[0065] (1) The present invention precisely designs a layered reward structure. The structure has two reward functions and a total of four adjustment layers. The control strategy can be adjusted according to the different driving states of the vehicle, and unnecessary repeated exploration behaviors are reduced, which not only ensures the The reward function is comprehensively adjusted for different driving modes, and avoids the waste of on-board computing resources, ena
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap