Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A td3-based heuristic series-parallel hybrid energy management method

An energy management and hybrid technology, applied in hybrid vehicles, motor vehicles, control devices, etc., can solve the problems of slow training, imperfect control, inability to achieve high-dimensional and continuous motion control, and achieve control energy optimization Effect

Active Publication Date: 2022-06-28
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, ordinary reinforcement learning cannot achieve high-dimensional and continuous motion control, so the control effect is not significant, and ordinary deep reinforcement learning still has problems such as slow training and imperfect control in terms of training speed and control effect.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A td3-based heuristic series-parallel hybrid energy management method
  • A td3-based heuristic series-parallel hybrid energy management method
  • A td3-based heuristic series-parallel hybrid energy management method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments:

[0040] figure 1 is a schematic diagram of the overall framework of the deep reinforcement learning TD3 agent provided by the embodiment of the present application;

[0041] like figure 1As shown, in this implementation environment, by collecting the parameters that may affect the energy management of the experimental vehicle under fixed route conditions, and using the reward value and the parameters and observations that may affect the energy management as input data, the energy management parameters may be affected. Input the controlled object, input the input data into the TD3 agent deep reinforcement learning agent and the local controller respectively, and then combine the TD3 agent and the local controller to output the optimal action of the control quantity, that is, the engine torque and speed and the motor torque. The control signal...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a TD3-based heuristic series-parallel hybrid energy management method, which belongs to the technical field of hybrid electric vehicles and can effectively improve the fuel economy of hybrid electric vehicles; using TD3 agent combined with experience-based heuristic exploration can effectively speed up The training convergence speed and training effect solve the technical problem of the lack of an online energy management method for series-parallel hybrid electric vehicles in related technologies. The invention includes: establishing a series-parallel hybrid electric vehicle model; obtaining parameters affecting the energy management under different working conditions; based on the parameters and observations affecting the energy management, using an improved DDPG agent—double delay depth determinism Policy gradient (TD3 agent) combined with heuristic exploration for model training to obtain a trained deep reinforcement learning agent; based on the above agent for energy management control in the actual driving process.

Description

technical field [0001] The invention belongs to the technical field of hybrid electric vehicles, in particular to a TD3-based heuristic series-parallel hybrid energy management method. Background technique [0002] Most of the energy management methods of hybrid electric vehicles currently used in real-time online applications are based on rules. Through professional experience, certain energy management thresholds are formulated. For example, the most common plug-in hybrid rule is to consume battery energy first, and then carry out battery energy. The maintenance of electricity and energy management. The representative benchmark for optimization-based strategies is dynamic programming (DP). The optimal energy management of hybrid electric buses is obtained offline when the global operating condition information is known, but it cannot be applied online. [0003] In the existing real-time online technology, the engineers' experience is used to formulate rules for energy man...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): B60W20/10B60W50/00B60W10/26B60W10/06B60W10/08B60W20/20
CPCB60W20/00B60W50/00B60W2050/0002B60W2050/0031B60W2050/0039
Inventor 周健豪薛四伍廖宇晖刘军薛源
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com