Loading...

Design of a HEV’s Controller Using Learning-based Methods

Zare, Aramchehr | 2022

196 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55679 (46)
  4. University: Sharif University of Technology
  5. Department: Energy Engineering
  6. Advisor(s): Boroushaki, Mehrdad
  7. Abstract:
  8. Hybrid electric vehicles (HEV) are proving to be one of the most promising innovations in advanced transportation systems to reduce air pollution and fossil fuel consumption. EMS is one of the most vital aspects of the HEV powertrain system. This research aims to design an optimal EMS under the condition of meeting the goals of drivability control, fuel consumption reduction, and battery charge stability. The current EMS is based on the classical rule-based method derived from fuzzy logic, which guides to the suboptimal solution in episodic driving cycles. Previous experiences in implementing Reinforcement Learning (RL) suffer from late convergence, instability in tracking the driving cycles, and undesired performance under real driving conditions. This research presents an intelligent EMS based on the hybridization of an expert Knowledge-Assisted system with the Deep Deterministic Policy Gradient (KA-DDPG) and Deep Q-Network (KA-DQN) to overcome the RL difficulties and obtain the optimal EMS actions under different driving conditions. The simulation results show reduce computation time, reduce fuel consumption between 3.15% to 7.26%, and retain SoC's stability which leads to longer battery life by KA-DDPG and KA-DQN. The proposed method improves the average negative electric motor torque between 1.29% to 3.16% and leads to more energy savings. This research was done on the Prius Sedan model.
  9. Keywords:
  10. Hybrid Electric Vehicle (HEV) ; Deep Deterministic Policy Gradient ; Knowledge Argument ; Deep Reinforcement Learning ; Energy Management Standards ; Energy Management

 Digital Object List

 Bookmark

...see more