Power Management Controller for a Hybrid Electric Vehicle With Predicted Future Acceleration
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- SCIEScopus
- 저널 순위
- JCR Q1Scopus Q1
- 저널
- IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY68(11) · pp.10477 · 2019
- 피인용
- Web of Science 27Scopus 28
- FWCI (Scopus)
- 1.47
- JCR IF
- JCR 2018 5.339
- ISSN
- 0018-9545
저자
초록
Load profiles or duty cycles on a powertrain system are one of the major factors that affect the fuel economy of hybrid electric vehicles. Most of optimal power management controllers that are designed for minimum fuel consumption take into account the upcoming duty cycles explicitly or implicitly. Due to this non-causal nature, many optimal algorithms are not implementable in real-time, or they reluctantly assume simple future duty cycles for real-time implementation at the cost of performance. This paper presents an optimal power management controller that uses the predicted near-future duty cycle instead of hypothesized duty cycles. Model predictive control is used for the controller, and a deep neural network is designed for the estimation of the future duty cycle. Signals from a radar sensor and signals from the ego vehicle are used as the input signals for the deep neural network. A model predictive controller with a well-estimated near-future duty cycles showed significantly improved fuel economy than a model predictive controller with simply assumed duty cycles. Even a less accurately estimated future duty cycle helps improve the fuel economy more than a simply assumed future duty cycle does. We observed that some knowledge about the future duty cycle in the model predictive controller is better for improving fuel economy than the simple assumption if the information has the right directional tendency, even if it is not accurate.
키워드
Deep Neural NetworkDuty Cycle EstimationHybrid Electric Vehicle (HEV)Model Predictive Control (MPC)PONTRYAGINS MINIMUM PRINCIPLEENERGY MANAGEMENTCONTROL STRATEGYOPTIMIZATIONSPLITCONSUMPTIONBEHAVIORSYSTEM
식별자
- Scopus EID
- 2-s2.0-85077744992
- WoS UID
- 000501358800012



로그인
연구물 목록으로