Online Markov Chain-based energy management for a hybrid tracked vehicle with speedy Q-learning

Li, Teng; Wang, Bo; Yang, Chenglang

doi:10.1016/j.energy.2018.07.022

Cited by 112 publications

(39 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The increasing interest in sustainable mobility has led to the study and development of new hybrid architectures, which can be mainly divided in three main categories [1]: parallel [2][3][4][5][6], series/parallel (also known as power-split) [6][7][8][9][10][11][12][13][14], and series hybrid [15][16][17][18][19][20][21]. Passalacqua et al [22] proposed a new series architecture configuration for medium size cars, with a storage system based only on supercapacitors and they highlighted the benefits in terms of internal combustion engine (ICE) optimal working points.…”

Section: Introductionmentioning

confidence: 99%

Turbocompound Power Unit Modelling for a Supercapacitor-Based Series Hybrid Vehicle Application

et al. 2020

View full text Add to dashboard Cite

In this paper, starting from the measurements available for a 2000 cm3 turbocharged diesel engine, an analytical model of the turbocharger is proposed and validated. The model is then used to extrapolate the efficiency of a power unit with a diesel engine combined with a turbocompound system. The obtained efficiency map is used to evaluate the fuel economy of a supercapacitor-based series hybrid vehicle equipped with the turbocompound power unit. The turbocompound model, in accordance with the studies available in the technical literature, shows that the advantages (in terms of efficiency increase) are significant at high loads. For this reason, turbocompound introduction allows a significant efficiency improvement in a series hybrid vehicle, where the engine always works at high-load. The fuel economy of the proposed vehicle is compared with other hybrid and conventional vehicle configurations.

show abstract

Section: Introductionmentioning

confidence: 99%

Turbocompound Power Unit Modelling for a Supercapacitor-Based Series Hybrid Vehicle Application

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In Refs. [23,24], a reinforcement learning algorithm is employed to optimally control HEVs using MC-based predictors. Compared with Ref.…”

Section: Introductionmentioning

confidence: 99%

“…[23], the main improvement of Ref. [24] is to utilize an online updating policy for updating the transition probability of the MC models. Ref.…”

Section: Introductionmentioning

confidence: 99%

Dual-loop online intelligent programming for driver-oriented predict energy management of plug-in hybrid electric vehicles

Zhou

et al. 2019

Applied Energy

View full text Add to dashboard Cite

“…Ref. [17] proposed a different Tabular QL-based EMS, where the SOC and the speed of the engine were taken as the states, and the throttle of the engine was taken as the action. For the latter, Ref.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Energy Management for Plug-in Hybrid Electric Bus with Limited State Space

Guo

Zhao

et al. 2019

Processes

View full text Add to dashboard Cite

Tabular Q-learning (QL) can be easily implemented into a controller to realize self-learning energy management control of a plug-in hybrid electric bus (PHEB). However, the “curse of dimensionality” problem is difficult to avoid, as the design space is huge. This paper proposes a QL-PMP algorithm (QL and Pontryagin minimum principle (PMP)) to address the problem. The main novelty is that the difference between the feedback SOC (state of charge) and the reference SOC is exclusively designed as state, and then a limited state space with 50 rows and 25 columns is proposed. The off-line training process shows that the limited state space is reasonable and adequate for the self-learning; the Hardware-in-Loop (HIL) simulation results show that the QL-PMP strategy can be implemented into a controller to realize real-time control, and can on average improve the fuel economy by 20.42%, compared to the charge depleting–charge sustaining (CDCS) strategy.

show abstract

Online Markov Chain-based energy management for a hybrid tracked vehicle with speedy Q-learning

Cited by 112 publications

References 26 publications

Turbocompound Power Unit Modelling for a Supercapacitor-Based Series Hybrid Vehicle Application

Turbocompound Power Unit Modelling for a Supercapacitor-Based Series Hybrid Vehicle Application

Dual-loop online intelligent programming for driver-oriented predict energy management of plug-in hybrid electric vehicles

Intelligent Energy Management for Plug-in Hybrid Electric Bus with Limited State Space

Contact Info

Product

Resources

About