Energy management for hybrid electric vehicles based on imitation reinforcement learning

Liu, Yonggang; Wu, Yitao; Wang, Xiangyu; Li, Liang; Zhang, Hongjie; Chen, Zheng

doi:10.1016/j.energy.2022.125890

Cited by 32 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The EMS used in this study considers restricting the battery capacity depending on SOC to a max‐min criterion, giving enough power to the electric motor for various settings, as well as battery's charging in deceleration and acceleration phases. The load's power requirement (EVs), needed for vehicle propulsion is no more than the product of its speed and the load torque applied on it which is also met by two sources (FCs and batteries), is given by 4,39 :

\{\begin{matrix} P_{italicLoad} = ω_{((), wheels)} T_{L} = P_{italicbatt} + P_{italicFC} \\ T_{L} = R \times F_{italictot} \end{matrix}

where

P_{italicLoad}

is the fluctuation in the amount of power required by the electric vehicle and

T_{L}

is the load torque applied to the wheels. The states of commutation of interrupters required to obtain these modes of operation and switches state, rely on the three switches K 1 , K 2 , and K 3 provided in Table 1.…”

Section: Proposed Hybrid Battery‐pemfcs Energy Management Algorithmmentioning

confidence: 99%

“…A battery is a device that accumulates electrical energy in electrochemical form and then releases it as needed. The battery's model and state of charge (SOC) is formulated as 38,39 :…”

Section: Modelling Of the Bssmentioning

confidence: 99%

“…The EMS used in this study considers restricting the battery capacity depending on SOC to a max-min criterion, giving enough power to the electric motor for various settings, as well as battery's charging in deceleration and acceleration phases. The load's power requirement (EVs), needed for vehicle propulsion is no more than the product of its speed and the load torque applied on it which is also met by two sources (FCs and batteries), is given by 4,39 :…”

Section: Proposed Hybrid Battery-pemfcs Energy Management Algorithmmentioning

confidence: 99%

“…A battery is a device that accumulates electrical energy in electrochemical form and then releases it as needed. The battery's model and state of charge (SOC) is formulated as 38,39 :

V_{italicbat} = E - R_{italicin} I_{italicbat}

E = E_{0} - K \frac{Q}{Q - k \int i_{l} dt} + A ∙ \exp (- B \int i_{l} \begin{matrix} italicdt \end{matrix})

SOC = 100 (1 + \frac{\int I_{italicbat} dt}{Q})

where

E

V_{italicbat}

I_{italicbat}

, and Q are the battery electromotive force, the battery voltage, the battery current, and ampere‐hours stored.

E_{0}

K

A

, and

B

are the unloaded battery voltage, polarization voltage, exponential zone amplitude, and exponential zone time inverse constant respectively,

i_{l}

is the limiting current at which the fuel is used up at a rate equal to its maximum supply rate, and

R_{italicin}

is the internal battery resistance The maximum current accumulated in a battery over period t equal to a rated value Q and a load current

I_{italicbat}

.…”

Section: The Hybrid Systemmentioning

confidence: 99%

See 3 more Smart Citations

Hybrid power management and control of fuel cells‐battery energy storage system in hybrid electric vehicle under three different modes

2023

View full text Add to dashboard Cite

In most situations, fuel cells (FCs) are insufficient to supply power demands in hybrid electric vehicles (HEVs), thus battery storage systems (BSSs) are used to make the system more efficient like as rapid starting, high power density, and enhanced dynamic set response. How the power sources are regulated and distributed determines the accomplishment efficiency of the driving forces in such a configuration. The most critical aspect should be how to guarantee torque stability of the traction motor which is in our case a permanent magnet synchronous motor (PMSM) while attaining quick reaction. This study discusses a hybrid battery‐FCs energy storage and management system for a hybrid electric vehicle (HEV), as well as an integrated PMSM's passivity‐based control (PBC) technique to enable power integration and increase the hybrid electric vehicle (HEV)'s operating speed. The present paper is separated into two sections. First, a power management control (PMC) technology is used to manage the FCs‐battery system to guarantee that the HEV gets continuous power from the hybrid energy resources, where a fuzzy logic controller is used as an artificial intelligence system for the FCs converter to maximize the power produced. The second is dedicated to the new proposed PBC control of the EV's PMSM to rectify non‐linearities, external disturbances, and parametric fluctuations. The standard proportional‐integral (PI) control and sliding mode control (SMC) are built for comparison with the proposed PBC dedicated to the PMSM in order to properly assess the efficacy of the proposed control strategy. The simulation results obtained using MATALB/Simulink show that the proposed PBC technique and hybrid battery‐ proton‐exchange membrane PEMFCs energy management enables high power integration and increase the EV's operational speed.

show abstract

\{\begin{matrix} P_{italicLoad} = ω_{((), wheels)} T_{L} = P_{italicbatt} + P_{italicFC} \\ T_{L} = R \times F_{italictot} \end{matrix}

where

P_{italicLoad}

is the fluctuation in the amount of power required by the electric vehicle and

T_{L}

Section: Proposed Hybrid Battery‐pemfcs Energy Management Algorithmmentioning

confidence: 99%

“…A battery is a device that accumulates electrical energy in electrochemical form and then releases it as needed. The battery's model and state of charge (SOC) is formulated as 38,39 :…”

Section: Modelling Of the Bssmentioning

confidence: 99%

Section: Proposed Hybrid Battery-pemfcs Energy Management Algorithmmentioning

confidence: 99%

“…A battery is a device that accumulates electrical energy in electrochemical form and then releases it as needed. The battery's model and state of charge (SOC) is formulated as 38,39 :

V_{italicbat} = E - R_{italicin} I_{italicbat}

E = E_{0} - K \frac{Q}{Q - k \int i_{l} dt} + A ∙ \exp (- B \int i_{l} \begin{matrix} italicdt \end{matrix})

SOC = 100 (1 + \frac{\int I_{italicbat} dt}{Q})

where

E

V_{italicbat}

I_{italicbat}

, and Q are the battery electromotive force, the battery voltage, the battery current, and ampere‐hours stored.

E_{0}

K

A

, and

B

are the unloaded battery voltage, polarization voltage, exponential zone amplitude, and exponential zone time inverse constant respectively,

i_{l}

is the limiting current at which the fuel is used up at a rate equal to its maximum supply rate, and

R_{italicin}

is the internal battery resistance The maximum current accumulated in a battery over period t equal to a rated value Q and a load current

I_{italicbat}

.…”

Section: The Hybrid Systemmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid power management and control of fuel cells‐battery energy storage system in hybrid electric vehicle under three different modes

2023

View full text Add to dashboard Cite

show abstract

“…Learning-based techniques, as an area of artificial intelligence, recently leverage developments in machine learning, notably reinforcement learning (RL) [33,34] and deep learning (DL) [35,36]. They have shown their efficacy in various fields, most notably image categorization, which has led to the broad implementation of their use in energy management [37][38][39][40][41]. The databases are required to train a model; however, they are not yet accessible.…”

Section: Introductionmentioning

confidence: 99%

Optimal Adaptive Fractional Order Integral Sliding Mode Controller-Energy Management Strategy for Electric Vehicles Based on Bald Eagle Search Algorithm

Ghadbane,

Barkat,

Houari

et al. 2024

International Journal of Energy Research

View full text Add to dashboard Cite

This research presents an optimal energy management system (EMS) for a lithium-ion battery-supercapacitor hybrid storage system used to power an electric vehicle. The storage systems are connected in parallel to the DC bus by bidirectional DC-DC converters and feed a synchronous reluctance motor through an inverter. The proposed energy management strategy is built on the idea to take full benefits of two combined methods: the bald eagle search algorithm and fractional order integral sliding mode control. To evaluate the effectiveness of the suggested optimal energy management strategy, an urban dynamometer driving schedule (UDDS) driving cycle is considered. The obtained results are compared to a classical fractional order integral sliding mode control-based energy management strategy in terms of voltage ripples, overshoots, and battery final state of charge. The ultimate results approve the ability of the proposed energy management system to enhance the power quality and enhance battery power consumption at the same time. Comprehensive processor-in-the-loop (PIL) cosimulations were conducted on the electric vehicle using the C2000 launchxl-f28379d digital signal processing (DSP) board to assess the practicability and effectiveness of the proposed EMS.

show abstract

Imperative Role of Proton Exchange Membrane Fuel Cell System and Hydrogen Energy Storage for Modern Electric Vehicle Transportation

Pachauri,

Sharma,

Mondal

et al. 2024

Clean and Renewable Energy Production

View full text Add to dashboard Cite

Energy management for hybrid electric vehicles based on imitation reinforcement learning

Cited by 32 publications

References 38 publications

Hybrid power management and control of fuel cells‐battery energy storage system in hybrid electric vehicle under three different modes

Hybrid power management and control of fuel cells‐battery energy storage system in hybrid electric vehicle under three different modes

Optimal Adaptive Fractional Order Integral Sliding Mode Controller-Energy Management Strategy for Electric Vehicles Based on Bald Eagle Search Algorithm

Imperative Role of Proton Exchange Membrane Fuel Cell System and Hydrogen Energy Storage for Modern Electric Vehicle Transportation

Contact Info

Product

Resources

About