Using Dynamic Neural Networks for Battery State of Charge Estimation in Electric Vehicles

David Jiménez-Bermejo; Jesús Fraile-Ardanuy; Sandra Castaño-Solis; Julia Merino; Roberto Alvaro-Hermana

doi:10.1016/j.procs.2018.04.077

Using Dynamic Neural Networks for Battery State of Charge Estimation in Electric Vehicles

David Jiménez-Bermejo
, Jesús Fraile-Ardanuy
, Sandra Castaño-Solis
, Julia Merino
, Roberto Alvaro-Hermana

TECNALIA Research & Innovation

Technical University of Madrid
University of Deusto

Producción científica: Contribución a una revista › Artículo de la conferencia › revisión exhaustiva

77 Citas (Scopus)

4 Descargas (Pure)

Resumen

Due to urban pollution, transport electrification is being currently promoted in different countries. Electric Vehicles (EVs) sales are growing all over the world, but there are still some challenges to be solved before a mass adoption of this type of vehicles occurs. One of the main drawbacks of EVs are their limited range, for that reason an accurate estimation of the state-of-charge (SOC) is required. The main contribution of this work is the design of a Nonlinear Autoregressive with External Input (NARX) artificial neural network to estimate the SOC of an EV using real data extracted from the car during its daily trips. The network is trained using voltage, current and four different battery pack temperatures as input and SOC as output. This network has been tested using 54 different real driving cycles, obtaining highly accurate results, with a mean squared error lower than 1e-6 in all situations

Idioma original	Inglés
Páginas (desde-hasta)	533-540
Número de páginas	8
Publicación	Procedia Computer Science
Volumen	130
DOI	https://doi.org/10.1016/j.procs.2018.04.077
Estado	Publicada - 2018
Evento	9th International Conference on Ambient Systems, Networks and Technologies, ANT 2018 - Porto, Indonesia Duración: 8 may 2018 → 11 may 2018

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

ODS 7: Energía asequible y no contaminante
ODS 11: Ciudades y comunidades sostenibles

Palabras clave

Artificial neural network
Battery pack
Electric vehicles
State-of-charge

Project and Funding Information

Funding Info
This work has been partially financed by the Spanish Ministry of Economy and Competitiveness within the framework of the project DEMS: “Sistema distribuido de gestión de energía en redes eléctricas inteligentes (TEC2015-66126-R)".

Acceder al documento

10.1016/j.procs.2018.04.077

1-s2Versión publicada final, 0,98 MB

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

@article{fe9ab3c242344c269f8ec987a2a3258c,

title = "Using Dynamic Neural Networks for Battery State of Charge Estimation in Electric Vehicles",

abstract = "Due to urban pollution, transport electrification is being currently promoted in different countries. Electric Vehicles (EVs) sales are growing all over the world, but there are still some challenges to be solved before a mass adoption of this type of vehicles occurs. One of the main drawbacks of EVs are their limited range, for that reason an accurate estimation of the state-of-charge (SOC) is required. The main contribution of this work is the design of a Nonlinear Autoregressive with External Input (NARX) artificial neural network to estimate the SOC of an EV using real data extracted from the car during its daily trips. The network is trained using voltage, current and four different battery pack temperatures as input and SOC as output. This network has been tested using 54 different real driving cycles, obtaining highly accurate results, with a mean squared error lower than 1e-6 in all situations",

keywords = "Artificial neural network, Battery pack, Electric vehicles, State-of-charge, Artificial neural network, Battery pack, Electric vehicles, State-of-charge",

author = "David Jim{\'e}nez-Bermejo and Jes{\'u}s Fraile-Ardanuy and Sandra Casta{\~n}o-Solis and Julia Merino and Roberto Alvaro-Hermana",

note = "Publisher Copyright: {\textcopyright} 2018 The Authors. Published by Elsevier B.V.; 9th International Conference on Ambient Systems, Networks and Technologies, ANT 2018 ; Conference date: 08-05-2018 Through 11-05-2018",

year = "2018",

doi = "10.1016/j.procs.2018.04.077",

language = "English",

volume = "130",

pages = "533--540",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - Using Dynamic Neural Networks for Battery State of Charge Estimation in Electric Vehicles

AU - Jiménez-Bermejo, David

AU - Fraile-Ardanuy, Jesús

AU - Castaño-Solis, Sandra

AU - Merino, Julia

AU - Alvaro-Hermana, Roberto

PY - 2018

Y1 - 2018

N2 - Due to urban pollution, transport electrification is being currently promoted in different countries. Electric Vehicles (EVs) sales are growing all over the world, but there are still some challenges to be solved before a mass adoption of this type of vehicles occurs. One of the main drawbacks of EVs are their limited range, for that reason an accurate estimation of the state-of-charge (SOC) is required. The main contribution of this work is the design of a Nonlinear Autoregressive with External Input (NARX) artificial neural network to estimate the SOC of an EV using real data extracted from the car during its daily trips. The network is trained using voltage, current and four different battery pack temperatures as input and SOC as output. This network has been tested using 54 different real driving cycles, obtaining highly accurate results, with a mean squared error lower than 1e-6 in all situations

AB - Due to urban pollution, transport electrification is being currently promoted in different countries. Electric Vehicles (EVs) sales are growing all over the world, but there are still some challenges to be solved before a mass adoption of this type of vehicles occurs. One of the main drawbacks of EVs are their limited range, for that reason an accurate estimation of the state-of-charge (SOC) is required. The main contribution of this work is the design of a Nonlinear Autoregressive with External Input (NARX) artificial neural network to estimate the SOC of an EV using real data extracted from the car during its daily trips. The network is trained using voltage, current and four different battery pack temperatures as input and SOC as output. This network has been tested using 54 different real driving cycles, obtaining highly accurate results, with a mean squared error lower than 1e-6 in all situations

KW - Artificial neural network

KW - Battery pack

KW - Electric vehicles

KW - State-of-charge

KW - Artificial neural network

KW - Battery pack

KW - Electric vehicles

KW - State-of-charge

UR - https://www.scopus.com/pages/publications/85051217310

U2 - 10.1016/j.procs.2018.04.077

DO - 10.1016/j.procs.2018.04.077

M3 - Conference article

SN - 1877-0509

VL - 130

SP - 533

EP - 540

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 9th International Conference on Ambient Systems, Networks and Technologies, ANT 2018

Y2 - 8 May 2018 through 11 May 2018

ER -

Using Dynamic Neural Networks for Battery State of Charge Estimation in Electric Vehicles

Resumen

ODS de las Naciones Unidas

Palabras clave

Project and Funding Information

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto