Ensemble Surrogate Models for Fast LIB Performance Predictions
Battery Cell design and control have been widely explored through modeling and simulation. On the one hand, Doyle’s pseudo-two-dimensional (P2D) model and Single Particle Models are among the most popular electrochemical models capable of predicting battery performance and therefore guiding cell cha...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/14/14/4115 |
_version_ | 1797527216209264640 |
---|---|
author | Marco Quartulli Amaia Gil Ane Miren Florez-Tapia Pablo Cereijo Elixabete Ayerbe Igor G. Olaizola |
author_facet | Marco Quartulli Amaia Gil Ane Miren Florez-Tapia Pablo Cereijo Elixabete Ayerbe Igor G. Olaizola |
author_sort | Marco Quartulli |
collection | DOAJ |
description | Battery Cell design and control have been widely explored through modeling and simulation. On the one hand, Doyle’s pseudo-two-dimensional (P2D) model and Single Particle Models are among the most popular electrochemical models capable of predicting battery performance and therefore guiding cell characterization. On the other hand, empirical models obtained, for example, by Machine Learning (ML) methods represent a simpler and computationally more efficient complement to electrochemical models and have been widely used for Battery Management System (BMS) control purposes. This article proposes ML-based ensemble models to be used for the estimation of the performance of an LIB cell across a wide range of input material characteristics and parameters and evaluates 1. Deep Learning ensembles for simulation convergence classification and 2. structured regressors for battery energy and power predictions. The results represent an improvement on state-of-the-art LIB surrogate models and indicate that deep ensembles represent a promising direction for battery modeling and design. |
first_indexed | 2024-03-10T09:40:52Z |
format | Article |
id | doaj.art-1e6fd58b801c4eacacb64ee7b27be8b1 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T09:40:52Z |
publishDate | 2021-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-1e6fd58b801c4eacacb64ee7b27be8b12023-11-22T03:40:19ZengMDPI AGEnergies1996-10732021-07-011414411510.3390/en14144115Ensemble Surrogate Models for Fast LIB Performance PredictionsMarco Quartulli0Amaia Gil1Ane Miren Florez-Tapia2Pablo Cereijo3Elixabete Ayerbe4Igor G. Olaizola5Vicomtech, Basque Research and Technology Alliance, Mikeletegi 57, 20009 Donostia-San Sebastián (ES), SpainVicomtech, Basque Research and Technology Alliance, Mikeletegi 57, 20009 Donostia-San Sebastián (ES), SpainVicomtech, Basque Research and Technology Alliance, Mikeletegi 57, 20009 Donostia-San Sebastián (ES), SpainCIDETEC, Basque Research and Technology Alliance, Pº Miramón 196, 20014 Donostia-San Sebastián (ES), SpainCIDETEC, Basque Research and Technology Alliance, Pº Miramón 196, 20014 Donostia-San Sebastián (ES), SpainVicomtech, Basque Research and Technology Alliance, Mikeletegi 57, 20009 Donostia-San Sebastián (ES), SpainBattery Cell design and control have been widely explored through modeling and simulation. On the one hand, Doyle’s pseudo-two-dimensional (P2D) model and Single Particle Models are among the most popular electrochemical models capable of predicting battery performance and therefore guiding cell characterization. On the other hand, empirical models obtained, for example, by Machine Learning (ML) methods represent a simpler and computationally more efficient complement to electrochemical models and have been widely used for Battery Management System (BMS) control purposes. This article proposes ML-based ensemble models to be used for the estimation of the performance of an LIB cell across a wide range of input material characteristics and parameters and evaluates 1. Deep Learning ensembles for simulation convergence classification and 2. structured regressors for battery energy and power predictions. The results represent an improvement on state-of-the-art LIB surrogate models and indicate that deep ensembles represent a promising direction for battery modeling and design.https://www.mdpi.com/1996-1073/14/14/4115Li-ion batterysurrogate modelingdeep learning ensembles |
spellingShingle | Marco Quartulli Amaia Gil Ane Miren Florez-Tapia Pablo Cereijo Elixabete Ayerbe Igor G. Olaizola Ensemble Surrogate Models for Fast LIB Performance Predictions Energies Li-ion battery surrogate modeling deep learning ensembles |
title | Ensemble Surrogate Models for Fast LIB Performance Predictions |
title_full | Ensemble Surrogate Models for Fast LIB Performance Predictions |
title_fullStr | Ensemble Surrogate Models for Fast LIB Performance Predictions |
title_full_unstemmed | Ensemble Surrogate Models for Fast LIB Performance Predictions |
title_short | Ensemble Surrogate Models for Fast LIB Performance Predictions |
title_sort | ensemble surrogate models for fast lib performance predictions |
topic | Li-ion battery surrogate modeling deep learning ensembles |
url | https://www.mdpi.com/1996-1073/14/14/4115 |
work_keys_str_mv | AT marcoquartulli ensemblesurrogatemodelsforfastlibperformancepredictions AT amaiagil ensemblesurrogatemodelsforfastlibperformancepredictions AT anemirenfloreztapia ensemblesurrogatemodelsforfastlibperformancepredictions AT pablocereijo ensemblesurrogatemodelsforfastlibperformancepredictions AT elixabeteayerbe ensemblesurrogatemodelsforfastlibperformancepredictions AT igorgolaizola ensemblesurrogatemodelsforfastlibperformancepredictions |