Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field

Batteries degrade over time. Such degradation leads to performance loss, but more importantly, safety issues arise. To evaluate the battery degradation, traditional diagnostic techniques rely on model-based or data-driven approaches; however, those methods often require controlled conditions or spec...

Full description

Saved in:
Bibliographic Details
Main Authors: Hojin Cheon, Jihun Jeon, Byungil Jung, Hongseok Kim
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/9/2405
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030639690022912
author Hojin Cheon
Jihun Jeon
Byungil Jung
Hongseok Kim
author_facet Hojin Cheon
Jihun Jeon
Byungil Jung
Hongseok Kim
author_sort Hojin Cheon
collection DOAJ
description Batteries degrade over time. Such degradation leads to performance loss, but more importantly, safety issues arise. To evaluate the battery degradation, traditional diagnostic techniques rely on model-based or data-driven approaches; however, those methods often require controlled conditions or specific tests, which may not be applicable in real fields. In this regard, we propose a deep learning-based method addressing these limitations by accurately modeling batteries using real-world operational data from photovoltaic (PV)-integrated battery energy storage system (BESSs), where charging currents vary dynamically and SOC is capped at 70% by regulation. The proposed method is based on a neural surrogate model for batteries, employing a sequence-to-sequence architecture, which directly captures the dynamic behavior of batteries from operational data, eliminating the need for specialized characterization tests or feature extraction. The proposed model synthesizes the terminal voltage with a mean absolute error of 6.4 mV for lithium–iron–phosphate (LFP) cells and 49 mV for nickel–cobalt–manganese (NCM) battery modules, respectively, which is only 0.4% and 0.29% of the voltage swing. As a health indicator, we also propose the concept of voltage deviation (VD), defined as the deviation between the synthesized and actual terminal voltages. We demonstrate that VD can be evaluated not only in laboratory data but also in field data.
format Article
id doaj-art-2a44f35c2896458fb972c0bc9338b59d
institution DOAJ
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-2a44f35c2896458fb972c0bc9338b59d2025-08-20T02:59:11ZengMDPI AGEnergies1996-10732025-05-01189240510.3390/en18092405Battery Health Diagnosis via Neural Surrogate Model: From Lab to FieldHojin Cheon0Jihun Jeon1Byungil Jung2Hongseok Kim3Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaDepartment of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaDoosan Enerbility, Seongnam 13557, Republic of KoreaDepartment of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaBatteries degrade over time. Such degradation leads to performance loss, but more importantly, safety issues arise. To evaluate the battery degradation, traditional diagnostic techniques rely on model-based or data-driven approaches; however, those methods often require controlled conditions or specific tests, which may not be applicable in real fields. In this regard, we propose a deep learning-based method addressing these limitations by accurately modeling batteries using real-world operational data from photovoltaic (PV)-integrated battery energy storage system (BESSs), where charging currents vary dynamically and SOC is capped at 70% by regulation. The proposed method is based on a neural surrogate model for batteries, employing a sequence-to-sequence architecture, which directly captures the dynamic behavior of batteries from operational data, eliminating the need for specialized characterization tests or feature extraction. The proposed model synthesizes the terminal voltage with a mean absolute error of 6.4 mV for lithium–iron–phosphate (LFP) cells and 49 mV for nickel–cobalt–manganese (NCM) battery modules, respectively, which is only 0.4% and 0.29% of the voltage swing. As a health indicator, we also propose the concept of voltage deviation (VD), defined as the deviation between the synthesized and actual terminal voltages. We demonstrate that VD can be evaluated not only in laboratory data but also in field data.https://www.mdpi.com/1996-1073/18/9/2405Li-ion batterydeep learningneural networksbattery management systemsenergy storage systems
spellingShingle Hojin Cheon
Jihun Jeon
Byungil Jung
Hongseok Kim
Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field
Energies
Li-ion battery
deep learning
neural networks
battery management systems
energy storage systems
title Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field
title_full Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field
title_fullStr Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field
title_full_unstemmed Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field
title_short Battery Health Diagnosis via Neural Surrogate Model: From Lab to Field
title_sort battery health diagnosis via neural surrogate model from lab to field
topic Li-ion battery
deep learning
neural networks
battery management systems
energy storage systems
url https://www.mdpi.com/1996-1073/18/9/2405
work_keys_str_mv AT hojincheon batteryhealthdiagnosisvianeuralsurrogatemodelfromlabtofield
AT jihunjeon batteryhealthdiagnosisvianeuralsurrogatemodelfromlabtofield
AT byungiljung batteryhealthdiagnosisvianeuralsurrogatemodelfromlabtofield
AT hongseokkim batteryhealthdiagnosisvianeuralsurrogatemodelfromlabtofield