Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data

This study introduces a novel Sequence-to-Sequence (Seq2Seq) deep learning model for predicting lithium-ion batteries’ remaining useful life. We address the challenge of extrapolating battery performance from high-rate to low-rate charging conditions, a significant limitation in previous studies. Ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Seok Bae, Sungwon Lee, Janghyuk Moon
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Batteries
Subjects:
Online Access:https://www.mdpi.com/2313-0105/10/11/389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217528688640000
author Yong Seok Bae
Sungwon Lee
Janghyuk Moon
author_facet Yong Seok Bae
Sungwon Lee
Janghyuk Moon
author_sort Yong Seok Bae
collection DOAJ
description This study introduces a novel Sequence-to-Sequence (Seq2Seq) deep learning model for predicting lithium-ion batteries’ remaining useful life. We address the challenge of extrapolating battery performance from high-rate to low-rate charging conditions, a significant limitation in previous studies. Experiments were also conducted on commercial cells using charge rates from 1C to 3C. Comparative analysis of fully connected neural networks, convolutional neural networks, and long short-term memory networks revealed their limitations in extrapolating to untrained conditions. Our Seq2Seq model overcomes these limitations, predicting charging profiles and discharge capacity for untrained, low-rate conditions using only high-rate charging data. The Seq2Seq model demonstrated superior performance with low error and high curve-fitting accuracy for 1C and 1.2C untrained data. Unlike traditional models, it predicts complete charging profiles (voltage, current, temperature) for subsequent cycles, offering a comprehensive view of battery degradation. This method significantly reduces battery life testing time while maintaining high prediction accuracy. The findings have important implications for lithium-ion battery development, potentially accelerating advancements in electric vehicle technology and energy storage.
format Article
id doaj-art-178ba371e8c94dc0b8a19edfbebf2e0e
institution OA Journals
issn 2313-0105
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Batteries
spelling doaj-art-178ba371e8c94dc0b8a19edfbebf2e0e2025-08-20T02:08:02ZengMDPI AGBatteries2313-01052024-11-01101138910.3390/batteries10110389Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation DataYong Seok Bae0Sungwon Lee1Janghyuk Moon2Department of Energy Systems Engineering, Chung-Ang University, Seoul 06974, Republic of KoreaDepartment of Energy Systems Engineering, Chung-Ang University, Seoul 06974, Republic of KoreaDepartment of Energy Systems Engineering, Chung-Ang University, Seoul 06974, Republic of KoreaThis study introduces a novel Sequence-to-Sequence (Seq2Seq) deep learning model for predicting lithium-ion batteries’ remaining useful life. We address the challenge of extrapolating battery performance from high-rate to low-rate charging conditions, a significant limitation in previous studies. Experiments were also conducted on commercial cells using charge rates from 1C to 3C. Comparative analysis of fully connected neural networks, convolutional neural networks, and long short-term memory networks revealed their limitations in extrapolating to untrained conditions. Our Seq2Seq model overcomes these limitations, predicting charging profiles and discharge capacity for untrained, low-rate conditions using only high-rate charging data. The Seq2Seq model demonstrated superior performance with low error and high curve-fitting accuracy for 1C and 1.2C untrained data. Unlike traditional models, it predicts complete charging profiles (voltage, current, temperature) for subsequent cycles, offering a comprehensive view of battery degradation. This method significantly reduces battery life testing time while maintaining high prediction accuracy. The findings have important implications for lithium-ion battery development, potentially accelerating advancements in electric vehicle technology and energy storage.https://www.mdpi.com/2313-0105/10/11/389lithium-ion batteryremaining useful life (RUL)sequence-to-sequence (Seq2Seq)acceleration of battery degradation
spellingShingle Yong Seok Bae
Sungwon Lee
Janghyuk Moon
Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
Batteries
lithium-ion battery
remaining useful life (RUL)
sequence-to-sequence (Seq2Seq)
acceleration of battery degradation
title Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
title_full Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
title_fullStr Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
title_full_unstemmed Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
title_short Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
title_sort developing an innovative seq2seq model to predict the remaining useful life of low charged battery performance using high speed degradation data
topic lithium-ion battery
remaining useful life (RUL)
sequence-to-sequence (Seq2Seq)
acceleration of battery degradation
url https://www.mdpi.com/2313-0105/10/11/389
work_keys_str_mv AT yongseokbae developinganinnovativeseq2seqmodeltopredicttheremainingusefullifeoflowchargedbatteryperformanceusinghighspeeddegradationdata
AT sungwonlee developinganinnovativeseq2seqmodeltopredicttheremainingusefullifeoflowchargedbatteryperformanceusinghighspeeddegradationdata
AT janghyukmoon developinganinnovativeseq2seqmodeltopredicttheremainingusefullifeoflowchargedbatteryperformanceusinghighspeeddegradationdata