Application of deep learning image recognition for lithium battery State of Health assessment

Yanli Liu; Yu Su; Shaofan Zhang; Vladimir Terzija; Ze Cheng

doi:10.1049/enc2.70016

您当前的位置：

首页 >

文章列表页 >

Application of deep learning image recognition for lithium battery State of Health assessment

更新时间：2026-03-24

- Application of deep learning image recognition for lithium battery State of Health assessment
- Energy Conversion and Economics Vol. 6, Issue 4, (2025)
- 作者机构：
  
  1. School of Electrical and Information Engineering, Tianjin University,Tianjin,China
  2. Vladimir Terzija, Newcastle University,Newcastle,UK
  3. Contribution: Methodology, Validation, Writing - original draft
  4. Guangdong Power Grid Co., Ltd. Guangzhou Power Supply Bureau,Guangzhou,China
  5. Contribution: Investigation, Project administration, Software, Supervision, Writing - review & editing
  6. Newcastle University,Newcastle,UK
  7. Yanli Liu, School of Electrical and Information Engineering, Tianjin University,Tianjin,China,300072
  8. Contribution: Resources, Supervision, Writing - review & editing
  9. Contribution: Data curation, Methodology
- 作者简介：
- 基金信息：
- DOI：10.1049/enc2.70016
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
Yanli Liu, Yu Su, Shaofan Zhang, et al. Application of deep learning image recognition for lithium battery State of Health assessment[J]. Energy Conversion and Economics, 2025, 6(4).
DOI：

Yanli Liu, Yu Su, Shaofan Zhang, et al. Application of deep learning image recognition for lithium battery State of Health assessment[J]. Energy Conversion and Economics, 2025, 6(4). DOI： 10.1049/enc2.70016.

摘要

Abstract

Accurately estimating the State of Health (SOH) of lithium-ion batteries is essential for ensuring their reliable operation. The constant-current charging voltage curves of batteries at different aging levels show significant deviations. Traditional methods based on one-dimensional time-series data face limitations in capturing and characterizing these complex patterns. To address this issue

this paper leverages the one-dimensional (1D) time series data of the lithium battery constant-current charging voltage segment

selected using incremental capacity analysis. This data is then transformed into a two-dimensional representation using the Gramian angular summation field algorithm. Utilizing the exceptional image-recognition capabilities of ResNet

this approach achieves high-accuracy SOH estimation. Validation using publicly available datasets from the University of Oxford and the University of Maryland demonstrates a significant improvement in battery SOH estimation accuracy compared to traditional techniques

which directly input voltage segments into the network.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Structural optimisation design of liquid cooling system for lithium-ion battery based on improved Kriging method

State-of-health estimation of lithium-ion batteries: A comprehensive literature review from cell to pack levels

Related Author

Jinjun Bai

Lidong Dong

Chengbo Sun

Shaoran Gao

Zhaoyang Dong

Related Institution

College of Marine Electrical Engineering, Dalian Maritime University

Contribution: Conceptualization, Data curation, Formal analysis, Funding acquisition, Methodology, Visualization, Writing - original draft

Contribution: Methodology, Software, Writing - review & editing

Contribution: Conceptualization, Methodology, Resources, Supervision, Writing - review & editing

Contribution: Conceptualization, Methodology, Writing - review & editing

AI问答

⁰