Lithium-ion battery state of health prediction based on state-space modeling and multi-scale temporal compression

Kuo Yang

doi:10.1016/j.seta.2026.105137

Lithium-ion battery state of health prediction based on state-space modeling and multi-scale temporal compression

2026-06-16

0

PRE

AI

K

Kuo Yang

Y

Yanjie Cai

Z

Zixi Liu

X

Xing Hu

X

Xiangdong Kong

Y

Yugui Tang

G

Guanqiang Ruan *

DOI：10.1016/j.seta.2026.105137

Original

Original request for help

Save

Abstract

En 中文

• A state-space model captures time-series dependencies in SOH degradation. • Multi-scale learning improves feature extraction and captures complex degradation patterns. • Transfer learning reduces training costs and enhances adaptability to new battery systems.

Keywords:

State-of-health

Hybrid neural network

State-space modeling

Degradation prediction

Transfer learning

Lithium-ion battery state of health prediction based on state-space modeling and multi-scale temporal compression

Abstract

Journal

Organization

Cited Papers

Citing Papers