Research on predicting the state of health of lithium-ion batteries via back propagation network based on multi-feature combination of electrochemical impedance spectroscopy
Fei Chen, Shulei Sun, Xiuxian Jia, Zhong Ren, Xiaorong Huang, Xianan Shu, Jun Li · 2026
Read Research on predicting the state of health of lithium-ion batteries via back propagation network based on multi-feature combination of electrochemical impedance spectroscopy by Fei Chen, Shulei Sun, Xiuxian Jia, Zhong Ren, Xiaorong Huang, Xianan Shu, Jun Li (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354706.txt.
Description
Fei Chen and co-authors propose in 2026 a better way to estimate the health of lithium ion batteries from electrical response tests. Single response measures miss how ageing parts of a battery interact, giving weak predictions. Their method picks several response features that track capacity loss, then feeds them to a neural network tuned by three search methods borrowed from nature.
Across test conditions with plenty of data and with noisy, scarce data, tuned networks kept errors low and stable. Two of the tuning methods stood out in the hardest cases. Reliable health estimates matter for safe use of batteries in vehicles and portable devices.
Catalog record
| CREATOR | Fei Chen, Shulei Sun, Xiuxian Jia, Zhong Ren, Xiaorong Huang, Xianan Shu, Jun Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39132 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |