An approach of state-of-charge prediction for lithium-ion batteries using hybrid Pyraformer-LSTM learning network

Xianbin Wang, Liping Zhang, Qihua Fan, Yiyin Hu, Jian Zhang, Huimin Chen · 2026

Read An approach of state-of-charge prediction for lithium-ion batteries using hybrid Pyraformer-LSTM learning network by Xianbin Wang, Liping Zhang, Qihua Fan, Yiyin Hu, Jian Zhang, Huimin Chen (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-0353298.txt.

Description

Wang and colleagues, in a 2026 paper, build a hybrid model to guess how much charge is left in a lithium-ion battery. That number, called state of charge, guides electric cars and devices, yet it is hard to pin down because battery behavior bends and drifts over time. Guessing wrong can strand a driver or wear the battery out early.

Their model pairs two designs. A pyramidal attention part reads the battery's recent history at several time scales at once, from quick swings to slow trends. A memory network then tracks the long story and the quirks in between. Tested on battery data gathered at several temperatures, the hybrid beat six rival methods on error scores. The authors say the multi-scale reading is the key gain, and they offer the model for battery systems that must work in heat and cold alike.

Catalog record

CREATORXianbin Wang, Liping Zhang, Qihua Fan, Yiyin Hu, Jian Zhang, Huimin Chen
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE44256
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0353298

Browse the full library · About the Tower of Babel