A battery management system with charge balancing and aging detection based on ANN

Tsung Wen Sun, Tsung Heng Tsai*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

A battery management system with aging detection based on artificial neural network (ANN) for the state of charge (SOC) balancing is proposed in this paper. The charger adopts a single-inductor multiple-output architecture to achieve charge balancing among different battery cells. In constant current mode, the pulse charging is utilized to improve the charging speed and slow down the aging rate. Moreover, an ANN is proposed to detect the state of health (SOH) of the battery cells and improve the accuracy of the SOC estimation. TSMC 0.35-μm process and TensorFlow are used for simulations. A 94% power efficiency of the charger is achieved. The active area of this design is 1.5 x 1.5 mm2. Experimental results show that 0.32% root-mean square errors for the SOC estimation is obtained.

Original languageEnglish
Title of host publication2021 IEEE International Symposium on Circuits and Systems, ISCAS 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728192017
DOIs
StatePublished - 2021
Event53rd IEEE International Symposium on Circuits and Systems, ISCAS 2021 - Daegu, Korea, Republic of
Duration: 22 May 202128 May 2021

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2021-May
ISSN (Print)0271-4310

Conference

Conference53rd IEEE International Symposium on Circuits and Systems, ISCAS 2021
Country/TerritoryKorea, Republic of
CityDaegu
Period22/05/2128/05/21

Keywords

  • Artificial neural network (ANN)
  • Battery aging
  • Battery model
  • Cell balancing
  • Li-ion battery charger
  • Pulse charging

Fingerprint

Dive into the research topics of 'A battery management system with charge balancing and aging detection based on ANN'. Together they form a unique fingerprint.

Cite this