Abstract

Machine learning technologies have gained considerable attention for state of health (SOH) estimation of Lithium-ion batteries due to their advantages in learning the behavior of non-linear systems. The mapping between the features and the SOH can be established according to learning and optimization theory. However, the SOH features can become invalid under different conditions as the battery aging process is closely related to the operating conditions. In this work, the fuzzy entropy (FE) of the voltage, extracted from short-term current pulses, is proposed as a feature for support vector machine-based (SVM-based) SOH estimation. The robustness and effectiveness of the proposed methods are verified by extended experiments performed on the three most common Li-ion battery chemistries, i.e., NMC, LFP, and NCA. The obtained Pearson correlation coefficient, relating the FE feature to the SOH, returns values higher than 0.9. Finally, the proposed FE-based SVM model can estimate the SOH of the considered batteries with MAPE below 1.6% when the battery state of charge (SOC) is known and MAPE below 3.4% when the SOC is not known.
Original languageEnglish
Title of host publication2022 IEEE Energy Conversion Congress and Exposition (ECCE)
PublisherIEEE
Publication dateDec 2022
ISBN (Electronic)9781728193878
DOIs
Publication statusPublished - Dec 2022
Event2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022 - Detroit, United States
Duration: 9 Oct 202213 Oct 2022

Conference

Conference2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022
Country/TerritoryUnited States
CityDetroit
Period09/10/202213/10/2022
SeriesIEEE Energy Conversion Congress and Exposition
ISSN2329-3721

Keywords

  • Fuzzy Entropy
  • Lithium-Ion Battery
  • Robust Estimation
  • State of Health

Fingerprint

Dive into the research topics of 'Robust Fuzzy Entropy-Based SOH Estimation for Different Lithium-Ion Battery Chemistries'. Together they form a unique fingerprint.

Cite this