TY - GEN
T1 - Lithium Plating Diagnosis of Lithium-ion Batteries Based on Clustering with Dual Impedance Models
AU - Dai, Runrun
AU - Lin, Ni
AU - Lie, Tek Tjing
AU - Wei, Zhongbao
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Lithium-ion batteries (LIBs) have become an important component in today's energy storage, electric vehicles, and other industries due to their superior performance. However, lithium plating faults in batteries can lead to rapid degradation of battery performance and, in severe cases, cause safety accidents, making it one of the main problems constraining LIBs development. To address this challenge, this paper proposes a clustering based diagnostic method for lithium plating using features from dual impedance models. By extracting parameters from the equivalent circuit model and the electrochemical impedance spectroscopy model, and utilizing a cluster algorithm based on fuzzy and weighted shared neighbor, high-precision diagnosis of lithium plating is achieved. Validated by the capacity decay method, the diagnostic accuracy reaches 9 6. 3 1 %.
AB - Lithium-ion batteries (LIBs) have become an important component in today's energy storage, electric vehicles, and other industries due to their superior performance. However, lithium plating faults in batteries can lead to rapid degradation of battery performance and, in severe cases, cause safety accidents, making it one of the main problems constraining LIBs development. To address this challenge, this paper proposes a clustering based diagnostic method for lithium plating using features from dual impedance models. By extracting parameters from the equivalent circuit model and the electrochemical impedance spectroscopy model, and utilizing a cluster algorithm based on fuzzy and weighted shared neighbor, high-precision diagnosis of lithium plating is achieved. Validated by the capacity decay method, the diagnostic accuracy reaches 9 6. 3 1 %.
KW - cluster analysis
KW - lithium plating diagnosis
KW - lithium-ion battery
KW - model feature extraction
UR - https://www.scopus.com/pages/publications/105015515502
U2 - 10.1109/AAIEE64965.2025.11100487
DO - 10.1109/AAIEE64965.2025.11100487
M3 - Conference contribution
AN - SCOPUS:105015515502
T3 - 2025 IEEE International Symposium on the Application of Artificial Intelligence in Electrical Engineering, AAIEE 2025
SP - 357
EP - 361
BT - 2025 IEEE International Symposium on the Application of Artificial Intelligence in Electrical Engineering, AAIEE 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE International Symposium on the Application of Artificial Intelligence in Electrical Engineering, AAIEE 2025
Y2 - 25 April 2025 through 28 April 2025
ER -