| Title |
Study on Lithium-ion Battery SOH Estimation Based on Incremental Capacity Analysis and Deep Learning |
| Authors |
박민식(Min-Sik Park) ; 김정수(Jeong-Su Kim) ; 김병우(Byeong-Woo Kim) |
| DOI |
https://doi.org/10.5370/KIEE.2024.73.2.349 |
| Keywords |
Lithium-ion Battery; Incremental Capacity Analysis; Correlation analysis; Deep learning; RNN(Recurrent Neural Network); LSTM(Long Short Term Memory); GRU(Gate Recurrent Unit); SOH Estimation. |
| Abstract |
Lithium-ion batteries are being utilized as energy sources for electric vehicles due to their advantages such as high energy density, long life, and high efficiency. In order to ensure the safe condition of lithium-ion batteries under various driving conditions of electric vehicles, it is necessary to analyze the degradation status and causes of lithium-ion batteries and accurately estimate their state of health (SOH). Therefore, this paper proposes a method for estimating the SOH of lithium-ion batteries using incremental capacity analysis and deep learning. Incremental capacity analysis is a technique that analyzes the electrochemical state inside a lithium-ion battery and can identify the degradation state of the battery. Through this method, parameters related to degradation were extracted, and their usefulness as characteristic parameters for SOH estimation was verified by correlation analysis. The characteristic parameters validated through correlation analysis were used as inputs to deep learning algorithms for SOH estimation to compare the accuracy of SOH estimation by different estimation algorithms. |