In this digest, fuzzy entropy (FE), as a new feature, is applied for LiFeO4 battery state of health (SOH) estimation. Compared with sample entropy, FE introduces the exponential function to measure the similarity of voltage vectors and the mean of the match templates is removed. As a result, FE can capture the variation of voltage during the battery degradation more efficiently in terms of the data size, parameter selection and data noise. Then the entropy-SOH mapping is established by combining FE with support vector machine, and the effectiveness of the proposed method is verified by experimental results.
|Titel||2020 IEEE 9th International Power Electronics and Motion Control Conference (IPEMC 2020-ECCE Asia)|
|Status||Accepteret/In press - 2020|