Lithium Battery Life Prediction Based on DBN and LSTM
In: Journal of Physics: Conference Series, Jg. 2433 (2023), Heft 1, S. 012020
academicJournal
Zugriff:
Aiming at the low adaptability and inaccuracy of a single network in predicting the Remaining Useful Life (RUL) of lithium batteries, this paper proposed a prediction method based on the combination of Deep Belief Network (DBN) and Mogrifier Long Short-Term Memory network (LSTM). Firstly, the Ensemble Empirical Mode Decomposition (EEMD) method was used to preprocess the capacity data of lithium battery, and the feature information of the data was extracted by correlation analysis, which can effectively solve the regeneration of battery capacity. In addition, the decomposed high-frequency and low-frequency data are trained and predicted by DBN and Mogrifier LSTM networks respectively. The experimental results show that this method has high effectiveness and superiority.
Titel: |
Lithium Battery Life Prediction Based on DBN and LSTM
|
---|---|
Autor/in / Beteiligte Person: | Ran, Bo ; Yuan, Huimei |
Link: | |
Zeitschrift: | Journal of Physics: Conference Series, Jg. 2433 (2023), Heft 1, S. 012020 |
Veröffentlichung: | IOP Publishing, 2023 |
Medientyp: | academicJournal |
ISSN: | 1742-6588 |
DOI: | 10.1088/1742-6596/2433/1/012020 |
Sonstiges: |
|