Rapid charging of Li-ion batteries is vital for the commercialization of electric propulsion systems. But, during the fast-charging process, reduction in the battery capacity and temperature increases must be considered in real-time. Most Li-ion battery chargers follow the charging profile of an open-loop system, which has been determined based on prior knowledge. However, such a system does not reflect the temperature change of the battery and the degree of aging. Therefore, in this study, we propose a neural network-based charging profile model by applying a closed-loop system to reflect the various states of batteries; we also show two battery-state characteristics in addition to temperature. Consequently, we show battery characteristics other than those shown in the past, such as the battery voltage and temperature trends. In addition to the design of the charging current, an improvement of approximately 22 ∼ 50% based on the mean absolute error (MAE) is achieved. By considering the various characteristics, the long short-term memory performance is determined to be better when compared to the feed-forward neural network, and this performance is improved by 35% based on MAE.
|Title of host publication||Proceedings - 20th IEEE International Conference on Data Mining Workshops, ICDMW 2020|
|Editors||Giuseppe Di Fatta, Victor Sheng, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu|
|Publisher||IEEE Computer Society|
|Number of pages||7|
|Publication status||Published - 2020 Nov|
|Event||20th IEEE International Conference on Data Mining Workshops, ICDMW 2020 - Virtual, Sorrento, Italy|
Duration: 2020 Nov 17 → 2020 Nov 20
|Name||IEEE International Conference on Data Mining Workshops, ICDMW|
|Conference||20th IEEE International Conference on Data Mining Workshops, ICDMW 2020|
|Period||20/11/17 → 20/11/20|
Bibliographical notePublisher Copyright:
© 2020 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Science Applications