The machine learning in lithium-ion batteries: A review. (August 2022)

• Record Type: Journal Article
• Authors: Zhang, Liyuan; Shen, Zijun; Sajadi, S. Mohammad; Prabuwono, Anton Satria; Mahmoud, Mustafa Z.; Cheraghian, G.; Tag El Din, ElSayed M.
• Is Part Of: Engineering analysis with boundary elements. Volume 141(2022)
• Page Start: 1
• Page End: 16
• Publication Date: 2022-08
• Subjects: Lithium-ion batteries -- Machine learning -- Heatsinks -- State estimation; Boundary element methods -- Periodicals; Engineering mathematics -- Periodicals; Équations intégrales de frontière, Méthodes des -- Périodiques; Mathématiques de l'ingénieur -- Périodiques; Boundary element methods; Engineering mathematics; Periodicals; 620.00151
• DOI: 10.1016/j.enganabound.2022.04.035
• Languages: English
• ISSNs: 0955-7997

Abstract

Abstract: Among energy storage devices (ESDs), lithium-ion batteries (LIBs) have widespread utilization in cleaner productions. Hence, accurate estimation of the state of LIBs has attracted the attention of many researchers. On the other hand, the design of LIBs requires a compromise between large groups of effective factors. Machine learning (ML) utilized in chemistry, physics, biology, engineering, and materials science can improve the estimation accuracy of LIBs by reducing the calculation burden. This review paper begins with the introduction of ESDs and ML. Then, five popular ML terminologies are reviewed. Numerical and analytical evaluation of PCM-based heatsinks employed in LIBs is presented to introduce how effective data can be collected. LIBs and several studies in the field of batteries are discussed and finally, ML for LIBs is described by reviewing some relevant articles. Conclusions and future directions are also provided.