A support vector machine classifier detected cell faults within large parallel lithium-ion battery packs with an accuracy of 83% using current information from only 27% of the cells.
A support vector machine classifier can accurately detect faulty lithium-ion cells in large parallel battery packs using current information from a limited number of cells, potentially improving battery management systems.
Absolute Event Rate: 83% vs 47%
Abstract One of the main concerns affecting the uptake of battery packs is safety, particularly with respect to fires caused by cell faults. Mitigating possible risks from faults requires advances in battery management systems and an understanding of the dynamics of large packs. To address this, a machine learning classifier based upon a support vector machine was developed that detects cell faults within large packs using a limited number of current sensors. To train the classifier, a modelling framework for parallel-connected packs is introduced and shown to generalise to Doyle-Fuller-Newman electrochemical models. The fault classification performance was found to be satisfactory, with an accuracy of 83% using current information from only 27% of the cells. Validation on experimental pack data is also shown. These results highlight the potential to combine mathematical modelling and machine learning to improve battery management systems and deal with the complexities of large packs.
Lambert et al. (Wed,) conducted a other in Lithium-ion battery faults. Support vector machine (SVM) classifier vs. Recurrent neural network (RNN) was evaluated on Fault classification accuracy. A support vector machine classifier detected cell faults within large parallel lithium-ion battery packs with an accuracy of 83% using current information from only 27% of the cells.