One of the main issues affecting the uptake of battery packs are safety concerns, particularly with respect to the fires caused by cell faults. Managing the risks from faults requires advances in battery management systems and an understanding of the dynamics of large packs. To address this issue, a machine learning classifier based upon a support vector machine was developed to detect cell faults within large packs using a limited number of current sensors. To train the classifier, a modelling framework for parallel connected packs was 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. These results highlight the potential of combining mathematical modelling and machine learning to improve battery management systems and deal with the complexities of large packs.