Abstract
The rapid growth in the battery electric vehicle (BEV) market has brought lithium-ion battery (LIB) packs to the forefront due to their superior power and energy density properties. However, LIBs are highly susceptible to environmental factors, operating conditions, and manufacturing inconsistencies and operate within a narrow safety operating window. Battery faults pose significant risks, including potentially catastrophic thermal runaway, that can be initiated even by small faults, propagating further into a chain reaction cascade of failures. Aiming to improve the safety of such battery packs, this article presents the developed autoencoder-based fault detection method. The method, enhanced by computational intelligence and machine learning, is a result of extensive research into optical liquid detection systems (OLDSs) for immersion-cooled battery packs, where optical rather than electrical signals are used inside high-voltage areas. The performance was evaluated using recorded real-life datasets under faultless states and under simulated fault states through specific model performance indicators as well as detection performance indicators.