Automotive Battery Thermal Management by Federated Learning methodology - Prognosis of Thermal runaway.

Today's battery thermal management systems include cloud-based predictive analytics technologies. When the first data is sent to the cloud, battery digital twin models begin to run. This allows for the prediction of critical parameters such as state of charge (SOC), state of health (SOH), remaining useful life (RUL), and the possibility of thermal runaway events. The battery and the automobile are dynamic systems that must be monitored in real time for temperature overrun. However, relying only on cloud-based computations adds significant latency to time-sensitive procedures such as thermal runaway monitoring. Because automobiles operate in various areas throughout the intended path of travel, internet connectivity varies, resulting in a delay in data delivery to the cloud. As a result, the inherent lag in data transfer between the cloud and cars challenges the present deployment of cloud-based real-time monitoring solutions. This study proposes applying a thermal runaway model on edge devices as a strategy to reduce processing costs and delays. When computer functions are shifted to the edge, battery thermal management systems become more responsive and cost-effective. This is accomplished through improved time and cost efficiencies. Furthermore, this will ensure a rapid and efficient client experience, perhaps giving OEMs a competitive advantage in the digital technology arena.