All-electric systems use batteries as the only source of propulsion power on the aircraft. The design and usage optimization of electric propulsion architectures over a range of aircraft designs and series of missions is complex. Technology advancement demands energy storage devices and systems with better performance, longer life, higher reliability, and smarter management strategy. Designing such systems involve a trade-off among a large set of parameters, whereas advanced control strategies need to rely on the instantaneous status of many indicators. Machine learning can dramatically accelerate calculations, capture complex mechanisms to improve the prediction accuracy, and make optimized decisions based on comprehensive status information. The computational efficiency makes it applicable for real-time management.
The machine learning models and algorithms is further developed and optimized to suit the requirement of the energy storage devices and systems, such as maintaining higher learning accuracy and higher training efficiency.