Apr 25, 2024
5:00pm - 7:00pm
Flex Hall C, Level 2, Summit
Edward Michaud1,2,Dayakar Penumadu2
Volkswagen Group of America1,The University of Tennessee, Knoxville2
Edward Michaud1,2,Dayakar Penumadu2
Volkswagen Group of America1,The University of Tennessee, Knoxville2
Battery electric vehicles (BEVs) offer significant environmental benefits over traditional internal combustion engine (ICE) vehicles, including zero tailpipe emissions and improved energy efficiency. Despite this, typical BEV batteries can weigh up to 500kg, substantially heavier than a conventional vehicle's engine and fuel tank. This makes BEVs great candidates for lightweighting, offering improvements in driving range, acceleration, handling, and overall efficiency. At the same time, these batteries must be protected from side-impact even further than a conventional ICE vehicle.<br/>In this study, we aim to leverage computational modeling and artificial intelligence (AI) methods to lightweight the battery's protective structures beyond capabilities achievable by a typical human. Specifically, we focus on the methods necessary to fully train an artificial intelligence architectutre such that models can be rapidly generated and validated hundreds to thousands of times. Ultimately, this research will contribute to the development of more efficient and sustainable BEVs, which can help to mitigate climate change and reduce the environmental impact of transportation while maintaining or impmroving safety standards.