New AI Tool Accelerates EV Power Train Development

GRAZ, Austria—Engineers at the Graz University of Technology (TU Graz) have harnessed artificial intelligence technology to develop a way to streamline the amount of time it takes to develop next-generation power trains. The Optimization of Electric Drives (OPED) system quickly analyzes important objectives such as cost, efficiency and package space requirements

Based on technical requirements, it combines around 50 design parameters simultaneously. The new method can shorten the development phase of EV power trains by several months.

“Electric drives consist of a large number of components that can be designed very differently in order to fulfil the desired requirements,” says Martin Hofstetter, a mechanical engineer at TU Graz’s Institute of Automotive Engineering who is heading up the project. “If I make a small change to the electric machine, it has an effect on the transmission and the power electronics. So, it’s extremely complex to make optimal decisions.

“An additional difficulty is that there is no one perfect solution for a power train, as the priorities of the manufacturers also play a role,” explains Hofstetter. “These could be production costs, the weight and volume of the power train or energy efficiency.”

The OPED software makes it possible to significantly reduce this complexity. Bad variants are dropped, while better ones are further optimized. After several hundred thousand calculation and simulation cycles, OPED finds options that come closest to priorities.

“What engineers would need months to do without AI support takes about a day with OPED,” claims Hofstetter. “This allows development teams to focus on top-level decisions instead of investing their limited time in manual calculation and simulation work.”