Researchers at Graz University of Technology have introduced an artificial intelligence (AI) system aimed at accelerating the development of battery electric vehicle powertrains. The AI, known as the Optimisation of Electric Drives (OPED), integrates simulation models with evolutionary optimisation algorithms to automatically refine components such as power electronics, electric machines, and transmissions based on specific manufacturer requirements.
“Electric drives consist of a large number of components that can be designed very differently in order to fulfil the desired requirements,” said Martin Hofstetter from the Institute of Automotive Engineering at TU Graz. “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.”
See also: TU Graz Receives Major Funding for ‘Battery4Life’ Research Center
The OPED system begins by inputting technical specifications, including drive power, service life, maximum speed, and spatial constraints within the vehicle. It then evaluates approximately 50 design parameters simultaneously, aligning simulated powertrain configurations with the manufacturer’s priorities, which may encompass production costs, weight, volume, and energy efficiency.
Through extensive simulation cycles, OPED identifies optimal solutions that align with the manufacturer’s objectives. These solutions are then presented for further development and detailed implementation. According to Hofstetter, this AI-driven approach can reduce a process that would typically take engineers months to about a day, allowing development teams to focus on higher-level decisions rather than manual calculations and simulations.
See also: Graz University of Technology Enhances Battery Assessment Method for Electric Vehicle Batteries
The system’s flexibility also permits the inclusion of factors such as CO2 emissions across the supply chain. Recent advancements have extended OPED’s capabilities to optimize electric drives across entire vehicle platforms, facilitating the identification of optimal components that can be standardized across different models to reduce development and production costs.
“The OPED approach can be used for a wide variety of product developments,” Hofstetter noted, “and we are happy to work with new industrial partners to adapt it to their challenges and goals.”
