Charged EVs | ZF introduces TempAI to optimize EV electric motor thermal management

ZF has introduced TempAI, a production-ready, AI-based temperature management technology designed to improve the performance and efficiency of electric motors in electric vehicles. Utilizing a self-learning temperature model, TempAI enhances temperature prediction accuracy by over 15 percent, enabling more precise thermal utilization of electric motors and increasing performance without compromising reliability.

The TempAI platform automatically generates physics-based models from extensive measurement data, becoming operational quickly and requiring minimal computing resources. Existing control units are sufficient, allowing for cost-efficient implementation in series production. According to ZF, TempAI delivers targeted electric motor control right up to thermal operating limits, resulting in up to six percent higher peak power and measurable efficiency improvements in the Worldwide Harmonized Light Vehicle Test Procedure (WLTP) cycle. Under dynamic driving scenarios—such as high-performance circuits like the Nürburgring Nordschleife—the technology reduces energy consumption by 6 to 18 percent, dependent on load conditions.

TempAI also enables ecological benefits, as its optimized thermal design can significantly reduce the reliance on heavy rare earth materials. The solution also offers substantial time savings during development, reducing durations from several months to merely a few days via AI-driven modeling.

During motor development, AI-driven TempAI models effectively learn and predict internal motor thermal processes that are otherwise difficult or expensive to measure directly, such as rotor temperatures. The technology capitalizes on extensive dataset analyses collected during functional tests on test benches and in test vehicles, involving millions of data points related to variables like ambient temperatures, rotor speeds and driver behavior patterns.

“This technology enables us to further increase the efficiency and reliability of our drives,” said Dr. Stefan Sicklinger, Head of AI, Digital Engineering, and Validation in R&D, ZF. “At the same time, TempAI demonstrates how data-driven development can be not only faster, but also more sustainable and more powerful.”

Source: ZF